R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merged upstream

Browse Source
This commit is contained in:
Dennis Fink 2016-10-03 00:27:37 +02:00
commit 978b6c6f98
763 changed files with 73536 additions and 18356 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

58
.github/ISSUE_TEMPLATE.md vendored Normal file
View File

@ -0,0 +1,58 @@
## Please follow the guide below
- You will be asked some questions and requested to provide some information, please read them **carefully** and answer honestly
- Put an `x` into all the boxes [ ] relevant to your *issue* (like that [x])
- Use *Preview* tab to see how your issue will actually look like
---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.10.02*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.10.02**
### Before submitting an *issue* make sure you have:
- [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
- [ ] [Searched](https://github.com/rg3/youtube-dl/search?type=Issues) the bugtracker for similar issues including closed ones
### What is the purpose of your *issue*?
- [ ] Bug report (encountered problems with youtube-dl)
- [ ] Site support request (request for adding support for a new site)
- [ ] Feature request (request for a new functionality)
- [ ] Question
- [ ] Other
---
### The following sections concretize particular purposed issues, you can erase any section (the contents between triple ---) not applicable to your *issue*
---
### If the purpose of this *issue* is a *bug report*, *site support request* or you are not completely sure provide the full verbose output as follows:
Add `-v` flag to **your command line** you run youtube-dl with, copy the **whole** output and insert it here. It should look similar to one below (replace it with **your** log inserted between triple ```):
```
$ youtube-dl -v <your command line>
[debug] System config: []
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2016.10.02
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}
...
<end of log>
```
---
### If the purpose of this *issue* is a *site support request* please provide all kinds of example URLs support for which should be included (replace following example URLs by **yours**):
- Single video: https://www.youtube.com/watch?v=BaW_jenozKc
- Single video: https://youtu.be/BaW_jenozKc
- Playlist: https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc
---
### Description of your *issue*, suggested solution and other information
Explanation of your *issue* in arbitrary form goes here. Please make sure the [description is worded well enough to be understood](https://github.com/rg3/youtube-dl#is-the-description-of-the-issue-itself-sufficient). Provide as much context and examples as possible.
If work on your *issue* requires account credentials please provide them or explain how one can obtain them.

58
.github/ISSUE_TEMPLATE_tmpl.md vendored Normal file
View File

@ -0,0 +1,58 @@
## Please follow the guide below
- You will be asked some questions and requested to provide some information, please read them **carefully** and answer honestly
- Put an `x` into all the boxes [ ] relevant to your *issue* (like that [x])
- Use *Preview* tab to see how your issue will actually look like
---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *%(version)s*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **%(version)s**
### Before submitting an *issue* make sure you have:
- [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
- [ ] [Searched](https://github.com/rg3/youtube-dl/search?type=Issues) the bugtracker for similar issues including closed ones
### What is the purpose of your *issue*?
- [ ] Bug report (encountered problems with youtube-dl)
- [ ] Site support request (request for adding support for a new site)
- [ ] Feature request (request for a new functionality)
- [ ] Question
- [ ] Other
---
### The following sections concretize particular purposed issues, you can erase any section (the contents between triple ---) not applicable to your *issue*
---
### If the purpose of this *issue* is a *bug report*, *site support request* or you are not completely sure provide the full verbose output as follows:
Add `-v` flag to **your command line** you run youtube-dl with, copy the **whole** output and insert it here. It should look similar to one below (replace it with **your** log inserted between triple ```):
```
$ youtube-dl -v <your command line>
[debug] System config: []
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version %(version)s
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}
...
<end of log>
```
---
### If the purpose of this *issue* is a *site support request* please provide all kinds of example URLs support for which should be included (replace following example URLs by **yours**):
- Single video: https://www.youtube.com/watch?v=BaW_jenozKc
- Single video: https://youtu.be/BaW_jenozKc
- Playlist: https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc
---
### Description of your *issue*, suggested solution and other information
Explanation of your *issue* in arbitrary form goes here. Please make sure the [description is worded well enough to be understood](https://github.com/rg3/youtube-dl#is-the-description-of-the-issue-itself-sufficient). Provide as much context and examples as possible.
If work on your *issue* requires account credentials please provide them or explain how one can obtain them.

27
.github/PULL_REQUEST_TEMPLATE.md vendored Normal file
View File

@ -0,0 +1,27 @@
## Please follow the guide below
- You will be asked some questions, please read them **carefully** and answer honestly
- Put an `x` into all the boxes [ ] relevant to your *pull request* (like that [x])
- Use *Preview* tab to see how your *pull request* will actually look like
---
### Before submitting a *pull request* make sure you have:
- [ ] At least skimmed through [adding new extractor tutorial](https://github.com/rg3/youtube-dl#adding-support-for-a-new-site) and [youtube-dl coding conventions](https://github.com/rg3/youtube-dl#youtube-dl-coding-conventions) sections
- [ ] [Searched](https://github.com/rg3/youtube-dl/search?q=is%3Apr&type=Issues) the bugtracker for similar pull requests
### In order to be accepted and merged into youtube-dl each piece of code must be in public domain or released under [Unlicense](http://unlicense.org/). Check one of the following options:
- [ ] I am the original author of this code and I am willing to release it under [Unlicense](http://unlicense.org/)
- [ ] I am not the original author of this code but it is in public domain or released under [Unlicense](http://unlicense.org/) (provide reliable evidence)
### What is the purpose of your *pull request*?
- [ ] Bug fix
- [ ] Improvement
- [ ] New extractor
- [ ] New feature
---
### Description of your *pull request* and other information
Explanation of your *pull request* in arbitrary form goes here. Please make sure the description explains the purpose and effect of your *pull request* and is worded well enough to be understood. Provide as much context and examples as possible.

11
.gitignore vendored
View File

@ -1,5 +1,6 @@
*.pyc
*.pyo
*.class
*~
*.DS_Store
wine-py2exe/
@ -12,6 +13,7 @@ README.txt
youtube-dl.1
youtube-dl.bash-completion
youtube-dl.fish
youtube_dl/extractor/lazy_extractors.py
youtube-dl
youtube-dl.exe
youtube-dl.tar.gz
@ -26,10 +28,17 @@ updates_key.pem
*.mp4
*.m4a
*.m4v
*.mp3
*.3gp
*.part
*.swp
test/testdata
test/local_parameters.json
.tox
youtube-dl.zsh
# IntelliJ related files
.idea
.idea/*
*.iml
tmp/

4
.travis.yml
View File

@ -2,13 +2,15 @@ language: python
python:
- "2.6"
- "2.7"
- "3.2"
- "3.3"
- "3.4"
- "3.5"
sudo: false
script: nosetests test --verbose
notifications:
email:
- filippo.valsorda@gmail.com
- phihag@phihag.de
- yasoob.khld@gmail.com
# irc:
# channels:

82
AUTHORS
View File

@ -103,3 +103,85 @@ Christopher Krooss
Ondřej Caletka
Dinesh S
Johan K. Jensen
Yen Chi Hsuan
Enam Mijbah Noor
David Luhmer
Shaya Goldberg
Paul Hartmann
Frans de Jonge
Robin de Rooij
Ryan Schmidt
Leslie P. Polzer
Duncan Keall
Alexander Mamay
Devin J. Pohly
Eduardo Ferro Aldama
Jeff Buchbinder
Amish Bhadeshia
Joram Schrijver
Will W.
Mohammad Teimori Pabandi
Roman Le Négrate
Matthias Küch
Julian Richen
Ping O.
Mister Hat
Peter Ding
jackyzy823
George Brighton
Remita Amine
Aurélio A. Heckert
Bernhard Minks
sceext
Zach Bruggeman
Tjark Saul
slangangular
Behrouz Abbasi
ngld
nyuszika7h
Shaun Walbridge
Lee Jenkins
Anssi Hannula
Lukáš Lalinský
Qijiang Fan
Rémy Léone
Marco Ferragina
reiv
Muratcan Simsek
Evan Lu
flatgreen
Brian Foley
Vignesh Venkat
Tom Gijselinck
Founder Fang
Andrew Alexeyew
Saso Bezlaj
Erwin de Haan
Jens Wille
Robin Houtevelts
Patrick Griffis
Aidan Rowe
mutantmonkey
Ben Congdon
Kacper Michajłow
José Joaquín Atria
Viťas Strádal
Kagami Hiiragi
Philip Huppert
blahgeek
Kevin Deldycke
inondle
Tomáš Čech
Déstin Reed
Roman Tsiupa
Artur Krysiak
Jakub Adam Wieczorek
Aleksandar Topuzović
Nehal Patel
Rob van Bekkum
Petr Zvoníček
Pratyush Singh
Aleksander Nitecki
Sebastian Blunt
Matěj Cepl
Xie Yanbo

196
CONTRIBUTING.md
View File

@ -1,4 +1,20 @@
Please include the full output of the command when run with `--verbose`. The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
**Please include the full output of youtube-dl when run with `-v`**, i.e. **add** `-v` flag to **your command line**, copy the **whole** output and post it in the issue body wrapped in \`\`\` for better formatting. It should look similar to this:
```
$ youtube-dl -v <your command line>
[debug] System config: []
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2015.12.06
[debug] Git HEAD: 135392e
[debug] Python version 2.6.6 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}
...
```
**Do not post screenshots of verbose log only plain text is acceptable.**
The output (including the first lines) contains important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
Please re-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist):
@ -12,23 +28,25 @@ So please elaborate on what feature you are requesting, or what bug you want to
- How it could be fixed
- How your proposed solution would look like
If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We're often too polite to close the issue outright, but the missing info makes misinterpretation likely. As a commiter myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over.
If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We're often too polite to close the issue outright, but the missing info makes misinterpretation likely. As a committer myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over.
For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the -v flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information.
For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the `-v` flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information.
Site support requests **must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
If your server has multiple IPs or you suspect censorship, adding `--call-home` may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/).
**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like `http://www.youtube.com/watch?v=BaW_jenozKc`. There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. `http://www.youtube.com/`) is *not* an example URL.
### Are you using the latest version?
Before reporting any issue, type youtube-dl -U. This should report that you're up-to-date. About 20% of the reports we receive are already fixed, but people are using outdated versions. This goes for feature requests as well.
Before reporting any issue, type `youtube-dl -U`. This should report that you're up-to-date. About 20% of the reports we receive are already fixed, but people are using outdated versions. This goes for feature requests as well.
### Is the issue already documented?
Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or at https://github.com/rg3/youtube-dl/search?type=Issues . If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity.
Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or browse the [GitHub Issues](https://github.com/rg3/youtube-dl/search?type=Issues) of this repository. If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity.
### Why are existing options not enough?
Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#synopsis). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#options). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
### Is there enough context in your bug report?
@ -67,19 +85,29 @@ To run the test, simply invoke your favorite test runner, or execute a test file
If you want to create a build of youtube-dl yourself, you'll need
* python
* make
* make (both GNU make and BSD make are supported)
* pandoc
* zip
* nosetests
### Adding support for a new site
If you want to add support for a new site, you can follow this quick list (assuming your service is called `yourextractor`):
If you want to add support for a new site, first of all **make sure** this site is **not dedicated to [copyright infringement](#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. youtube-dl does **not support** such sites thus pull requests adding support for them **will be rejected**.
After you have ensured this site is distributing it's content legally, you can follow this quick list (assuming your service is called `yourextractor`):
1. [Fork this repository](https://github.com/rg3/youtube-dl/fork)
2. Check out the source code with `git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git`
3. Start a new git branch with `cd youtube-dl; git checkout -b yourextractor`
2. Check out the source code with:
git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git
3. Start a new git branch with
cd youtube-dl
git checkout -b yourextractor
4. Start with this simple template and save it to `youtube_dl/extractor/yourextractor.py`:
```python
# coding: utf-8
from __future__ import unicode_literals
@ -110,22 +138,23 @@ If you want to add support for a new site, you can follow this quick list (assum
webpage = self._download_webpage(url, video_id)
# TODO more code goes here, for example ...
title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
return {
'id': video_id,
'title': title,
'description': self._og_search_description(webpage),
'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False),
# TODO more properties (see youtube_dl/extractor/common.py)
}
```
5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
7. Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Add tests and code for as many as you want.
8. If you can, check the code with [pyflakes](https://pypi.python.org/pypi/pyflakes) (a good idea) and [pep8](https://pypi.python.org/pypi/pep8) (optional, ignore E501).
5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.py).
6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L74-L252). Add tests and code for as many as you want.
8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](http://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+.
9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
$ git add youtube_dl/extractor/__init__.py
$ git add youtube_dl/extractor/extractors.py
$ git add youtube_dl/extractor/yourextractor.py
$ git commit -m '[yourextractor] Add new extractor'
$ git push origin yourextractor
@ -134,3 +163,136 @@ If you want to add support for a new site, you can follow this quick list (assum
In any case, thank you very much for your contributions!
## youtube-dl coding conventions
This section introduces a guide lines for writing idiomatic, robust and future-proof extractor code.
Extractors are very fragile by nature since they depend on the layout of the source data provided by 3rd party media hoster out of your control and this layout tend to change. As an extractor implementer your task is not only to write code that will extract media links and metadata correctly but also to minimize code dependency on source's layout changes and even to make the code foresee potential future changes and be ready for that. This is important because it will allow extractor not to break on minor layout changes thus keeping old youtube-dl versions working. Even though this breakage issue is easily fixed by emitting a new version of youtube-dl with fix incorporated all the previous version become broken in all repositories and distros' packages that may not be so prompt in fetching the update from us. Needless to say some may never receive an update at all that is possible for non rolling release distros.
### Mandatory and optional metafields
For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by [information dictionary](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L75-L257) or simply *info dict*. Only the following meta fields in *info dict* are considered mandatory for successful extraction process by youtube-dl:
- `id` (media identifier)
- `title` (media title)
- `url` (media download URL) or `formats`
In fact only the last option is technically mandatory (i.e. if you can't figure out the download location of the media the extraction does not make any sense). But by convention youtube-dl also treats `id` and `title` to be mandatory. Thus aforementioned metafields are the critical data the extraction does not make any sense without and if any of them fail to be extracted then extractor is considered completely broken.
[Any field](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L149-L257) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields.
#### Example
Say you have some source dictionary `meta` that you've fetched as JSON with HTTP request and it has a key `summary`:
```python
meta = self._download_json(url, video_id)
```
Assume at this point `meta`'s layout is:
```python
{
...
"summary": "some fancy summary text",
...
}
```
Assume you want to extract `summary` and put into resulting info dict as `description`. Since `description` is optional metafield you should be ready that this key may be missing from the `meta` dict, so that you should extract it like:
```python
description = meta.get('summary') # correct
```
and not like:
```python
description = meta['summary'] # incorrect
```
The latter will break extraction process with `KeyError` if `summary` disappears from `meta` at some time later but with former approach extraction will just go ahead with `description` set to `None` that is perfectly fine (remember `None` is equivalent for absence of data).
Similarly, you should pass `fatal=False` when extracting optional data from a webpage with `_search_regex`, `_html_search_regex` or similar methods, for instance:
```python
description = self._search_regex(
r'<span[^>]+id="title"[^>]*>([^<]+)<',
webpage, 'description', fatal=False)
```
With `fatal` set to `False` if `_search_regex` fails to extract `description` it will emit a warning and continue extraction.
You can also pass `default=<some fallback value>`, for example:
```python
description = self._search_regex(
r'<span[^>]+id="title"[^>]*>([^<]+)<',
webpage, 'description', default=None)
```
On failure this code will silently continue the extraction with `description` set to `None`. That is useful for metafields that are known to may or may not be present.
### Provide fallbacks
When extracting metadata try to provide several scenarios for that. For example if `title` is present in several places/sources try extracting from at least some of them. This would make it more future-proof in case some of the sources became unavailable.
#### Example
Say `meta` from previous example has a `title` and you are about to extract it. Since `title` is mandatory meta field you should end up with something like:
```python
title = meta['title']
```
If `title` disappeares from `meta` in future due to some changes on hoster's side the extraction would fail since `title` is mandatory. That's expected.
Assume that you have some another source you can extract `title` from, for example `og:title` HTML meta of a `webpage`. In this case you can provide a fallback scenario:
```python
title = meta.get('title') or self._og_search_title(webpage)
```
This code will try to extract from `meta` first and if it fails it will try extracting `og:title` from a `webpage`.
### Make regular expressions flexible
When using regular expressions try to write them fuzzy and flexible.
#### Example
Say you need to extract `title` from the following HTML code:
```html
<span style="position: absolute; left: 910px; width: 90px; float: right; z-index: 9999;" class="title">some fancy title</span>
```
The code for that task should look similar to:
```python
title = self._search_regex(
r'<span[^>]+class="title"[^>]*>([^<]+)', webpage, 'title')
```
Or even better:
```python
title = self._search_regex(
r'<span[^>]+class=(["\'])title\1[^>]*>(?P<title>[^<]+)',
webpage, 'title', group='title')
```
Note how you tolerate potential changes in `style` attribute's value or switch from using double quotes to single for `class` attribute:
The code definitely should not look like:
```python
title = self._search_regex(
r'<span style="position: absolute; left: 910px; width: 90px; float: right; z-index: 9999;" class="title">(.*?)</span>',
webpage, 'title', group='title')
```
### Use safe conversion functions
Wrap all extracted numeric data into safe functions from `utils`: `int_or_none`, `float_or_none`. Use them for string to number conversions as well.

760
ChangeLog Normal file
View File

@ -0,0 +1,760 @@
version 2016.10.02
Core
* Fix possibly lost extended attributes during post-processing
+ Support pyxattr as well as python-xattr for --xattrs and
--xattr-set-filesize (#9054)
Extractors
+ [jwplatform] Support DASH streams in JWPlayer
+ [jwplatform] Support old-style JWPlayer playlists
+ [byutv:event] Add extractor
* [periscope:user] Fix extraction (#10820)
* [dctp] Fix extraction (#10734)
+ [instagram] Extract video dimensions (#10790)
+ [tvland] Extend URL regular expression (#10812)
+ [vgtv] Add support for tv.aftonbladet.se (#10800)
- [aftonbladet] Remove extractor
* [vk] Fix timestamp and view count extraction (#10760)
+ [vk] Add support for running and finished live streams (#10799)
+ [leeco] Recognize more Le Sports URLs (#10794)
+ [instagram] Extract comments (#10788)
+ [ketnet] Extract mzsource formats (#10770)
* [limelight:media] Improve HTTP formats extraction
version 2016.09.27
Core
+ Add hdcore query parameter to akamai f4m formats
+ Delegate HLS live streams downloading to ffmpeg
+ Improved support for HTML5 subtitles
Extractors
+ [vk] Add support for dailymotion embeds (#10661)
* [promptfile] Fix extraction (#10634)
* [kaltura] Speed up embed regular expressions (#10764)
+ [npo] Add support for anderetijden.nl (#10754)
+ [prosiebensat1] Add support for advopedia sites
* [mwave] Relax URL regular expression (#10735, #10748)
* [prosiebensat1] Fix playlist support (#10745)
+ [prosiebensat1] Add support for sat1gold sites (#10745)
+ [cbsnews:livevideo] Fix extraction and extract m3u8 formats
+ [brightcove:new] Add support for live streams
* [soundcloud] Generalize playlist entries extraction (#10733)
+ [mtv] Add support for new URL schema (#8169, #9808)
* [einthusan] Fix extraction (#10714)
+ [twitter] Support Periscope embeds (#10737)
+ [openload] Support subtitles (#10625)
version 2016.09.24
Core
+ Add support for watchTVeverywhere.com authentication provider based MSOs for
Adobe Pass authentication (#10709)
Extractors
+ [soundcloud:playlist] Provide video id for early playlist entries (#10733)
+ [prosiebensat1] Add support for kabeleinsdoku (#10732)
* [cbs] Extract info from thunder videoPlayerService (#10728)
* [openload] Fix extraction (#10408)
+ [ustream] Support the new HLS streams (#10698)
+ [ooyala] Extract all HLS formats
+ [cartoonnetwork] Add support for Adobe Pass authentication
+ [soundcloud] Extract license metadata
+ [fox] Add support for Adobe Pass authentication (#8584)
+ [tbs] Add support for Adobe Pass authentication (#10642, #10222)
+ [trutv] Add support for Adobe Pass authentication (#10519)
+ [turner] Add support for Adobe Pass authentication
version 2016.09.19
Extractors
+ [crunchyroll] Check if already authenticated (#10700)
- [twitch:stream] Remove fallback to profile extraction when stream is offline
* [thisav] Improve title extraction (#10682)
* [vyborymos] Improve station info extraction
version 2016.09.18
Core
+ Introduce manifest_url and fragments fields in formats dictionary for
fragmented media
+ Provide manifest_url field for DASH segments, HLS and HDS
+ Provide fragments field for DASH segments
* Rework DASH segments downloader to use fragments field
+ Add helper method for Wowza Streaming Engine formats extraction
Extractors
+ [vyborymos] Add extractor for vybory.mos.ru (#10692)
+ [xfileshare] Add title regular expression for streamin.to (#10646)
+ [globo:article] Add support for multiple videos (#10653)
+ [thisav] Recognize HTML5 videos (#10447)
* [jwplatform] Improve JWPlayer detection
+ [mangomolo] Add support for Mangomolo embeds
+ [toutv] Add support for authentication (#10669)
* [franceinter] Fix upload date extraction
* [tv4] Fix HLS and HDS formats extraction (#10659)
version 2016.09.15
Core
* Improve _hidden_inputs
+ Introduce improved explicit Adobe Pass support
+ Add --ap-mso to provide multiple-system operator identifier
+ Add --ap-username to provide MSO account username
+ Add --ap-password to provide MSO account password
+ Add --ap-list-mso to list all supported MSOs
+ Add support for Rogers Cable multiple-system operator (#10606)
Extractors
* [crunchyroll] Fix authentication (#10655)
* [twitch] Fix API calls (#10654, #10660)
+ [bellmedia] Add support for more Bell Media Television sites
* [franceinter] Fix extraction (#10538, #2105)
* [kuwo] Improve error detection (#10650)
+ [go] Add support for free full episodes (#10439)
* [bilibili] Fix extraction for specific videos (#10647)
* [nhk] Fix extraction (#10633)
* [kaltura] Improve audio detection
* [kaltura] Skip chun format
+ [vimeo:ondemand] Pass Referer along with embed URL (#10624)
+ [nbc] Add support for NBC Olympics (#10361)
version 2016.09.11.1
Extractors
+ [tube8] Extract categories and tags (#10579)
+ [pornhub] Extract categories and tags (#10499)
* [openload] Temporary fix (#10408)
+ [foxnews] Add support Fox News articles (#10598)
* [viafree] Improve video id extraction (#10615)
* [iwara] Fix extraction after relaunch (#10462, #3215)
+ [tfo] Add extractor for tfo.org
* [lrt] Fix audio extraction (#10566)
* [9now] Fix extraction (#10561)
+ [canalplus] Add support for c8.fr (#10577)
* [newgrounds] Fix uploader extraction (#10584)
+ [polskieradio:category] Add support for category lists (#10576)
+ [ketnet] Add extractor for ketnet.be (#10343)
+ [canvas] Add support for een.be (#10605)
+ [telequebec] Add extractor for telequebec.tv (#1999)
* [parliamentliveuk] Fix extraction (#9137)
version 2016.09.08
Extractors
+ [jwplatform] Extract height from format label
+ [yahoo] Extract Brightcove Legacy Studio embeds (#9345)
* [videomore] Fix extraction (#10592)
* [foxgay] Fix extraction (#10480)
+ [rmcdecouverte] Add extractor for rmcdecouverte.bfmtv.com (#9709)
* [gamestar] Fix metadata extraction (#10479)
* [puls4] Fix extraction (#10583)
+ [cctv] Add extractor for CCTV and CNTV (#8153)
+ [lci] Add extractor for lci.fr (#10573)
+ [wat] Extract DASH formats
+ [viafree] Improve video id detection (#10569)
+ [trutv] Add extractor for trutv.com (#10519)
+ [nick] Add support for nickelodeon.nl (#10559)
+ [abcotvs:clips] Add support for clips.abcotvs.com
+ [abcotvs] Add support for ABC Owned Television Stations sites (#9551)
+ [miaopai] Add extractor for miaopai.com (#10556)
* [gamestar] Fix metadata extraction (#10479)
+ [bilibili] Add support for episodes (#10190)
+ [tvnoe] Add extractor for tvnoe.cz (#10524)
version 2016.09.04.1
Core
* In DASH downloader if the first segment fails, abort the whole download
process to prevent throttling (#10497)
+ Add support for --skip-unavailable-fragments and --fragment retries in
hlsnative downloader (#10165, #10448).
+ Add support for --skip-unavailable-fragments in DASH downloader
+ Introduce --skip-unavailable-fragments option for fragment based downloaders
that allows to skip fragments unavailable due to a HTTP error
* Fix extraction of video/audio entries with src attribute in
_parse_html5_media_entries (#10540)
Extractors
* [theplatform] Relax URL regular expression (#10546)
* [youtube:playlist] Extend URL regular expression
* [rottentomatoes] Delegate extraction to internetvideoarchive extractor
* [internetvideoarchive] Extract all formats
* [pornvoisines] Fix extraction (#10469)
* [rottentomatoes] Fix extraction (#10467)
* [espn] Extend URL regular expression (#10549)
* [vimple] Extend URL regular expression (#10547)
* [youtube:watchlater] Fix extraction (#10544)
* [youjizz] Fix extraction (#10437)
+ [foxnews] Add support for FoxNews Insider (#10445)
+ [fc2] Recognize Flash player URLs (#10512)
version 2016.09.03
Core
* Restore usage of NAME attribute from EXT-X-MEDIA tag for formats codes in
_extract_m3u8_formats (#10522)
* Handle semicolon in mimetype2ext
Extractors
+ [youtube] Add support for rental videos' previews (#10532)
* [youtube:playlist] Fallback to video extraction for video/playlist URLs when
no playlist is actually served (#10537)
+ [drtv] Add support for dr.dk/nyheder (#10536)
+ [facebook:plugins:video] Add extractor (#10530)
+ [go] Add extractor for *.go.com sites
* [adobepass] Check for authz_token expiration (#10527)
* [nytimes] improve extraction
* [thestar] Fix extraction (#10465)
* [glide] Fix extraction (#10478)
- [exfm] Remove extractor (#10482)
* [youporn] Fix categories and tags extraction (#10521)
+ [curiositystream] Add extractor for app.curiositystream.com
- [thvideo] Remove extractor (#10464)
* [movingimage] Fix for the new site name (#10466)
+ [cbs] Add support for once formats (#10515)
* [limelight] Skip ism snd duplicate manifests
+ [porncom] Extract categories and tags (#10510)
+ [facebook] Extract timestamp (#10508)
+ [yahoo] Extract more formats
version 2016.08.31
Extractors
* [soundcloud] Fix URL regular expression to avoid clashes with sets (#10505)
* [bandcamp:album] Fix title extraction (#10455)
* [pyvideo] Fix extraction (#10468)
+ [ctv] Add support for tsn.ca, bnn.ca and thecomedynetwork.ca (#10016)
* [9c9media] Extract more metadata
* [9c9media] Fix multiple stacks extraction (#10016)
* [adultswim] Improve video info extraction (#10492)
* [vodplatform] Improve embed regular expression
- [played] Remove extractor (#10470)
+ [tbs] Add extractor for tbs.com and tntdrama.com (#10222)
+ [cartoonnetwork] Add extractor for cartoonnetwork.com (#10110)
* [adultswim] Rework in terms of turner extractor
* [cnn] Rework in terms of turner extractor
* [nba] Rework in terms of turner extractor
+ [turner] Add base extractor for Turner Broadcasting System based sites
* [bilibili] Fix extraction (#10375)
* [openload] Fix extraction (#10408)
version 2016.08.28
Core
+ Add warning message that ffmpeg doesn't support SOCKS
* Improve thumbnail sorting
+ Extract formats from #EXT-X-MEDIA tags in _extract_m3u8_formats
* Fill IV with leading zeros for IVs shorter than 16 octets in hlsnative
+ Add ac-3 to the list of audio codecs in parse_codecs
Extractors
* [periscope:user] Fix extraction (#10453)
* [douyutv] Fix extraction (#10153, #10318, #10444)
+ [nhk:vod] Add extractor for www3.nhk.or.jp on demand (#4437, #10424)
- [trutube] Remove extractor (#10438)
+ [usanetwork] Add extractor for usanetwork.com
* [crackle] Fix extraction (#10333)
* [spankbang] Fix description and uploader extraction (#10339)
* [discoverygo] Detect cable provider restricted videos (#10425)
+ [cbc] Add support for watch.cbc.ca
* [kickstarter] Silent the warning for og:description (#10415)
* [mtvservices:embedded] Fix extraction for the new 'edge' player (#10363)
version 2016.08.24.1
Extractors
+ [pluralsight] Add support for subtitles (#9681)
version 2016.08.24
Extractors
* [youtube] Fix authentication (#10392)
* [openload] Fix extraction (#10408)
+ [bravotv] Add support for Adobe Pass (#10407)
* [bravotv] Fix clip info extraction (#10407)
* [eagleplatform] Improve embedded videos detection (#10409)
* [awaan] Fix extraction
* [mtvservices:embedded] Update config URL
+ [abc:iview] Add extractor (#6148)
version 2016.08.22
Core
* Improve formats and subtitles extension auto calculation
+ Recognize full unit names in parse_filesize
+ Add support for m3u8 manifests in HTML5 multimedia tags
* Fix octal/hexadecimal number detection in js_to_json
Extractors
+ [ivi] Add support for 720p and 1080p
+ [charlierose] Add new extractor (#10382)
* [1tv] Fix extraction (#9249)
* [twitch] Renew authentication
* [kaltura] Improve subtitles extension calculation
+ [zingmp3] Add support for video clips
* [zingmp3] Fix extraction (#10041)
* [kaltura] Improve subtitles extraction (#10279)
* [cultureunplugged] Fix extraction (#10330)
+ [cnn] Add support for money.cnn.com (#2797)
* [cbsnews] Fix extraction (#10362)
* [cbs] Fix extraction (#10393)
+ [litv] Support 'promo' URLs (#10385)
* [snotr] Fix extraction (#10338)
* [n-tv.de] Fix extraction (#10331)
* [globo:article] Relax URL and video id regular expressions (#10379)
version 2016.08.19
Core
- Remove output template description from --help
* Recognize lowercase units in parse_filesize
Extractors
+ [porncom] Add extractor for porn.com (#2251, #10251)
+ [generic] Add support for DBTV embeds
* [vk:wallpost] Fix audio extraction for new site layout
* [vk] Fix authentication
+ [hgtvcom:show] Add extractor for hgtv.com shows (#10365)
+ [discoverygo] Add support for another GO network sites
version 2016.08.17
Core
+ Add _get_netrc_login_info
Extractors
* [mofosex] Extract all formats (#10335)
+ [generic] Add support for vbox7 embeds
+ [vbox7] Add support for embed URLs
+ [viafree] Add extractor (#10358)
+ [mtg] Add support for viafree URLs (#10358)
* [theplatform] Extract all subtitles per language
+ [xvideos] Fix HLS extraction (#10356)
+ [amcnetworks] Add extractor
+ [bbc:playlist] Add support for pagination (#10349)
+ [fxnetworks] Add extractor (#9462)
* [cbslocal] Fix extraction for SendtoNews-based videos
* [sendtonews] Fix extraction
* [jwplatform] Extract video id from JWPlayer data
- [zippcast] Remove extractor (#10332)
+ [viceland] Add extractor (#8799)
+ [adobepass] Add base extractor for Adobe Pass Authentication
* [life:embed] Improve extraction
* [vgtv] Detect geo restricted videos (#10348)
+ [uplynk] Add extractor
* [xiami] Fix extraction (#10342)
version 2016.08.13
Core
* Show progress for curl external downloader
* Forward more options to curl external downloader
Extractors
* [pbs] Fix description extraction
* [franceculture] Fix extraction (#10324)
* [pornotube] Fix extraction (#10322)
* [4tube] Fix metadata extraction (#10321)
* [imgur] Fix width and height extraction (#10325)
* [expotv] Improve extraction
+ [vbox7] Fix extraction (#10309)
- [tapely] Remove extractor (#10323)
* [muenchentv] Fix extraction (#10313)
+ [24video] Add support for .me and .xxx TLDs
* [24video] Fix comment count extraction
* [sunporno] Add support for embed URLs
* [sunporno] Fix metadata extraction (#10316)
+ [hgtv] Add extractor for hgtv.ca (#3999)
- [pbs] Remove request to unavailable API
+ [pbs] Add support for high quality HTTP formats
+ [crunchyroll] Add support for HLS formats (#10301)
version 2016.08.12
Core
* Subtitles are now written as is. Newline conversions are disabled. (#10268)
+ Recognize more formats in unified_timestamp
Extractors
- [goldenmoustache] Remove extractor (#10298)
* [drtuber] Improve title extraction
* [drtuber] Make dislike count optional (#10297)
* [chirbit] Fix extraction (#10296)
* [francetvinfo] Relax URL regular expression
* [rtlnl] Relax URL regular expression (#10282)
* [formula1] Relax URL regular expression (#10283)
* [wat] Improve extraction (#10281)
* [ctsnews] Fix extraction
version 2016.08.10
Core
* Make --metadata-from-title non fatal when title does not match the pattern
* Introduce options for randomized sleep before each download
--min-sleep-interval and --max-sleep-interval (#9930)
* Respect default in _search_json_ld
Extractors
+ [uol] Add extractor for uol.com.br (#4263)
* [rbmaradio] Fix extraction and extract all formats (#10242)
+ [sonyliv] Add extractor for sonyliv.com (#10258)
* [aparat] Fix extraction
* [cwtv] Extract HTTP formats
+ [rozhlas] Add extractor for prehravac.rozhlas.cz (#10253)
* [kuwo:singer] Fix extraction
version 2016.08.07
Core
+ Add support for TV Parental Guidelines ratings in parse_age_limit
+ Add decode_png (#9706)
+ Add support for partOfTVSeries in JSON-LD
* Lower master M3U8 manifest preference for better format sorting
Extractors
+ [discoverygo] Add extractor (#10245)
* [flipagram] Make JSON-LD extraction non fatal
* [generic] Make JSON-LD extraction non fatal
+ [bbc] Add support for morph embeds (#10239)
* [tnaflixnetworkbase] Improve title extraction
* [tnaflix] Fix metadata extraction (#10249)
* [fox] Fix theplatform release URL query
* [openload] Fix extraction (#9706)
* [bbc] Skip duplicate manifest URLs
* [bbc] Improve format code
+ [bbc] Add support for DASH and F4M
* [bbc] Improve format sorting and listing
* [bbc] Improve playlist extraction
+ [pokemon] Add extractor (#10093)
+ [condenast] Add fallback scenario for video info extraction
version 2016.08.06
Core
* Add support for JSON-LD root list entries (#10203)
* Improve unified_timestamp
* Lower preference of RTSP formats in generic sorting
+ Add support for multiple properties in _og_search_property
* Improve password hiding from verbose output
Extractors
+ [adultswim] Add support for trailers (#10235)
* [archiveorg] Improve extraction (#10219)
+ [jwplatform] Add support for playlists
+ [jwplatform] Add support for relative URLs
* [jwplatform] Improve audio detection
+ [tvplay] Capture and output native error message
+ [tvplay] Extract series metadata
+ [tvplay] Add support for subtitles (#10194)
* [tvp] Improve extraction (#7799)
* [cbslocal] Fix timestamp parsing (#10213)
+ [naver] Add support for subtitles (#8096)
* [naver] Improve extraction
* [condenast] Improve extraction
* [engadget] Relax URL regular expression
* [5min] Fix extraction
+ [nationalgeographic] Add support for Episode Guide
+ [kaltura] Add support for subtitles
* [kaltura] Optimize network requests
+ [vodplatform] Add extractor for vod-platform.net
- [gamekings] Remove extractor
* [limelight] Extract HTTP formats
* [ntvru] Fix extraction
+ [comedycentral] Re-add :tds and :thedailyshow shortnames
version 2016.08.01
Fixed/improved extractors
- [yandexmusic:track] Adapt to changes in track location JSON (#10193)
- [bloomberg] Support another form of player (#10187)
- [limelight] Skip DRM protected videos
- [safari] Relax regular expressions for URL matching (#10202)
- [cwtv] Add support for cwtvpr.com (#10196)
version 2016.07.30
Fixed/improved extractors
- [twitch:clips] Sort formats
- [tv2] Use m3u8_native
- [tv2:article] Fix video detection (#10188)
- rtve (#10076)
- [dailymotion:playlist] Optimize download archive processing (#10180)
version 2016.07.28
Fixed/improved extractors
- shared (#10170)
- soundcloud (#10179)
- twitch (#9767)
version 2016.07.26.2
Fixed/improved extractors
- smotri
- camdemy
- mtv
- comedycentral
- cmt
- cbc
- mgtv
- orf
version 2016.07.24
New extractors
- arkena (#8682)
- lcp (#8682)
Fixed/improved extractors
- facebook (#10151)
- dailymail
- telegraaf
- dcn
- onet
- tvp
Miscellaneous
- Support $Time$ in DASH manifests
version 2016.07.22
New extractors
- odatv (#9285)
Fixed/improved extractors
- bbc
- youjizz (#10131)
- youtube (#10140)
- pornhub (#10138)
- eporner (#10139)
version 2016.07.17
New extractors
- nintendo (#9986)
- streamable (#9122)
Fixed/improved extractors
- ard (#10095)
- mtv
- comedycentral (#10101)
- viki (#10098)
- spike (#10106)
Miscellaneous
- Improved twitter player detection (#10090)
version 2016.07.16
New extractors
- ninenow (#5181)
Fixed/improved extractors
- rtve (#10076)
- brightcove
- 3qsdn
- syfy (#9087, #3820, #2388)
- youtube (#10083)
Miscellaneous
- Fix subtitle embedding for video-only and audio-only files (#10081)
version 2016.07.13
New extractors
- rudo
Fixed/improved extractors
- biobiochiletv
- tvplay
- dbtv
- brightcove
- tmz
- youtube (#10059)
- shahid (#10062)
- vk
- ellentv (#10067)
version 2016.07.11
New Extractors
- roosterteeth (#9864)
Fixed/improved extractors
- miomio (#9605)
- vuclip
- youtube
- vidzi (#10058)
version 2016.07.09.2
Fixed/improved extractors
- vimeo (#1638)
- facebook (#10048)
- lynda (#10047)
- animeondemand
Fixed/improved features
- Embedding subtitles no longer throws an error with problematic inputs (#9063)
version 2016.07.09.1
Fixed/improved extractors
- youtube
- ard
- srmediatek (#9373)
version 2016.07.09
New extractors
- Flipagram (#9898)
Fixed/improved extractors
- telecinco
- toutv
- radiocanada
- tweakers (#9516)
- lynda
- nick (#7542)
- polskieradio (#10028)
- le
- facebook (#9851)
- mgtv
- animeondemand (#10031)
Fixed/improved features
- `--postprocessor-args` and `--downloader-args` now accepts non-ASCII inputs
on non-Windows systems
version 2016.07.07
New extractors
- kamcord (#10001)
Fixed/improved extractors
- spiegel (#10018)
- metacafe (#8539, #3253)
- onet (#9950)
- francetv (#9955)
- brightcove (#9965)
- daum (#9972)
version 2016.07.06
Fixed/improved extractors
- youtube (#10007, #10009)
- xuite
- stitcher
- spiegel
- slideshare
- sandia
- rtvnh
- prosiebensat1
- onionstudios
version 2016.07.05
Fixed/improved extractors
- brightcove
- yahoo (#9995)
- pornhub (#9997)
- iqiyi
- kaltura (#5557)
- la7
- Changed features
- Rename --cn-verfication-proxy to --geo-verification-proxy
Miscellaneous
- Add script for displaying downloads statistics
version 2016.07.03.1
Fixed/improved extractors
- theplatform
- aenetworks
- nationalgeographic
- hrti (#9482)
- facebook (#5701)
- buzzfeed (#5701)
- rai (#8617, #9157, #9232, #8552, #8551)
- nationalgeographic (#9991)
- iqiyi
version 2016.07.03
New extractors
- hrti (#9482)
Fixed/improved extractors
- vk (#9981)
- facebook (#9938)
- xtube (#9953, #9961)
version 2016.07.02
New extractors
- fusion (#9958)
Fixed/improved extractors
- twitch (#9975)
- vine (#9970)
- periscope (#9967)
- pornhub (#8696)
version 2016.07.01
New extractors
- 9c9media
- ctvnews (#2156)
- ctv (#4077)
Fixed/Improved extractors
- rds
- meta (#8789)
- pornhub (#9964)
- sixplay (#2183)
New features
- Accept quoted strings across multiple lines (#9940)

46
Makefile
View File

@ -1,10 +1,9 @@
all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites
clean:
rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part *.info.json CONTRIBUTING.md.tmp
cleanall: clean
rm -f youtube-dl youtube-dl.exe
rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part* *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
find . -name "*.pyc" -delete
find . -name "*.class" -delete
PREFIX ?= /usr/local
BINDIR ?= $(PREFIX)/bin
@ -13,15 +12,7 @@ SHAREDIR ?= $(PREFIX)/share
PYTHON ?= /usr/bin/env python
# set SYSCONFDIR to /etc if PREFIX=/usr or PREFIX=/usr/local
ifeq ($(PREFIX),/usr)
SYSCONFDIR=/etc
else
ifeq ($(PREFIX),/usr/local)
SYSCONFDIR=/etc
else
SYSCONFDIR=$(PREFIX)/etc
endif
endif
SYSCONFDIR != if [ $(PREFIX) = /usr -o $(PREFIX) = /usr/local ]; then echo /etc; else echo $(PREFIX)/etc; fi
install: youtube-dl youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
install -d $(DESTDIR)$(BINDIR)
@ -46,7 +37,7 @@ test:
ot: offlinetest
offlinetest: codetest
nosetests --verbose test --exclude test_download --exclude test_age_restriction --exclude test_subtitles --exclude test_write_annotations --exclude test_youtube_lists
$(PYTHON) -m nose --verbose test --exclude test_download.py --exclude test_age_restriction.py --exclude test_subtitles.py --exclude test_write_annotations.py --exclude test_youtube_lists.py --exclude test_iqiyi_sdk_interpreter.py --exclude test_socks.py
tar: youtube-dl.tar.gz
@ -63,38 +54,47 @@ youtube-dl: youtube_dl/*.py youtube_dl/*/*.py
chmod a+x youtube-dl
README.md: youtube_dl/*.py youtube_dl/*/*.py
COLUMNS=80 python youtube_dl/__main__.py --help | python devscripts/make_readme.py
COLUMNS=80 $(PYTHON) youtube_dl/__main__.py --help | $(PYTHON) devscripts/make_readme.py
CONTRIBUTING.md: README.md
python devscripts/make_contributing.py README.md CONTRIBUTING.md
$(PYTHON) devscripts/make_contributing.py README.md CONTRIBUTING.md
.github/ISSUE_TEMPLATE.md: devscripts/make_issue_template.py .github/ISSUE_TEMPLATE_tmpl.md youtube_dl/version.py
$(PYTHON) devscripts/make_issue_template.py .github/ISSUE_TEMPLATE_tmpl.md .github/ISSUE_TEMPLATE.md
supportedsites:
python devscripts/make_supportedsites.py docs/supportedsites.md
$(PYTHON) devscripts/make_supportedsites.py docs/supportedsites.md
README.txt: README.md
pandoc -f markdown -t plain README.md -o README.txt
youtube-dl.1: README.md
python devscripts/prepare_manpage.py >youtube-dl.1.temp.md
$(PYTHON) devscripts/prepare_manpage.py youtube-dl.1.temp.md
pandoc -s -f markdown -t man youtube-dl.1.temp.md -o youtube-dl.1
rm -f youtube-dl.1.temp.md
youtube-dl.bash-completion: youtube_dl/*.py youtube_dl/*/*.py devscripts/bash-completion.in
python devscripts/bash-completion.py
$(PYTHON) devscripts/bash-completion.py
bash-completion: youtube-dl.bash-completion
youtube-dl.zsh: youtube_dl/*.py youtube_dl/*/*.py devscripts/zsh-completion.in
python devscripts/zsh-completion.py
$(PYTHON) devscripts/zsh-completion.py
zsh-completion: youtube-dl.zsh
youtube-dl.fish: youtube_dl/*.py youtube_dl/*/*.py devscripts/fish-completion.in
python devscripts/fish-completion.py
$(PYTHON) devscripts/fish-completion.py
fish-completion: youtube-dl.fish
youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
lazy-extractors: youtube_dl/extractor/lazy_extractors.py
_EXTRACTOR_FILES != find youtube_dl/extractor -iname '*.py' -and -not -iname 'lazy_extractors.py'
youtube_dl/extractor/lazy_extractors.py: devscripts/make_lazy_extractors.py devscripts/lazy_load_template.py $(_EXTRACTOR_FILES)
$(PYTHON) devscripts/make_lazy_extractors.py $@
youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish ChangeLog
@tar -czf youtube-dl.tar.gz --transform "s|^|youtube-dl/|" --owner 0 --group 0 \
--exclude '*.DS_Store' \
--exclude '*.kate-swp' \
@ -107,7 +107,7 @@ youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-
--exclude 'docs/_build' \
-- \
bin devscripts test youtube_dl docs \
LICENSE README.md README.txt \
ChangeLog LICENSE README.md README.txt \
Makefile MANIFEST.in youtube-dl.1 youtube-dl.bash-completion \
youtube-dl.zsh youtube-dl.fish setup.py \
youtube-dl

1031
README.md
View File

File diff suppressed because it is too large Load Diff

2
devscripts/bash-completion.py
View File

@ -5,7 +5,7 @@ import os
from os.path import dirname as dirn
import sys
sys.path.append(dirn(dirn((os.path.abspath(__file__)))))
sys.path.insert(0, dirn(dirn((os.path.abspath(__file__)))))
import youtube_dl
BASH_COMPLETION_FILE = "youtube-dl.bash-completion"

75
devscripts/buildserver.py
View File

@ -1,17 +1,38 @@
#!/usr/bin/python3
from http.server import HTTPServer, BaseHTTPRequestHandler
from socketserver import ThreadingMixIn
import argparse
import ctypes
import functools
import shutil
import subprocess
import sys
import tempfile
import threading
import traceback
import os.path
sys.path.insert(0, os.path.dirname(os.path.dirname((os.path.abspath(__file__)))))
from youtube_dl.compat import (
compat_input,
compat_http_server,
compat_str,
compat_urlparse,
)
class BuildHTTPServer(ThreadingMixIn, HTTPServer):
# These are not used outside of buildserver.py thus not in compat.py
try:
import winreg as compat_winreg
except ImportError: # Python 2
import _winreg as compat_winreg
try:
import socketserver as compat_socketserver
except ImportError: # Python 2
import SocketServer as compat_socketserver
class BuildHTTPServer(compat_socketserver.ThreadingMixIn, compat_http_server.HTTPServer):
allow_reuse_address = True
@ -191,7 +212,7 @@ def main(args=None):
action='store_const', dest='action', const='service',
help='Run as a Windows service')
parser.add_argument('-b', '--bind', metavar='<host:port>',
action='store', default='localhost:8142',
action='store', default='0.0.0.0:8142',
help='Bind to host:port (default %default)')
options = parser.parse_args(args=args)
@ -216,7 +237,7 @@ def main(args=None):
srv = BuildHTTPServer((host, port), BuildHTTPRequestHandler)
thr = threading.Thread(target=srv.serve_forever)
thr.start()
input('Press ENTER to shut down')
compat_input('Press ENTER to shut down')
srv.shutdown()
thr.join()
@ -231,8 +252,6 @@ def rmtree(path):
os.remove(fname)
os.rmdir(path)
#==============================================================================
class BuildError(Exception):
def __init__(self, output, code=500):
@ -249,15 +268,25 @@ class HTTPError(BuildError):
class PythonBuilder(object):
def __init__(self, **kwargs):
pythonVersion = kwargs.pop('python', '2.7')
try:
key = _winreg.OpenKey(_winreg.HKEY_LOCAL_MACHINE, r'SOFTWARE\Python\PythonCore\%s\InstallPath' % pythonVersion)
python_version = kwargs.pop('python', '3.4')
python_path = None
for node in ('Wow6432Node\\', ''):
try:
self.pythonPath, _ = _winreg.QueryValueEx(key, '')
finally:
_winreg.CloseKey(key)
except Exception:
raise BuildError('No such Python version: %s' % pythonVersion)
key = compat_winreg.OpenKey(
compat_winreg.HKEY_LOCAL_MACHINE,
r'SOFTWARE\%sPython\PythonCore\%s\InstallPath' % (node, python_version))
try:
python_path, _ = compat_winreg.QueryValueEx(key, '')
finally:
compat_winreg.CloseKey(key)
break
except Exception:
pass
if not python_path:
raise BuildError('No such Python version: %s' % python_version)
self.pythonPath = python_path
super(PythonBuilder, self).__init__(**kwargs)
@ -305,8 +334,10 @@ class YoutubeDLBuilder(object):
def build(self):
try:
subprocess.check_output([os.path.join(self.pythonPath, 'python.exe'), 'setup.py', 'py2exe'],
cwd=self.buildPath)
proc = subprocess.Popen([os.path.join(self.pythonPath, 'python.exe'), 'setup.py', 'py2exe'], stdin=subprocess.PIPE, cwd=self.buildPath)
proc.wait()
#subprocess.check_output([os.path.join(self.pythonPath, 'python.exe'), 'setup.py', 'py2exe'],
# cwd=self.buildPath)
except subprocess.CalledProcessError as e:
raise BuildError(e.output)
@ -369,12 +400,12 @@ class Builder(PythonBuilder, GITBuilder, YoutubeDLBuilder, DownloadBuilder, Clea
pass
class BuildHTTPRequestHandler(BaseHTTPRequestHandler):
class BuildHTTPRequestHandler(compat_http_server.BaseHTTPRequestHandler):
actionDict = {'build': Builder, 'download': Builder} # They're the same, no more caching.
def do_GET(self):
path = urlparse.urlparse(self.path)
paramDict = dict([(key, value[0]) for key, value in urlparse.parse_qs(path.query).items()])
path = compat_urlparse.urlparse(self.path)
paramDict = dict([(key, value[0]) for key, value in compat_urlparse.parse_qs(path.query).items()])
action, _, path = path.path.strip('/').partition('/')
if path:
path = path.split('/')
@ -388,7 +419,7 @@ class BuildHTTPRequestHandler(BaseHTTPRequestHandler):
builder.close()
except BuildError as e:
self.send_response(e.code)
msg = unicode(e).encode('UTF-8')
msg = compat_str(e).encode('UTF-8')
self.send_header('Content-Type', 'text/plain; charset=UTF-8')
self.send_header('Content-Length', len(msg))
self.end_headers()
@ -400,7 +431,5 @@ class BuildHTTPRequestHandler(BaseHTTPRequestHandler):
else:
self.send_response(500, 'Malformed URL')
#==============================================================================
if __name__ == '__main__':
main()

10
devscripts/check-porn.py
View File

@ -28,7 +28,7 @@ for test in get_testcases():
if METHOD == 'EURISTIC':
try:
webpage = compat_urllib_request.urlopen(test['url'], timeout=10).read()
except:
except Exception:
print('\nFail: {0}'.format(test['name']))
continue
@ -45,12 +45,12 @@ for test in get_testcases():
RESULT = ('.' + domain + '\n' in LIST or '\n' + domain + '\n' in LIST)
if RESULT and ('info_dict' not in test or 'age_limit' not in test['info_dict']
or test['info_dict']['age_limit'] != 18):
if RESULT and ('info_dict' not in test or 'age_limit' not in test['info_dict'] or
test['info_dict']['age_limit'] != 18):
print('\nPotential missing age_limit check: {0}'.format(test['name']))
elif not RESULT and ('info_dict' in test and 'age_limit' in test['info_dict']
and test['info_dict']['age_limit'] == 18):
elif not RESULT and ('info_dict' in test and 'age_limit' in test['info_dict'] and
test['info_dict']['age_limit'] == 18):
print('\nPotential false negative: {0}'.format(test['name']))
else:

111
devscripts/create-github-release.py Normal file
View File

@ -0,0 +1,111 @@
#!/usr/bin/env python
from __future__ import unicode_literals
import base64
import json
import mimetypes
import netrc
import optparse
import os
import sys
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.compat import (
compat_basestring,
compat_input,
compat_getpass,
compat_print,
compat_urllib_request,
)
from youtube_dl.utils import (
make_HTTPS_handler,
sanitized_Request,
)
class GitHubReleaser(object):
_API_URL = 'https://api.github.com/repos/rg3/youtube-dl/releases'
_UPLOADS_URL = 'https://uploads.github.com/repos/rg3/youtube-dl/releases/%s/assets?name=%s'
_NETRC_MACHINE = 'github.com'
def __init__(self, debuglevel=0):
self._init_github_account()
https_handler = make_HTTPS_handler({}, debuglevel=debuglevel)
self._opener = compat_urllib_request.build_opener(https_handler)
def _init_github_account(self):
try:
info = netrc.netrc().authenticators(self._NETRC_MACHINE)
if info is not None:
self._username = info[0]
self._password = info[2]
compat_print('Using GitHub credentials found in .netrc...')
return
else:
compat_print('No GitHub credentials found in .netrc')
except (IOError, netrc.NetrcParseError):
compat_print('Unable to parse .netrc')
self._username = compat_input(
'Type your GitHub username or email address and press [Return]: ')
self._password = compat_getpass(
'Type your GitHub password and press [Return]: ')
def _call(self, req):
if isinstance(req, compat_basestring):
req = sanitized_Request(req)
# Authorizing manually since GitHub does not response with 401 with
# WWW-Authenticate header set (see
# https://developer.github.com/v3/#basic-authentication)
b64 = base64.b64encode(
('%s:%s' % (self._username, self._password)).encode('utf-8')).decode('ascii')
req.add_header('Authorization', 'Basic %s' % b64)
response = self._opener.open(req).read().decode('utf-8')
return json.loads(response)
def list_releases(self):
return self._call(self._API_URL)
def create_release(self, tag_name, name=None, body='', draft=False, prerelease=False):
data = {
'tag_name': tag_name,
'target_commitish': 'master',
'name': name,
'body': body,
'draft': draft,
'prerelease': prerelease,
}
req = sanitized_Request(self._API_URL, json.dumps(data).encode('utf-8'))
return self._call(req)
def create_asset(self, release_id, asset):
asset_name = os.path.basename(asset)
url = self._UPLOADS_URL % (release_id, asset_name)
# Our files are small enough to be loaded directly into memory.
data = open(asset, 'rb').read()
req = sanitized_Request(url, data)
mime_type, _ = mimetypes.guess_type(asset_name)
req.add_header('Content-Type', mime_type or 'application/octet-stream')
return self._call(req)
def main():
parser = optparse.OptionParser(usage='%prog VERSION BUILDPATH')
options, args = parser.parse_args()
if len(args) != 2:
parser.error('Expected a version and a build directory')
version, build_path = args
releaser = GitHubReleaser()
new_release = releaser.create_release(version, name='youtube-dl %s' % version)
release_id = new_release['id']
for asset in os.listdir(build_path):
compat_print('Uploading %s...' % asset)
releaser.create_asset(release_id, os.path.join(build_path, asset))
if __name__ == '__main__':
main()

2
devscripts/fish-completion.py
View File

@ -6,7 +6,7 @@ import os
from os.path import dirname as dirn
import sys
sys.path.append(dirn(dirn((os.path.abspath(__file__)))))
sys.path.insert(0, dirn(dirn((os.path.abspath(__file__)))))
import youtube_dl
from youtube_dl.utils import shell_quote

42
devscripts/generate_aes_testdata.py Normal file
View File

@ -0,0 +1,42 @@
from __future__ import unicode_literals
import codecs
import subprocess
import os
import sys
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.utils import intlist_to_bytes
from youtube_dl.aes import aes_encrypt, key_expansion
secret_msg = b'Secret message goes here'
def hex_str(int_list):
return codecs.encode(intlist_to_bytes(int_list), 'hex')
def openssl_encode(algo, key, iv):
cmd = ['openssl', 'enc', '-e', '-' + algo, '-K', hex_str(key), '-iv', hex_str(iv)]
prog = subprocess.Popen(cmd, stdin=subprocess.PIPE, stdout=subprocess.PIPE)
out, _ = prog.communicate(secret_msg)
return out
iv = key = [0x20, 0x15] + 14 * [0]
r = openssl_encode('aes-128-cbc', key, iv)
print('aes_cbc_decrypt')
print(repr(r))
password = key
new_key = aes_encrypt(password, key_expansion(password))
r = openssl_encode('aes-128-ctr', new_key, iv)
print('aes_decrypt_text 16')
print(repr(r))
password = key + 16 * [0]
new_key = aes_encrypt(password, key_expansion(password)) * (32 // 16)
r = openssl_encode('aes-256-ctr', new_key, iv)
print('aes_decrypt_text 32')
print(repr(r))

4
devscripts/gh-pages/generate-download.py
View File

@ -15,13 +15,9 @@ data = urllib.request.urlopen(URL).read()
with open('download.html.in', 'r', encoding='utf-8') as tmplf:
template = tmplf.read()
md5sum = hashlib.md5(data).hexdigest()
sha1sum = hashlib.sha1(data).hexdigest()
sha256sum = hashlib.sha256(data).hexdigest()
template = template.replace('@PROGRAM_VERSION@', version)
template = template.replace('@PROGRAM_URL@', URL)
template = template.replace('@PROGRAM_MD5SUM@', md5sum)
template = template.replace('@PROGRAM_SHA1SUM@', sha1sum)
template = template.replace('@PROGRAM_SHA256SUM@', sha256sum)
template = template.replace('@EXE_URL@', versions_info['versions'][version]['exe'][0])
template = template.replace('@EXE_SHA256SUM@', versions_info['versions'][version]['exe'][1])

2
devscripts/gh-pages/update-copyright.py
View File

@ -5,7 +5,7 @@ from __future__ import with_statement, unicode_literals
import datetime
import glob
import io # For Python 2 compatibilty
import io # For Python 2 compatibility
import os
import re

2
devscripts/gh-pages/update-sites.py
View File

@ -6,7 +6,7 @@ import os
import textwrap
# We must be able to import youtube_dl
sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
import youtube_dl

19
devscripts/lazy_load_template.py Normal file
View File

@ -0,0 +1,19 @@
# encoding: utf-8
from __future__ import unicode_literals
import re
class LazyLoadExtractor(object):
_module = None
@classmethod
def ie_key(cls):
return cls.__name__[:-2]
def __new__(cls, *args, **kwargs):
mod = __import__(cls._module, fromlist=(cls.__name__,))
real_cls = getattr(mod, cls.__name__)
instance = real_cls.__new__(real_cls)
instance.__init__(*args, **kwargs)
return instance

29
devscripts/make_issue_template.py Normal file
View File

@ -0,0 +1,29 @@
#!/usr/bin/env python
from __future__ import unicode_literals
import io
import optparse
def main():
parser = optparse.OptionParser(usage='%prog INFILE OUTFILE')
options, args = parser.parse_args()
if len(args) != 2:
parser.error('Expected an input and an output filename')
infile, outfile = args
with io.open(infile, encoding='utf-8') as inf:
issue_template_tmpl = inf.read()
# Get the version from youtube_dl/version.py without importing the package
exec(compile(open('youtube_dl/version.py').read(),
'youtube_dl/version.py', 'exec'))
out = issue_template_tmpl % {'version': locals()['__version__']}
with io.open(outfile, 'w', encoding='utf-8') as outf:
outf.write(out)
if __name__ == '__main__':
main()

98
devscripts/make_lazy_extractors.py Normal file
View File

@ -0,0 +1,98 @@
from __future__ import unicode_literals, print_function
from inspect import getsource
import os
from os.path import dirname as dirn
import sys
print('WARNING: Lazy loading extractors is an experimental feature that may not always work', file=sys.stderr)
sys.path.insert(0, dirn(dirn((os.path.abspath(__file__)))))
lazy_extractors_filename = sys.argv[1]
if os.path.exists(lazy_extractors_filename):
os.remove(lazy_extractors_filename)
from youtube_dl.extractor import _ALL_CLASSES
from youtube_dl.extractor.common import InfoExtractor, SearchInfoExtractor
with open('devscripts/lazy_load_template.py', 'rt') as f:
module_template = f.read()
module_contents = [
module_template + '\n' + getsource(InfoExtractor.suitable) + '\n',
'class LazyLoadSearchExtractor(LazyLoadExtractor):\n pass\n']
ie_template = '''
class {name}({bases}):
_VALID_URL = {valid_url!r}
_module = '{module}'
'''
make_valid_template = '''
@classmethod
def _make_valid_url(cls):
return {valid_url!r}
'''
def get_base_name(base):
if base is InfoExtractor:
return 'LazyLoadExtractor'
elif base is SearchInfoExtractor:
return 'LazyLoadSearchExtractor'
else:
return base.__name__
def build_lazy_ie(ie, name):
valid_url = getattr(ie, '_VALID_URL', None)
s = ie_template.format(
name=name,
bases=', '.join(map(get_base_name, ie.__bases__)),
valid_url=valid_url,
module=ie.__module__)
if ie.suitable.__func__ is not InfoExtractor.suitable.__func__:
s += '\n' + getsource(ie.suitable)
if hasattr(ie, '_make_valid_url'):
# search extractors
s += make_valid_template.format(valid_url=ie._make_valid_url())
return s
# find the correct sorting and add the required base classes so that sublcasses
# can be correctly created
classes = _ALL_CLASSES[:-1]
ordered_cls = []
while classes:
for c in classes[:]:
bases = set(c.__bases__) - set((object, InfoExtractor, SearchInfoExtractor))
stop = False
for b in bases:
if b not in classes and b not in ordered_cls:
if b.__name__ == 'GenericIE':
exit()
classes.insert(0, b)
stop = True
if stop:
break
if all(b in ordered_cls for b in bases):
ordered_cls.append(c)
classes.remove(c)
break
ordered_cls.append(_ALL_CLASSES[-1])
names = []
for ie in ordered_cls:
name = ie.__name__
src = build_lazy_ie(ie, name)
module_contents.append(src)
if ie in _ALL_CLASSES:
names.append(name)
module_contents.append(
'_ALL_CLASSES = [{0}]'.format(', '.join(names)))
module_src = '\n'.join(module_contents) + '\n'
with open(lazy_extractors_filename, 'wt') as f:
f.write(module_src)

2
devscripts/make_supportedsites.py
View File

@ -9,7 +9,7 @@ import sys
# Import youtube_dl
ROOT_DIR = os.path.join(os.path.dirname(__file__), '..')
sys.path.append(ROOT_DIR)
sys.path.insert(0, ROOT_DIR)
import youtube_dl

68
devscripts/prepare_manpage.py
View File

@ -1,16 +1,13 @@
from __future__ import unicode_literals
import io
import optparse
import os.path
import sys
import re
ROOT_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
README_FILE = os.path.join(ROOT_DIR, 'README.md')
with io.open(README_FILE, encoding='utf-8') as f:
readme = f.read()
PREFIX = '''%YOUTUBE-DL(1)
# NAME
@ -22,11 +19,60 @@ youtube\-dl \- download videos from youtube.com or other video platforms
**youtube-dl** \[OPTIONS\] URL [URL...]
'''
readme = re.sub(r'(?s)^.*?(?=# DESCRIPTION)', '', readme)
readme = re.sub(r'\s+youtube-dl \[OPTIONS\] URL \[URL\.\.\.\]', '', readme)
readme = PREFIX + readme
if sys.version_info < (3, 0):
print(readme.encode('utf-8'))
else:
print(readme)
def main():
parser = optparse.OptionParser(usage='%prog OUTFILE.md')
options, args = parser.parse_args()
if len(args) != 1:
parser.error('Expected an output filename')
outfile, = args
with io.open(README_FILE, encoding='utf-8') as f:
readme = f.read()
readme = re.sub(r'(?s)^.*?(?=# DESCRIPTION)', '', readme)
readme = re.sub(r'\s+youtube-dl \[OPTIONS\] URL \[URL\.\.\.\]', '', readme)
readme = PREFIX + readme
readme = filter_options(readme)
with io.open(outfile, 'w', encoding='utf-8') as outf:
outf.write(readme)
def filter_options(readme):
ret = ''
in_options = False
for line in readme.split('\n'):
if line.startswith('# '):
if line[2:].startswith('OPTIONS'):
in_options = True
else:
in_options = False
if in_options:
if line.lstrip().startswith('-'):
split = re.split(r'\s{2,}', line.lstrip())
# Description string may start with `-` as well. If there is
# only one piece then it's a description bit not an option.
if len(split) > 1:
option, description = split
split_option = option.split(' ')
if not split_option[-1].startswith('-'): # metavar
option = ' '.join(split_option[:-1] + ['*%s*' % split_option[-1]])
# Pandoc's definition_lists. See http://pandoc.org/README.html
# for more information.
ret += '\n%s\n: %s\n' % (option, description)
continue
ret += line.lstrip() + '\n'
else:
ret += line + '\n'
return ret
if __name__ == '__main__':
main()

65
devscripts/release.sh
View File

@ -6,7 +6,7 @@
# * the git config user.signingkey is properly set
# You will need
# pip install coverage nose rsa
# pip install coverage nose rsa wheel
# TODO
# release notes
@ -15,10 +15,33 @@
set -e
skip_tests=true
if [ "$1" = '--run-tests' ]; then
skip_tests=false
shift
fi
gpg_sign_commits=""
buildserver='localhost:8142'
while true
do
case "$1" in
--run-tests)
skip_tests=false
shift
;;
--gpg-sign-commits|-S)
gpg_sign_commits="-S"
shift
;;
--buildserver)
buildserver="$2"
shift 2
;;
--*)
echo "ERROR: unknown option $1"
exit 1
;;
*)
break
;;
esac
done
if [ -z "$1" ]; then echo "ERROR: specify version number like this: $0 1994.09.06"; exit 1; fi
version="$1"
@ -33,9 +56,15 @@ if [ ! -z "`git status --porcelain | grep -v CHANGELOG`" ]; then echo 'ERROR: th
useless_files=$(find youtube_dl -type f -not -name '*.py')
if [ ! -z "$useless_files" ]; then echo "ERROR: Non-.py files in youtube_dl: $useless_files"; exit 1; fi
if [ ! -f "updates_key.pem" ]; then echo 'ERROR: updates_key.pem missing'; exit 1; fi
if ! type pandoc >/dev/null 2>/dev/null; then echo 'ERROR: pandoc is missing'; exit 1; fi
if ! python3 -c 'import rsa' 2>/dev/null; then echo 'ERROR: python3-rsa is missing'; exit 1; fi
if ! python3 -c 'import wheel' 2>/dev/null; then echo 'ERROR: wheel is missing'; exit 1; fi
read -p "Is ChangeLog up to date? (y/n) " -n 1
if [[ ! $REPLY =~ ^[Yy]$ ]]; then exit 1; fi
/bin/echo -e "\n### First of all, testing..."
make cleanall
make clean
if $skip_tests ; then
echo 'SKIPPING TESTS'
else
@ -45,10 +74,13 @@ fi
/bin/echo -e "\n### Changing version in version.py..."
sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/version.py
/bin/echo -e "\n### Committing README.md and youtube_dl/version.py..."
make README.md
git add README.md youtube_dl/version.py
git commit -m "release $version"
/bin/echo -e "\n### Changing version in ChangeLog..."
sed -i "s/<unreleased>/$version/" ChangeLog
/bin/echo -e "\n### Committing documentation, templates and youtube_dl/version.py..."
make README.md CONTRIBUTING.md .github/ISSUE_TEMPLATE.md supportedsites
git add README.md CONTRIBUTING.md .github/ISSUE_TEMPLATE.md docs/supportedsites.md youtube_dl/version.py ChangeLog
git commit $gpg_sign_commits -m "release $version"
/bin/echo -e "\n### Now tagging, signing and pushing..."
git tag -s -m "Release $version" "$version"
@ -64,7 +96,7 @@ git push origin "$version"
REV=$(git rev-parse HEAD)
make youtube-dl youtube-dl.tar.gz
read -p "VM running? (y/n) " -n 1
wget "http://localhost:8142/build/rg3/youtube-dl/youtube-dl.exe?rev=$REV" -O youtube-dl.exe
wget "http://$buildserver/build/rg3/youtube-dl/youtube-dl.exe?rev=$REV" -O youtube-dl.exe
mkdir -p "build/$version"
mv youtube-dl youtube-dl.exe "build/$version"
mv youtube-dl.tar.gz "build/$version/youtube-dl-$version.tar.gz"
@ -74,15 +106,16 @@ RELEASE_FILES="youtube-dl youtube-dl.exe youtube-dl-$version.tar.gz"
(cd build/$version/ && sha256sum $RELEASE_FILES > SHA2-256SUMS)
(cd build/$version/ && sha512sum $RELEASE_FILES > SHA2-512SUMS)
/bin/echo -e "\n### Signing and uploading the new binaries to yt-dl.org ..."
/bin/echo -e "\n### Signing and uploading the new binaries to GitHub..."
for f in $RELEASE_FILES; do gpg --passphrase-repeat 5 --detach-sig "build/$version/$f"; done
scp -r "build/$version" ytdl@yt-dl.org:html/tmp/
ssh ytdl@yt-dl.org "mv html/tmp/$version html/downloads/"
ROOT=$(pwd)
python devscripts/create-github-release.py $version "$ROOT/build/$version"
ssh ytdl@yt-dl.org "sh html/update_latest.sh $version"
/bin/echo -e "\n### Now switching to gh-pages..."
git clone --branch gh-pages --single-branch . build/gh-pages
ROOT=$(pwd)
(
set -e
ORIGIN_URL=$(git config --get remote.origin.url)
@ -94,7 +127,7 @@ ROOT=$(pwd)
"$ROOT/devscripts/gh-pages/update-copyright.py"
"$ROOT/devscripts/gh-pages/update-sites.py"
git add *.html *.html.in update
git commit -m "release $version"
git commit $gpg_sign_commits -m "release $version"
git push "$ROOT" gh-pages
git push "$ORIGIN_URL" gh-pages
)

47
devscripts/show-downloads-statistics.py Normal file
View File

@ -0,0 +1,47 @@
#!/usr/bin/env python
from __future__ import unicode_literals
import itertools
import json
import os
import re
import sys
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.compat import (
compat_print,
compat_urllib_request,
)
from youtube_dl.utils import format_bytes
def format_size(bytes):
return '%s (%d bytes)' % (format_bytes(bytes), bytes)
total_bytes = 0
for page in itertools.count(1):
releases = json.loads(compat_urllib_request.urlopen(
'https://api.github.com/repos/rg3/youtube-dl/releases?page=%s' % page
).read().decode('utf-8'))
if not releases:
break
for release in releases:
compat_print(release['name'])
for asset in release['assets']:
asset_name = asset['name']
total_bytes += asset['download_count'] * asset['size']
if all(not re.match(p, asset_name) for p in (
r'^youtube-dl$',
r'^youtube-dl-\d{4}\.\d{2}\.\d{2}(?:\.\d+)?\.tar\.gz$',
r'^youtube-dl\.exe$')):
continue
compat_print(
' %s size: %s downloads: %d'
% (asset_name, format_size(asset['size']), asset['download_count']))
compat_print('total downloads traffic: %s' % format_size(total_bytes))

2
devscripts/zsh-completion.py
View File

@ -5,7 +5,7 @@ import os
from os.path import dirname as dirn
import sys
sys.path.append(dirn(dirn((os.path.abspath(__file__)))))
sys.path.insert(0, dirn(dirn((os.path.abspath(__file__)))))
import youtube_dl
ZSH_COMPLETION_FILE = "youtube-dl.zsh"

618
docs/supportedsites.md
View File

File diff suppressed because it is too large Load Diff

4
setup.cfg
View File

@ -2,5 +2,5 @@
universal = True
[flake8]
exclude = youtube_dl/extractor/__init__.py,devscripts/buildserver.py,setup.py,build
ignore = E501
exclude = youtube_dl/extractor/__init__.py,devscripts/buildserver.py,devscripts/lazy_load_template.py,devscripts/make_issue_template.py,setup.py,build,.git
ignore = E402,E501,E731

80
setup.py
View File

@ -8,11 +8,12 @@ import warnings
import sys
try:
from setuptools import setup
from setuptools import setup, Command
setuptools_available = True
except ImportError:
from distutils.core import setup
from distutils.core import setup, Command
setuptools_available = False
from distutils.spawn import spawn
try:
# This will create an exe that needs Microsoft Visual C++ 2008
@ -20,25 +21,37 @@ try:
import py2exe
except ImportError:
if len(sys.argv) >= 2 and sys.argv[1] == 'py2exe':
print("Cannot import py2exe", file=sys.stderr)
print('Cannot import py2exe', file=sys.stderr)
exit(1)
py2exe_options = {
"bundle_files": 1,
"compressed": 1,
"optimize": 2,
"dist_dir": '.',
"dll_excludes": ['w9xpopen.exe'],
'bundle_files': 1,
'compressed': 1,
'optimize': 2,
'dist_dir': '.',
'dll_excludes': ['w9xpopen.exe', 'crypt32.dll'],
}
# Get the version from youtube_dl/version.py without importing the package
exec(compile(open('youtube_dl/version.py').read(),
'youtube_dl/version.py', 'exec'))
DESCRIPTION = 'YouTube video downloader'
LONG_DESCRIPTION = 'Command-line program to download videos from YouTube.com and other video sites'
py2exe_console = [{
"script": "./youtube_dl/__main__.py",
"dest_base": "youtube-dl",
'script': './youtube_dl/__main__.py',
'dest_base': 'youtube-dl',
'version': __version__,
'description': DESCRIPTION,
'comments': LONG_DESCRIPTION,
'product_name': 'youtube-dl',
'product_version': __version__,
}]
py2exe_params = {
'console': py2exe_console,
'options': {"py2exe": py2exe_options},
'options': {'py2exe': py2exe_options},
'zipfile': None
}
@ -70,16 +83,27 @@ else:
else:
params['scripts'] = ['bin/youtube-dl']
# Get the version from youtube_dl/version.py without importing the package
exec(compile(open('youtube_dl/version.py').read(),
'youtube_dl/version.py', 'exec'))
class build_lazy_extractors(Command):
description = 'Build the extractor lazy loading module'
user_options = []
def initialize_options(self):
pass
def finalize_options(self):
pass
def run(self):
spawn(
[sys.executable, 'devscripts/make_lazy_extractors.py', 'youtube_dl/extractor/lazy_extractors.py'],
dry_run=self.dry_run,
)
setup(
name='youtube_dl',
version=__version__,
description='YouTube video downloader',
long_description='Small command-line program to download videos from'
' YouTube.com and other video sites.',
description=DESCRIPTION,
long_description=LONG_DESCRIPTION,
url='https://github.com/rg3/youtube-dl',
author='Ricardo Garcia',
author_email='ytdl@yt-dl.org',
@ -95,17 +119,19 @@ setup(
# test_requires = ['nosetest'],
classifiers=[
"Topic :: Multimedia :: Video",
"Development Status :: 5 - Production/Stable",
"Environment :: Console",
"License :: Public Domain",
"Programming Language :: Python :: 2.6",
"Programming Language :: Python :: 2.7",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.2",
"Programming Language :: Python :: 3.3",
"Programming Language :: Python :: 3.4",
'Topic :: Multimedia :: Video',
'Development Status :: 5 - Production/Stable',
'Environment :: Console',
'License :: Public Domain',
'Programming Language :: Python :: 2.6',
'Programming Language :: Python :: 2.7',
'Programming Language :: Python :: 3',
'Programming Language :: Python :: 3.2',
'Programming Language :: Python :: 3.3',
'Programming Language :: Python :: 3.4',
'Programming Language :: Python :: 3.5',
],
cmdclass={'build_lazy_extractors': build_lazy_extractors},
**params
)

140
test/helper.py
View File

@ -11,8 +11,11 @@ import sys
import youtube_dl.extractor
from youtube_dl import YoutubeDL
from youtube_dl.utils import (
from youtube_dl.compat import (
compat_os_name,
compat_str,
)
from youtube_dl.utils import (
preferredencoding,
write_string,
)
@ -21,8 +24,13 @@ from youtube_dl.utils import (
def get_params(override=None):
PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)),
"parameters.json")
LOCAL_PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)),
"local_parameters.json")
with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
parameters = json.load(pf)
if os.path.exists(LOCAL_PARAMETERS_FILE):
with io.open(LOCAL_PARAMETERS_FILE, encoding='utf-8') as pf:
parameters.update(json.load(pf))
if override:
parameters.update(override)
return parameters
@ -42,7 +50,7 @@ def report_warning(message):
Print the message to stderr, it will be prefixed with 'WARNING:'
If stderr is a tty file the 'WARNING:' will be colored
'''
if sys.stderr.isatty() and os.name != 'nt':
if sys.stderr.isatty() and compat_os_name != 'nt':
_msg_header = '\033[0;33mWARNING:\033[0m'
else:
_msg_header = 'WARNING:'
@ -89,48 +97,86 @@ def gettestcases(include_onlymatching=False):
md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
def expect_info_dict(self, got_dict, expected_dict):
for info_field, expected in expected_dict.items():
if isinstance(expected, compat_str) and expected.startswith('re:'):
got = got_dict.get(info_field)
match_str = expected[len('re:'):]
match_rex = re.compile(match_str)
def expect_value(self, got, expected, field):
if isinstance(expected, compat_str) and expected.startswith('re:'):
match_str = expected[len('re:'):]
match_rex = re.compile(match_str)
self.assertTrue(
isinstance(got, compat_str),
'Expected a %s object, but got %s for field %s' % (
compat_str.__name__, type(got).__name__, field))
self.assertTrue(
match_rex.match(got),
'field %s (value: %r) should match %r' % (field, got, match_str))
elif isinstance(expected, compat_str) and expected.startswith('startswith:'):
start_str = expected[len('startswith:'):]
self.assertTrue(
isinstance(got, compat_str),
'Expected a %s object, but got %s for field %s' % (
compat_str.__name__, type(got).__name__, field))
self.assertTrue(
got.startswith(start_str),
'field %s (value: %r) should start with %r' % (field, got, start_str))
elif isinstance(expected, compat_str) and expected.startswith('contains:'):
contains_str = expected[len('contains:'):]
self.assertTrue(
isinstance(got, compat_str),
'Expected a %s object, but got %s for field %s' % (
compat_str.__name__, type(got).__name__, field))
self.assertTrue(
contains_str in got,
'field %s (value: %r) should contain %r' % (field, got, contains_str))
elif isinstance(expected, type):
self.assertTrue(
isinstance(got, expected),
'Expected type %r for field %s, but got value %r of type %r' % (expected, field, got, type(got)))
elif isinstance(expected, dict) and isinstance(got, dict):
expect_dict(self, got, expected)
elif isinstance(expected, list) and isinstance(got, list):
self.assertEqual(
len(expected), len(got),
'Expect a list of length %d, but got a list of length %d for field %s' % (
len(expected), len(got), field))
for index, (item_got, item_expected) in enumerate(zip(got, expected)):
type_got = type(item_got)
type_expected = type(item_expected)
self.assertEqual(
type_expected, type_got,
'Type mismatch for list item at index %d for field %s, expected %r, got %r' % (
index, field, type_expected, type_got))
expect_value(self, item_got, item_expected, field)
else:
if isinstance(expected, compat_str) and expected.startswith('md5:'):
self.assertTrue(
isinstance(got, compat_str),
'Expected a %s object, but got %s for field %s' % (
compat_str.__name__, type(got).__name__, info_field))
'Expected field %s to be a unicode object, but got value %r of type %r' % (field, got, type(got)))
got = 'md5:' + md5(got)
elif isinstance(expected, compat_str) and expected.startswith('mincount:'):
self.assertTrue(
match_rex.match(got),
'field %s (value: %r) should match %r' % (info_field, got, match_str))
elif isinstance(expected, type):
got = got_dict.get(info_field)
self.assertTrue(isinstance(got, expected),
'Expected type %r for field %s, but got value %r of type %r' % (expected, info_field, got, type(got)))
else:
if isinstance(expected, compat_str) and expected.startswith('md5:'):
got = 'md5:' + md5(got_dict.get(info_field))
elif isinstance(expected, compat_str) and expected.startswith('mincount:'):
got = got_dict.get(info_field)
self.assertTrue(
isinstance(got, list),
'Expected field %s to be a list, but it is of type %s' % (
info_field, type(got).__name__))
expected_num = int(expected.partition(':')[2])
assertGreaterEqual(
self, len(got), expected_num,
'Expected %d items in field %s, but only got %d' % (
expected_num, info_field, len(got)
)
)
continue
else:
got = got_dict.get(info_field)
self.assertEqual(expected, got,
'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
isinstance(got, (list, dict)),
'Expected field %s to be a list or a dict, but it is of type %s' % (
field, type(got).__name__))
expected_num = int(expected.partition(':')[2])
assertGreaterEqual(
self, len(got), expected_num,
'Expected %d items in field %s, but only got %d' % (expected_num, field, len(got)))
return
self.assertEqual(
expected, got,
'Invalid value for field %s, expected %r, got %r' % (field, expected, got))
def expect_dict(self, got_dict, expected_dict):
for info_field, expected in expected_dict.items():
got = got_dict.get(info_field)
expect_value(self, got, expected, info_field)
def expect_info_dict(self, got_dict, expected_dict):
expect_dict(self, got_dict, expected_dict)
# Check for the presence of mandatory fields
if got_dict.get('_type') != 'playlist':
if got_dict.get('_type') not in ('playlist', 'multi_video'):
for key in ('id', 'url', 'title', 'ext'):
self.assertTrue(got_dict.get(key), 'Missing mandatory field %s' % key)
# Check for mandatory fields that are automatically set by YoutubeDL
@ -140,7 +186,7 @@ def expect_info_dict(self, got_dict, expected_dict):
# Are checkable fields missing from the test case definition?
test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))
for key, value in got_dict.items()
if value and key in ('title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location'))
if value and key in ('id', 'title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location', 'age_limit'))
missing_keys = set(test_info_dict.keys()) - set(expected_dict.keys())
if missing_keys:
def _repr(v):
@ -148,11 +194,19 @@ def expect_info_dict(self, got_dict, expected_dict):
return "'%s'" % v.replace('\\', '\\\\').replace("'", "\\'").replace('\n', '\\n')
else:
return repr(v)
info_dict_str = ''.join(
' %s: %s,\n' % (_repr(k), _repr(v))
for k, v in test_info_dict.items())
info_dict_str = ''
if len(missing_keys) != len(expected_dict):
info_dict_str += ''.join(
' %s: %s,\n' % (_repr(k), _repr(v))
for k, v in test_info_dict.items() if k not in missing_keys)
if info_dict_str:
info_dict_str += '\n'
info_dict_str += ''.join(
' %s: %s,\n' % (_repr(k), _repr(test_info_dict[k]))
for k in missing_keys)
write_string(
'\n\'info_dict\': {\n' + info_dict_str + '}\n', out=sys.stderr)
'\n\'info_dict\': {\n' + info_dict_str + '},\n', out=sys.stderr)
self.assertFalse(
missing_keys,
'Missing keys in test definition: %s' % (

8
test/parameters.json
View File

@ -7,8 +7,7 @@
"forcethumbnail": false,
"forcetitle": false,
"forceurl": false,
"format": null,
"format_limit": null,
"format": "best",
"ignoreerrors": false,
"listformats": null,
"logtostderr": false,
@ -28,7 +27,7 @@
"retries": 10,
"simulate": false,
"subtitleslang": null,
"subtitlesformat": "srt",
"subtitlesformat": "best",
"test": true,
"updatetime": true,
"usenetrc": false,
@ -39,5 +38,6 @@
"writesubtitles": false,
"allsubtitles": false,
"listssubtitles": false,
"socket_timeout": 20
"socket_timeout": 20,
"fixup": "never"
}

26
test/test_InfoExtractor.py
View File

@ -11,6 +11,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import FakeYDL
from youtube_dl.extractor.common import InfoExtractor
from youtube_dl.extractor import YoutubeIE, get_info_extractor
from youtube_dl.utils import encode_data_uri, strip_jsonp, ExtractorError, RegexNotFoundError
class TestIE(InfoExtractor):
@ -35,10 +36,21 @@ class TestInfoExtractor(unittest.TestCase):
<meta name="og:title" content='Foo'/>
<meta content="Some video's description " name="og:description"/>
<meta property='og:image' content='http://domain.com/pic.jpg?key1=val1&amp;key2=val2'/>
<meta content='application/x-shockwave-flash' property='og:video:type'>
<meta content='Foo' property=og:foobar>
<meta name="og:test1" content='foo > < bar'/>
<meta name="og:test2" content="foo >//< bar"/>
'''
self.assertEqual(ie._og_search_title(html), 'Foo')
self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
self.assertEqual(ie._og_search_thumbnail(html), 'http://domain.com/pic.jpg?key1=val1&key2=val2')
self.assertEqual(ie._og_search_video_url(html, default=None), None)
self.assertEqual(ie._og_search_property('foobar', html), 'Foo')
self.assertEqual(ie._og_search_property('test1', html), 'foo > < bar')
self.assertEqual(ie._og_search_property('test2', html), 'foo >//< bar')
self.assertEqual(ie._og_search_property(('test0', 'test1'), html), 'foo > < bar')
self.assertRaises(RegexNotFoundError, ie._og_search_property, 'test0', html, None, fatal=True)
self.assertRaises(RegexNotFoundError, ie._og_search_property, ('test0', 'test00'), html, None, fatal=True)
def test_html_search_meta(self):
ie = self.ie
@ -57,6 +69,20 @@ class TestInfoExtractor(unittest.TestCase):
self.assertEqual(ie._html_search_meta('d', html), '4')
self.assertEqual(ie._html_search_meta('e', html), '5')
self.assertEqual(ie._html_search_meta('f', html), '6')
self.assertEqual(ie._html_search_meta(('a', 'b', 'c'), html), '1')
self.assertEqual(ie._html_search_meta(('c', 'b', 'a'), html), '3')
self.assertEqual(ie._html_search_meta(('z', 'x', 'c'), html), '3')
self.assertRaises(RegexNotFoundError, ie._html_search_meta, 'z', html, None, fatal=True)
self.assertRaises(RegexNotFoundError, ie._html_search_meta, ('z', 'x'), html, None, fatal=True)
def test_download_json(self):
uri = encode_data_uri(b'{"foo": "blah"}', 'application/json')
self.assertEqual(self.ie._download_json(uri, None), {'foo': 'blah'})
uri = encode_data_uri(b'callback({"foo": "blah"})', 'application/javascript')
self.assertEqual(self.ie._download_json(uri, None, transform_source=strip_jsonp), {'foo': 'blah'})
uri = encode_data_uri(b'{"foo": invalid}', 'application/json')
self.assertRaises(ExtractorError, self.ie._download_json, uri, None)
self.assertEqual(self.ie._download_json(uri, None, fatal=False), None)
if __name__ == '__main__':
unittest.main()

556
test/test_YoutubeDL.py
View File

@ -12,7 +12,13 @@ import copy
from test.helper import FakeYDL, assertRegexpMatches
from youtube_dl import YoutubeDL
from youtube_dl.compat import compat_str, compat_urllib_error
from youtube_dl.extractor import YoutubeIE
from youtube_dl.extractor.common import InfoExtractor
from youtube_dl.postprocessor.common import PostProcessor
from youtube_dl.utils import ExtractorError, match_filter_func
TEST_URL = 'http://localhost/sample.mp4'
class YDL(FakeYDL):
@ -45,8 +51,8 @@ class TestFormatSelection(unittest.TestCase):
ydl = YDL()
ydl.params['prefer_free_formats'] = True
formats = [
{'ext': 'webm', 'height': 460, 'url': 'x'},
{'ext': 'mp4', 'height': 460, 'url': 'y'},
{'ext': 'webm', 'height': 460, 'url': TEST_URL},
{'ext': 'mp4', 'height': 460, 'url': TEST_URL},
]
info_dict = _make_result(formats)
yie = YoutubeIE(ydl)
@ -59,8 +65,8 @@ class TestFormatSelection(unittest.TestCase):
ydl = YDL()
ydl.params['prefer_free_formats'] = True
formats = [
{'ext': 'webm', 'height': 720, 'url': 'a'},
{'ext': 'mp4', 'height': 1080, 'url': 'b'},
{'ext': 'webm', 'height': 720, 'url': TEST_URL},
{'ext': 'mp4', 'height': 1080, 'url': TEST_URL},
]
info_dict['formats'] = formats
yie = YoutubeIE(ydl)
@ -73,9 +79,9 @@ class TestFormatSelection(unittest.TestCase):
ydl = YDL()
ydl.params['prefer_free_formats'] = False
formats = [
{'ext': 'webm', 'height': 720, 'url': '_'},
{'ext': 'mp4', 'height': 720, 'url': '_'},
{'ext': 'flv', 'height': 720, 'url': '_'},
{'ext': 'webm', 'height': 720, 'url': TEST_URL},
{'ext': 'mp4', 'height': 720, 'url': TEST_URL},
{'ext': 'flv', 'height': 720, 'url': TEST_URL},
]
info_dict['formats'] = formats
yie = YoutubeIE(ydl)
@ -87,8 +93,8 @@ class TestFormatSelection(unittest.TestCase):
ydl = YDL()
ydl.params['prefer_free_formats'] = False
formats = [
{'ext': 'flv', 'height': 720, 'url': '_'},
{'ext': 'webm', 'height': 720, 'url': '_'},
{'ext': 'flv', 'height': 720, 'url': TEST_URL},
{'ext': 'webm', 'height': 720, 'url': TEST_URL},
]
info_dict['formats'] = formats
yie = YoutubeIE(ydl)
@ -97,45 +103,13 @@ class TestFormatSelection(unittest.TestCase):
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['ext'], 'flv')
def test_format_limit(self):
formats = [
{'format_id': 'meh', 'url': 'http://example.com/meh', 'preference': 1},
{'format_id': 'good', 'url': 'http://example.com/good', 'preference': 2},
{'format_id': 'great', 'url': 'http://example.com/great', 'preference': 3},
{'format_id': 'excellent', 'url': 'http://example.com/exc', 'preference': 4},
]
info_dict = _make_result(formats)
ydl = YDL()
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'excellent')
ydl = YDL({'format_limit': 'good'})
assert ydl.params['format_limit'] == 'good'
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'good')
ydl = YDL({'format_limit': 'great', 'format': 'all'})
ydl.process_ie_result(info_dict.copy())
self.assertEqual(ydl.downloaded_info_dicts[0]['format_id'], 'meh')
self.assertEqual(ydl.downloaded_info_dicts[1]['format_id'], 'good')
self.assertEqual(ydl.downloaded_info_dicts[2]['format_id'], 'great')
self.assertTrue('3' in ydl.msgs[0])
ydl = YDL()
ydl.params['format_limit'] = 'excellent'
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'excellent')
def test_format_selection(self):
formats = [
{'format_id': '35', 'ext': 'mp4', 'preference': 1, 'url': '_'},
{'format_id': '45', 'ext': 'webm', 'preference': 2, 'url': '_'},
{'format_id': '47', 'ext': 'webm', 'preference': 3, 'url': '_'},
{'format_id': '2', 'ext': 'flv', 'preference': 4, 'url': '_'},
{'format_id': '35', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL},
{'format_id': 'example-with-dashes', 'ext': 'webm', 'preference': 1, 'url': TEST_URL},
{'format_id': '45', 'ext': 'webm', 'preference': 2, 'url': TEST_URL},
{'format_id': '47', 'ext': 'webm', 'preference': 3, 'url': TEST_URL},
{'format_id': '2', 'ext': 'flv', 'preference': 4, 'url': TEST_URL},
]
info_dict = _make_result(formats)
@ -164,12 +138,17 @@ class TestFormatSelection(unittest.TestCase):
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], '35')
ydl = YDL({'format': 'example-with-dashes'})
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'example-with-dashes')
def test_format_selection_audio(self):
formats = [
{'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none', 'url': '_'},
{'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none', 'url': '_'},
{'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none', 'url': '_'},
{'format_id': 'vid', 'ext': 'mp4', 'preference': 4, 'url': '_'},
{'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL},
{'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none', 'url': TEST_URL},
{'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none', 'url': TEST_URL},
{'format_id': 'vid', 'ext': 'mp4', 'preference': 4, 'url': TEST_URL},
]
info_dict = _make_result(formats)
@ -184,8 +163,8 @@ class TestFormatSelection(unittest.TestCase):
self.assertEqual(downloaded['format_id'], 'audio-low')
formats = [
{'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1, 'url': '_'},
{'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2, 'url': '_'},
{'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL},
{'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2, 'url': TEST_URL},
]
info_dict = _make_result(formats)
@ -227,9 +206,9 @@ class TestFormatSelection(unittest.TestCase):
def test_format_selection_video(self):
formats = [
{'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': '_'},
{'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none', 'url': '_'},
{'format_id': 'vid', 'ext': 'mp4', 'preference': 3, 'url': '_'},
{'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': TEST_URL},
{'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none', 'url': TEST_URL},
{'format_id': 'vid', 'ext': 'mp4', 'preference': 3, 'url': TEST_URL},
]
info_dict = _make_result(formats)
@ -243,9 +222,24 @@ class TestFormatSelection(unittest.TestCase):
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'dash-video-low')
ydl = YDL({'format': 'bestvideo[format_id^=dash][format_id$=low]'})
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'dash-video-low')
formats = [
{'format_id': 'vid-vcodec-dot', 'ext': 'mp4', 'preference': 1, 'vcodec': 'avc1.123456', 'acodec': 'none', 'url': TEST_URL},
]
info_dict = _make_result(formats)
ydl = YDL({'format': 'bestvideo[vcodec=avc1.123456]'})
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'vid-vcodec-dot')
def test_youtube_format_selection(self):
order = [
'38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '36', '17', '13',
'38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '17', '36', '13',
# Apple HTTP Live Streaming
'96', '95', '94', '93', '92', '132', '151',
# 3D
@ -257,29 +251,262 @@ class TestFormatSelection(unittest.TestCase):
'141', '172', '140', '171', '139',
]
for f1id, f2id in zip(order, order[1:]):
f1 = YoutubeIE._formats[f1id].copy()
f1['format_id'] = f1id
f1['url'] = 'url:' + f1id
f2 = YoutubeIE._formats[f2id].copy()
f2['format_id'] = f2id
f2['url'] = 'url:' + f2id
def format_info(f_id):
info = YoutubeIE._formats[f_id].copy()
# XXX: In real cases InfoExtractor._parse_mpd_formats() fills up 'acodec'
# and 'vcodec', while in tests such information is incomplete since
# commit a6c2c24479e5f4827ceb06f64d855329c0a6f593
# test_YoutubeDL.test_youtube_format_selection is broken without
# this fix
if 'acodec' in info and 'vcodec' not in info:
info['vcodec'] = 'none'
elif 'vcodec' in info and 'acodec' not in info:
info['acodec'] = 'none'
info['format_id'] = f_id
info['url'] = 'url:' + f_id
return info
formats_order = [format_info(f_id) for f_id in order]
info_dict = _make_result(list(formats_order), extractor='youtube')
ydl = YDL({'format': 'bestvideo+bestaudio'})
yie = YoutubeIE(ydl)
yie._sort_formats(info_dict['formats'])
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], '137+141')
self.assertEqual(downloaded['ext'], 'mp4')
info_dict = _make_result(list(formats_order), extractor='youtube')
ydl = YDL({'format': 'bestvideo[height>=999999]+bestaudio/best'})
yie = YoutubeIE(ydl)
yie._sort_formats(info_dict['formats'])
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], '38')
info_dict = _make_result(list(formats_order), extractor='youtube')
ydl = YDL({'format': 'bestvideo/best,bestaudio'})
yie = YoutubeIE(ydl)
yie._sort_formats(info_dict['formats'])
ydl.process_ie_result(info_dict)
downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
self.assertEqual(downloaded_ids, ['137', '141'])
info_dict = _make_result(list(formats_order), extractor='youtube')
ydl = YDL({'format': '(bestvideo[ext=mp4],bestvideo[ext=webm])+bestaudio'})
yie = YoutubeIE(ydl)
yie._sort_formats(info_dict['formats'])
ydl.process_ie_result(info_dict)
downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
self.assertEqual(downloaded_ids, ['137+141', '248+141'])
info_dict = _make_result(list(formats_order), extractor='youtube')
ydl = YDL({'format': '(bestvideo[ext=mp4],bestvideo[ext=webm])[height<=720]+bestaudio'})
yie = YoutubeIE(ydl)
yie._sort_formats(info_dict['formats'])
ydl.process_ie_result(info_dict)
downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
self.assertEqual(downloaded_ids, ['136+141', '247+141'])
info_dict = _make_result(list(formats_order), extractor='youtube')
ydl = YDL({'format': '(bestvideo[ext=none]/bestvideo[ext=webm])+bestaudio'})
yie = YoutubeIE(ydl)
yie._sort_formats(info_dict['formats'])
ydl.process_ie_result(info_dict)
downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
self.assertEqual(downloaded_ids, ['248+141'])
for f1, f2 in zip(formats_order, formats_order[1:]):
info_dict = _make_result([f1, f2], extractor='youtube')
ydl = YDL()
ydl = YDL({'format': 'best/bestvideo'})
yie = YoutubeIE(ydl)
yie._sort_formats(info_dict['formats'])
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], f1id)
self.assertEqual(downloaded['format_id'], f1['format_id'])
info_dict = _make_result([f2, f1], extractor='youtube')
ydl = YDL()
ydl = YDL({'format': 'best/bestvideo'})
yie = YoutubeIE(ydl)
yie._sort_formats(info_dict['formats'])
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], f1id)
self.assertEqual(downloaded['format_id'], f1['format_id'])
def test_audio_only_extractor_format_selection(self):
# For extractors with incomplete formats (all formats are audio-only or
# video-only) best and worst should fallback to corresponding best/worst
# video-only or audio-only formats (as per
# https://github.com/rg3/youtube-dl/pull/5556)
formats = [
{'format_id': 'low', 'ext': 'mp3', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL},
{'format_id': 'high', 'ext': 'mp3', 'preference': 2, 'vcodec': 'none', 'url': TEST_URL},
]
info_dict = _make_result(formats)
ydl = YDL({'format': 'best'})
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'high')
ydl = YDL({'format': 'worst'})
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'low')
def test_format_not_available(self):
formats = [
{'format_id': 'regular', 'ext': 'mp4', 'height': 360, 'url': TEST_URL},
{'format_id': 'video', 'ext': 'mp4', 'height': 720, 'acodec': 'none', 'url': TEST_URL},
]
info_dict = _make_result(formats)
# This must fail since complete video-audio format does not match filter
# and extractor does not provide incomplete only formats (i.e. only
# video-only or audio-only).
ydl = YDL({'format': 'best[height>360]'})
self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
def test_invalid_format_specs(self):
def assert_syntax_error(format_spec):
ydl = YDL({'format': format_spec})
info_dict = _make_result([{'format_id': 'foo', 'url': TEST_URL}])
self.assertRaises(SyntaxError, ydl.process_ie_result, info_dict)
assert_syntax_error('bestvideo,,best')
assert_syntax_error('+bestaudio')
assert_syntax_error('bestvideo+')
assert_syntax_error('/')
def test_format_filtering(self):
formats = [
{'format_id': 'A', 'filesize': 500, 'width': 1000},
{'format_id': 'B', 'filesize': 1000, 'width': 500},
{'format_id': 'C', 'filesize': 1000, 'width': 400},
{'format_id': 'D', 'filesize': 2000, 'width': 600},
{'format_id': 'E', 'filesize': 3000},
{'format_id': 'F'},
{'format_id': 'G', 'filesize': 1000000},
]
for f in formats:
f['url'] = 'http://_/'
f['ext'] = 'unknown'
info_dict = _make_result(formats)
ydl = YDL({'format': 'best[filesize<3000]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'D')
ydl = YDL({'format': 'best[filesize<=3000]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'E')
ydl = YDL({'format': 'best[filesize <= ? 3000]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'F')
ydl = YDL({'format': 'best [filesize = 1000] [width>450]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'B')
ydl = YDL({'format': 'best [filesize = 1000] [width!=450]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'C')
ydl = YDL({'format': '[filesize>?1]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'G')
ydl = YDL({'format': '[filesize<1M]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'E')
ydl = YDL({'format': '[filesize<1MiB]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'G')
ydl = YDL({'format': 'all[width>=400][width<=600]'})
ydl.process_ie_result(info_dict)
downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
self.assertEqual(downloaded_ids, ['B', 'C', 'D'])
ydl = YDL({'format': 'best[height<40]'})
try:
ydl.process_ie_result(info_dict)
except ExtractorError:
pass
self.assertEqual(ydl.downloaded_info_dicts, [])
class TestYoutubeDL(unittest.TestCase):
def test_subtitles(self):
def s_formats(lang, autocaption=False):
return [{
'ext': ext,
'url': 'http://localhost/video.%s.%s' % (lang, ext),
'_auto': autocaption,
} for ext in ['vtt', 'srt', 'ass']]
subtitles = dict((l, s_formats(l)) for l in ['en', 'fr', 'es'])
auto_captions = dict((l, s_formats(l, True)) for l in ['it', 'pt', 'es'])
info_dict = {
'id': 'test',
'title': 'Test',
'url': 'http://localhost/video.mp4',
'subtitles': subtitles,
'automatic_captions': auto_captions,
'extractor': 'TEST',
}
def get_info(params={}):
params.setdefault('simulate', True)
ydl = YDL(params)
ydl.report_warning = lambda *args, **kargs: None
return ydl.process_video_result(info_dict, download=False)
result = get_info()
self.assertFalse(result.get('requested_subtitles'))
self.assertEqual(result['subtitles'], subtitles)
self.assertEqual(result['automatic_captions'], auto_captions)
result = get_info({'writesubtitles': True})
subs = result['requested_subtitles']
self.assertTrue(subs)
self.assertEqual(set(subs.keys()), set(['en']))
self.assertTrue(subs['en'].get('data') is None)
self.assertEqual(subs['en']['ext'], 'ass')
result = get_info({'writesubtitles': True, 'subtitlesformat': 'foo/srt'})
subs = result['requested_subtitles']
self.assertEqual(subs['en']['ext'], 'srt')
result = get_info({'writesubtitles': True, 'subtitleslangs': ['es', 'fr', 'it']})
subs = result['requested_subtitles']
self.assertTrue(subs)
self.assertEqual(set(subs.keys()), set(['es', 'fr']))
result = get_info({'writesubtitles': True, 'writeautomaticsub': True, 'subtitleslangs': ['es', 'pt']})
subs = result['requested_subtitles']
self.assertTrue(subs)
self.assertEqual(set(subs.keys()), set(['es', 'pt']))
self.assertFalse(subs['es']['_auto'])
self.assertTrue(subs['pt']['_auto'])
result = get_info({'writeautomaticsub': True, 'subtitleslangs': ['es', 'pt']})
subs = result['requested_subtitles']
self.assertTrue(subs)
self.assertEqual(set(subs.keys()), set(['es', 'pt']))
self.assertTrue(subs['es']['_auto'])
self.assertTrue(subs['pt']['_auto'])
def test_add_extra_info(self):
test_dict = {
@ -314,6 +541,201 @@ class TestFormatSelection(unittest.TestCase):
assertRegexpMatches(self, ydl._format_note({
'vbr': 10,
}), '^\s*10k$')
assertRegexpMatches(self, ydl._format_note({
'fps': 30,
}), '^30fps$')
def test_postprocessors(self):
filename = 'post-processor-testfile.mp4'
audiofile = filename + '.mp3'
class SimplePP(PostProcessor):
def run(self, info):
with open(audiofile, 'wt') as f:
f.write('EXAMPLE')
return [info['filepath']], info
def run_pp(params, PP):
with open(filename, 'wt') as f:
f.write('EXAMPLE')
ydl = YoutubeDL(params)
ydl.add_post_processor(PP())
ydl.post_process(filename, {'filepath': filename})
run_pp({'keepvideo': True}, SimplePP)
self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
os.unlink(filename)
os.unlink(audiofile)
run_pp({'keepvideo': False}, SimplePP)
self.assertFalse(os.path.exists(filename), '%s exists' % filename)
self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
os.unlink(audiofile)
class ModifierPP(PostProcessor):
def run(self, info):
with open(info['filepath'], 'wt') as f:
f.write('MODIFIED')
return [], info
run_pp({'keepvideo': False}, ModifierPP)
self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
os.unlink(filename)
def test_match_filter(self):
class FilterYDL(YDL):
def __init__(self, *args, **kwargs):
super(FilterYDL, self).__init__(*args, **kwargs)
self.params['simulate'] = True
def process_info(self, info_dict):
super(YDL, self).process_info(info_dict)
def _match_entry(self, info_dict, incomplete):
res = super(FilterYDL, self)._match_entry(info_dict, incomplete)
if res is None:
self.downloaded_info_dicts.append(info_dict)
return res
first = {
'id': '1',
'url': TEST_URL,
'title': 'one',
'extractor': 'TEST',
'duration': 30,
'filesize': 10 * 1024,
}
second = {
'id': '2',
'url': TEST_URL,
'title': 'two',
'extractor': 'TEST',
'duration': 10,
'description': 'foo',
'filesize': 5 * 1024,
}
videos = [first, second]
def get_videos(filter_=None):
ydl = FilterYDL({'match_filter': filter_})
for v in videos:
ydl.process_ie_result(v, download=True)
return [v['id'] for v in ydl.downloaded_info_dicts]
res = get_videos()
self.assertEqual(res, ['1', '2'])
def f(v):
if v['id'] == '1':
return None
else:
return 'Video id is not 1'
res = get_videos(f)
self.assertEqual(res, ['1'])
f = match_filter_func('duration < 30')
res = get_videos(f)
self.assertEqual(res, ['2'])
f = match_filter_func('description = foo')
res = get_videos(f)
self.assertEqual(res, ['2'])
f = match_filter_func('description =? foo')
res = get_videos(f)
self.assertEqual(res, ['1', '2'])
f = match_filter_func('filesize > 5KiB')
res = get_videos(f)
self.assertEqual(res, ['1'])
def test_playlist_items_selection(self):
entries = [{
'id': compat_str(i),
'title': compat_str(i),
'url': TEST_URL,
} for i in range(1, 5)]
playlist = {
'_type': 'playlist',
'id': 'test',
'entries': entries,
'extractor': 'test:playlist',
'extractor_key': 'test:playlist',
'webpage_url': 'http://example.com',
}
def get_ids(params):
ydl = YDL(params)
# make a copy because the dictionary can be modified
ydl.process_ie_result(playlist.copy())
return [int(v['id']) for v in ydl.downloaded_info_dicts]
result = get_ids({})
self.assertEqual(result, [1, 2, 3, 4])
result = get_ids({'playlistend': 10})
self.assertEqual(result, [1, 2, 3, 4])
result = get_ids({'playlistend': 2})
self.assertEqual(result, [1, 2])
result = get_ids({'playliststart': 10})
self.assertEqual(result, [])
result = get_ids({'playliststart': 2})
self.assertEqual(result, [2, 3, 4])
result = get_ids({'playlist_items': '2-4'})
self.assertEqual(result, [2, 3, 4])
result = get_ids({'playlist_items': '2,4'})
self.assertEqual(result, [2, 4])
result = get_ids({'playlist_items': '10'})
self.assertEqual(result, [])
def test_urlopen_no_file_protocol(self):
# see https://github.com/rg3/youtube-dl/issues/8227
ydl = YDL()
self.assertRaises(compat_urllib_error.URLError, ydl.urlopen, 'file:///etc/passwd')
def test_do_not_override_ie_key_in_url_transparent(self):
ydl = YDL()
class Foo1IE(InfoExtractor):
_VALID_URL = r'foo1:'
def _real_extract(self, url):
return {
'_type': 'url_transparent',
'url': 'foo2:',
'ie_key': 'Foo2',
}
class Foo2IE(InfoExtractor):
_VALID_URL = r'foo2:'
def _real_extract(self, url):
return {
'_type': 'url',
'url': 'foo3:',
'ie_key': 'Foo3',
}
class Foo3IE(InfoExtractor):
_VALID_URL = r'foo3:'
def _real_extract(self, url):
return _make_result([{'url': TEST_URL}])
ydl.add_info_extractor(Foo1IE(ydl))
ydl.add_info_extractor(Foo2IE(ydl))
ydl.add_info_extractor(Foo3IE(ydl))
ydl.extract_info('foo1:')
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['url'], TEST_URL)
if __name__ == '__main__':
unittest.main()

55
test/test_aes.py Normal file
View File

@ -0,0 +1,55 @@
#!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.aes import aes_decrypt, aes_encrypt, aes_cbc_decrypt, aes_decrypt_text
from youtube_dl.utils import bytes_to_intlist, intlist_to_bytes
import base64
# the encrypted data can be generate with 'devscripts/generate_aes_testdata.py'
class TestAES(unittest.TestCase):
def setUp(self):
self.key = self.iv = [0x20, 0x15] + 14 * [0]
self.secret_msg = b'Secret message goes here'
def test_encrypt(self):
msg = b'message'
key = list(range(16))
encrypted = aes_encrypt(bytes_to_intlist(msg), key)
decrypted = intlist_to_bytes(aes_decrypt(encrypted, key))
self.assertEqual(decrypted, msg)
def test_cbc_decrypt(self):
data = bytes_to_intlist(
b"\x97\x92+\xe5\x0b\xc3\x18\x91ky9m&\xb3\xb5@\xe6'\xc2\x96.\xc8u\x88\xab9-[\x9e|\xf1\xcd"
)
decrypted = intlist_to_bytes(aes_cbc_decrypt(data, self.key, self.iv))
self.assertEqual(decrypted.rstrip(b'\x08'), self.secret_msg)
def test_decrypt_text(self):
password = intlist_to_bytes(self.key).decode('utf-8')
encrypted = base64.b64encode(
intlist_to_bytes(self.iv[:8]) +
b'\x17\x15\x93\xab\x8d\x80V\xcdV\xe0\t\xcdo\xc2\xa5\xd8ksM\r\xe27N\xae'
).decode('utf-8')
decrypted = (aes_decrypt_text(encrypted, password, 16))
self.assertEqual(decrypted, self.secret_msg)
password = intlist_to_bytes(self.key).decode('utf-8')
encrypted = base64.b64encode(
intlist_to_bytes(self.iv[:8]) +
b'\x0b\xe6\xa4\xd9z\x0e\xb8\xb9\xd0\xd4i_\x85\x1d\x99\x98_\xe5\x80\xe7.\xbf\xa5\x83'
).decode('utf-8')
decrypted = (aes_decrypt_text(encrypted, password, 32))
self.assertEqual(decrypted, self.secret_msg)
if __name__ == '__main__':
unittest.main()

45
test/test_all_urls.py
View File

@ -6,6 +6,7 @@ from __future__ import unicode_literals
import os
import sys
import unittest
import collections
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
@ -14,7 +15,6 @@ from test.helper import gettestcases
from youtube_dl.extractor import (
FacebookIE,
gen_extractors,
TwitchIE,
YoutubeIE,
)
@ -57,10 +57,10 @@ class TestAllURLsMatching(unittest.TestCase):
assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')
def test_youtube_user_matching(self):
self.assertMatch('www.youtube.com/NASAgovVideo/videos', ['youtube:user'])
self.assertMatch('http://www.youtube.com/NASAgovVideo/videos', ['youtube:user'])
def test_youtube_feeds(self):
self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watch_later'])
self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watchlater'])
self.assertMatch('https://www.youtube.com/feed/subscriptions', ['youtube:subscriptions'])
self.assertMatch('https://www.youtube.com/feed/recommended', ['youtube:recommended'])
self.assertMatch('https://www.youtube.com/my_favorites', ['youtube:favorites'])
@ -72,18 +72,6 @@ class TestAllURLsMatching(unittest.TestCase):
self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
def test_twitch_channelid_matching(self):
self.assertTrue(TwitchIE.suitable('twitch.tv/vanillatv'))
self.assertTrue(TwitchIE.suitable('www.twitch.tv/vanillatv'))
self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/vanillatv'))
self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/vanillatv/'))
def test_twitch_videoid_matching(self):
self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/vanillatv/b/328087483'))
def test_twitch_chapterid_matching(self):
self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/tsm_theoddone/c/2349361'))
def test_youtube_extract(self):
assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
@ -113,17 +101,13 @@ class TestAllURLsMatching(unittest.TestCase):
self.assertMatch(':ytsubs', ['youtube:subscriptions'])
self.assertMatch(':ytsubscriptions', ['youtube:subscriptions'])
self.assertMatch(':ythistory', ['youtube:history'])
self.assertMatch(':thedailyshow', ['ComedyCentralShows'])
self.assertMatch(':tds', ['ComedyCentralShows'])
self.assertMatch(':colbertreport', ['ComedyCentralShows'])
self.assertMatch(':cr', ['ComedyCentralShows'])
def test_vimeo_matching(self):
self.assertMatch('http://vimeo.com/channels/tributes', ['vimeo:channel'])
self.assertMatch('http://vimeo.com/channels/31259', ['vimeo:channel'])
self.assertMatch('http://vimeo.com/channels/31259/53576664', ['vimeo'])
self.assertMatch('http://vimeo.com/user7108434', ['vimeo:user'])
self.assertMatch('http://vimeo.com/user7108434/videos', ['vimeo:user'])
self.assertMatch('https://vimeo.com/channels/tributes', ['vimeo:channel'])
self.assertMatch('https://vimeo.com/channels/31259', ['vimeo:channel'])
self.assertMatch('https://vimeo.com/channels/31259/53576664', ['vimeo'])
self.assertMatch('https://vimeo.com/user7108434', ['vimeo:user'])
self.assertMatch('https://vimeo.com/user7108434/videos', ['vimeo:user'])
self.assertMatch('https://vimeo.com/user21297594/review/75524534/3c257a1b5d', ['vimeo:review'])
# https://github.com/rg3/youtube-dl/issues/1930
@ -136,8 +120,8 @@ class TestAllURLsMatching(unittest.TestCase):
def test_pbs(self):
# https://github.com/rg3/youtube-dl/issues/2350
self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['PBS'])
self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['PBS'])
self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['pbs'])
self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['pbs'])
def test_yahoo_https(self):
# https://github.com/rg3/youtube-dl/issues/2701
@ -145,6 +129,15 @@ class TestAllURLsMatching(unittest.TestCase):
'https://screen.yahoo.com/smartwatches-latest-wearable-gadgets-163745379-cbs.html',
['Yahoo'])
def test_no_duplicated_ie_names(self):
name_accu = collections.defaultdict(list)
for ie in self.ies:
name_accu[ie.IE_NAME.lower()].append(type(ie).__name__)
for (ie_name, ie_list) in name_accu.items():
self.assertEqual(
len(ie_list), 1,
'Multiple extractors with the same IE_NAME "%s" (%s)' % (ie_name, ', '.join(ie_list)))
if __name__ == '__main__':
unittest.main()

89
test/test_compat.py
View File

@ -10,29 +10,39 @@ import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.utils import get_filesystem_encoding
from youtube_dl.compat import (
compat_getenv,
compat_setenv,
compat_etree_fromstring,
compat_expanduser,
compat_shlex_split,
compat_str,
compat_struct_unpack,
compat_urllib_parse_unquote,
compat_urllib_parse_unquote_plus,
compat_urllib_parse_urlencode,
)
class TestCompat(unittest.TestCase):
def test_compat_getenv(self):
test_str = 'тест'
os.environ['YOUTUBE-DL-TEST'] = (
test_str if sys.version_info >= (3, 0)
else test_str.encode(get_filesystem_encoding()))
compat_setenv('YOUTUBE-DL-TEST', test_str)
self.assertEqual(compat_getenv('YOUTUBE-DL-TEST'), test_str)
def test_compat_setenv(self):
test_var = 'YOUTUBE-DL-TEST'
test_str = 'тест'
compat_setenv(test_var, test_str)
compat_getenv(test_var)
self.assertEqual(compat_getenv(test_var), test_str)
def test_compat_expanduser(self):
old_home = os.environ.get('HOME')
test_str = 'C:\Documents and Settings\тест\Application Data'
os.environ['HOME'] = (
test_str if sys.version_info >= (3, 0)
else test_str.encode(get_filesystem_encoding()))
compat_setenv('HOME', test_str)
self.assertEqual(compat_expanduser('~'), test_str)
os.environ['HOME'] = old_home
compat_setenv('HOME', old_home or '')
def test_all_present(self):
import youtube_dl.compat
@ -42,5 +52,68 @@ class TestCompat(unittest.TestCase):
dir(youtube_dl.compat))) - set(['unicode_literals'])
self.assertEqual(all_names, sorted(present_names))
def test_compat_urllib_parse_unquote(self):
self.assertEqual(compat_urllib_parse_unquote('abc%20def'), 'abc def')
self.assertEqual(compat_urllib_parse_unquote('%7e/abc+def'), '~/abc+def')
self.assertEqual(compat_urllib_parse_unquote(''), '')
self.assertEqual(compat_urllib_parse_unquote('%'), '%')
self.assertEqual(compat_urllib_parse_unquote('%%'), '%%')
self.assertEqual(compat_urllib_parse_unquote('%%%'), '%%%')
self.assertEqual(compat_urllib_parse_unquote('%2F'), '/')
self.assertEqual(compat_urllib_parse_unquote('%2f'), '/')
self.assertEqual(compat_urllib_parse_unquote('%E6%B4%A5%E6%B3%A2'), '津波')
self.assertEqual(
compat_urllib_parse_unquote('''<meta property="og:description" content="%E2%96%81%E2%96%82%E2%96%83%E2%96%84%25%E2%96%85%E2%96%86%E2%96%87%E2%96%88" />
%<a href="https://ar.wikipedia.org/wiki/%D8%AA%D8%B3%D9%88%D9%86%D8%A7%D9%85%D9%8A">%a'''),
'''<meta property="og:description" content="▁▂▃▄%▅▆▇█" />
%<a href="https://ar.wikipedia.org/wiki/تسونامي">%a''')
self.assertEqual(
compat_urllib_parse_unquote('''%28%5E%E2%97%A3_%E2%97%A2%5E%29%E3%81%A3%EF%B8%BB%E3%83%87%E2%95%90%E4%B8%80 %E2%87%80 %E2%87%80 %E2%87%80 %E2%87%80 %E2%87%80 %E2%86%B6%I%Break%25Things%'''),
'''(^◣_◢^)っ︻デ═一 ⇀ ⇀ ⇀ ⇀ ⇀ ↶%I%Break%Things%''')
def test_compat_urllib_parse_unquote_plus(self):
self.assertEqual(compat_urllib_parse_unquote_plus('abc%20def'), 'abc def')
self.assertEqual(compat_urllib_parse_unquote_plus('%7e/abc+def'), '~/abc def')
def test_compat_urllib_parse_urlencode(self):
self.assertEqual(compat_urllib_parse_urlencode({'abc': 'def'}), 'abc=def')
self.assertEqual(compat_urllib_parse_urlencode({'abc': b'def'}), 'abc=def')
self.assertEqual(compat_urllib_parse_urlencode({b'abc': 'def'}), 'abc=def')
self.assertEqual(compat_urllib_parse_urlencode({b'abc': b'def'}), 'abc=def')
self.assertEqual(compat_urllib_parse_urlencode([('abc', 'def')]), 'abc=def')
self.assertEqual(compat_urllib_parse_urlencode([('abc', b'def')]), 'abc=def')
self.assertEqual(compat_urllib_parse_urlencode([(b'abc', 'def')]), 'abc=def')
self.assertEqual(compat_urllib_parse_urlencode([(b'abc', b'def')]), 'abc=def')
def test_compat_shlex_split(self):
self.assertEqual(compat_shlex_split('-option "one two"'), ['-option', 'one two'])
self.assertEqual(compat_shlex_split('-option "one\ntwo" \n -flag'), ['-option', 'one\ntwo', '-flag'])
self.assertEqual(compat_shlex_split('-val 中文'), ['-val', '中文'])
def test_compat_etree_fromstring(self):
xml = '''
<root foo="bar" spam="中文">
<normal>foo</normal>
<chinese>中文</chinese>
<foo><bar>spam</bar></foo>
</root>
'''
doc = compat_etree_fromstring(xml.encode('utf-8'))
self.assertTrue(isinstance(doc.attrib['foo'], compat_str))
self.assertTrue(isinstance(doc.attrib['spam'], compat_str))
self.assertTrue(isinstance(doc.find('normal').text, compat_str))
self.assertTrue(isinstance(doc.find('chinese').text, compat_str))
self.assertTrue(isinstance(doc.find('foo/bar').text, compat_str))
def test_compat_etree_fromstring_doctype(self):
xml = '''<?xml version="1.0"?>
<!DOCTYPE smil PUBLIC "-//W3C//DTD SMIL 2.0//EN" "http://www.w3.org/2001/SMIL20/SMIL20.dtd">
<smil xmlns="http://www.w3.org/2001/SMIL20/Language"></smil>'''
compat_etree_fromstring(xml)
def test_struct_unpack(self):
self.assertEqual(compat_struct_unpack('!B', b'\x00'), (0,))
if __name__ == '__main__':
unittest.main()

12
test/test_download.py
View File

@ -89,7 +89,7 @@ def generator(test_case):
for tc in test_cases:
info_dict = tc.get('info_dict', {})
if not tc.get('file') and not (info_dict.get('id') and info_dict.get('ext')):
if not (info_dict.get('id') and info_dict.get('ext')):
raise Exception('Test definition incorrect. The output file cannot be known. Are both \'id\' and \'ext\' keys present?')
if 'skip' in test_case:
@ -102,7 +102,7 @@ def generator(test_case):
params = get_params(test_case.get('params', {}))
if is_playlist and 'playlist' not in test_case:
params.setdefault('extract_flat', True)
params.setdefault('extract_flat', 'in_playlist')
params.setdefault('skip_download', True)
ydl = YoutubeDL(params, auto_init=False)
@ -116,7 +116,7 @@ def generator(test_case):
expect_warnings(ydl, test_case.get('expected_warnings', []))
def get_tc_filename(tc):
return tc.get('file') or ydl.prepare_filename(tc.get('info_dict', {}))
return ydl.prepare_filename(tc.get('info_dict', {}))
res_dict = None
@ -136,7 +136,9 @@ def generator(test_case):
# We're not using .download here sine that is just a shim
# for outside error handling, and returns the exit code
# instead of the result dict.
res_dict = ydl.extract_info(test_case['url'])
res_dict = ydl.extract_info(
test_case['url'],
force_generic_extractor=params.get('force_generic_extractor', False))
except (DownloadError, ExtractorError) as err:
# Check if the exception is not a network related one
if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError, compat_http_client.BadStatusLine) or (err.exc_info[0] == compat_HTTPError and err.exc_info[1].code == 503):
@ -153,7 +155,7 @@ def generator(test_case):
break
if is_playlist:
self.assertEqual(res_dict['_type'], 'playlist')
self.assertTrue(res_dict['_type'] in ['playlist', 'multi_video'])
self.assertTrue('entries' in res_dict)
expect_info_dict(self, res_dict, test_case.get('info_dict', {}))

12
test/test_execution.py
View File

@ -1,4 +1,6 @@
#!/usr/bin/env python
# coding: utf-8
from __future__ import unicode_literals
import unittest
@ -6,6 +8,9 @@ import unittest
import sys
import os
import subprocess
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.utils import encodeArgument
rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
@ -27,5 +32,12 @@ class TestExecution(unittest.TestCase):
def test_main_exec(self):
subprocess.check_call([sys.executable, 'youtube_dl/__main__.py', '--version'], cwd=rootDir, stdout=_DEV_NULL)
def test_cmdline_umlauts(self):
p = subprocess.Popen(
[sys.executable, 'youtube_dl/__main__.py', encodeArgument('ä'), '--version'],
cwd=rootDir, stdout=_DEV_NULL, stderr=subprocess.PIPE)
_, stderr = p.communicate()
self.assertFalse(stderr)
if __name__ == '__main__':
unittest.main()

173
test/test_http.py Normal file
View File

@ -0,0 +1,173 @@
#!/usr/bin/env python
# coding: utf-8
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl import YoutubeDL
from youtube_dl.compat import compat_http_server, compat_urllib_request
import ssl
import threading
TEST_DIR = os.path.dirname(os.path.abspath(__file__))
def http_server_port(httpd):
if os.name == 'java' and isinstance(httpd.socket, ssl.SSLSocket):
# In Jython SSLSocket is not a subclass of socket.socket
sock = httpd.socket.sock
else:
sock = httpd.socket
return sock.getsockname()[1]
class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
def log_message(self, format, *args):
pass
def do_GET(self):
if self.path == '/video.html':
self.send_response(200)
self.send_header('Content-Type', 'text/html; charset=utf-8')
self.end_headers()
self.wfile.write(b'<html><video src="/vid.mp4" /></html>')
elif self.path == '/vid.mp4':
self.send_response(200)
self.send_header('Content-Type', 'video/mp4')
self.end_headers()
self.wfile.write(b'\x00\x00\x00\x00\x20\x66\x74[video]')
elif self.path == '/302':
if sys.version_info[0] == 3:
# XXX: Python 3 http server does not allow non-ASCII header values
self.send_response(404)
self.end_headers()
return
new_url = 'http://localhost:%d/中文.html' % http_server_port(self.server)
self.send_response(302)
self.send_header(b'Location', new_url.encode('utf-8'))
self.end_headers()
elif self.path == '/%E4%B8%AD%E6%96%87.html':
self.send_response(200)
self.send_header('Content-Type', 'text/html; charset=utf-8')
self.end_headers()
self.wfile.write(b'<html><video src="/vid.mp4" /></html>')
else:
assert False
class FakeLogger(object):
def debug(self, msg):
pass
def warning(self, msg):
pass
def error(self, msg):
pass
class TestHTTP(unittest.TestCase):
def setUp(self):
self.httpd = compat_http_server.HTTPServer(
('localhost', 0), HTTPTestRequestHandler)
self.port = http_server_port(self.httpd)
self.server_thread = threading.Thread(target=self.httpd.serve_forever)
self.server_thread.daemon = True
self.server_thread.start()
def test_unicode_path_redirection(self):
# XXX: Python 3 http server does not allow non-ASCII header values
if sys.version_info[0] == 3:
return
ydl = YoutubeDL({'logger': FakeLogger()})
r = ydl.extract_info('http://localhost:%d/302' % self.port)
self.assertEqual(r['url'], 'http://localhost:%d/vid.mp4' % self.port)
class TestHTTPS(unittest.TestCase):
def setUp(self):
certfn = os.path.join(TEST_DIR, 'testcert.pem')
self.httpd = compat_http_server.HTTPServer(
('localhost', 0), HTTPTestRequestHandler)
self.httpd.socket = ssl.wrap_socket(
self.httpd.socket, certfile=certfn, server_side=True)
self.port = http_server_port(self.httpd)
self.server_thread = threading.Thread(target=self.httpd.serve_forever)
self.server_thread.daemon = True
self.server_thread.start()
def test_nocheckcertificate(self):
if sys.version_info >= (2, 7, 9): # No certificate checking anyways
ydl = YoutubeDL({'logger': FakeLogger()})
self.assertRaises(
Exception,
ydl.extract_info, 'https://localhost:%d/video.html' % self.port)
ydl = YoutubeDL({'logger': FakeLogger(), 'nocheckcertificate': True})
r = ydl.extract_info('https://localhost:%d/video.html' % self.port)
self.assertEqual(r['url'], 'https://localhost:%d/vid.mp4' % self.port)
def _build_proxy_handler(name):
class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
proxy_name = name
def log_message(self, format, *args):
pass
def do_GET(self):
self.send_response(200)
self.send_header('Content-Type', 'text/plain; charset=utf-8')
self.end_headers()
self.wfile.write('{self.proxy_name}: {self.path}'.format(self=self).encode('utf-8'))
return HTTPTestRequestHandler
class TestProxy(unittest.TestCase):
def setUp(self):
self.proxy = compat_http_server.HTTPServer(
('localhost', 0), _build_proxy_handler('normal'))
self.port = http_server_port(self.proxy)
self.proxy_thread = threading.Thread(target=self.proxy.serve_forever)
self.proxy_thread.daemon = True
self.proxy_thread.start()
self.geo_proxy = compat_http_server.HTTPServer(
('localhost', 0), _build_proxy_handler('geo'))
self.geo_port = http_server_port(self.geo_proxy)
self.geo_proxy_thread = threading.Thread(target=self.geo_proxy.serve_forever)
self.geo_proxy_thread.daemon = True
self.geo_proxy_thread.start()
def test_proxy(self):
geo_proxy = 'localhost:{0}'.format(self.geo_port)
ydl = YoutubeDL({
'proxy': 'localhost:{0}'.format(self.port),
'geo_verification_proxy': geo_proxy,
})
url = 'http://foo.com/bar'
response = ydl.urlopen(url).read().decode('utf-8')
self.assertEqual(response, 'normal: {0}'.format(url))
req = compat_urllib_request.Request(url)
req.add_header('Ytdl-request-proxy', geo_proxy)
response = ydl.urlopen(req).read().decode('utf-8')
self.assertEqual(response, 'geo: {0}'.format(url))
def test_proxy_with_idn(self):
ydl = YoutubeDL({
'proxy': 'localhost:{0}'.format(self.port),
})
url = 'http://中文.tw/'
response = ydl.urlopen(url).read().decode('utf-8')
# b'xn--fiq228c' is '中文'.encode('idna')
self.assertEqual(response, 'normal: http://xn--fiq228c.tw/')
if __name__ == '__main__':
unittest.main()

47
test/test_iqiyi_sdk_interpreter.py Normal file
View File

@ -0,0 +1,47 @@
#!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import FakeYDL
from youtube_dl.extractor import IqiyiIE
class IqiyiIEWithCredentials(IqiyiIE):
def _get_login_info(self):
return 'foo', 'bar'
class WarningLogger(object):
def __init__(self):
self.messages = []
def warning(self, msg):
self.messages.append(msg)
def debug(self, msg):
pass
def error(self, msg):
pass
class TestIqiyiSDKInterpreter(unittest.TestCase):
def test_iqiyi_sdk_interpreter(self):
'''
Test the functionality of IqiyiSDKInterpreter by trying to log in
If `sign` is incorrect, /validate call throws an HTTP 556 error
'''
logger = WarningLogger()
ie = IqiyiIEWithCredentials(FakeYDL({'logger': logger}))
ie._login()
self.assertTrue('unable to log in:' in logger.messages[0])
if __name__ == '__main__':
unittest.main()

109
test/test_jsinterp.py Normal file
View File

@ -0,0 +1,109 @@
#!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.jsinterp import JSInterpreter
class TestJSInterpreter(unittest.TestCase):
def test_basic(self):
jsi = JSInterpreter('function x(){;}')
self.assertEqual(jsi.call_function('x'), None)
jsi = JSInterpreter('function x3(){return 42;}')
self.assertEqual(jsi.call_function('x3'), 42)
jsi = JSInterpreter('var x5 = function(){return 42;}')
self.assertEqual(jsi.call_function('x5'), 42)
def test_calc(self):
jsi = JSInterpreter('function x4(a){return 2*a+1;}')
self.assertEqual(jsi.call_function('x4', 3), 7)
def test_empty_return(self):
jsi = JSInterpreter('function f(){return; y()}')
self.assertEqual(jsi.call_function('f'), None)
def test_morespace(self):
jsi = JSInterpreter('function x (a) { return 2 * a + 1 ; }')
self.assertEqual(jsi.call_function('x', 3), 7)
jsi = JSInterpreter('function f () { x = 2 ; return x; }')
self.assertEqual(jsi.call_function('f'), 2)
def test_strange_chars(self):
jsi = JSInterpreter('function $_xY1 ($_axY1) { var $_axY2 = $_axY1 + 1; return $_axY2; }')
self.assertEqual(jsi.call_function('$_xY1', 20), 21)
def test_operators(self):
jsi = JSInterpreter('function f(){return 1 << 5;}')
self.assertEqual(jsi.call_function('f'), 32)
jsi = JSInterpreter('function f(){return 19 & 21;}')
self.assertEqual(jsi.call_function('f'), 17)
jsi = JSInterpreter('function f(){return 11 >> 2;}')
self.assertEqual(jsi.call_function('f'), 2)
def test_array_access(self):
jsi = JSInterpreter('function f(){var x = [1,2,3]; x[0] = 4; x[0] = 5; x[2] = 7; return x;}')
self.assertEqual(jsi.call_function('f'), [5, 2, 7])
def test_parens(self):
jsi = JSInterpreter('function f(){return (1) + (2) * ((( (( (((((3)))))) )) ));}')
self.assertEqual(jsi.call_function('f'), 7)
jsi = JSInterpreter('function f(){return (1 + 2) * 3;}')
self.assertEqual(jsi.call_function('f'), 9)
def test_assignments(self):
jsi = JSInterpreter('function f(){var x = 20; x = 30 + 1; return x;}')
self.assertEqual(jsi.call_function('f'), 31)
jsi = JSInterpreter('function f(){var x = 20; x += 30 + 1; return x;}')
self.assertEqual(jsi.call_function('f'), 51)
jsi = JSInterpreter('function f(){var x = 20; x -= 30 + 1; return x;}')
self.assertEqual(jsi.call_function('f'), -11)
def test_comments(self):
'Skipping: Not yet fully implemented'
return
jsi = JSInterpreter('''
function x() {
var x = /* 1 + */ 2;
var y = /* 30
* 40 */ 50;
return x + y;
}
''')
self.assertEqual(jsi.call_function('x'), 52)
jsi = JSInterpreter('''
function f() {
var x = "/*";
var y = 1 /* comment */ + 2;
return y;
}
''')
self.assertEqual(jsi.call_function('f'), 3)
def test_precedence(self):
jsi = JSInterpreter('''
function x() {
var a = [10, 20, 30, 40, 50];
var b = 6;
a[0]=a[b%a.length];
return a;
}''')
self.assertEqual(jsi.call_function('x'), [20, 20, 30, 40, 50])
if __name__ == '__main__':
unittest.main()

26
test/test_netrc.py Normal file
View File

@ -0,0 +1,26 @@
# coding: utf-8
from __future__ import unicode_literals
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.extractor import (
gen_extractors,
)
class TestNetRc(unittest.TestCase):
def test_netrc_present(self):
for ie in gen_extractors():
if not hasattr(ie, '_login'):
continue
self.assertTrue(
hasattr(ie, '_NETRC_MACHINE'),
'Extractor %s supports login, but is missing a _NETRC_MACHINE property' % ie.IE_NAME)
if __name__ == '__main__':
unittest.main()

17
test/test_postprocessors.py Normal file
View File

@ -0,0 +1,17 @@
#!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.postprocessor import MetadataFromTitlePP
class TestMetadataFromTitle(unittest.TestCase):
def test_format_to_regex(self):
pp = MetadataFromTitlePP(None, '%(title)s - %(artist)s')
self.assertEqual(pp._titleregex, '(?P<title>.+)\ \-\ (?P<artist>.+)')

118
test/test_socks.py Normal file
View File

@ -0,0 +1,118 @@
#!/usr/bin/env python
# coding: utf-8
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import random
import subprocess
from test.helper import (
FakeYDL,
get_params,
)
from youtube_dl.compat import (
compat_str,
compat_urllib_request,
)
class TestMultipleSocks(unittest.TestCase):
@staticmethod
def _check_params(attrs):
params = get_params()
for attr in attrs:
if attr not in params:
print('Missing %s. Skipping.' % attr)
return
return params
def test_proxy_http(self):
params = self._check_params(['primary_proxy', 'primary_server_ip'])
if params is None:
return
ydl = FakeYDL({
'proxy': params['primary_proxy']
})
self.assertEqual(
ydl.urlopen('http://yt-dl.org/ip').read().decode('utf-8'),
params['primary_server_ip'])
def test_proxy_https(self):
params = self._check_params(['primary_proxy', 'primary_server_ip'])
if params is None:
return
ydl = FakeYDL({
'proxy': params['primary_proxy']
})
self.assertEqual(
ydl.urlopen('https://yt-dl.org/ip').read().decode('utf-8'),
params['primary_server_ip'])
def test_secondary_proxy_http(self):
params = self._check_params(['secondary_proxy', 'secondary_server_ip'])
if params is None:
return
ydl = FakeYDL()
req = compat_urllib_request.Request('http://yt-dl.org/ip')
req.add_header('Ytdl-request-proxy', params['secondary_proxy'])
self.assertEqual(
ydl.urlopen(req).read().decode('utf-8'),
params['secondary_server_ip'])
def test_secondary_proxy_https(self):
params = self._check_params(['secondary_proxy', 'secondary_server_ip'])
if params is None:
return
ydl = FakeYDL()
req = compat_urllib_request.Request('https://yt-dl.org/ip')
req.add_header('Ytdl-request-proxy', params['secondary_proxy'])
self.assertEqual(
ydl.urlopen(req).read().decode('utf-8'),
params['secondary_server_ip'])
class TestSocks(unittest.TestCase):
_SKIP_SOCKS_TEST = True
def setUp(self):
if self._SKIP_SOCKS_TEST:
return
self.port = random.randint(20000, 30000)
self.server_process = subprocess.Popen([
'srelay', '-f', '-i', '127.0.0.1:%d' % self.port],
stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
def tearDown(self):
if self._SKIP_SOCKS_TEST:
return
self.server_process.terminate()
self.server_process.communicate()
def _get_ip(self, protocol):
if self._SKIP_SOCKS_TEST:
return '127.0.0.1'
ydl = FakeYDL({
'proxy': '%s://127.0.0.1:%d' % (protocol, self.port),
})
return ydl.urlopen('http://yt-dl.org/ip').read().decode('utf-8')
def test_socks4(self):
self.assertTrue(isinstance(self._get_ip('socks4'), compat_str))
def test_socks4a(self):
self.assertTrue(isinstance(self._get_ip('socks4a'), compat_str))
def test_socks5(self):
self.assertTrue(isinstance(self._get_ip('socks5'), compat_str))
if __name__ == '__main__':
unittest.main()

375
test/test_subtitles.py
View File

@ -11,13 +11,23 @@ from test.helper import FakeYDL, md5
from youtube_dl.extractor import (
BlipTVIE,
YoutubeIE,
DailymotionIE,
TEDIE,
VimeoIE,
WallaIE,
CeskaTelevizeIE,
LyndaIE,
NPOIE,
ComedyCentralIE,
NRKTVIE,
RaiTVIE,
VikiIE,
ThePlatformIE,
ThePlatformFeedIE,
RTVEALaCartaIE,
FunnyOrDieIE,
DemocracynowIE,
)
@ -27,48 +37,44 @@ class BaseTestSubtitles(unittest.TestCase):
def setUp(self):
self.DL = FakeYDL()
self.ie = self.IE(self.DL)
self.ie = self.IE()
self.DL.add_info_extractor(self.ie)
def getInfoDict(self):
info_dict = self.ie.extract(self.url)
info_dict = self.DL.extract_info(self.url, download=False)
return info_dict
def getSubtitles(self):
info_dict = self.getInfoDict()
return info_dict['subtitles']
subtitles = info_dict['requested_subtitles']
if not subtitles:
return subtitles
for sub_info in subtitles.values():
if sub_info.get('data') is None:
uf = self.DL.urlopen(sub_info['url'])
sub_info['data'] = uf.read().decode('utf-8')
return dict((l, sub_info['data']) for l, sub_info in subtitles.items())
class TestYoutubeSubtitles(BaseTestSubtitles):
url = 'QRS8MkLhQmM'
IE = YoutubeIE
def test_youtube_no_writesubtitles(self):
self.DL.params['writesubtitles'] = False
subtitles = self.getSubtitles()
self.assertEqual(subtitles, None)
def test_youtube_subtitles(self):
self.DL.params['writesubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), '4cd9278a35ba2305f47354ee13472260')
def test_youtube_subtitles_lang(self):
self.DL.params['writesubtitles'] = True
self.DL.params['subtitleslangs'] = ['it']
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['it']), '164a51f16f260476a05b50fe4c2f161d')
def test_youtube_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(len(subtitles.keys()), 13)
self.assertEqual(md5(subtitles['en']), '3cb210999d3e021bd6c7f0ea751eab06')
self.assertEqual(md5(subtitles['it']), '6d752b98c31f1cf8d597050c7a2cb4b5')
for lang in ['fr', 'de']:
self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
def test_youtube_subtitles_sbv_format(self):
def test_youtube_subtitles_ttml_format(self):
self.DL.params['writesubtitles'] = True
self.DL.params['subtitlesformat'] = 'sbv'
self.DL.params['subtitlesformat'] = 'ttml'
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), '13aeaa0c245a8bed9a451cb643e3ad8b')
self.assertEqual(md5(subtitles['en']), 'e306f8c42842f723447d9f63ad65df54')
def test_youtube_subtitles_vtt_format(self):
self.DL.params['writesubtitles'] = True
@ -76,12 +82,6 @@ class TestYoutubeSubtitles(BaseTestSubtitles):
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), '3cb210999d3e021bd6c7f0ea751eab06')
def test_youtube_list_subtitles(self):
self.DL.expect_warning('Video doesn\'t have automatic captions')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_youtube_automatic_captions(self):
self.url = '8YoUxe5ncPo'
self.DL.params['writeautomaticsub'] = True
@ -103,55 +103,22 @@ class TestYoutubeSubtitles(BaseTestSubtitles):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(len(subtitles), 0)
def test_youtube_multiple_langs(self):
self.url = 'QRS8MkLhQmM'
self.DL.params['writesubtitles'] = True
langs = ['it', 'fr', 'de']
self.DL.params['subtitleslangs'] = langs
subtitles = self.getSubtitles()
for lang in langs:
self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
self.assertFalse(subtitles)
class TestDailymotionSubtitles(BaseTestSubtitles):
url = 'http://www.dailymotion.com/video/xczg00'
IE = DailymotionIE
def test_no_writesubtitles(self):
subtitles = self.getSubtitles()
self.assertEqual(subtitles, None)
def test_subtitles(self):
self.DL.params['writesubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), '976553874490cba125086bbfea3ff76f')
def test_subtitles_lang(self):
self.DL.params['writesubtitles'] = True
self.DL.params['subtitleslangs'] = ['fr']
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['fr']), '594564ec7d588942e384e920e5341792')
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(len(subtitles.keys()), 5)
def test_list_subtitles(self):
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_automatic_captions(self):
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['writeautomaticsub'] = True
self.DL.params['subtitleslang'] = ['en']
subtitles = self.getSubtitles()
self.assertTrue(len(subtitles.keys()) == 0)
self.assertTrue(len(subtitles.keys()) >= 6)
self.assertEqual(md5(subtitles['en']), '976553874490cba125086bbfea3ff76f')
self.assertEqual(md5(subtitles['fr']), '594564ec7d588942e384e920e5341792')
for lang in ['es', 'fr', 'de']:
self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
def test_nosubtitles(self):
self.DL.expect_warning('video doesn\'t have subtitles')
@ -159,120 +126,35 @@ class TestDailymotionSubtitles(BaseTestSubtitles):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(len(subtitles), 0)
def test_multiple_langs(self):
self.DL.params['writesubtitles'] = True
langs = ['es', 'fr', 'de']
self.DL.params['subtitleslangs'] = langs
subtitles = self.getSubtitles()
for lang in langs:
self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
self.assertFalse(subtitles)
class TestTedSubtitles(BaseTestSubtitles):
url = 'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html'
IE = TEDIE
def test_no_writesubtitles(self):
subtitles = self.getSubtitles()
self.assertEqual(subtitles, None)
def test_subtitles(self):
self.DL.params['writesubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), '4262c1665ff928a2dada178f62cb8d14')
def test_subtitles_lang(self):
self.DL.params['writesubtitles'] = True
self.DL.params['subtitleslangs'] = ['fr']
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['fr']), '66a63f7f42c97a50f8c0e90bc7797bb5')
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertTrue(len(subtitles.keys()) >= 28)
def test_list_subtitles(self):
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_automatic_captions(self):
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['writeautomaticsub'] = True
self.DL.params['subtitleslang'] = ['en']
subtitles = self.getSubtitles()
self.assertTrue(len(subtitles.keys()) == 0)
def test_multiple_langs(self):
self.DL.params['writesubtitles'] = True
langs = ['es', 'fr', 'de']
self.DL.params['subtitleslangs'] = langs
subtitles = self.getSubtitles()
for lang in langs:
self.assertEqual(md5(subtitles['en']), '4262c1665ff928a2dada178f62cb8d14')
self.assertEqual(md5(subtitles['fr']), '66a63f7f42c97a50f8c0e90bc7797bb5')
for lang in ['es', 'fr', 'de']:
self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
class TestBlipTVSubtitles(BaseTestSubtitles):
url = 'http://blip.tv/a/a-6603250'
IE = BlipTVIE
def test_list_subtitles(self):
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_allsubtitles(self):
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), '5b75c300af65fe4476dff79478bb93e4')
class TestVimeoSubtitles(BaseTestSubtitles):
url = 'http://vimeo.com/76979871'
IE = VimeoIE
def test_no_writesubtitles(self):
subtitles = self.getSubtitles()
self.assertEqual(subtitles, None)
def test_subtitles(self):
self.DL.params['writesubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), '26399116d23ae3cf2c087cea94bc43b4')
def test_subtitles_lang(self):
self.DL.params['writesubtitles'] = True
self.DL.params['subtitleslangs'] = ['fr']
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['fr']), 'b6191146a6c5d3a452244d853fde6dc8')
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['de', 'en', 'es', 'fr']))
def test_list_subtitles(self):
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_automatic_captions(self):
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['writeautomaticsub'] = True
self.DL.params['subtitleslang'] = ['en']
subtitles = self.getSubtitles()
self.assertTrue(len(subtitles.keys()) == 0)
self.assertEqual(md5(subtitles['en']), '8062383cf4dec168fc40a088aa6d5888')
self.assertEqual(md5(subtitles['fr']), 'b6191146a6c5d3a452244d853fde6dc8')
def test_nosubtitles(self):
self.DL.expect_warning('video doesn\'t have subtitles')
@ -280,27 +162,13 @@ class TestVimeoSubtitles(BaseTestSubtitles):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(len(subtitles), 0)
def test_multiple_langs(self):
self.DL.params['writesubtitles'] = True
langs = ['es', 'fr', 'de']
self.DL.params['subtitleslangs'] = langs
subtitles = self.getSubtitles()
for lang in langs:
self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
self.assertFalse(subtitles)
class TestWallaSubtitles(BaseTestSubtitles):
url = 'http://vod.walla.co.il/movie/2705958/the-yes-men'
IE = WallaIE
def test_list_subtitles(self):
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_allsubtitles(self):
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['writesubtitles'] = True
@ -315,26 +183,20 @@ class TestWallaSubtitles(BaseTestSubtitles):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(len(subtitles), 0)
self.assertFalse(subtitles)
class TestCeskaTelevizeSubtitles(BaseTestSubtitles):
url = 'http://www.ceskatelevize.cz/ivysilani/10600540290-u6-uzasny-svet-techniky'
IE = CeskaTelevizeIE
def test_list_subtitles(self):
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_allsubtitles(self):
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['cs']))
self.assertEqual(md5(subtitles['cs']), '9bf52d9549533c32c427e264bf0847d4')
self.assertTrue(len(subtitles['cs']) > 20000)
def test_nosubtitles(self):
self.DL.expect_warning('video doesn\'t have subtitles')
@ -342,7 +204,154 @@ class TestCeskaTelevizeSubtitles(BaseTestSubtitles):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(len(subtitles), 0)
self.assertFalse(subtitles)
class TestLyndaSubtitles(BaseTestSubtitles):
url = 'http://www.lynda.com/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html'
IE = LyndaIE
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), '09bbe67222259bed60deaa26997d73a7')
class TestNPOSubtitles(BaseTestSubtitles):
url = 'http://www.npo.nl/nos-journaal/28-08-2014/POW_00722860'
IE = NPOIE
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['nl']))
self.assertEqual(md5(subtitles['nl']), 'fc6435027572b63fb4ab143abd5ad3f4')
class TestMTVSubtitles(BaseTestSubtitles):
url = 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother'
IE = ComedyCentralIE
def getInfoDict(self):
return super(TestMTVSubtitles, self).getInfoDict()['entries'][0]
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), 'b9f6ca22a6acf597ec76f61749765e65')
class TestNRKSubtitles(BaseTestSubtitles):
url = 'http://tv.nrk.no/serie/ikke-gjoer-dette-hjemme/DMPV73000411/sesong-2/episode-1'
IE = NRKTVIE
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['no']))
self.assertEqual(md5(subtitles['no']), '544fa917d3197fcbee64634559221cc2')
class TestRaiSubtitles(BaseTestSubtitles):
url = 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html'
IE = RaiTVIE
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['it']))
self.assertEqual(md5(subtitles['it']), 'b1d90a98755126b61e667567a1f6680a')
class TestVikiSubtitles(BaseTestSubtitles):
url = 'http://www.viki.com/videos/1060846v-punch-episode-18'
IE = VikiIE
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), '53cb083a5914b2d84ef1ab67b880d18a')
class TestThePlatformSubtitles(BaseTestSubtitles):
# from http://www.3playmedia.com/services-features/tools/integrations/theplatform/
# (see http://theplatform.com/about/partners/type/subtitles-closed-captioning/)
url = 'theplatform:JFUjUE1_ehvq'
IE = ThePlatformIE
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), '97e7670cbae3c4d26ae8bcc7fdd78d4b')
class TestThePlatformFeedSubtitles(BaseTestSubtitles):
url = 'http://feed.theplatform.com/f/7wvmTC/msnbc_video-p-test?form=json&pretty=true&range=-40&byGuid=n_hardball_5biden_140207'
IE = ThePlatformFeedIE
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), '48649a22e82b2da21c9a67a395eedade')
class TestRtveSubtitles(BaseTestSubtitles):
url = 'http://www.rtve.es/alacarta/videos/los-misterios-de-laura/misterios-laura-capitulo-32-misterio-del-numero-17-2-parte/2428621/'
IE = RTVEALaCartaIE
def test_allsubtitles(self):
print('Skipping, only available from Spain')
return
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['es']))
self.assertEqual(md5(subtitles['es']), '69e70cae2d40574fb7316f31d6eb7fca')
class TestFunnyOrDieSubtitles(BaseTestSubtitles):
url = 'http://www.funnyordie.com/videos/224829ff6d/judd-apatow-will-direct-your-vine'
IE = FunnyOrDieIE
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), 'c5593c193eacd353596c11c2d4f9ecc4')
class TestDemocracynowSubtitles(BaseTestSubtitles):
url = 'http://www.democracynow.org/shows/2015/7/3'
IE = DemocracynowIE
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), 'acaca989e24a9e45a6719c9b3d60815c')
def test_subtitles_in_page(self):
self.url = 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree'
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), 'acaca989e24a9e45a6719c9b3d60815c')
if __name__ == '__main__':

4
test/test_swfinterp.py
View File

@ -34,8 +34,8 @@ def _make_testfunc(testfile):
def test_func(self):
as_file = os.path.join(TEST_DIR, testfile)
swf_file = os.path.join(TEST_DIR, test_id + '.swf')
if ((not os.path.exists(swf_file))
or os.path.getmtime(swf_file) < os.path.getmtime(as_file)):
if ((not os.path.exists(swf_file)) or
os.path.getmtime(swf_file) < os.path.getmtime(as_file)):
# Recompile
try:
subprocess.check_call([

11
test/test_unicode_literals.py
View File

@ -17,13 +17,22 @@ IGNORED_FILES = [
'buildserver.py',
]
IGNORED_DIRS = [
'.git',
'.tox',
]
from test.helper import assertRegexpMatches
class TestUnicodeLiterals(unittest.TestCase):
def test_all_files(self):
for dirpath, _, filenames in os.walk(rootDir):
for dirpath, dirnames, filenames in os.walk(rootDir):
for ignore_dir in IGNORED_DIRS:
if ignore_dir in dirnames:
# If we remove the directory from dirnames os.walk won't
# recurse into it
dirnames.remove(ignore_dir)
for basename in filenames:
if not basename.endswith('.py'):
continue

30
test/test_update.py Normal file
View File

@ -0,0 +1,30 @@
#!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import json
from youtube_dl.update import rsa_verify
class TestUpdate(unittest.TestCase):
def test_rsa_verify(self):
UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537)
with open(os.path.join(os.path.dirname(os.path.abspath(__file__)), 'versions.json'), 'rb') as f:
versions_info = f.read().decode()
versions_info = json.loads(versions_info)
signature = versions_info['signature']
del versions_info['signature']
self.assertTrue(rsa_verify(
json.dumps(versions_info, sort_keys=True).encode('utf-8'),
signature, UPDATES_RSA_KEY))
if __name__ == '__main__':
unittest.main()

674
test/test_utils.py
View File

@ -18,39 +18,79 @@ import xml.etree.ElementTree
from youtube_dl.utils import (
age_restricted,
args_to_str,
encode_base_n,
clean_html,
date_from_str,
DateRange,
detect_exe_version,
determine_ext,
dict_get,
encode_compat_str,
encodeFilename,
escape_rfc3986,
escape_url,
extract_attributes,
ExtractorError,
find_xpath_attr,
fix_xml_ampersands,
get_element_by_class,
InAdvancePagedList,
intlist_to_bytes,
is_html,
js_to_json,
limit_length,
mimetype2ext,
month_by_name,
ohdave_rsa_encrypt,
OnDemandPagedList,
orderedSet,
parse_age_limit,
parse_duration,
parse_filesize,
parse_count,
parse_iso8601,
read_batch_urls,
sanitize_filename,
sanitize_path,
prepend_extension,
replace_extension,
remove_start,
remove_end,
remove_quotes,
shell_quote,
smuggle_url,
str_to_int,
strip_jsonp,
struct_unpack,
timeconvert,
unescapeHTML,
unified_strdate,
unified_timestamp,
unsmuggle_url,
uppercase_escape,
lowercase_escape,
url_basename,
urlencode_postdata,
urshift,
update_url_query,
version_tuple,
xpath_with_ns,
xpath_element,
xpath_text,
xpath_attr,
render_table,
match_str,
parse_dfxp_time_expr,
dfxp2srt,
cli_option,
cli_valueless_option,
cli_bool_option,
parse_codecs,
)
from youtube_dl.compat import (
compat_chr,
compat_etree_fromstring,
compat_urlparse,
compat_parse_qs,
)
@ -83,6 +123,11 @@ class TestUtil(unittest.TestCase):
sanitize_filename('New World record at 0:12:34'),
'New World record at 0_12_34')
self.assertEqual(sanitize_filename('--gasdgf'), '_-gasdgf')
self.assertEqual(sanitize_filename('--gasdgf', is_id=True), '--gasdgf')
self.assertEqual(sanitize_filename('.gasdgf'), 'gasdgf')
self.assertEqual(sanitize_filename('.gasdgf', is_id=True), '.gasdgf')
forbidden = '"\0\\/'
for fc in forbidden:
for fbc in forbidden:
@ -102,8 +147,8 @@ class TestUtil(unittest.TestCase):
self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
tests = 'a\xe4b\u4e2d\u56fd\u7684c'
self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
tests = 'aäb\u4e2d\u56fd\u7684c'
self.assertEqual(sanitize_filename(tests, restricted=True), 'aab_c')
self.assertTrue(sanitize_filename('\xf6', restricted=True) != '') # No empty filename
forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
@ -118,11 +163,86 @@ class TestUtil(unittest.TestCase):
self.assertTrue(sanitize_filename('-', restricted=True) != '')
self.assertTrue(sanitize_filename(':', restricted=True) != '')
self.assertEqual(sanitize_filename(
'ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ', restricted=True),
'AAAAAAAECEEEEIIIIDNOOOOOOOOEUUUUUYPssaaaaaaaeceeeeiiiionooooooooeuuuuuypy')
def test_sanitize_ids(self):
self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
def test_sanitize_path(self):
if sys.platform != 'win32':
return
self.assertEqual(sanitize_path('abc'), 'abc')
self.assertEqual(sanitize_path('abc/def'), 'abc\\def')
self.assertEqual(sanitize_path('abc\\def'), 'abc\\def')
self.assertEqual(sanitize_path('abc|def'), 'abc#def')
self.assertEqual(sanitize_path('<>:"|?*'), '#######')
self.assertEqual(sanitize_path('C:/abc/def'), 'C:\\abc\\def')
self.assertEqual(sanitize_path('C?:/abc/def'), 'C##\\abc\\def')
self.assertEqual(sanitize_path('\\\\?\\UNC\\ComputerName\\abc'), '\\\\?\\UNC\\ComputerName\\abc')
self.assertEqual(sanitize_path('\\\\?\\UNC/ComputerName/abc'), '\\\\?\\UNC\\ComputerName\\abc')
self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
self.assertEqual(sanitize_path('\\\\?\\C:/abc'), '\\\\?\\C:\\abc')
self.assertEqual(sanitize_path('\\\\?\\C:\\ab?c\\de:f'), '\\\\?\\C:\\ab#c\\de#f')
self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
self.assertEqual(
sanitize_path('youtube/%(uploader)s/%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s'),
'youtube\\%(uploader)s\\%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s')
self.assertEqual(
sanitize_path('youtube/TheWreckingYard ./00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part'),
'youtube\\TheWreckingYard #\\00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part')
self.assertEqual(sanitize_path('abc/def...'), 'abc\\def..#')
self.assertEqual(sanitize_path('abc.../def'), 'abc..#\\def')
self.assertEqual(sanitize_path('abc.../def...'), 'abc..#\\def..#')
self.assertEqual(sanitize_path('../abc'), '..\\abc')
self.assertEqual(sanitize_path('../../abc'), '..\\..\\abc')
self.assertEqual(sanitize_path('./abc'), 'abc')
self.assertEqual(sanitize_path('./../abc'), '..\\abc')
def test_prepend_extension(self):
self.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
self.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
self.assertEqual(prepend_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
self.assertEqual(prepend_extension('abc', 'temp'), 'abc.temp')
self.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp')
self.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext')
def test_replace_extension(self):
self.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp')
self.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp')
self.assertEqual(replace_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
self.assertEqual(replace_extension('abc', 'temp'), 'abc.temp')
self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
def test_remove_start(self):
self.assertEqual(remove_start(None, 'A - '), None)
self.assertEqual(remove_start('A - B', 'A - '), 'B')
self.assertEqual(remove_start('B - A', 'A - '), 'B - A')
def test_remove_end(self):
self.assertEqual(remove_end(None, ' - B'), None)
self.assertEqual(remove_end('A - B', ' - B'), 'A')
self.assertEqual(remove_end('B - A', ' - B'), 'B - A')
def test_remove_quotes(self):
self.assertEqual(remove_quotes(None), None)
self.assertEqual(remove_quotes('"'), '"')
self.assertEqual(remove_quotes("'"), "'")
self.assertEqual(remove_quotes(';'), ';')
self.assertEqual(remove_quotes('";'), '";')
self.assertEqual(remove_quotes('""'), '')
self.assertEqual(remove_quotes('";"'), ';')
def test_ordered_set(self):
self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
self.assertEqual(orderedSet([]), [])
@ -132,8 +252,19 @@ class TestUtil(unittest.TestCase):
def test_unescape_html(self):
self.assertEqual(unescapeHTML('%20;'), '%20;')
self.assertEqual(
unescapeHTML('&eacute;'), 'é')
self.assertEqual(unescapeHTML('&#x2F;'), '/')
self.assertEqual(unescapeHTML('&#47;'), '/')
self.assertEqual(unescapeHTML('&eacute;'), 'é')
self.assertEqual(unescapeHTML('&#2013266066;'), '&#2013266066;')
# HTML5 entities
self.assertEqual(unescapeHTML('&period;&apos;'), '.\'')
def test_date_from_str(self):
self.assertEqual(date_from_str('yesterday'), date_from_str('now-1day'))
self.assertEqual(date_from_str('now+7day'), date_from_str('now+1week'))
self.assertEqual(date_from_str('now+14day'), date_from_str('now+2week'))
self.assertEqual(date_from_str('now+365day'), date_from_str('now+1year'))
self.assertEqual(date_from_str('now+30day'), date_from_str('now+1month'))
def test_daterange(self):
_20century = DateRange("19000101", "20000101")
@ -154,6 +285,42 @@ class TestUtil(unittest.TestCase):
self.assertEqual(
unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
'20141126')
self.assertEqual(
unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
'20150202')
self.assertEqual(unified_strdate('Feb 14th 2016 5:45PM'), '20160214')
self.assertEqual(unified_strdate('25-09-2014'), '20140925')
self.assertEqual(unified_strdate('27.02.2016 17:30'), '20160227')
self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
self.assertEqual(unified_strdate('Feb 7, 2016 at 6:35 pm'), '20160207')
def test_unified_timestamps(self):
self.assertEqual(unified_timestamp('December 21, 2010'), 1292889600)
self.assertEqual(unified_timestamp('8/7/2009'), 1247011200)
self.assertEqual(unified_timestamp('Dec 14, 2012'), 1355443200)
self.assertEqual(unified_timestamp('2012/10/11 01:56:38 +0000'), 1349920598)
self.assertEqual(unified_timestamp('1968 12 10'), -33436800)
self.assertEqual(unified_timestamp('1968-12-10'), -33436800)
self.assertEqual(unified_timestamp('28/01/2014 21:00:00 +0100'), 1390939200)
self.assertEqual(
unified_timestamp('11/26/2014 11:30:00 AM PST', day_first=False),
1417001400)
self.assertEqual(
unified_timestamp('2/2/2015 6:47:40 PM', day_first=False),
1422902860)
self.assertEqual(unified_timestamp('Feb 14th 2016 5:45PM'), 1455471900)
self.assertEqual(unified_timestamp('25-09-2014'), 1411603200)
self.assertEqual(unified_timestamp('27.02.2016 17:30'), 1456594200)
self.assertEqual(unified_timestamp('UNKNOWN DATE FORMAT'), None)
self.assertEqual(unified_timestamp('May 16, 2016 11:15 PM'), 1463440500)
self.assertEqual(unified_timestamp('Feb 7, 2016 at 6:35 pm'), 1454870100)
def test_determine_ext(self):
self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
self.assertEqual(determine_ext('http://example.com/foo/bar/?download', None), None)
self.assertEqual(determine_ext('http://example.com/foo/bar.nonext/?download', None), None)
self.assertEqual(determine_ext('http://example.com/foo/bar/mp4?download', None), None)
self.assertEqual(determine_ext('http://example.com/foo/bar.m3u8//?download'), 'm3u8')
def test_find_xpath_attr(self):
testxml = '''<root>
@ -161,12 +328,21 @@ class TestUtil(unittest.TestCase):
<node x="a"/>
<node x="a" y="c" />
<node x="b" y="d" />
<node x="" />
</root>'''
doc = xml.etree.ElementTree.fromstring(testxml)
doc = compat_etree_fromstring(testxml)
self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n'), None)
self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
self.assertEqual(find_xpath_attr(doc, './/node', 'n'), None)
self.assertEqual(find_xpath_attr(doc, './/node', 'n', 'v'), None)
self.assertEqual(find_xpath_attr(doc, './/node', 'x'), doc[1])
self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'b'), doc[3])
self.assertEqual(find_xpath_attr(doc, './/node', 'y'), doc[2])
self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'd'), doc[3])
self.assertEqual(find_xpath_attr(doc, './/node', 'x', ''), doc[4])
def test_xpath_with_ns(self):
testxml = '''<root xmlns:media="http://example.com/">
@ -175,12 +351,56 @@ class TestUtil(unittest.TestCase):
<url>http://server.com/download.mp3</url>
</media:song>
</root>'''
doc = xml.etree.ElementTree.fromstring(testxml)
doc = compat_etree_fromstring(testxml)
find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
self.assertTrue(find('media:song') is not None)
self.assertEqual(find('media:song/media:author').text, 'The Author')
self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
def test_xpath_element(self):
doc = xml.etree.ElementTree.Element('root')
div = xml.etree.ElementTree.SubElement(doc, 'div')
p = xml.etree.ElementTree.SubElement(div, 'p')
p.text = 'Foo'
self.assertEqual(xpath_element(doc, 'div/p'), p)
self.assertEqual(xpath_element(doc, ['div/p']), p)
self.assertEqual(xpath_element(doc, ['div/bar', 'div/p']), p)
self.assertEqual(xpath_element(doc, 'div/bar', default='default'), 'default')
self.assertEqual(xpath_element(doc, ['div/bar'], default='default'), 'default')
self.assertTrue(xpath_element(doc, 'div/bar') is None)
self.assertTrue(xpath_element(doc, ['div/bar']) is None)
self.assertTrue(xpath_element(doc, ['div/bar'], 'div/baz') is None)
self.assertRaises(ExtractorError, xpath_element, doc, 'div/bar', fatal=True)
self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar'], fatal=True)
self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar', 'div/baz'], fatal=True)
def test_xpath_text(self):
testxml = '''<root>
<div>
<p>Foo</p>
</div>
</root>'''
doc = compat_etree_fromstring(testxml)
self.assertEqual(xpath_text(doc, 'div/p'), 'Foo')
self.assertEqual(xpath_text(doc, 'div/bar', default='default'), 'default')
self.assertTrue(xpath_text(doc, 'div/bar') is None)
self.assertRaises(ExtractorError, xpath_text, doc, 'div/bar', fatal=True)
def test_xpath_attr(self):
testxml = '''<root>
<div>
<p x="a">Foo</p>
</div>
</root>'''
doc = compat_etree_fromstring(testxml)
self.assertEqual(xpath_attr(doc, 'div/p', 'x'), 'a')
self.assertEqual(xpath_attr(doc, 'div/bar', 'x'), None)
self.assertEqual(xpath_attr(doc, 'div/p', 'y'), None)
self.assertEqual(xpath_attr(doc, 'div/bar', 'x', default='default'), 'default')
self.assertEqual(xpath_attr(doc, 'div/p', 'y', default='default'), 'default')
self.assertRaises(ExtractorError, xpath_attr, doc, 'div/bar', 'x', fatal=True)
self.assertRaises(ExtractorError, xpath_attr, doc, 'div/p', 'y', fatal=True)
def test_smuggle_url(self):
data = {"ö": "ö", "abc": [3]}
url = 'https://foo.bar/baz?x=y#a'
@ -193,6 +413,12 @@ class TestUtil(unittest.TestCase):
self.assertEqual(res_url, url)
self.assertEqual(res_data, None)
smug_url = smuggle_url(url, {'a': 'b'})
smug_smug_url = smuggle_url(smug_url, {'c': 'd'})
res_url, res_data = unsmuggle_url(smug_smug_url)
self.assertEqual(res_url, url)
self.assertEqual(res_data, {'a': 'b', 'c': 'd'})
def test_shell_quote(self):
args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")
@ -211,6 +437,20 @@ class TestUtil(unittest.TestCase):
url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
'trailer.mp4')
def test_parse_age_limit(self):
self.assertEqual(parse_age_limit(None), None)
self.assertEqual(parse_age_limit(False), None)
self.assertEqual(parse_age_limit('invalid'), None)
self.assertEqual(parse_age_limit(0), 0)
self.assertEqual(parse_age_limit(18), 18)
self.assertEqual(parse_age_limit(21), 21)
self.assertEqual(parse_age_limit(22), None)
self.assertEqual(parse_age_limit('18'), 18)
self.assertEqual(parse_age_limit('18+'), 18)
self.assertEqual(parse_age_limit('PG-13'), 13)
self.assertEqual(parse_age_limit('TV-14'), 14)
self.assertEqual(parse_age_limit('TV-MA'), 17)
def test_parse_duration(self):
self.assertEqual(parse_duration(None), None)
self.assertEqual(parse_duration(False), None)
@ -236,6 +476,11 @@ class TestUtil(unittest.TestCase):
self.assertEqual(parse_duration('5 s'), 5)
self.assertEqual(parse_duration('3 min'), 180)
self.assertEqual(parse_duration('2.5 hours'), 9000)
self.assertEqual(parse_duration('02:03:04'), 7384)
self.assertEqual(parse_duration('01:02:03:04'), 93784)
self.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
self.assertEqual(parse_duration('87 Min.'), 5220)
self.assertEqual(parse_duration('PT1H0.040S'), 3600.04)
def test_fix_xml_ampersands(self):
self.assertEqual(
@ -275,9 +520,6 @@ class TestUtil(unittest.TestCase):
testPL(5, 2, (2, 99), [2, 3, 4])
testPL(5, 2, (20, 99), [])
def test_struct_unpack(self):
self.assertEqual(struct_unpack('!B', b'\x00'), (0,))
def test_read_batch_urls(self):
f = io.StringIO('''\xef\xbb\xbf foo
bar\r
@ -291,11 +533,73 @@ class TestUtil(unittest.TestCase):
data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
self.assertTrue(isinstance(data, bytes))
def test_update_url_query(self):
def query_dict(url):
return compat_parse_qs(compat_urlparse.urlparse(url).query)
self.assertEqual(query_dict(update_url_query(
'http://example.com/path', {'quality': ['HD'], 'format': ['mp4']})),
query_dict('http://example.com/path?quality=HD&format=mp4'))
self.assertEqual(query_dict(update_url_query(
'http://example.com/path', {'system': ['LINUX', 'WINDOWS']})),
query_dict('http://example.com/path?system=LINUX&system=WINDOWS'))
self.assertEqual(query_dict(update_url_query(
'http://example.com/path', {'fields': 'id,formats,subtitles'})),
query_dict('http://example.com/path?fields=id,formats,subtitles'))
self.assertEqual(query_dict(update_url_query(
'http://example.com/path', {'fields': ('id,formats,subtitles', 'thumbnails')})),
query_dict('http://example.com/path?fields=id,formats,subtitles&fields=thumbnails'))
self.assertEqual(query_dict(update_url_query(
'http://example.com/path?manifest=f4m', {'manifest': []})),
query_dict('http://example.com/path'))
self.assertEqual(query_dict(update_url_query(
'http://example.com/path?system=LINUX&system=WINDOWS', {'system': 'LINUX'})),
query_dict('http://example.com/path?system=LINUX'))
self.assertEqual(query_dict(update_url_query(
'http://example.com/path', {'fields': b'id,formats,subtitles'})),
query_dict('http://example.com/path?fields=id,formats,subtitles'))
self.assertEqual(query_dict(update_url_query(
'http://example.com/path', {'width': 1080, 'height': 720})),
query_dict('http://example.com/path?width=1080&height=720'))
self.assertEqual(query_dict(update_url_query(
'http://example.com/path', {'bitrate': 5020.43})),
query_dict('http://example.com/path?bitrate=5020.43'))
self.assertEqual(query_dict(update_url_query(
'http://example.com/path', {'test': '第二行тест'})),
query_dict('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82'))
def test_dict_get(self):
FALSE_VALUES = {
'none': None,
'false': False,
'zero': 0,
'empty_string': '',
'empty_list': [],
}
d = FALSE_VALUES.copy()
d['a'] = 42
self.assertEqual(dict_get(d, 'a'), 42)
self.assertEqual(dict_get(d, 'b'), None)
self.assertEqual(dict_get(d, 'b', 42), 42)
self.assertEqual(dict_get(d, ('a', )), 42)
self.assertEqual(dict_get(d, ('b', 'a', )), 42)
self.assertEqual(dict_get(d, ('b', 'c', 'a', 'd', )), 42)
self.assertEqual(dict_get(d, ('b', 'c', )), None)
self.assertEqual(dict_get(d, ('b', 'c', ), 42), 42)
for key, false_value in FALSE_VALUES.items():
self.assertEqual(dict_get(d, ('b', 'c', key, )), None)
self.assertEqual(dict_get(d, ('b', 'c', key, ), skip_false_values=False), false_value)
def test_encode_compat_str(self):
self.assertEqual(encode_compat_str(b'\xd1\x82\xd0\xb5\xd1\x81\xd1\x82', 'utf-8'), 'тест')
self.assertEqual(encode_compat_str('тест', 'utf-8'), 'тест')
def test_parse_iso8601(self):
self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
self.assertEqual(parse_iso8601('2015-09-29T08:27:31.727'), 1443515251)
self.assertEqual(parse_iso8601('2015-09-29T08-27-31.727'), None)
def test_strip_jsonp(self):
stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
@ -306,10 +610,18 @@ class TestUtil(unittest.TestCase):
d = json.loads(stripped)
self.assertEqual(d, {'STATUS': 'OK'})
stripped = strip_jsonp('ps.embedHandler({"status": "success"});')
d = json.loads(stripped)
self.assertEqual(d, {'status': 'success'})
def test_uppercase_escape(self):
self.assertEqual(uppercase_escape('aä'), 'aä')
self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
def test_lowercase_escape(self):
self.assertEqual(lowercase_escape('aä'), 'aä')
self.assertEqual(lowercase_escape('\\u0026'), '&')
def test_limit_length(self):
self.assertEqual(limit_length(None, 12), None)
self.assertEqual(limit_length('foo', 12), 'foo')
@ -317,6 +629,45 @@ class TestUtil(unittest.TestCase):
limit_length('foo bar baz asd', 12).startswith('foo bar'))
self.assertTrue('...' in limit_length('foo bar baz asd', 12))
def test_mimetype2ext(self):
self.assertEqual(mimetype2ext(None), None)
self.assertEqual(mimetype2ext('video/x-flv'), 'flv')
self.assertEqual(mimetype2ext('application/x-mpegURL'), 'm3u8')
self.assertEqual(mimetype2ext('text/vtt'), 'vtt')
self.assertEqual(mimetype2ext('text/vtt;charset=utf-8'), 'vtt')
self.assertEqual(mimetype2ext('text/html; charset=utf-8'), 'html')
def test_month_by_name(self):
self.assertEqual(month_by_name(None), None)
self.assertEqual(month_by_name('December', 'en'), 12)
self.assertEqual(month_by_name('décembre', 'fr'), 12)
self.assertEqual(month_by_name('December'), 12)
self.assertEqual(month_by_name('décembre'), None)
self.assertEqual(month_by_name('Unknown', 'unknown'), None)
def test_parse_codecs(self):
self.assertEqual(parse_codecs(''), {})
self.assertEqual(parse_codecs('avc1.77.30, mp4a.40.2'), {
'vcodec': 'avc1.77.30',
'acodec': 'mp4a.40.2',
})
self.assertEqual(parse_codecs('mp4a.40.2'), {
'vcodec': 'none',
'acodec': 'mp4a.40.2',
})
self.assertEqual(parse_codecs('mp4a.40.5,avc1.42001e'), {
'vcodec': 'avc1.42001e',
'acodec': 'mp4a.40.5',
})
self.assertEqual(parse_codecs('avc3.640028'), {
'vcodec': 'avc3.640028',
'acodec': 'none',
})
self.assertEqual(parse_codecs(', h264,,newcodec,aac'), {
'vcodec': 'h264',
'acodec': 'aac',
})
def test_escape_rfc3986(self):
reserved = "!*'();:@&=+$,/?#[]"
unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
@ -338,11 +689,11 @@ class TestUtil(unittest.TestCase):
)
self.assertEqual(
escape_url('http://тест.рф/фрагмент'),
'http://тест.рф/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
'http://xn--e1aybc.xn--p1ai/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
)
self.assertEqual(
escape_url('http://тест.рф/абв?абв=абв#абв'),
'http://тест.рф/%D0%B0%D0%B1%D0%B2?%D0%B0%D0%B1%D0%B2=%D0%B0%D0%B1%D0%B2#%D0%B0%D0%B1%D0%B2'
'http://xn--e1aybc.xn--p1ai/%D0%B0%D0%B1%D0%B2?%D0%B0%D0%B1%D0%B2=%D0%B0%D0%B1%D0%B2#%D0%B0%D0%B1%D0%B2'
)
self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
@ -362,6 +713,28 @@ class TestUtil(unittest.TestCase):
"playlist":[{"controls":{"all":null}}]
}''')
inp = '''"The CW\\'s \\'Crazy Ex-Girlfriend\\'"'''
self.assertEqual(js_to_json(inp), '''"The CW's 'Crazy Ex-Girlfriend'"''')
inp = '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
json_code = js_to_json(inp)
self.assertEqual(json.loads(json_code), json.loads(inp))
inp = '''{
0:{src:'skipped', type: 'application/dash+xml'},
1:{src:'skipped', type: 'application/vnd.apple.mpegURL'},
}'''
self.assertEqual(js_to_json(inp), '''{
"0":{"src":"skipped", "type": "application/dash+xml"},
"1":{"src":"skipped", "type": "application/vnd.apple.mpegURL"}
}''')
inp = '''{"foo":101}'''
self.assertEqual(js_to_json(inp), '''{"foo":101}''')
inp = '''{"duration": "00:01:07"}'''
self.assertEqual(js_to_json(inp), '''{"duration": "00:01:07"}''')
def test_js_to_json_edgecases(self):
on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
@ -369,6 +742,81 @@ class TestUtil(unittest.TestCase):
on = js_to_json('{"abc": true}')
self.assertEqual(json.loads(on), {'abc': True})
# Ignore JavaScript code as well
on = js_to_json('''{
"x": 1,
y: "a",
z: some.code
}''')
d = json.loads(on)
self.assertEqual(d['x'], 1)
self.assertEqual(d['y'], 'a')
on = js_to_json('["abc", "def",]')
self.assertEqual(json.loads(on), ['abc', 'def'])
on = js_to_json('{"abc": "def",}')
self.assertEqual(json.loads(on), {'abc': 'def'})
on = js_to_json('{ 0: /* " \n */ ",]" , }')
self.assertEqual(json.loads(on), {'0': ',]'})
on = js_to_json(r'["<p>x<\/p>"]')
self.assertEqual(json.loads(on), ['<p>x</p>'])
on = js_to_json(r'["\xaa"]')
self.assertEqual(json.loads(on), ['\u00aa'])
on = js_to_json("['a\\\nb']")
self.assertEqual(json.loads(on), ['ab'])
on = js_to_json('{0xff:0xff}')
self.assertEqual(json.loads(on), {'255': 255})
on = js_to_json('{077:077}')
self.assertEqual(json.loads(on), {'63': 63})
on = js_to_json('{42:42}')
self.assertEqual(json.loads(on), {'42': 42})
def test_extract_attributes(self):
self.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'})
self.assertEqual(extract_attributes("<e x='y'>"), {'x': 'y'})
self.assertEqual(extract_attributes('<e x=y>'), {'x': 'y'})
self.assertEqual(extract_attributes('<e x="a \'b\' c">'), {'x': "a 'b' c"})
self.assertEqual(extract_attributes('<e x=\'a "b" c\'>'), {'x': 'a "b" c'})
self.assertEqual(extract_attributes('<e x="&#121;">'), {'x': 'y'})
self.assertEqual(extract_attributes('<e x="&#x79;">'), {'x': 'y'})
self.assertEqual(extract_attributes('<e x="&amp;">'), {'x': '&'}) # XML
self.assertEqual(extract_attributes('<e x="&quot;">'), {'x': '"'})
self.assertEqual(extract_attributes('<e x="&pound;">'), {'x': '£'}) # HTML 3.2
self.assertEqual(extract_attributes('<e x="&lambda;">'), {'x': 'λ'}) # HTML 4.0
self.assertEqual(extract_attributes('<e x="&foo">'), {'x': '&foo'})
self.assertEqual(extract_attributes('<e x="\'">'), {'x': "'"})
self.assertEqual(extract_attributes('<e x=\'"\'>'), {'x': '"'})
self.assertEqual(extract_attributes('<e x >'), {'x': None})
self.assertEqual(extract_attributes('<e x=y a>'), {'x': 'y', 'a': None})
self.assertEqual(extract_attributes('<e x= y>'), {'x': 'y'})
self.assertEqual(extract_attributes('<e x=1 y=2 x=3>'), {'y': '2', 'x': '3'})
self.assertEqual(extract_attributes('<e \nx=\ny\n>'), {'x': 'y'})
self.assertEqual(extract_attributes('<e \nx=\n"y"\n>'), {'x': 'y'})
self.assertEqual(extract_attributes("<e \nx=\n'y'\n>"), {'x': 'y'})
self.assertEqual(extract_attributes('<e \nx="\ny\n">'), {'x': '\ny\n'})
self.assertEqual(extract_attributes('<e CAPS=x>'), {'caps': 'x'}) # Names lowercased
self.assertEqual(extract_attributes('<e x=1 X=2>'), {'x': '2'})
self.assertEqual(extract_attributes('<e X=1 x=2>'), {'x': '2'})
self.assertEqual(extract_attributes('<e _:funny-name1=1>'), {'_:funny-name1': '1'})
self.assertEqual(extract_attributes('<e x="Fáilte 世界 \U0001f600">'), {'x': 'Fáilte 世界 \U0001f600'})
self.assertEqual(extract_attributes('<e x="décompose&#769;">'), {'x': 'décompose\u0301'})
# "Narrow" Python builds don't support unicode code points outside BMP.
try:
compat_chr(0x10000)
supports_outside_bmp = True
except ValueError:
supports_outside_bmp = False
if supports_outside_bmp:
self.assertEqual(extract_attributes('<e x="Smile &#128512;!">'), {'x': 'Smile \U0001f600!'})
def test_clean_html(self):
self.assertEqual(clean_html('a:\nb'), 'a: b')
self.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
@ -392,7 +840,21 @@ class TestUtil(unittest.TestCase):
self.assertEqual(parse_filesize('2 MiB'), 2097152)
self.assertEqual(parse_filesize('5 GB'), 5000000000)
self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
self.assertEqual(parse_filesize('1.2tb'), 1200000000000)
self.assertEqual(parse_filesize('1,24 KB'), 1240)
self.assertEqual(parse_filesize('1,24 kb'), 1240)
self.assertEqual(parse_filesize('8.5 megabytes'), 8500000)
def test_parse_count(self):
self.assertEqual(parse_count(None), None)
self.assertEqual(parse_count(''), None)
self.assertEqual(parse_count('0'), 0)
self.assertEqual(parse_count('1000'), 1000)
self.assertEqual(parse_count('1.000'), 1000)
self.assertEqual(parse_count('1.1k'), 1100)
self.assertEqual(parse_count('1.1kk'), 1100000)
self.assertEqual(parse_count('1.1kk '), 1100000)
self.assertEqual(parse_count('1.1kk views'), 1100000)
def test_version_tuple(self):
self.assertEqual(version_tuple('1'), (1,))
@ -417,5 +879,193 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
self.assertTrue(age_restricted(18, 14))
self.assertFalse(age_restricted(18, 18))
def test_is_html(self):
self.assertFalse(is_html(b'\x49\x44\x43<html'))
self.assertTrue(is_html(b'<!DOCTYPE foo>\xaaa'))
self.assertTrue(is_html( # UTF-8 with BOM
b'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
self.assertTrue(is_html( # UTF-16-LE
b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
))
self.assertTrue(is_html( # UTF-16-BE
b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
))
self.assertTrue(is_html( # UTF-32-BE
b'\x00\x00\xFE\xFF\x00\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4'))
self.assertTrue(is_html( # UTF-32-LE
b'\xFF\xFE\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4\x00\x00\x00'))
def test_render_table(self):
self.assertEqual(
render_table(
['a', 'bcd'],
[[123, 4], [9999, 51]]),
'a bcd\n'
'123 4\n'
'9999 51')
def test_match_str(self):
self.assertRaises(ValueError, match_str, 'xy>foobar', {})
self.assertFalse(match_str('xy', {'x': 1200}))
self.assertTrue(match_str('!xy', {'x': 1200}))
self.assertTrue(match_str('x', {'x': 1200}))
self.assertFalse(match_str('!x', {'x': 1200}))
self.assertTrue(match_str('x', {'x': 0}))
self.assertFalse(match_str('x>0', {'x': 0}))
self.assertFalse(match_str('x>0', {}))
self.assertTrue(match_str('x>?0', {}))
self.assertTrue(match_str('x>1K', {'x': 1200}))
self.assertFalse(match_str('x>2K', {'x': 1200}))
self.assertTrue(match_str('x>=1200 & x < 1300', {'x': 1200}))
self.assertFalse(match_str('x>=1100 & x < 1200', {'x': 1200}))
self.assertFalse(match_str('y=a212', {'y': 'foobar42'}))
self.assertTrue(match_str('y=foobar42', {'y': 'foobar42'}))
self.assertFalse(match_str('y!=foobar42', {'y': 'foobar42'}))
self.assertTrue(match_str('y!=foobar2', {'y': 'foobar42'}))
self.assertFalse(match_str(
'like_count > 100 & dislike_count <? 50 & description',
{'like_count': 90, 'description': 'foo'}))
self.assertTrue(match_str(
'like_count > 100 & dislike_count <? 50 & description',
{'like_count': 190, 'description': 'foo'}))
self.assertFalse(match_str(
'like_count > 100 & dislike_count <? 50 & description',
{'like_count': 190, 'dislike_count': 60, 'description': 'foo'}))
self.assertFalse(match_str(
'like_count > 100 & dislike_count <? 50 & description',
{'like_count': 190, 'dislike_count': 10}))
def test_parse_dfxp_time_expr(self):
self.assertEqual(parse_dfxp_time_expr(None), None)
self.assertEqual(parse_dfxp_time_expr(''), None)
self.assertEqual(parse_dfxp_time_expr('0.1'), 0.1)
self.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1)
self.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0)
self.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1)
self.assertEqual(parse_dfxp_time_expr('00:00:01:100'), 1.1)
def test_dfxp2srt(self):
dfxp_data = '''<?xml version="1.0" encoding="UTF-8"?>
<tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
<body>
<div xml:lang="en">
<p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
<p begin="1" end="2">第二行<br/>♪♪</p>
<p begin="2" dur="1"><span>Third<br/>Line</span></p>
<p begin="3" end="-1">Lines with invalid timestamps are ignored</p>
<p begin="-1" end="-1">Ignore, two</p>
<p begin="3" dur="-1">Ignored, three</p>
</div>
</body>
</tt>'''
srt_data = '''1
00:00:00,000 --> 00:00:01,000
The following line contains Chinese characters and special symbols
2
00:00:01,000 --> 00:00:02,000
第二行
♪♪
3
00:00:02,000 --> 00:00:03,000
Third
Line
'''
self.assertEqual(dfxp2srt(dfxp_data), srt_data)
dfxp_data_no_default_namespace = '''<?xml version="1.0" encoding="UTF-8"?>
<tt xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
<body>
<div xml:lang="en">
<p begin="0" end="1">The first line</p>
</div>
</body>
</tt>'''
srt_data = '''1
00:00:00,000 --> 00:00:01,000
The first line
'''
self.assertEqual(dfxp2srt(dfxp_data_no_default_namespace), srt_data)
def test_cli_option(self):
self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), [])
self.assertEqual(cli_option({}, '--proxy', 'proxy'), [])
self.assertEqual(cli_option({'retries': 10}, '--retries', 'retries'), ['--retries', '10'])
def test_cli_valueless_option(self):
self.assertEqual(cli_valueless_option(
{'downloader': 'external'}, '--external-downloader', 'downloader', 'external'), ['--external-downloader'])
self.assertEqual(cli_valueless_option(
{'downloader': 'internal'}, '--external-downloader', 'downloader', 'external'), [])
self.assertEqual(cli_valueless_option(
{'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'), ['--no-check-certificate'])
self.assertEqual(cli_valueless_option(
{'nocheckcertificate': False}, '--no-check-certificate', 'nocheckcertificate'), [])
self.assertEqual(cli_valueless_option(
{'checkcertificate': True}, '--no-check-certificate', 'checkcertificate', False), [])
self.assertEqual(cli_valueless_option(
{'checkcertificate': False}, '--no-check-certificate', 'checkcertificate', False), ['--no-check-certificate'])
def test_cli_bool_option(self):
self.assertEqual(
cli_bool_option(
{'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'),
['--no-check-certificate', 'true'])
self.assertEqual(
cli_bool_option(
{'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate', separator='='),
['--no-check-certificate=true'])
self.assertEqual(
cli_bool_option(
{'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
['--check-certificate', 'false'])
self.assertEqual(
cli_bool_option(
{'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
['--check-certificate=false'])
self.assertEqual(
cli_bool_option(
{'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
['--check-certificate', 'true'])
self.assertEqual(
cli_bool_option(
{'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
['--check-certificate=true'])
def test_ohdave_rsa_encrypt(self):
N = 0xab86b6371b5318aaa1d3c9e612a9f1264f372323c8c0f19875b5fc3b3fd3afcc1e5bec527aa94bfa85bffc157e4245aebda05389a5357b75115ac94f074aefcd
e = 65537
self.assertEqual(
ohdave_rsa_encrypt(b'aa111222', e, N),
'726664bd9a23fd0c70f9f1b84aab5e3905ce1e45a584e9cbcf9bcc7510338fc1986d6c599ff990d923aa43c51c0d9013cd572e13bc58f4ae48f2ed8c0b0ba881')
def test_encode_base_n(self):
self.assertEqual(encode_base_n(0, 30), '0')
self.assertEqual(encode_base_n(80, 30), '2k')
custom_table = '9876543210ZYXWVUTSRQPONMLKJIHGFEDCBA'
self.assertEqual(encode_base_n(0, 30, custom_table), '9')
self.assertEqual(encode_base_n(80, 30, custom_table), '7P')
self.assertRaises(ValueError, encode_base_n, 0, 70)
self.assertRaises(ValueError, encode_base_n, 0, 60, custom_table)
def test_urshift(self):
self.assertEqual(urshift(3, 1), 1)
self.assertEqual(urshift(-3, 1), 2147483646)
def test_get_element_by_class(self):
html = '''
<span class="foo bar">nice</span>
'''
self.assertEqual(get_element_by_class('foo', html), 'nice')
self.assertEqual(get_element_by_class('no-such-class', html), None)
if __name__ == '__main__':
unittest.main()

70
test/test_verbose_output.py Normal file
View File

@ -0,0 +1,70 @@
#!/usr/bin/env python
# coding: utf-8
from __future__ import unicode_literals
import unittest
import sys
import os
import subprocess
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
class TestVerboseOutput(unittest.TestCase):
def test_private_info_arg(self):
outp = subprocess.Popen(
[
sys.executable, 'youtube_dl/__main__.py', '-v',
'--username', 'johnsmith@gmail.com',
'--password', 'secret',
], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
sout, serr = outp.communicate()
self.assertTrue(b'--username' in serr)
self.assertTrue(b'johnsmith' not in serr)
self.assertTrue(b'--password' in serr)
self.assertTrue(b'secret' not in serr)
def test_private_info_shortarg(self):
outp = subprocess.Popen(
[
sys.executable, 'youtube_dl/__main__.py', '-v',
'-u', 'johnsmith@gmail.com',
'-p', 'secret',
], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
sout, serr = outp.communicate()
self.assertTrue(b'-u' in serr)
self.assertTrue(b'johnsmith' not in serr)
self.assertTrue(b'-p' in serr)
self.assertTrue(b'secret' not in serr)
def test_private_info_eq(self):
outp = subprocess.Popen(
[
sys.executable, 'youtube_dl/__main__.py', '-v',
'--username=johnsmith@gmail.com',
'--password=secret',
], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
sout, serr = outp.communicate()
self.assertTrue(b'--username' in serr)
self.assertTrue(b'johnsmith' not in serr)
self.assertTrue(b'--password' in serr)
self.assertTrue(b'secret' not in serr)
def test_private_info_shortarg_eq(self):
outp = subprocess.Popen(
[
sys.executable, 'youtube_dl/__main__.py', '-v',
'-u=johnsmith@gmail.com',
'-p=secret',
], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
sout, serr = outp.communicate()
self.assertTrue(b'-u' in serr)
self.assertTrue(b'johnsmith' not in serr)
self.assertTrue(b'-p' in serr)
self.assertTrue(b'secret' not in serr)
if __name__ == '__main__':
unittest.main()

4
test/test_write_annotations.py
View File

@ -33,7 +33,7 @@ params = get_params({
TEST_ID = 'gr51aVj-mLg'
ANNOTATIONS_FILE = TEST_ID + '.flv.annotations.xml'
ANNOTATIONS_FILE = TEST_ID + '.annotations.xml'
EXPECTED_ANNOTATIONS = ['Speech bubble', 'Note', 'Title', 'Spotlight', 'Label']
@ -66,7 +66,7 @@ class TestAnnotations(unittest.TestCase):
textTag = a.find('TEXT')
text = textTag.text
self.assertTrue(text in expected) # assertIn only added in python 2.7
# remove the first occurance, there could be more than one annotation with the same text
# remove the first occurrence, there could be more than one annotation with the same text
expected.remove(text)
# We should have seen (and removed) all the expected annotation texts.
self.assertEqual(len(expected), 0, 'Not all expected annotations were found.')

13
test/test_youtube_lists.py
View File

@ -34,7 +34,7 @@ class TestYoutubeLists(unittest.TestCase):
ie = YoutubePlaylistIE(dl)
# TODO find a > 100 (paginating?) videos course
result = ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
entries = result['entries']
entries = list(result['entries'])
self.assertEqual(YoutubeIE().extract_id(entries[0]['url']), 'j9WZyLZCBzs')
self.assertEqual(len(entries), 25)
self.assertEqual(YoutubeIE().extract_id(entries[-1]['url']), 'rYefUsYuEp0')
@ -44,7 +44,7 @@ class TestYoutubeLists(unittest.TestCase):
ie = YoutubePlaylistIE(dl)
result = ie.extract('https://www.youtube.com/watch?v=W01L70IGBgE&index=2&list=RDOQpdSVF_k_w')
entries = result['entries']
self.assertTrue(len(entries) >= 20)
self.assertTrue(len(entries) >= 50)
original_video = entries[0]
self.assertEqual(original_video['id'], 'OQpdSVF_k_w')
@ -57,5 +57,14 @@ class TestYoutubeLists(unittest.TestCase):
entries = result['entries']
self.assertEqual(len(entries), 100)
def test_youtube_flat_playlist_titles(self):
dl = FakeYDL()
dl.params['extract_flat'] = True
ie = YoutubePlaylistIE(dl)
result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
self.assertIsPlaylist(result)
for entry in result['entries']:
self.assertTrue(entry.get('title'))
if __name__ == '__main__':
unittest.main()

11
test/test_youtube_signature.py
View File

@ -8,11 +8,11 @@ import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import io
import re
import string
from test.helper import FakeYDL
from youtube_dl.extractor import YoutubeIE
from youtube_dl.compat import compat_str, compat_urlretrieve
@ -64,6 +64,12 @@ _TESTS = [
'js',
'4646B5181C6C3020DF1D9C7FCFEA.AD80ABF70C39BD369CCCAE780AFBB98FA6B6CB42766249D9488C288',
'82C8849D94266724DC6B6AF89BBFA087EACCD963.B93C07FBA084ACAEFCF7C9D1FD0203C6C1815B6B'
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflKjOTVq/html5player.js',
'js',
'312AA52209E3623129A412D56A40F11CB0AF14AE.3EE09501CB14E3BCDC3B2AE808BF3F1D14E7FBF12',
'112AA5220913623229A412D56A40F11CB0AF14AE.3EE0950FCB14EEBCDC3B2AE808BF331D14E7FBF3',
)
]
@ -88,7 +94,8 @@ def make_tfunc(url, stype, sig_input, expected_sig):
if not os.path.exists(fn):
compat_urlretrieve(url, fn)
ie = YoutubeIE()
ydl = FakeYDL()
ie = YoutubeIE(ydl)
if stype == 'js':
with io.open(fn, encoding='utf-8') as testf:
jscode = testf.read()

52
test/testcert.pem Normal file
View File

@ -0,0 +1,52 @@
-----BEGIN PRIVATE KEY-----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-----END PRIVATE KEY-----
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----

34
test/versions.json Normal file
View File

@ -0,0 +1,34 @@
{
"latest": "2013.01.06",
"signature": "72158cdba391628569ffdbea259afbcf279bbe3d8aeb7492690735dc1cfa6afa754f55c61196f3871d429599ab22f2667f1fec98865527b32632e7f4b3675a7ef0f0fbe084d359256ae4bba68f0d33854e531a70754712f244be71d4b92e664302aa99653ee4df19800d955b6c4149cd2b3f24288d6e4b40b16126e01f4c8ce6",
"versions": {
"2013.01.02": {
"bin": [
"http://youtube-dl.org/downloads/2013.01.02/youtube-dl",
"f5b502f8aaa77675c4884938b1e4871ebca2611813a0c0e74f60c0fbd6dcca6b"
],
"exe": [
"http://youtube-dl.org/downloads/2013.01.02/youtube-dl.exe",
"75fa89d2ce297d102ff27675aa9d92545bbc91013f52ec52868c069f4f9f0422"
],
"tar": [
"http://youtube-dl.org/downloads/2013.01.02/youtube-dl-2013.01.02.tar.gz",
"6a66d022ac8e1c13da284036288a133ec8dba003b7bd3a5179d0c0daca8c8196"
]
},
"2013.01.06": {
"bin": [
"http://youtube-dl.org/downloads/2013.01.06/youtube-dl",
"64b6ed8865735c6302e836d4d832577321b4519aa02640dc508580c1ee824049"
],
"exe": [
"http://youtube-dl.org/downloads/2013.01.06/youtube-dl.exe",
"58609baf91e4389d36e3ba586e21dab882daaaee537e4448b1265392ae86ff84"
],
"tar": [
"http://youtube-dl.org/downloads/2013.01.06/youtube-dl-2013.01.06.tar.gz",
"fe77ab20a95d980ed17a659aa67e371fdd4d656d19c4c7950e7b720b0c2f1a86"
]
}
}
}

10
tox.ini
View File

@ -1,8 +1,14 @@
[tox]
envlist = py26,py27,py33
envlist = py26,py27,py33,py34,py35
[testenv]
deps =
nose
coverage
commands = nosetests --verbose {posargs:test} # --with-coverage --cover-package=youtube_dl --cover-html
# We need a valid $HOME for test_compat_expanduser
passenv = HOME
defaultargs = test --exclude test_download.py --exclude test_age_restriction.py
--exclude test_subtitles.py --exclude test_write_annotations.py
--exclude test_youtube_lists.py --exclude test_iqiyi_sdk_interpreter.py
--exclude test_socks.py
commands = nosetests --verbose {posargs:{[testenv]defaultargs}} # --with-coverage --cover-package=youtube_dl --cover-html
# test.test_download:TestDownload.test_NowVideo

1256
youtube_dl/YoutubeDL.py
View File

File diff suppressed because it is too large Load Diff

154
youtube_dl/__init__.py
View File

@ -18,14 +18,15 @@ from .options import (
from .compat import (
compat_expanduser,
compat_getpass,
compat_print,
compat_shlex_split,
workaround_optparse_bug9161,
)
from .utils import (
DateRange,
DEFAULT_OUTTMPL,
decodeOption,
DEFAULT_OUTTMPL,
DownloadError,
match_filter_func,
MaxDownloadsReached,
preferredencoding,
read_batch_urls,
@ -33,12 +34,14 @@ from .utils import (
setproctitle,
std_headers,
write_string,
render_table,
)
from .update import update_self
from .downloader import (
FileDownloader,
)
from .extractor import gen_extractors, list_extractors
from .extractor.adobepass import MSO_INFO
from .YoutubeDL import YoutubeDL
@ -65,16 +68,16 @@ def _real_main(argv=None):
# Custom HTTP headers
if opts.headers is not None:
for h in opts.headers:
if h.find(':', 1) < 0:
if ':' not in h:
parser.error('wrong header formatting, it should be key:value, not "%s"' % h)
key, value = h.split(':', 2)
key, value = h.split(':', 1)
if opts.verbose:
write_string('[debug] Adding header from command line option %s:%s\n' % (key, value))
std_headers[key] = value
# Dump user agent
if opts.dump_user_agent:
compat_print(std_headers['User-Agent'])
write_string(std_headers['User-Agent'] + '\n', out=sys.stdout)
sys.exit(0)
# Batch file verification
@ -84,7 +87,9 @@ def _real_main(argv=None):
if opts.batchfile == '-':
batchfd = sys.stdin
else:
batchfd = io.open(opts.batchfile, 'r', encoding='utf-8', errors='ignore')
batchfd = io.open(
compat_expanduser(opts.batchfile),
'r', encoding='utf-8', errors='ignore')
batch_urls = read_batch_urls(batchfd)
if opts.verbose:
write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
@ -97,10 +102,10 @@ def _real_main(argv=None):
if opts.list_extractors:
for ie in list_extractors(opts.age_limit):
compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
write_string(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '') + '\n', out=sys.stdout)
matchedUrls = [url for url in all_urls if ie.suitable(url)]
for mu in matchedUrls:
compat_print(' ' + mu)
write_string(' ' + mu + '\n', out=sys.stdout)
sys.exit(0)
if opts.list_extractor_descriptions:
for ie in list_extractors(opts.age_limit):
@ -113,7 +118,11 @@ def _real_main(argv=None):
_SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
_COUNTS = ('', '5', '10', 'all')
desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
compat_print(desc)
write_string(desc + '\n', out=sys.stdout)
sys.exit(0)
if opts.ap_list_mso:
table = [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()]
write_string('Supported TV Providers:\n' + render_table(['mso', 'mso name'], table) + '\n', out=sys.stdout)
sys.exit(0)
# Conflicting, missing and erroneous options
@ -121,12 +130,16 @@ def _real_main(argv=None):
parser.error('using .netrc conflicts with giving username/password')
if opts.password is not None and opts.username is None:
parser.error('account username missing\n')
if opts.ap_password is not None and opts.ap_username is None:
parser.error('TV Provider account username missing\n')
if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
parser.error('using output template conflicts with using title, video ID or auto number')
if opts.usetitle and opts.useid:
parser.error('using title conflicts with using video ID')
if opts.username is not None and opts.password is None:
opts.password = compat_getpass('Type account password and press [Return]: ')
if opts.ap_username is not None and opts.ap_password is None:
opts.ap_password = compat_getpass('Type TV provider account password and press [Return]: ')
if opts.ratelimit is not None:
numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
if numeric_limit is None:
@ -142,11 +155,32 @@ def _real_main(argv=None):
if numeric_limit is None:
parser.error('invalid max_filesize specified')
opts.max_filesize = numeric_limit
if opts.sleep_interval is not None:
if opts.sleep_interval < 0:
parser.error('sleep interval must be positive or 0')
if opts.max_sleep_interval is not None:
if opts.max_sleep_interval < 0:
parser.error('max sleep interval must be positive or 0')
if opts.max_sleep_interval < opts.sleep_interval:
parser.error('max sleep interval must be greater than or equal to min sleep interval')
else:
opts.max_sleep_interval = opts.sleep_interval
if opts.ap_mso and opts.ap_mso not in MSO_INFO:
parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers')
def parse_retries(retries):
if retries in ('inf', 'infinite'):
parsed_retries = float('inf')
else:
try:
parsed_retries = int(retries)
except (TypeError, ValueError):
parser.error('invalid retry count specified')
return parsed_retries
if opts.retries is not None:
try:
opts.retries = int(opts.retries)
except (TypeError, ValueError):
parser.error('invalid retry count specified')
opts.retries = parse_retries(opts.retries)
if opts.fragment_retries is not None:
opts.fragment_retries = parse_retries(opts.fragment_retries)
if opts.buffersize is not None:
numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
if numeric_buffersize is None:
@ -164,8 +198,11 @@ def _real_main(argv=None):
if not opts.audioquality.isdigit():
parser.error('invalid audio quality specified')
if opts.recodevideo is not None:
if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']:
if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']:
parser.error('invalid video recode format specified')
if opts.convertsubtitles is not None:
if opts.convertsubtitles not in ['srt', 'vtt', 'ass']:
parser.error('invalid subtitle format specified')
if opts.date is not None:
date = DateRange.day(opts.date)
@ -181,18 +218,14 @@ def _real_main(argv=None):
if opts.allsubtitles and not opts.writeautomaticsub:
opts.writesubtitles = True
if sys.version_info < (3,):
# In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems)
if opts.outtmpl is not None:
opts.outtmpl = opts.outtmpl.decode(preferredencoding())
outtmpl = ((opts.outtmpl is not None and opts.outtmpl)
or (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s')
or (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s')
or (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s')
or (opts.usetitle and '%(title)s-%(id)s.%(ext)s')
or (opts.useid and '%(id)s.%(ext)s')
or (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s')
or DEFAULT_OUTTMPL)
outtmpl = ((opts.outtmpl is not None and opts.outtmpl) or
(opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s') or
(opts.format == '-1' and '%(id)s-%(format)s.%(ext)s') or
(opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s') or
(opts.usetitle and '%(title)s-%(id)s.%(ext)s') or
(opts.useid and '%(id)s.%(ext)s') or
(opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s') or
DEFAULT_OUTTMPL)
if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
parser.error('Cannot download a video and extract audio into the same'
' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
@ -205,6 +238,11 @@ def _real_main(argv=None):
# PostProcessors
postprocessors = []
# Add the metadata pp first, the other pps will copy it
if opts.metafromtitle:
postprocessors.append({
'key': 'MetadataFromTitle',
'titleformat': opts.metafromtitle
})
if opts.addmetadata:
postprocessors.append({'key': 'FFmpegMetadata'})
if opts.extractaudio:
@ -219,25 +257,43 @@ def _real_main(argv=None):
'key': 'FFmpegVideoConvertor',
'preferedformat': opts.recodevideo,
})
if opts.convertsubtitles:
postprocessors.append({
'key': 'FFmpegSubtitlesConvertor',
'format': opts.convertsubtitles,
})
if opts.embedsubtitles:
postprocessors.append({
'key': 'FFmpegEmbedSubtitle',
'subtitlesformat': opts.subtitlesformat,
})
if opts.embedthumbnail:
already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
postprocessors.append({
'key': 'EmbedThumbnail',
'already_have_thumbnail': already_have_thumbnail
})
if not already_have_thumbnail:
opts.writethumbnail = True
# XAttrMetadataPP should be run after post-processors that may change file
# contents
if opts.xattrs:
postprocessors.append({'key': 'XAttrMetadata'})
if opts.embedthumbnail:
if not opts.addmetadata:
postprocessors.append({'key': 'FFmpegAudioFix'})
postprocessors.append({'key': 'AtomicParsley'})
# Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
# So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
if opts.exec_cmd:
postprocessors.append({
'key': 'ExecAfterDownload',
'verboseOutput': opts.verbose,
'exec_cmd': opts.exec_cmd,
})
external_downloader_args = None
if opts.external_downloader_args:
external_downloader_args = compat_shlex_split(opts.external_downloader_args)
postprocessor_args = None
if opts.postprocessor_args:
postprocessor_args = compat_shlex_split(opts.postprocessor_args)
match_filter = (
None if opts.match_filter is None
else match_filter_func(opts.match_filter))
ydl_opts = {
'usenetrc': opts.usenetrc,
@ -245,6 +301,9 @@ def _real_main(argv=None):
'password': opts.password,
'twofactor': opts.twofactor,
'videopassword': opts.videopassword,
'ap_mso': opts.ap_mso,
'ap_username': opts.ap_username,
'ap_password': opts.ap_password,
'quiet': (opts.quiet or any_getting or any_printing),
'no_warnings': opts.no_warnings,
'forceurl': opts.geturl,
@ -260,15 +319,17 @@ def _real_main(argv=None):
'simulate': opts.simulate or any_getting,
'skip_download': opts.skip_download,
'format': opts.format,
'format_limit': opts.format_limit,
'listformats': opts.listformats,
'outtmpl': outtmpl,
'autonumber_size': opts.autonumber_size,
'restrictfilenames': opts.restrictfilenames,
'ignoreerrors': opts.ignoreerrors,
'force_generic_extractor': opts.force_generic_extractor,
'ratelimit': opts.ratelimit,
'nooverwrites': opts.nooverwrites,
'retries': opts.retries,
'fragment_retries': opts.fragment_retries,
'skip_unavailable_fragments': opts.skip_unavailable_fragments,
'buffersize': opts.buffersize,
'noresizebuffer': opts.noresizebuffer,
'continuedl': opts.continue_dl,
@ -286,6 +347,7 @@ def _real_main(argv=None):
'writeannotations': opts.writeannotations,
'writeinfojson': opts.writeinfojson,
'writethumbnail': opts.writethumbnail,
'write_all_thumbnails': opts.write_all_thumbnails,
'writesubtitles': opts.writesubtitles,
'writeautomaticsub': opts.writeautomaticsub,
'allsubtitles': opts.allsubtitles,
@ -322,19 +384,35 @@ def _real_main(argv=None):
'default_search': opts.default_search,
'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
'encoding': opts.encoding,
'exec_cmd': opts.exec_cmd,
'extract_flat': opts.extract_flat,
'mark_watched': opts.mark_watched,
'merge_output_format': opts.merge_output_format,
'postprocessors': postprocessors,
'fixup': opts.fixup,
'source_address': opts.source_address,
'call_home': opts.call_home,
'sleep_interval': opts.sleep_interval,
'max_sleep_interval': opts.max_sleep_interval,
'external_downloader': opts.external_downloader,
'list_thumbnails': opts.list_thumbnails,
'playlist_items': opts.playlist_items,
'xattr_set_filesize': opts.xattr_set_filesize,
'match_filter': match_filter,
'no_color': opts.no_color,
'ffmpeg_location': opts.ffmpeg_location,
'hls_prefer_native': opts.hls_prefer_native,
'hls_use_mpegts': opts.hls_use_mpegts,
'external_downloader_args': external_downloader_args,
'postprocessor_args': postprocessor_args,
'cn_verification_proxy': opts.cn_verification_proxy,
'geo_verification_proxy': opts.geo_verification_proxy,
}
with YoutubeDL(ydl_opts) as ydl:
# Update version
if opts.update_self:
update_self(ydl.to_screen, opts.verbose)
update_self(ydl.to_screen, opts.verbose, ydl._opener)
# Remove cache dir
if opts.rm_cachedir:
@ -346,11 +424,13 @@ def _real_main(argv=None):
sys.exit()
ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
parser.error('you must provide at least one URL')
parser.error(
'You must provide at least one URL.\n'
'Type youtube-dl --help to see a list of all options.')
try:
if opts.load_info_filename is not None:
retcode = ydl.download_with_info_file(opts.load_info_filename)
retcode = ydl.download_with_info_file(compat_expanduser(opts.load_info_filename))
else:
retcode = ydl.download(all_urls)
except MaxDownloadsReached:

4
youtube_dl/__main__.py
View File

@ -7,11 +7,11 @@ from __future__ import unicode_literals
import sys
if __package__ is None and not hasattr(sys, "frozen"):
if __package__ is None and not hasattr(sys, 'frozen'):
# direct call of __main__.py
import os.path
path = os.path.realpath(os.path.abspath(__file__))
sys.path.append(os.path.dirname(os.path.dirname(path)))
sys.path.insert(0, os.path.dirname(os.path.dirname(path)))
import youtube_dl

8
youtube_dl/aes.py
View File

@ -1,7 +1,5 @@
from __future__ import unicode_literals
__all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_cbc_decrypt', 'aes_decrypt_text']
import base64
from math import ceil
@ -154,7 +152,7 @@ def aes_decrypt_text(data, password, key_size_bytes):
"""
NONCE_LENGTH_BYTES = 8
data = bytes_to_intlist(base64.b64decode(data))
data = bytes_to_intlist(base64.b64decode(data.encode('utf-8')))
password = bytes_to_intlist(password.encode('utf-8'))
key = password[:key_size_bytes] + [0] * (key_size_bytes - len(password))
@ -163,7 +161,7 @@ def aes_decrypt_text(data, password, key_size_bytes):
nonce = data[:NONCE_LENGTH_BYTES]
cipher = data[NONCE_LENGTH_BYTES:]
class Counter:
class Counter(object):
__value = nonce + [0] * (BLOCK_SIZE_BYTES - NONCE_LENGTH_BYTES)
def next_value(self):
@ -329,3 +327,5 @@ def inc(data):
data[i] = data[i] + 1
break
return data
__all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_cbc_decrypt', 'aes_decrypt_text']

2661
youtube_dl/compat.py
View File

File diff suppressed because it is too large Load Diff

63
youtube_dl/downloader/__init__.py
View File

@ -1,35 +1,54 @@
from __future__ import unicode_literals
from .common import FileDownloader
from .hls import HlsFD
from .hls import NativeHlsFD
from .http import HttpFD
from .mplayer import MplayerFD
from .rtmp import RtmpFD
from .f4m import F4mFD
from ..utils import (
determine_ext,
from .hls import HlsFD
from .http import HttpFD
from .rtmp import RtmpFD
from .dash import DashSegmentsFD
from .rtsp import RtspFD
from .external import (
get_external_downloader,
FFmpegFD,
)
from ..utils import (
determine_protocol,
)
def get_suitable_downloader(info_dict):
PROTOCOL_MAP = {
'rtmp': RtmpFD,
'm3u8_native': HlsFD,
'm3u8': FFmpegFD,
'mms': RtspFD,
'rtsp': RtspFD,
'f4m': F4mFD,
'http_dash_segments': DashSegmentsFD,
}
def get_suitable_downloader(info_dict, params={}):
"""Get the downloader class that can handle the info dict."""
url = info_dict['url']
protocol = info_dict.get('protocol')
protocol = determine_protocol(info_dict)
info_dict['protocol'] = protocol
if url.startswith('rtmp'):
return RtmpFD
if protocol == 'm3u8_native':
return NativeHlsFD
if (protocol == 'm3u8') or (protocol is None and determine_ext(url) == 'm3u8'):
# if (info_dict.get('start_time') or info_dict.get('end_time')) and not info_dict.get('requested_formats') and FFmpegFD.can_download(info_dict):
# return FFmpegFD
external_downloader = params.get('external_downloader')
if external_downloader is not None:
ed = get_external_downloader(external_downloader)
if ed.can_download(info_dict):
return ed
if protocol == 'm3u8' and params.get('hls_prefer_native') is True:
return HlsFD
if url.startswith('mms') or url.startswith('rtsp'):
return MplayerFD
if determine_ext(url) == 'f4m':
return F4mFD
else:
return HttpFD
if protocol == 'm3u8_native' and params.get('hls_prefer_native') is False:
return FFmpegFD
return PROTOCOL_MAP.get(protocol, HttpFD)
__all__ = [
'get_suitable_downloader',

181
youtube_dl/downloader/common.py
View File

@ -1,13 +1,16 @@
from __future__ import unicode_literals
from __future__ import division, unicode_literals
import os
import re
import sys
import time
import random
from ..compat import compat_str
from ..compat import compat_os_name
from ..utils import (
encodeFilename,
error_to_compat_str,
decodeArgument,
format_bytes,
timeconvert,
)
@ -25,21 +28,26 @@ class FileDownloader(object):
Available options:
verbose: Print additional info to stdout.
quiet: Do not print messages to stdout.
ratelimit: Download speed limit, in bytes/sec.
retries: Number of times to retry for HTTP error 5xx
buffersize: Size of download buffer in bytes.
noresizebuffer: Do not automatically resize the download buffer.
continuedl: Try to continue downloads if possible.
noprogress: Do not print the progress bar.
logtostderr: Log messages to stderr instead of stdout.
consoletitle: Display progress in console window's titlebar.
nopart: Do not use temporary .part files.
updatetime: Use the Last-modified header to set output file timestamps.
test: Download only first bytes to test the downloader.
min_filesize: Skip files smaller than this size
max_filesize: Skip files larger than this size
verbose: Print additional info to stdout.
quiet: Do not print messages to stdout.
ratelimit: Download speed limit, in bytes/sec.
retries: Number of times to retry for HTTP error 5xx
buffersize: Size of download buffer in bytes.
noresizebuffer: Do not automatically resize the download buffer.
continuedl: Try to continue downloads if possible.
noprogress: Do not print the progress bar.
logtostderr: Log messages to stderr instead of stdout.
consoletitle: Display progress in console window's titlebar.
nopart: Do not use temporary .part files.
updatetime: Use the Last-modified header to set output file timestamps.
test: Download only first bytes to test the downloader.
min_filesize: Skip files smaller than this size
max_filesize: Skip files larger than this size
xattr_set_filesize: Set ytdl.filesize user xattribute with expected size.
(experimental)
external_downloader_args: A list of additional command-line arguments for the
external downloader.
hls_use_mpegts: Use the mpegts container for HLS videos.
Subclasses of this one must re-define the real_download method.
"""
@ -52,6 +60,7 @@ class FileDownloader(object):
self.ydl = ydl
self._progress_hooks = []
self.params = params
self.add_progress_hook(self.report_progress)
@staticmethod
def format_seconds(seconds):
@ -107,6 +116,10 @@ class FileDownloader(object):
return '%10s' % '---b/s'
return '%10s' % ('%s/s' % format_bytes(speed))
@staticmethod
def format_retries(retries):
return 'inf' if retries == float('inf') else '%.0f' % retries
@staticmethod
def best_block_size(elapsed_time, bytes):
new_min = max(bytes / 2.0, 1.0)
@ -150,7 +163,7 @@ class FileDownloader(object):
def slow_down(self, start_time, now, byte_counter):
"""Sleep if the download speed is over the rate limit."""
rate_limit = self.params.get('ratelimit', None)
rate_limit = self.params.get('ratelimit')
if rate_limit is None or byte_counter == 0:
return
if now is None:
@ -180,7 +193,7 @@ class FileDownloader(object):
return
os.rename(encodeFilename(old_filename), encodeFilename(new_filename))
except (IOError, OSError) as err:
self.report_error('unable to rename file: %s' % compat_str(err))
self.report_error('unable to rename file: %s' % error_to_compat_str(err))
def try_utime(self, filename, last_modified_hdr):
"""Try to set the last-modified time of the given file."""
@ -199,7 +212,7 @@ class FileDownloader(object):
return
try:
os.utime(filename, (time.time(), filetime))
except:
except Exception:
pass
return filetime
@ -212,7 +225,7 @@ class FileDownloader(object):
if self.params.get('progress_with_newline', False):
self.to_screen(fullmsg)
else:
if os.name == 'nt':
if compat_os_name == 'nt':
prev_len = getattr(self, '_report_progress_prev_line_length',
0)
if prev_len > len(fullmsg):
@ -224,42 +237,64 @@ class FileDownloader(object):
self.to_screen(clear_line + fullmsg, skip_eol=not is_last_line)
self.to_console_title('youtube-dl ' + msg)
def report_progress(self, percent, data_len_str, speed, eta):
"""Report download progress."""
if self.params.get('noprogress', False):
def report_progress(self, s):
if s['status'] == 'finished':
if self.params.get('noprogress', False):
self.to_screen('[download] Download completed')
else:
s['_total_bytes_str'] = format_bytes(s['total_bytes'])
if s.get('elapsed') is not None:
s['_elapsed_str'] = self.format_seconds(s['elapsed'])
msg_template = '100%% of %(_total_bytes_str)s in %(_elapsed_str)s'
else:
msg_template = '100%% of %(_total_bytes_str)s'
self._report_progress_status(
msg_template % s, is_last_line=True)
if self.params.get('noprogress'):
return
if eta is not None:
eta_str = self.format_eta(eta)
else:
eta_str = 'Unknown ETA'
if percent is not None:
percent_str = self.format_percent(percent)
else:
percent_str = 'Unknown %'
speed_str = self.format_speed(speed)
msg = ('%s of %s at %s ETA %s' %
(percent_str, data_len_str, speed_str, eta_str))
self._report_progress_status(msg)
def report_progress_live_stream(self, downloaded_data_len, speed, elapsed):
if self.params.get('noprogress', False):
if s['status'] != 'downloading':
return
downloaded_str = format_bytes(downloaded_data_len)
speed_str = self.format_speed(speed)
elapsed_str = FileDownloader.format_seconds(elapsed)
msg = '%s at %s (%s)' % (downloaded_str, speed_str, elapsed_str)
self._report_progress_status(msg)
def report_finish(self, data_len_str, tot_time):
"""Report download finished."""
if self.params.get('noprogress', False):
self.to_screen('[download] Download completed')
if s.get('eta') is not None:
s['_eta_str'] = self.format_eta(s['eta'])
else:
self._report_progress_status(
('100%% of %s in %s' %
(data_len_str, self.format_seconds(tot_time))),
is_last_line=True)
s['_eta_str'] = 'Unknown ETA'
if s.get('total_bytes') and s.get('downloaded_bytes') is not None:
s['_percent_str'] = self.format_percent(100 * s['downloaded_bytes'] / s['total_bytes'])
elif s.get('total_bytes_estimate') and s.get('downloaded_bytes') is not None:
s['_percent_str'] = self.format_percent(100 * s['downloaded_bytes'] / s['total_bytes_estimate'])
else:
if s.get('downloaded_bytes') == 0:
s['_percent_str'] = self.format_percent(0)
else:
s['_percent_str'] = 'Unknown %'
if s.get('speed') is not None:
s['_speed_str'] = self.format_speed(s['speed'])
else:
s['_speed_str'] = 'Unknown speed'
if s.get('total_bytes') is not None:
s['_total_bytes_str'] = format_bytes(s['total_bytes'])
msg_template = '%(_percent_str)s of %(_total_bytes_str)s at %(_speed_str)s ETA %(_eta_str)s'
elif s.get('total_bytes_estimate') is not None:
s['_total_bytes_estimate_str'] = format_bytes(s['total_bytes_estimate'])
msg_template = '%(_percent_str)s of ~%(_total_bytes_estimate_str)s at %(_speed_str)s ETA %(_eta_str)s'
else:
if s.get('downloaded_bytes') is not None:
s['_downloaded_bytes_str'] = format_bytes(s['downloaded_bytes'])
if s.get('elapsed'):
s['_elapsed_str'] = self.format_seconds(s['elapsed'])
msg_template = '%(_downloaded_bytes_str)s at %(_speed_str)s (%(_elapsed_str)s)'
else:
msg_template = '%(_downloaded_bytes_str)s at %(_speed_str)s'
else:
msg_template = '%(_percent_str)s % at %(_speed_str)s ETA %(_eta_str)s'
self._report_progress_status(msg_template % s)
def report_resuming_byte(self, resume_len):
"""Report attempt to resume at given byte."""
@ -267,7 +302,9 @@ class FileDownloader(object):
def report_retry(self, count, retries):
"""Report retry in case of HTTP error 5xx"""
self.to_screen('[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
self.to_screen(
'[download] Got server HTTP error. Retrying (attempt %d of %s)...'
% (count, self.format_retries(retries)))
def report_file_already_downloaded(self, file_name):
"""Report file has already been fully downloaded."""
@ -284,19 +321,20 @@ class FileDownloader(object):
"""Download to a filename using the info from info_dict
Return True on success and False otherwise
"""
nooverwrites_and_exists = (
self.params.get('nooverwrites', False)
and os.path.exists(encodeFilename(filename))
self.params.get('nooverwrites', False) and
os.path.exists(encodeFilename(filename))
)
continuedl_and_exists = (
self.params.get('continuedl', False)
and os.path.isfile(encodeFilename(filename))
and not self.params.get('nopart', False)
self.params.get('continuedl', True) and
os.path.isfile(encodeFilename(filename)) and
not self.params.get('nopart', False)
)
# Check file already present
if filename != '-' and nooverwrites_and_exists or continuedl_and_exists:
if filename != '-' and (nooverwrites_and_exists or continuedl_and_exists):
self.report_file_already_downloaded(filename)
self._hook_progress({
'filename': filename,
@ -305,6 +343,14 @@ class FileDownloader(object):
})
return True
min_sleep_interval = self.params.get('sleep_interval')
if min_sleep_interval:
max_sleep_interval = self.params.get('max_sleep_interval', min_sleep_interval)
print(min_sleep_interval, max_sleep_interval)
sleep_interval = random.uniform(min_sleep_interval, max_sleep_interval)
self.to_screen('[download] Sleeping %s seconds...' % sleep_interval)
time.sleep(sleep_interval)
return self.real_download(filename, info_dict)
def real_download(self, filename, info_dict):
@ -319,3 +365,20 @@ class FileDownloader(object):
# See YoutubeDl.py (search for progress_hooks) for a description of
# this interface
self._progress_hooks.append(ph)
def _debug_cmd(self, args, exe=None):
if not self.params.get('verbose', False):
return
str_args = [decodeArgument(a) for a in args]
if exe is None:
exe = os.path.basename(str_args[0])
try:
import pipes
shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))
except ImportError:
shell_quote = repr
self.to_screen('[debug] %s command line: %s' % (
exe, shell_quote(str_args)))

81
youtube_dl/downloader/dash.py Normal file
View File

@ -0,0 +1,81 @@
from __future__ import unicode_literals
import os
from .fragment import FragmentFD
from ..compat import compat_urllib_error
from ..utils import (
sanitize_open,
encodeFilename,
)
class DashSegmentsFD(FragmentFD):
"""
Download segments in a DASH manifest
"""
FD_NAME = 'dashsegments'
def real_download(self, filename, info_dict):
segments = info_dict['fragments'][:1] if self.params.get(
'test', False) else info_dict['fragments']
ctx = {
'filename': filename,
'total_frags': len(segments),
}
self._prepare_and_start_frag_download(ctx)
segments_filenames = []
fragment_retries = self.params.get('fragment_retries', 0)
skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
def process_segment(segment, tmp_filename, num):
segment_url = segment['url']
segment_name = 'Frag%d' % num
target_filename = '%s-%s' % (tmp_filename, segment_name)
# In DASH, the first segment contains necessary headers to
# generate a valid MP4 file, so always abort for the first segment
fatal = num == 0 or not skip_unavailable_fragments
count = 0
while count <= fragment_retries:
try:
success = ctx['dl'].download(target_filename, {'url': segment_url})
if not success:
return False
down, target_sanitized = sanitize_open(target_filename, 'rb')
ctx['dest_stream'].write(down.read())
down.close()
segments_filenames.append(target_sanitized)
break
except compat_urllib_error.HTTPError as err:
# YouTube may often return 404 HTTP error for a fragment causing the
# whole download to fail. However if the same fragment is immediately
# retried with the same request data this usually succeeds (1-2 attemps
# is usually enough) thus allowing to download the whole file successfully.
# To be future-proof we will retry all fragments that fail with any
# HTTP error.
count += 1
if count <= fragment_retries:
self.report_retry_fragment(err, segment_name, count, fragment_retries)
if count > fragment_retries:
if not fatal:
self.report_skip_fragment(segment_name)
return True
self.report_error('giving up after %s fragment retries' % fragment_retries)
return False
return True
for i, segment in enumerate(segments):
if not process_segment(segment, ctx['tmpfilename'], i):
return False
self._finish_frag_download(ctx)
for segment_file in segments_filenames:
os.remove(encodeFilename(segment_file))
return True

312
youtube_dl/downloader/external.py Normal file
View File

@ -0,0 +1,312 @@
from __future__ import unicode_literals
import os.path
import subprocess
import sys
import re
from .common import FileDownloader
from ..compat import compat_setenv
from ..postprocessor.ffmpeg import FFmpegPostProcessor, EXT_TO_OUT_FORMATS
from ..utils import (
cli_option,
cli_valueless_option,
cli_bool_option,
cli_configuration_args,
encodeFilename,
encodeArgument,
handle_youtubedl_headers,
check_executable,
)
class ExternalFD(FileDownloader):
def real_download(self, filename, info_dict):
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
retval = self._call_downloader(tmpfilename, info_dict)
if retval == 0:
fsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('\r[%s] Downloaded %s bytes' % (self.get_basename(), fsize))
self.try_rename(tmpfilename, filename)
self._hook_progress({
'downloaded_bytes': fsize,
'total_bytes': fsize,
'filename': filename,
'status': 'finished',
})
return True
else:
self.to_stderr('\n')
self.report_error('%s exited with code %d' % (
self.get_basename(), retval))
return False
@classmethod
def get_basename(cls):
return cls.__name__[:-2].lower()
@property
def exe(self):
return self.params.get('external_downloader')
@classmethod
def available(cls):
return check_executable(cls.get_basename(), [cls.AVAILABLE_OPT])
@classmethod
def supports(cls, info_dict):
return info_dict['protocol'] in ('http', 'https', 'ftp', 'ftps')
@classmethod
def can_download(cls, info_dict):
return cls.available() and cls.supports(info_dict)
def _option(self, command_option, param):
return cli_option(self.params, command_option, param)
def _bool_option(self, command_option, param, true_value='true', false_value='false', separator=None):
return cli_bool_option(self.params, command_option, param, true_value, false_value, separator)
def _valueless_option(self, command_option, param, expected_value=True):
return cli_valueless_option(self.params, command_option, param, expected_value)
def _configuration_args(self, default=[]):
return cli_configuration_args(self.params, 'external_downloader_args', default)
def _call_downloader(self, tmpfilename, info_dict):
""" Either overwrite this or implement _make_cmd """
cmd = [encodeArgument(a) for a in self._make_cmd(tmpfilename, info_dict)]
self._debug_cmd(cmd)
p = subprocess.Popen(
cmd, stderr=subprocess.PIPE)
_, stderr = p.communicate()
if p.returncode != 0:
self.to_stderr(stderr.decode('utf-8', 'replace'))
return p.returncode
class CurlFD(ExternalFD):
AVAILABLE_OPT = '-V'
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '--location', '-o', tmpfilename]
for key, val in info_dict['http_headers'].items():
cmd += ['--header', '%s: %s' % (key, val)]
cmd += self._bool_option('--continue-at', 'continuedl', '-', '0')
cmd += self._valueless_option('--silent', 'noprogress')
cmd += self._valueless_option('--verbose', 'verbose')
cmd += self._option('--limit-rate', 'ratelimit')
cmd += self._option('--retry', 'retries')
cmd += self._option('--max-filesize', 'max_filesize')
cmd += self._option('--interface', 'source_address')
cmd += self._option('--proxy', 'proxy')
cmd += self._valueless_option('--insecure', 'nocheckcertificate')
cmd += self._configuration_args()
cmd += ['--', info_dict['url']]
return cmd
def _call_downloader(self, tmpfilename, info_dict):
cmd = [encodeArgument(a) for a in self._make_cmd(tmpfilename, info_dict)]
self._debug_cmd(cmd)
# curl writes the progress to stderr so don't capture it.
p = subprocess.Popen(cmd)
p.communicate()
return p.returncode
class AxelFD(ExternalFD):
AVAILABLE_OPT = '-V'
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '-o', tmpfilename]
for key, val in info_dict['http_headers'].items():
cmd += ['-H', '%s: %s' % (key, val)]
cmd += self._configuration_args()
cmd += ['--', info_dict['url']]
return cmd
class WgetFD(ExternalFD):
AVAILABLE_OPT = '--version'
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '-O', tmpfilename, '-nv', '--no-cookies']
for key, val in info_dict['http_headers'].items():
cmd += ['--header', '%s: %s' % (key, val)]
cmd += self._option('--bind-address', 'source_address')
cmd += self._option('--proxy', 'proxy')
cmd += self._valueless_option('--no-check-certificate', 'nocheckcertificate')
cmd += self._configuration_args()
cmd += ['--', info_dict['url']]
return cmd
class Aria2cFD(ExternalFD):
AVAILABLE_OPT = '-v'
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '-c']
cmd += self._configuration_args([
'--min-split-size', '1M', '--max-connection-per-server', '4'])
dn = os.path.dirname(tmpfilename)
if dn:
cmd += ['--dir', dn]
cmd += ['--out', os.path.basename(tmpfilename)]
for key, val in info_dict['http_headers'].items():
cmd += ['--header', '%s: %s' % (key, val)]
cmd += self._option('--interface', 'source_address')
cmd += self._option('--all-proxy', 'proxy')
cmd += self._bool_option('--check-certificate', 'nocheckcertificate', 'false', 'true', '=')
cmd += ['--', info_dict['url']]
return cmd
class HttpieFD(ExternalFD):
@classmethod
def available(cls):
return check_executable('http', ['--version'])
def _make_cmd(self, tmpfilename, info_dict):
cmd = ['http', '--download', '--output', tmpfilename, info_dict['url']]
for key, val in info_dict['http_headers'].items():
cmd += ['%s:%s' % (key, val)]
return cmd
class FFmpegFD(ExternalFD):
@classmethod
def supports(cls, info_dict):
return info_dict['protocol'] in ('http', 'https', 'ftp', 'ftps', 'm3u8', 'rtsp', 'rtmp', 'mms')
@classmethod
def available(cls):
return FFmpegPostProcessor().available
def _call_downloader(self, tmpfilename, info_dict):
url = info_dict['url']
ffpp = FFmpegPostProcessor(downloader=self)
if not ffpp.available:
self.report_error('m3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
return False
ffpp.check_version()
args = [ffpp.executable, '-y']
args += self._configuration_args()
# start_time = info_dict.get('start_time') or 0
# if start_time:
# args += ['-ss', compat_str(start_time)]
# end_time = info_dict.get('end_time')
# if end_time:
# args += ['-t', compat_str(end_time - start_time)]
if info_dict['http_headers'] and re.match(r'^https?://', url):
# Trailing \r\n after each HTTP header is important to prevent warning from ffmpeg/avconv:
# [http @ 00000000003d2fa0] No trailing CRLF found in HTTP header.
headers = handle_youtubedl_headers(info_dict['http_headers'])
args += [
'-headers',
''.join('%s: %s\r\n' % (key, val) for key, val in headers.items())]
env = None
proxy = self.params.get('proxy')
if proxy:
if not re.match(r'^[\da-zA-Z]+://', proxy):
proxy = 'http://%s' % proxy
if proxy.startswith('socks'):
self.report_warning(
'%s does not support SOCKS proxies. Downloading is likely to fail. '
'Consider adding --hls-prefer-native to your command.' % self.get_basename())
# Since December 2015 ffmpeg supports -http_proxy option (see
# http://git.videolan.org/?p=ffmpeg.git;a=commit;h=b4eb1f29ebddd60c41a2eb39f5af701e38e0d3fd)
# We could switch to the following code if we are able to detect version properly
# args += ['-http_proxy', proxy]
env = os.environ.copy()
compat_setenv('HTTP_PROXY', proxy, env=env)
compat_setenv('http_proxy', proxy, env=env)
protocol = info_dict.get('protocol')
if protocol == 'rtmp':
player_url = info_dict.get('player_url')
page_url = info_dict.get('page_url')
app = info_dict.get('app')
play_path = info_dict.get('play_path')
tc_url = info_dict.get('tc_url')
flash_version = info_dict.get('flash_version')
live = info_dict.get('rtmp_live', False)
if player_url is not None:
args += ['-rtmp_swfverify', player_url]
if page_url is not None:
args += ['-rtmp_pageurl', page_url]
if app is not None:
args += ['-rtmp_app', app]
if play_path is not None:
args += ['-rtmp_playpath', play_path]
if tc_url is not None:
args += ['-rtmp_tcurl', tc_url]
if flash_version is not None:
args += ['-rtmp_flashver', flash_version]
if live:
args += ['-rtmp_live', 'live']
args += ['-i', url, '-c', 'copy']
if protocol in ('m3u8', 'm3u8_native'):
if self.params.get('hls_use_mpegts', False) or tmpfilename == '-':
args += ['-f', 'mpegts']
else:
args += ['-f', 'mp4', '-bsf:a', 'aac_adtstoasc']
elif protocol == 'rtmp':
args += ['-f', 'flv']
else:
args += ['-f', EXT_TO_OUT_FORMATS.get(info_dict['ext'], info_dict['ext'])]
args = [encodeArgument(opt) for opt in args]
args.append(encodeFilename(ffpp._ffmpeg_filename_argument(tmpfilename), True))
self._debug_cmd(args)
proc = subprocess.Popen(args, stdin=subprocess.PIPE, env=env)
try:
retval = proc.wait()
except KeyboardInterrupt:
# subprocces.run would send the SIGKILL signal to ffmpeg and the
# mp4 file couldn't be played, but if we ask ffmpeg to quit it
# produces a file that is playable (this is mostly useful for live
# streams). Note that Windows is not affected and produces playable
# files (see https://github.com/rg3/youtube-dl/issues/8300).
if sys.platform != 'win32':
proc.communicate(b'q')
raise
return retval
class AVconvFD(FFmpegFD):
pass
_BY_NAME = dict(
(klass.get_basename(), klass)
for name, klass in globals().items()
if name.endswith('FD') and name != 'ExternalFD'
)
def list_external_downloaders():
return sorted(_BY_NAME.keys())
def get_external_downloader(external_downloader):
""" Given the name of the executable, see whether we support the given
downloader . """
# Drop .exe extension on Windows
bn = os.path.splitext(os.path.basename(external_downloader))[0]
return _BY_NAME[bn]

300
youtube_dl/downloader/f4m.py
View File

@ -1,47 +1,60 @@
from __future__ import unicode_literals
from __future__ import division, unicode_literals
import base64
import io
import itertools
import os
import time
import xml.etree.ElementTree as etree
from .common import FileDownloader
from .http import HttpFD
from .fragment import FragmentFD
from ..compat import (
compat_etree_fromstring,
compat_urlparse,
compat_urllib_error,
compat_urllib_parse_urlparse,
compat_struct_pack,
compat_struct_unpack,
)
from ..utils import (
struct_pack,
struct_unpack,
format_bytes,
encodeFilename,
fix_xml_ampersands,
sanitize_open,
xpath_text,
)
class DataTruncatedError(Exception):
pass
class FlvReader(io.BytesIO):
"""
Reader for Flv files
The file format is documented in https://www.adobe.com/devnet/f4v.html
"""
def read_bytes(self, n):
data = self.read(n)
if len(data) < n:
raise DataTruncatedError(
'FlvReader error: need %d bytes while only %d bytes got' % (
n, len(data)))
return data
# Utility functions for reading numbers and strings
def read_unsigned_long_long(self):
return struct_unpack('!Q', self.read(8))[0]
return compat_struct_unpack('!Q', self.read_bytes(8))[0]
def read_unsigned_int(self):
return struct_unpack('!I', self.read(4))[0]
return compat_struct_unpack('!I', self.read_bytes(4))[0]
def read_unsigned_char(self):
return struct_unpack('!B', self.read(1))[0]
return compat_struct_unpack('!B', self.read_bytes(1))[0]
def read_string(self):
res = b''
while True:
char = self.read(1)
char = self.read_bytes(1)
if char == b'\x00':
break
res += char
@ -52,18 +65,18 @@ class FlvReader(io.BytesIO):
Read a box and return the info as a tuple: (box_size, box_type, box_data)
"""
real_size = size = self.read_unsigned_int()
box_type = self.read(4)
box_type = self.read_bytes(4)
header_end = 8
if size == 1:
real_size = self.read_unsigned_long_long()
header_end = 16
return real_size, box_type, self.read(real_size - header_end)
return real_size, box_type, self.read_bytes(real_size - header_end)
def read_asrt(self):
# version
self.read_unsigned_char()
# flags
self.read(3)
self.read_bytes(3)
quality_entry_count = self.read_unsigned_char()
# QualityEntryCount
for i in range(quality_entry_count):
@ -84,7 +97,7 @@ class FlvReader(io.BytesIO):
# version
self.read_unsigned_char()
# flags
self.read(3)
self.read_bytes(3)
# time scale
self.read_unsigned_int()
@ -118,11 +131,12 @@ class FlvReader(io.BytesIO):
# version
self.read_unsigned_char()
# flags
self.read(3)
self.read_bytes(3)
self.read_unsigned_int() # BootstrapinfoVersion
# Profile,Live,Update,Reserved
self.read(1)
flags = self.read_unsigned_char()
live = flags & 0x20 != 0
# time scale
self.read_unsigned_int()
# CurrentMediaTime
@ -161,6 +175,7 @@ class FlvReader(io.BytesIO):
return {
'segments': segments,
'fragments': fragments,
'live': live,
}
def read_bootstrap_info(self):
@ -177,22 +192,30 @@ def build_fragments_list(boot_info):
""" Return a list of (segment, fragment) for each fragment in the video """
res = []
segment_run_table = boot_info['segments'][0]
# I've only found videos with one segment
segment_run_entry = segment_run_table['segment_run'][0]
n_frags = segment_run_entry[1]
fragment_run_entry_table = boot_info['fragments'][0]['fragments']
first_frag_number = fragment_run_entry_table[0]['first']
for (i, frag_number) in zip(range(1, n_frags + 1), itertools.count(first_frag_number)):
res.append((1, frag_number))
fragments_counter = itertools.count(first_frag_number)
for segment, fragments_count in segment_run_table['segment_run']:
# In some live HDS streams (for example Rai), `fragments_count` is
# abnormal and causing out-of-memory errors. It's OK to change the
# number of fragments for live streams as they are updated periodically
if fragments_count == 4294967295 and boot_info['live']:
fragments_count = 2
for _ in range(fragments_count):
res.append((segment, next(fragments_counter)))
if boot_info['live']:
res = res[-2:]
return res
def write_unsigned_int(stream, val):
stream.write(struct_pack('!I', val))
stream.write(compat_struct_pack('!I', val))
def write_unsigned_int_24(stream, val):
stream.write(struct_pack('!I', val)[1:])
stream.write(compat_struct_pack('!I', val)[1:])
def write_flv_header(stream):
@ -217,40 +240,91 @@ def write_metadata_tag(stream, metadata):
write_unsigned_int(stream, FLV_TAG_HEADER_LEN + len(metadata))
def remove_encrypted_media(media):
return list(filter(lambda e: 'drmAdditionalHeaderId' not in e.attrib and
'drmAdditionalHeaderSetId' not in e.attrib,
media))
def _add_ns(prop):
return '{http://ns.adobe.com/f4m/1.0}%s' % prop
class HttpQuietDownloader(HttpFD):
def to_screen(self, *args, **kargs):
pass
class F4mFD(FileDownloader):
class F4mFD(FragmentFD):
"""
A downloader for f4m manifests or AdobeHDS.
"""
FD_NAME = 'f4m'
def _get_unencrypted_media(self, doc):
media = doc.findall(_add_ns('media'))
if not media:
self.report_error('No media found')
for e in (doc.findall(_add_ns('drmAdditionalHeader')) +
doc.findall(_add_ns('drmAdditionalHeaderSet'))):
# If id attribute is missing it's valid for all media nodes
# without drmAdditionalHeaderId or drmAdditionalHeaderSetId attribute
if 'id' not in e.attrib:
self.report_error('Missing ID in f4m DRM')
media = remove_encrypted_media(media)
if not media:
self.report_error('Unsupported DRM')
return media
def _get_bootstrap_from_url(self, bootstrap_url):
bootstrap = self.ydl.urlopen(bootstrap_url).read()
return read_bootstrap_info(bootstrap)
def _update_live_fragments(self, bootstrap_url, latest_fragment):
fragments_list = []
retries = 30
while (not fragments_list) and (retries > 0):
boot_info = self._get_bootstrap_from_url(bootstrap_url)
fragments_list = build_fragments_list(boot_info)
fragments_list = [f for f in fragments_list if f[1] > latest_fragment]
if not fragments_list:
# Retry after a while
time.sleep(5.0)
retries -= 1
if not fragments_list:
self.report_error('Failed to update fragments')
return fragments_list
def _parse_bootstrap_node(self, node, base_url):
# Sometimes non empty inline bootstrap info can be specified along
# with bootstrap url attribute (e.g. dummy inline bootstrap info
# contains whitespace characters in [1]). We will prefer bootstrap
# url over inline bootstrap info when present.
# 1. http://live-1-1.rutube.ru/stream/1024/HDS/SD/C2NKsS85HQNckgn5HdEmOQ/1454167650/S-s604419906/move/four/dirs/upper/1024-576p.f4m
bootstrap_url = node.get('url')
if bootstrap_url:
bootstrap_url = compat_urlparse.urljoin(
base_url, bootstrap_url)
boot_info = self._get_bootstrap_from_url(bootstrap_url)
else:
bootstrap_url = None
bootstrap = base64.b64decode(node.text.encode('ascii'))
boot_info = read_bootstrap_info(bootstrap)
return boot_info, bootstrap_url
def real_download(self, filename, info_dict):
man_url = info_dict['url']
requested_bitrate = info_dict.get('tbr')
self.to_screen('[download] Downloading f4m manifest')
manifest = self.ydl.urlopen(man_url).read()
self.report_destination(filename)
http_dl = HttpQuietDownloader(
self.ydl,
{
'continuedl': True,
'quiet': True,
'noprogress': True,
'ratelimit': self.params.get('ratelimit', None),
'test': self.params.get('test', False),
}
)
self.to_screen('[%s] Downloading f4m manifest' % self.FD_NAME)
urlh = self.ydl.urlopen(man_url)
man_url = urlh.geturl()
# Some manifests may be malformed, e.g. prosiebensat1 generated manifests
# (see https://github.com/rg3/youtube-dl/issues/6215#issuecomment-121704244
# and https://github.com/rg3/youtube-dl/issues/7823)
manifest = fix_xml_ampersands(urlh.read().decode('utf-8', 'ignore')).strip()
doc = etree.fromstring(manifest)
formats = [(int(f.attrib.get('bitrate', -1)), f) for f in doc.findall(_add_ns('media'))]
if requested_bitrate is None:
doc = compat_etree_fromstring(manifest)
formats = [(int(f.attrib.get('bitrate', -1)), f)
for f in self._get_unencrypted_media(doc)]
if requested_bitrate is None or len(formats) == 1:
# get the best format
formats = sorted(formats, key=lambda f: f[0])
rate, media = formats[-1]
@ -260,95 +334,105 @@ class F4mFD(FileDownloader):
base_url = compat_urlparse.urljoin(man_url, media.attrib['url'])
bootstrap_node = doc.find(_add_ns('bootstrapInfo'))
if bootstrap_node.text is None:
bootstrap_url = compat_urlparse.urljoin(
base_url, bootstrap_node.attrib['url'])
bootstrap = self.ydl.urlopen(bootstrap_url).read()
else:
bootstrap = base64.b64decode(bootstrap_node.text)
# From Adobe F4M 3.0 spec:
# The <baseURL> element SHALL be the base URL for all relative
# (HTTP-based) URLs in the manifest. If <baseURL> is not present, said
# URLs should be relative to the location of the containing document.
boot_info, bootstrap_url = self._parse_bootstrap_node(bootstrap_node, man_url)
live = boot_info['live']
metadata_node = media.find(_add_ns('metadata'))
if metadata_node is not None:
metadata = base64.b64decode(metadata_node.text)
metadata = base64.b64decode(metadata_node.text.encode('ascii'))
else:
metadata = None
boot_info = read_bootstrap_info(bootstrap)
fragments_list = build_fragments_list(boot_info)
if self.params.get('test', False):
test = self.params.get('test', False)
if test:
# We only download the first fragment
fragments_list = fragments_list[:1]
total_frags = len(fragments_list)
# For some akamai manifests we'll need to add a query to the fragment url
akamai_pv = xpath_text(doc, _add_ns('pv-2.0'))
tmpfilename = self.temp_name(filename)
(dest_stream, tmpfilename) = sanitize_open(tmpfilename, 'wb')
write_flv_header(dest_stream)
write_metadata_tag(dest_stream, metadata)
# This dict stores the download progress, it's updated by the progress
# hook
state = {
'downloaded_bytes': 0,
'frag_counter': 0,
ctx = {
'filename': filename,
'total_frags': total_frags,
'live': live,
}
start = time.time()
def frag_progress_hook(status):
frag_total_bytes = status.get('total_bytes', 0)
estimated_size = (state['downloaded_bytes'] +
(total_frags - state['frag_counter']) * frag_total_bytes)
if status['status'] == 'finished':
state['downloaded_bytes'] += frag_total_bytes
state['frag_counter'] += 1
progress = self.calc_percent(state['frag_counter'], total_frags)
byte_counter = state['downloaded_bytes']
else:
frag_downloaded_bytes = status['downloaded_bytes']
byte_counter = state['downloaded_bytes'] + frag_downloaded_bytes
frag_progress = self.calc_percent(frag_downloaded_bytes,
frag_total_bytes)
progress = self.calc_percent(state['frag_counter'], total_frags)
progress += frag_progress / float(total_frags)
self._prepare_frag_download(ctx)
eta = self.calc_eta(start, time.time(), estimated_size, byte_counter)
self.report_progress(progress, format_bytes(estimated_size),
status.get('speed'), eta)
http_dl.add_progress_hook(frag_progress_hook)
dest_stream = ctx['dest_stream']
write_flv_header(dest_stream)
if not live:
write_metadata_tag(dest_stream, metadata)
base_url_parsed = compat_urllib_parse_urlparse(base_url)
self._start_frag_download(ctx)
frags_filenames = []
for (seg_i, frag_i) in fragments_list:
while fragments_list:
seg_i, frag_i = fragments_list.pop(0)
name = 'Seg%d-Frag%d' % (seg_i, frag_i)
url = base_url + name
query = []
if base_url_parsed.query:
query.append(base_url_parsed.query)
if akamai_pv:
url += '?' + akamai_pv.strip(';')
frag_filename = '%s-%s' % (tmpfilename, name)
success = http_dl.download(frag_filename, {'url': url})
if not success:
return False
with open(frag_filename, 'rb') as down:
query.append(akamai_pv.strip(';'))
if info_dict.get('extra_param_to_segment_url'):
query.append(info_dict['extra_param_to_segment_url'])
url_parsed = base_url_parsed._replace(path=base_url_parsed.path + name, query='&'.join(query))
frag_filename = '%s-%s' % (ctx['tmpfilename'], name)
try:
success = ctx['dl'].download(frag_filename, {'url': url_parsed.geturl()})
if not success:
return False
(down, frag_sanitized) = sanitize_open(frag_filename, 'rb')
down_data = down.read()
down.close()
reader = FlvReader(down_data)
while True:
_, box_type, box_data = reader.read_box_info()
try:
_, box_type, box_data = reader.read_box_info()
except DataTruncatedError:
if test:
# In tests, segments may be truncated, and thus
# FlvReader may not be able to parse the whole
# chunk. If so, write the segment as is
# See https://github.com/rg3/youtube-dl/issues/9214
dest_stream.write(down_data)
break
raise
if box_type == b'mdat':
dest_stream.write(box_data)
break
frags_filenames.append(frag_filename)
if live:
os.remove(encodeFilename(frag_sanitized))
else:
frags_filenames.append(frag_sanitized)
except (compat_urllib_error.HTTPError, ) as err:
if live and (err.code == 404 or err.code == 410):
# We didn't keep up with the live window. Continue
# with the next available fragment.
msg = 'Fragment %d unavailable' % frag_i
self.report_warning(msg)
fragments_list = []
else:
raise
dest_stream.close()
self.report_finish(format_bytes(state['downloaded_bytes']), time.time() - start)
if not fragments_list and not test and live and bootstrap_url:
fragments_list = self._update_live_fragments(bootstrap_url, frag_i)
total_frags += len(fragments_list)
if fragments_list and (fragments_list[0][1] > frag_i + 1):
msg = 'Missed %d fragments' % (fragments_list[0][1] - (frag_i + 1))
self.report_warning(msg)
self._finish_frag_download(ctx)
self.try_rename(tmpfilename, filename)
for frag_file in frags_filenames:
os.remove(frag_file)
fsize = os.path.getsize(encodeFilename(filename))
self._hook_progress({
'downloaded_bytes': fsize,
'total_bytes': fsize,
'filename': filename,
'status': 'finished',
})
os.remove(encodeFilename(frag_file))
return True

139
youtube_dl/downloader/fragment.py Normal file
View File

@ -0,0 +1,139 @@
from __future__ import division, unicode_literals
import os
import time
from .common import FileDownloader
from .http import HttpFD
from ..utils import (
error_to_compat_str,
encodeFilename,
sanitize_open,
)
class HttpQuietDownloader(HttpFD):
def to_screen(self, *args, **kargs):
pass
class FragmentFD(FileDownloader):
"""
A base file downloader class for fragmented media (e.g. f4m/m3u8 manifests).
Available options:
fragment_retries: Number of times to retry a fragment for HTTP error (DASH
and hlsnative only)
skip_unavailable_fragments:
Skip unavailable fragments (DASH and hlsnative only)
"""
def report_retry_fragment(self, err, fragment_name, count, retries):
self.to_screen(
'[download] Got server HTTP error: %s. Retrying fragment %s (attempt %d of %s)...'
% (error_to_compat_str(err), fragment_name, count, self.format_retries(retries)))
def report_skip_fragment(self, fragment_name):
self.to_screen('[download] Skipping fragment %s...' % fragment_name)
def _prepare_and_start_frag_download(self, ctx):
self._prepare_frag_download(ctx)
self._start_frag_download(ctx)
def _prepare_frag_download(self, ctx):
if 'live' not in ctx:
ctx['live'] = False
self.to_screen(
'[%s] Total fragments: %s'
% (self.FD_NAME, ctx['total_frags'] if not ctx['live'] else 'unknown (live)'))
self.report_destination(ctx['filename'])
dl = HttpQuietDownloader(
self.ydl,
{
'continuedl': True,
'quiet': True,
'noprogress': True,
'ratelimit': self.params.get('ratelimit'),
'retries': self.params.get('retries', 0),
'test': self.params.get('test', False),
}
)
tmpfilename = self.temp_name(ctx['filename'])
dest_stream, tmpfilename = sanitize_open(tmpfilename, 'wb')
ctx.update({
'dl': dl,
'dest_stream': dest_stream,
'tmpfilename': tmpfilename,
})
def _start_frag_download(self, ctx):
total_frags = ctx['total_frags']
# This dict stores the download progress, it's updated by the progress
# hook
state = {
'status': 'downloading',
'downloaded_bytes': 0,
'frag_index': 0,
'frag_count': total_frags,
'filename': ctx['filename'],
'tmpfilename': ctx['tmpfilename'],
}
start = time.time()
ctx.update({
'started': start,
# Total complete fragments downloaded so far in bytes
'complete_frags_downloaded_bytes': 0,
# Amount of fragment's bytes downloaded by the time of the previous
# frag progress hook invocation
'prev_frag_downloaded_bytes': 0,
})
def frag_progress_hook(s):
if s['status'] not in ('downloading', 'finished'):
return
time_now = time.time()
state['elapsed'] = time_now - start
frag_total_bytes = s.get('total_bytes') or 0
if not ctx['live']:
estimated_size = (
(ctx['complete_frags_downloaded_bytes'] + frag_total_bytes) /
(state['frag_index'] + 1) * total_frags)
state['total_bytes_estimate'] = estimated_size
if s['status'] == 'finished':
state['frag_index'] += 1
state['downloaded_bytes'] += frag_total_bytes - ctx['prev_frag_downloaded_bytes']
ctx['complete_frags_downloaded_bytes'] = state['downloaded_bytes']
ctx['prev_frag_downloaded_bytes'] = 0
else:
frag_downloaded_bytes = s['downloaded_bytes']
state['downloaded_bytes'] += frag_downloaded_bytes - ctx['prev_frag_downloaded_bytes']
if not ctx['live']:
state['eta'] = self.calc_eta(
start, time_now, estimated_size,
state['downloaded_bytes'])
state['speed'] = s.get('speed') or ctx.get('speed')
ctx['speed'] = state['speed']
ctx['prev_frag_downloaded_bytes'] = frag_downloaded_bytes
self._hook_progress(state)
ctx['dl'].add_progress_hook(frag_progress_hook)
return start
def _finish_frag_download(self, ctx):
ctx['dest_stream'].close()
elapsed = time.time() - ctx['started']
self.try_rename(ctx['tmpfilename'], ctx['filename'])
fsize = os.path.getsize(encodeFilename(ctx['filename']))
self._hook_progress({
'downloaded_bytes': fsize,
'total_bytes': fsize,
'filename': ctx['filename'],
'status': 'finished',
'elapsed': elapsed,
})

222
youtube_dl/downloader/hls.py
View File

@ -1,105 +1,169 @@
from __future__ import unicode_literals
import os
import os.path
import re
import subprocess
import binascii
try:
from Crypto.Cipher import AES
can_decrypt_frag = True
except ImportError:
can_decrypt_frag = False
from .fragment import FragmentFD
from .external import FFmpegFD
from ..postprocessor.ffmpeg import FFmpegPostProcessor
from .common import FileDownloader
from ..compat import (
compat_urllib_error,
compat_urlparse,
compat_urllib_request,
compat_struct_pack,
)
from ..utils import (
encodeFilename,
sanitize_open,
parse_m3u8_attributes,
update_url_query,
)
class HlsFD(FileDownloader):
def real_download(self, filename, info_dict):
url = info_dict['url']
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
class HlsFD(FragmentFD):
""" A limited implementation that does not require ffmpeg """
args = [
'-y', '-i', url, '-f', 'mp4', '-c', 'copy',
'-bsf:a', 'aac_adtstoasc',
encodeFilename(tmpfilename, for_subprocess=True)]
FD_NAME = 'hlsnative'
ffpp = FFmpegPostProcessor(downloader=self)
program = ffpp._executable
if program is None:
self.report_error('m3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
return False
ffpp.check_version()
cmd = [program] + args
@staticmethod
def can_download(manifest, info_dict):
UNSUPPORTED_FEATURES = (
r'#EXT-X-KEY:METHOD=(?!NONE|AES-128)', # encrypted streams [1]
r'#EXT-X-BYTERANGE', # playlists composed of byte ranges of media files [2]
retval = subprocess.call(cmd)
if retval == 0:
fsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('\r[%s] %s bytes' % (cmd[0], fsize))
self.try_rename(tmpfilename, filename)
self._hook_progress({
'downloaded_bytes': fsize,
'total_bytes': fsize,
'filename': filename,
'status': 'finished',
})
return True
else:
self.to_stderr('\n')
self.report_error('%s exited with code %d' % (program, retval))
return False
# Live streams heuristic does not always work (e.g. geo restricted to Germany
# http://hls-geo.daserste.de/i/videoportal/Film/c_620000/622873/format,716451,716457,716450,716458,716459,.mp4.csmil/index_4_av.m3u8?null=0)
# r'#EXT-X-MEDIA-SEQUENCE:(?!0$)', # live streams [3]
# This heuristic also is not correct since segments may not be appended as well.
# Twitch vods of finished streams have EXT-X-PLAYLIST-TYPE:EVENT despite
# no segments will definitely be appended to the end of the playlist.
# r'#EXT-X-PLAYLIST-TYPE:EVENT', # media segments may be appended to the end of
# # event media playlists [4]
class NativeHlsFD(FileDownloader):
""" A more limited implementation that does not require ffmpeg """
# 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.2.4
# 2. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.2.2
# 3. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.2
# 4. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.5
)
check_results = [not re.search(feature, manifest) for feature in UNSUPPORTED_FEATURES]
check_results.append(can_decrypt_frag or '#EXT-X-KEY:METHOD=AES-128' not in manifest)
check_results.append(not info_dict.get('is_live'))
return all(check_results)
def real_download(self, filename, info_dict):
url = info_dict['url']
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
man_url = info_dict['url']
self.to_screen('[%s] Downloading m3u8 manifest' % self.FD_NAME)
manifest = self.ydl.urlopen(man_url).read()
self.to_screen(
'[hlsnative] %s: Downloading m3u8 manifest' % info_dict['id'])
data = self.ydl.urlopen(url).read()
s = data.decode('utf-8', 'ignore')
segment_urls = []
s = manifest.decode('utf-8', 'ignore')
if not self.can_download(s, info_dict):
self.report_warning(
'hlsnative has detected features it does not support, '
'extraction will be delegated to ffmpeg')
fd = FFmpegFD(self.ydl, self.params)
for ph in self._progress_hooks:
fd.add_progress_hook(ph)
return fd.real_download(filename, info_dict)
total_frags = 0
for line in s.splitlines():
line = line.strip()
if line and not line.startswith('#'):
segment_url = (
line
if re.match(r'^https?://', line)
else compat_urlparse.urljoin(url, line))
segment_urls.append(segment_url)
total_frags += 1
is_test = self.params.get('test', False)
remaining_bytes = self._TEST_FILE_SIZE if is_test else None
byte_counter = 0
with open(tmpfilename, 'wb') as outf:
for i, segurl in enumerate(segment_urls):
self.to_screen(
'[hlsnative] %s: Downloading segment %d / %d' %
(info_dict['id'], i + 1, len(segment_urls)))
seg_req = compat_urllib_request.Request(segurl)
if remaining_bytes is not None:
seg_req.add_header('Range', 'bytes=0-%d' % (remaining_bytes - 1))
segment = self.ydl.urlopen(seg_req).read()
if remaining_bytes is not None:
segment = segment[:remaining_bytes]
remaining_bytes -= len(segment)
outf.write(segment)
byte_counter += len(segment)
if remaining_bytes is not None and remaining_bytes <= 0:
break
self._hook_progress({
'downloaded_bytes': byte_counter,
'total_bytes': byte_counter,
ctx = {
'filename': filename,
'status': 'finished',
})
self.try_rename(tmpfilename, filename)
'total_frags': total_frags,
}
self._prepare_and_start_frag_download(ctx)
fragment_retries = self.params.get('fragment_retries', 0)
skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
test = self.params.get('test', False)
extra_query = None
extra_param_to_segment_url = info_dict.get('extra_param_to_segment_url')
if extra_param_to_segment_url:
extra_query = compat_urlparse.parse_qs(extra_param_to_segment_url)
i = 0
media_sequence = 0
decrypt_info = {'METHOD': 'NONE'}
frags_filenames = []
for line in s.splitlines():
line = line.strip()
if line:
if not line.startswith('#'):
frag_url = (
line
if re.match(r'^https?://', line)
else compat_urlparse.urljoin(man_url, line))
frag_name = 'Frag%d' % i
frag_filename = '%s-%s' % (ctx['tmpfilename'], frag_name)
if extra_query:
frag_url = update_url_query(frag_url, extra_query)
count = 0
while count <= fragment_retries:
try:
success = ctx['dl'].download(frag_filename, {'url': frag_url})
if not success:
return False
down, frag_sanitized = sanitize_open(frag_filename, 'rb')
frag_content = down.read()
down.close()
break
except compat_urllib_error.HTTPError as err:
# Unavailable (possibly temporary) fragments may be served.
# First we try to retry then either skip or abort.
# See https://github.com/rg3/youtube-dl/issues/10165,
# https://github.com/rg3/youtube-dl/issues/10448).
count += 1
if count <= fragment_retries:
self.report_retry_fragment(err, frag_name, count, fragment_retries)
if count > fragment_retries:
if skip_unavailable_fragments:
i += 1
media_sequence += 1
self.report_skip_fragment(frag_name)
continue
self.report_error(
'giving up after %s fragment retries' % fragment_retries)
return False
if decrypt_info['METHOD'] == 'AES-128':
iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence)
frag_content = AES.new(
decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content)
ctx['dest_stream'].write(frag_content)
frags_filenames.append(frag_sanitized)
# We only download the first fragment during the test
if test:
break
i += 1
media_sequence += 1
elif line.startswith('#EXT-X-KEY'):
decrypt_info = parse_m3u8_attributes(line[11:])
if decrypt_info['METHOD'] == 'AES-128':
if 'IV' in decrypt_info:
decrypt_info['IV'] = binascii.unhexlify(decrypt_info['IV'][2:].zfill(32))
if not re.match(r'^https?://', decrypt_info['URI']):
decrypt_info['URI'] = compat_urlparse.urljoin(
man_url, decrypt_info['URI'])
if extra_query:
decrypt_info['URI'] = update_url_query(decrypt_info['URI'], extra_query)
decrypt_info['KEY'] = self.ydl.urlopen(decrypt_info['URI']).read()
elif line.startswith('#EXT-X-MEDIA-SEQUENCE'):
media_sequence = int(line[22:])
self._finish_frag_download(ctx)
for frag_file in frags_filenames:
os.remove(encodeFilename(frag_file))
return True

75
youtube_dl/downloader/http.py
View File

@ -1,18 +1,21 @@
from __future__ import unicode_literals
import errno
import os
import socket
import time
import re
from .common import FileDownloader
from ..compat import (
compat_urllib_request,
compat_urllib_error,
)
from ..compat import compat_urllib_error
from ..utils import (
ContentTooShortError,
encodeFilename,
sanitize_open,
format_bytes,
sanitized_Request,
write_xattr,
XAttrMetadataError,
XAttrUnavailableError,
)
@ -24,20 +27,11 @@ class HttpFD(FileDownloader):
# Do not include the Accept-Encoding header
headers = {'Youtubedl-no-compression': 'True'}
if 'user_agent' in info_dict:
headers['Youtubedl-user-agent'] = info_dict['user_agent']
if 'http_referer' in info_dict:
headers['Referer'] = info_dict['http_referer']
add_headers = info_dict.get('http_headers')
if add_headers:
headers.update(add_headers)
data = info_dict.get('http_post_data')
http_method = info_dict.get('http_method')
basic_request = compat_urllib_request.Request(url, data, headers)
request = compat_urllib_request.Request(url, data, headers)
if http_method is not None:
basic_request.get_method = lambda: http_method
request.get_method = lambda: http_method
basic_request = sanitized_Request(url, None, headers)
request = sanitized_Request(url, None, headers)
is_test = self.params.get('test', False)
@ -52,7 +46,7 @@ class HttpFD(FileDownloader):
open_mode = 'wb'
if resume_len != 0:
if self.params.get('continuedl', False):
if self.params.get('continuedl', True):
self.report_resuming_byte(resume_len)
request.add_header('Range', 'bytes=%d-' % resume_len)
open_mode = 'ab'
@ -65,6 +59,24 @@ class HttpFD(FileDownloader):
# Establish connection
try:
data = self.ydl.urlopen(request)
# When trying to resume, Content-Range HTTP header of response has to be checked
# to match the value of requested Range HTTP header. This is due to a webservers
# that don't support resuming and serve a whole file with no Content-Range
# set in response despite of requested Range (see
# https://github.com/rg3/youtube-dl/issues/6057#issuecomment-126129799)
if resume_len > 0:
content_range = data.headers.get('Content-Range')
if content_range:
content_range_m = re.search(r'bytes (\d+)-', content_range)
# Content-Range is present and matches requested Range, resume is possible
if content_range_m and resume_len == int(content_range_m.group(1)):
break
# Content-Range is either not present or invalid. Assuming remote webserver is
# trying to send the whole file, resume is not possible, so wiping the local file
# and performing entire redownload
self.report_unable_to_resume()
resume_len = 0
open_mode = 'wb'
break
except (compat_urllib_error.HTTPError, ) as err:
if (err.code < 500 or err.code >= 600) and err.code != 416:
@ -95,6 +107,8 @@ class HttpFD(FileDownloader):
self._hook_progress({
'filename': filename,
'status': 'finished',
'downloaded_bytes': resume_len,
'total_bytes': resume_len,
})
return True
else:
@ -103,6 +117,11 @@ class HttpFD(FileDownloader):
resume_len = 0
open_mode = 'wb'
break
except socket.error as e:
if e.errno != errno.ECONNRESET:
# Connection reset is no problem, just retry
raise
# Retry
count += 1
if count <= retries:
@ -124,8 +143,8 @@ class HttpFD(FileDownloader):
if data_len is not None:
data_len = int(data_len) + resume_len
min_data_len = self.params.get("min_filesize", None)
max_data_len = self.params.get("max_filesize", None)
min_data_len = self.params.get('min_filesize')
max_data_len = self.params.get('max_filesize')
if min_data_len is not None and data_len < min_data_len:
self.to_screen('\r[download] File is smaller than min-filesize (%s bytes < %s bytes). Aborting.' % (data_len, min_data_len))
return False
@ -133,7 +152,6 @@ class HttpFD(FileDownloader):
self.to_screen('\r[download] File is larger than max-filesize (%s bytes > %s bytes). Aborting.' % (data_len, max_data_len))
return False
data_len_str = format_bytes(data_len)
byte_counter = 0 + resume_len
block_size = self.params.get('buffersize', 1024)
start = time.time()
@ -161,6 +179,13 @@ class HttpFD(FileDownloader):
except (OSError, IOError) as err:
self.report_error('unable to open for writing: %s' % str(err))
return False
if self.params.get('xattr_set_filesize', False) and data_len is not None:
try:
write_xattr(tmpfilename, 'user.ytdl.filesize', str(data_len).encode('utf-8'))
except (XAttrUnavailableError, XAttrMetadataError) as err:
self.report_error('unable to set filesize xattr: %s' % str(err))
try:
stream.write(data_block)
except (IOError, OSError) as err:
@ -184,20 +209,19 @@ class HttpFD(FileDownloader):
# Progress message
speed = self.calc_speed(start, now, byte_counter - resume_len)
if data_len is None:
eta = percent = None
eta = None
else:
percent = self.calc_percent(byte_counter, data_len)
eta = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
self.report_progress(percent, data_len_str, speed, eta)
self._hook_progress({
'status': 'downloading',
'downloaded_bytes': byte_counter,
'total_bytes': data_len,
'tmpfilename': tmpfilename,
'filename': filename,
'status': 'downloading',
'eta': eta,
'speed': speed,
'elapsed': now - start,
})
if is_test and byte_counter == data_len:
@ -209,7 +233,7 @@ class HttpFD(FileDownloader):
return False
if tmpfilename != '-':
stream.close()
self.report_finish(data_len_str, (time.time() - start))
if data_len is not None and byte_counter != data_len:
raise ContentTooShortError(byte_counter, int(data_len))
self.try_rename(tmpfilename, filename)
@ -223,6 +247,7 @@ class HttpFD(FileDownloader):
'total_bytes': byte_counter,
'filename': filename,
'status': 'finished',
'elapsed': time.time() - start,
})
return True

86
youtube_dl/downloader/rtmp.py
View File

@ -3,7 +3,6 @@ from __future__ import unicode_literals
import os
import re
import subprocess
import sys
import time
from .common import FileDownloader
@ -11,7 +10,7 @@ from ..compat import compat_str
from ..utils import (
check_executable,
encodeFilename,
format_bytes,
encodeArgument,
get_exe_version,
)
@ -51,23 +50,23 @@ class RtmpFD(FileDownloader):
if not resume_percent:
resume_percent = percent
resume_downloaded_data_len = downloaded_data_len
eta = self.calc_eta(start, time.time(), 100 - resume_percent, percent - resume_percent)
speed = self.calc_speed(start, time.time(), downloaded_data_len - resume_downloaded_data_len)
time_now = time.time()
eta = self.calc_eta(start, time_now, 100 - resume_percent, percent - resume_percent)
speed = self.calc_speed(start, time_now, downloaded_data_len - resume_downloaded_data_len)
data_len = None
if percent > 0:
data_len = int(downloaded_data_len * 100 / percent)
data_len_str = '~' + format_bytes(data_len)
self.report_progress(percent, data_len_str, speed, eta)
cursor_in_new_line = False
self._hook_progress({
'status': 'downloading',
'downloaded_bytes': downloaded_data_len,
'total_bytes': data_len,
'total_bytes_estimate': data_len,
'tmpfilename': tmpfilename,
'filename': filename,
'status': 'downloading',
'eta': eta,
'elapsed': time_now - start,
'speed': speed,
})
cursor_in_new_line = False
else:
# no percent for live streams
mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec', line)
@ -75,15 +74,15 @@ class RtmpFD(FileDownloader):
downloaded_data_len = int(float(mobj.group(1)) * 1024)
time_now = time.time()
speed = self.calc_speed(start, time_now, downloaded_data_len)
self.report_progress_live_stream(downloaded_data_len, speed, time_now - start)
cursor_in_new_line = False
self._hook_progress({
'downloaded_bytes': downloaded_data_len,
'tmpfilename': tmpfilename,
'filename': filename,
'status': 'downloading',
'elapsed': time_now - start,
'speed': speed,
})
cursor_in_new_line = False
elif self.params.get('verbose', False):
if not cursor_in_new_line:
self.to_screen('')
@ -95,15 +94,18 @@ class RtmpFD(FileDownloader):
return proc.returncode
url = info_dict['url']
player_url = info_dict.get('player_url', None)
page_url = info_dict.get('page_url', None)
app = info_dict.get('app', None)
play_path = info_dict.get('play_path', None)
tc_url = info_dict.get('tc_url', None)
flash_version = info_dict.get('flash_version', None)
player_url = info_dict.get('player_url')
page_url = info_dict.get('page_url')
app = info_dict.get('app')
play_path = info_dict.get('play_path')
tc_url = info_dict.get('tc_url')
flash_version = info_dict.get('flash_version')
live = info_dict.get('rtmp_live', False)
conn = info_dict.get('rtmp_conn', None)
protocol = info_dict.get('rtmp_protocol', None)
conn = info_dict.get('rtmp_conn')
protocol = info_dict.get('rtmp_protocol')
real_time = info_dict.get('rtmp_real_time', False)
no_resume = info_dict.get('no_resume', False)
continue_dl = self.params.get('continuedl', True)
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
@ -115,9 +117,11 @@ class RtmpFD(FileDownloader):
return False
# Download using rtmpdump. rtmpdump returns exit code 2 when
# the connection was interrumpted and resuming appears to be
# the connection was interrupted and resuming appears to be
# possible. This is part of rtmpdump's normal usage, AFAIK.
basic_args = ['rtmpdump', '--verbose', '-r', url, '-o', tmpfilename]
basic_args = [
'rtmpdump', '--verbose', '-r', url,
'-o', tmpfilename]
if player_url is not None:
basic_args += ['--swfVfy', player_url]
if page_url is not None:
@ -127,7 +131,7 @@ class RtmpFD(FileDownloader):
if play_path is not None:
basic_args += ['--playpath', play_path]
if tc_url is not None:
basic_args += ['--tcUrl', url]
basic_args += ['--tcUrl', tc_url]
if test:
basic_args += ['--stop', '1']
if flash_version is not None:
@ -141,30 +145,18 @@ class RtmpFD(FileDownloader):
basic_args += ['--conn', conn]
if protocol is not None:
basic_args += ['--protocol', protocol]
args = basic_args + [[], ['--resume', '--skip', '1']][not live and self.params.get('continuedl', False)]
if real_time:
basic_args += ['--realtime']
if sys.platform == 'win32' and sys.version_info < (3, 0):
# Windows subprocess module does not actually support Unicode
# on Python 2.x
# See http://stackoverflow.com/a/9951851/35070
subprocess_encoding = sys.getfilesystemencoding()
args = [a.encode(subprocess_encoding, 'ignore') for a in args]
else:
subprocess_encoding = None
args = basic_args
if not no_resume and continue_dl and not live:
args += ['--resume']
if not live and continue_dl:
args += ['--skip', '1']
if self.params.get('verbose', False):
if subprocess_encoding:
str_args = [
a.decode(subprocess_encoding) if isinstance(a, bytes) else a
for a in args]
else:
str_args = args
try:
import pipes
shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))
except ImportError:
shell_quote = repr
self.to_screen('[debug] rtmpdump command line: ' + shell_quote(str_args))
args = [encodeArgument(a) for a in args]
self._debug_cmd(args, exe='rtmpdump')
RD_SUCCESS = 0
RD_FAILED = 1
@ -181,7 +173,11 @@ class RtmpFD(FileDownloader):
prevsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('[rtmpdump] %s bytes' % prevsize)
time.sleep(5.0) # This seems to be needed
retval = run_rtmpdump(basic_args + ['-e'] + [[], ['-k', '1']][retval == RD_FAILED])
args = basic_args + ['--resume']
if retval == RD_FAILED:
args += ['--skip', '1']
args = [encodeArgument(a) for a in args]
retval = run_rtmpdump(args)
cursize = os.path.getsize(encodeFilename(tmpfilename))
if prevsize == cursize and retval == RD_FAILED:
break

22
youtube_dl/downloader/mplayer.py → youtube_dl/downloader/rtsp.py
View File

@ -10,21 +10,25 @@ from ..utils import (
)
class MplayerFD(FileDownloader):
class RtspFD(FileDownloader):
def real_download(self, filename, info_dict):
url = info_dict['url']
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
args = [
'mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy',
'-dumpstream', '-dumpfile', tmpfilename, url]
# Check for mplayer first
if not check_executable('mplayer', ['-h']):
self.report_error('MMS or RTSP download detected but "%s" could not be run' % args[0])
if check_executable('mplayer', ['-h']):
args = [
'mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy',
'-dumpstream', '-dumpfile', tmpfilename, url]
elif check_executable('mpv', ['-h']):
args = [
'mpv', '-really-quiet', '--vo=null', '--stream-dump=' + tmpfilename, url]
else:
self.report_error('MMS or RTSP download detected but neither "mplayer" nor "mpv" could be run. Please install any.')
return False
# Download using mplayer.
self._debug_cmd(args)
retval = subprocess.call(args)
if retval == 0:
fsize = os.path.getsize(encodeFilename(tmpfilename))
@ -39,5 +43,5 @@ class MplayerFD(FileDownloader):
return True
else:
self.to_stderr('\n')
self.report_error('mplayer exited with code %d' % retval)
self.report_error('%s exited with code %d' % (args[0], retval))
return False

596
youtube_dl/extractor/__init__.py
View File

@ -1,587 +1,33 @@
from __future__ import unicode_literals
from .abc import ABCIE
from .academicearth import AcademicEarthCourseIE
from .addanime import AddAnimeIE
from .adobetv import AdobeTVIE
from .adultswim import AdultSwimIE
from .aftonbladet import AftonbladetIE
from .aljazeera import AlJazeeraIE
from .alphaporno import AlphaPornoIE
from .anitube import AnitubeIE
from .anysex import AnySexIE
from .aol import AolIE
from .allocine import AllocineIE
from .aparat import AparatIE
from .appletrailers import AppleTrailersIE
from .archiveorg import ArchiveOrgIE
from .ard import ARDIE, ARDMediathekIE
from .arte import (
ArteTvIE,
ArteTVPlus7IE,
ArteTVCreativeIE,
ArteTVConcertIE,
ArteTVFutureIE,
ArteTVDDCIE,
ArteTVEmbedIE,
)
from .atresplayer import AtresPlayerIE
from .atttechchannel import ATTTechChannelIE
from .audiomack import AudiomackIE, AudiomackAlbumIE
from .auengine import AUEngineIE
from .azubu import AzubuIE
from .bambuser import BambuserIE, BambuserChannelIE
from .bandcamp import BandcampIE, BandcampAlbumIE
from .bbccouk import BBCCoUkIE
from .beeg import BeegIE
from .behindkink import BehindKinkIE
from .bet import BetIE
from .bild import BildIE
from .bilibili import BiliBiliIE
from .blinkx import BlinkxIE
from .bliptv import BlipTVIE, BlipTVUserIE
from .bloomberg import BloombergIE
from .bpb import BpbIE
from .br import BRIE
from .breakcom import BreakIE
from .brightcove import BrightcoveIE
from .buzzfeed import BuzzFeedIE
from .byutv import BYUtvIE
from .c56 import C56IE
from .canal13cl import Canal13clIE
from .canalplus import CanalplusIE
from .canalc2 import Canalc2IE
from .cbs import CBSIE
from .cbsnews import CBSNewsIE
from .ceskatelevize import CeskaTelevizeIE
from .channel9 import Channel9IE
from .chilloutzone import ChilloutzoneIE
from .cinchcast import CinchcastIE
from .clipfish import ClipfishIE
from .cliphunter import CliphunterIE
from .clipsyndicate import ClipsyndicateIE
from .cloudy import CloudyIE
from .clubic import ClubicIE
from .cmt import CMTIE
from .cnet import CNETIE
from .cnn import (
CNNIE,
CNNBlogsIE,
CNNArticleIE,
)
from .collegehumor import CollegeHumorIE
from .collegerama import CollegeRamaIE
from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
from .comcarcoff import ComCarCoffIE
from .commonmistakes import CommonMistakesIE
from .condenast import CondeNastIE
from .cracked import CrackedIE
from .criterion import CriterionIE
from .crunchyroll import (
CrunchyrollIE,
CrunchyrollShowPlaylistIE
)
from .cspan import CSpanIE
from .dailymotion import (
DailymotionIE,
DailymotionPlaylistIE,
DailymotionUserIE,
)
from .daum import DaumIE
from .dbtv import DBTVIE
from .deezer import DeezerPlaylistIE
from .dfb import DFBIE
from .dotsub import DotsubIE
from .dreisat import DreiSatIE
from .drbonanza import DRBonanzaIE
from .drtuber import DrTuberIE
from .drtv import DRTVIE
from .dvtv import DVTVIE
from .dump import DumpIE
from .defense import DefenseGouvFrIE
from .discovery import DiscoveryIE
from .divxstage import DivxStageIE
from .dropbox import DropboxIE
from .ebaumsworld import EbaumsWorldIE
from .echomsk import EchoMskIE
from .ehow import EHowIE
from .eighttracks import EightTracksIE
from .einthusan import EinthusanIE
from .eitb import EitbIE
from .ellentv import (
EllenTVIE,
EllenTVClipsIE,
)
from .elpais import ElPaisIE
from .empflix import EMPFlixIE
from .engadget import EngadgetIE
from .eporner import EpornerIE
from .eroprofile import EroProfileIE
from .escapist import EscapistIE
from .everyonesmixtape import EveryonesMixtapeIE
from .exfm import ExfmIE
from .expotv import ExpoTVIE
from .extremetube import ExtremeTubeIE
from .facebook import FacebookIE
from .faz import FazIE
from .fc2 import FC2IE
from .firedrive import FiredriveIE
from .firstpost import FirstpostIE
from .firsttv import FirstTVIE
from .fivemin import FiveMinIE
from .fktv import (
FKTVIE,
FKTVPosteckeIE,
)
from .flickr import FlickrIE
from .folketinget import FolketingetIE
from .fourtube import FourTubeIE
from .foxgay import FoxgayIE
from .foxnews import FoxNewsIE
from .franceculture import FranceCultureIE
from .franceinter import FranceInterIE
from .francetv import (
PluzzIE,
FranceTvInfoIE,
FranceTVIE,
GenerationQuoiIE,
CultureboxIE,
)
from .freesound import FreesoundIE
from .freespeech import FreespeechIE
from .freevideo import FreeVideoIE
from .funnyordie import FunnyOrDieIE
from .gamekings import GamekingsIE
from .gameone import (
GameOneIE,
GameOnePlaylistIE,
)
from .gamespot import GameSpotIE
from .gamestar import GameStarIE
from .gametrailers import GametrailersIE
from .gdcvault import GDCVaultIE
from .generic import GenericIE
from .giantbomb import GiantBombIE
from .giga import GigaIE
from .glide import GlideIE
from .globo import GloboIE
from .godtube import GodTubeIE
from .goldenmoustache import GoldenMoustacheIE
from .golem import GolemIE
from .googleplus import GooglePlusIE
from .googlesearch import GoogleSearchIE
from .gorillavid import GorillaVidIE
from .goshgay import GoshgayIE
from .grooveshark import GroovesharkIE
from .groupon import GrouponIE
from .hark import HarkIE
from .heise import HeiseIE
from .hellporno import HellPornoIE
from .helsinki import HelsinkiIE
from .hentaistigma import HentaiStigmaIE
from .hitbox import HitboxIE, HitboxLiveIE
from .hornbunny import HornBunnyIE
from .hostingbulk import HostingBulkIE
from .hotnewhiphop import HotNewHipHopIE
from .howcast import HowcastIE
from .howstuffworks import HowStuffWorksIE
from .huffpost import HuffPostIE
from .hypem import HypemIE
from .iconosquare import IconosquareIE
from .ign import IGNIE, OneUPIE
from .imdb import (
ImdbIE,
ImdbListIE
)
from .ina import InaIE
from .infoq import InfoQIE
from .instagram import InstagramIE, InstagramUserIE
from .internetvideoarchive import InternetVideoArchiveIE
from .iprima import IPrimaIE
from .ivi import (
IviIE,
IviCompilationIE
)
from .izlesene import IzleseneIE
from .jadorecettepub import JadoreCettePubIE
from .jeuxvideo import JeuxVideoIE
from .jove import JoveIE
from .jukebox import JukeboxIE
from .jpopsukitv import JpopsukiIE
from .kankan import KankanIE
from .karaoketv import KaraoketvIE
from .keezmovies import KeezMoviesIE
from .khanacademy import KhanAcademyIE
from .kickstarter import KickStarterIE
from .keek import KeekIE
from .kontrtube import KontrTubeIE
from .krasview import KrasViewIE
from .ku6 import Ku6IE
from .la7 import LA7IE
from .laola1tv import Laola1TvIE
from .lifenews import LifeNewsIE
from .liveleak import LiveLeakIE
from .livestream import (
LivestreamIE,
LivestreamOriginalIE,
LivestreamShortenerIE,
)
from .lnkgo import LnkGoIE
from .lrt import LRTIE
from .lynda import (
LyndaIE,
LyndaCourseIE
)
from .m6 import M6IE
from .macgamestore import MacGameStoreIE
from .mailru import MailRuIE
from .malemotion import MalemotionIE
from .mdr import MDRIE
from .metacafe import MetacafeIE
from .metacritic import MetacriticIE
from .mgoon import MgoonIE
from .minhateca import MinhatecaIE
from .ministrygrid import MinistryGridIE
from .mit import TechTVMITIE, MITIE, OCWMITIE
from .mitele import MiTeleIE
from .mixcloud import MixcloudIE
from .mlb import MLBIE
from .mpora import MporaIE
from .moevideo import MoeVideoIE
from .mofosex import MofosexIE
from .mojvideo import MojvideoIE
from .moniker import MonikerIE
from .mooshare import MooshareIE
from .morningstar import MorningstarIE
from .motherless import MotherlessIE
from .motorsport import MotorsportIE
from .movieclips import MovieClipsIE
from .moviezine import MoviezineIE
from .movshare import MovShareIE
from .mtv import (
MTVIE,
MTVServicesEmbeddedIE,
MTVIggyIE,
)
from .muenchentv import MuenchenTVIE
from .musicplayon import MusicPlayOnIE
from .musicvault import MusicVaultIE
from .muzu import MuzuTVIE
from .myspace import MySpaceIE, MySpaceAlbumIE
from .myspass import MySpassIE
from .myvideo import MyVideoIE
from .myvidster import MyVidsterIE
from .naver import NaverIE
from .nba import NBAIE
from .nbc import (
NBCIE,
NBCNewsIE,
)
from .ndr import NDRIE
from .ndtv import NDTVIE
from .netzkino import NetzkinoIE
from .nerdcubed import NerdCubedFeedIE
from .newgrounds import NewgroundsIE
from .newstube import NewstubeIE
from .nfb import NFBIE
from .nfl import NFLIE
from .nhl import NHLIE, NHLVideocenterIE
from .niconico import NiconicoIE, NiconicoPlaylistIE
from .ninegag import NineGagIE
from .noco import NocoIE
from .normalboots import NormalbootsIE
from .nosvideo import NosVideoIE
from .novamov import NovaMovIE
from .nowness import NownessIE
from .nowvideo import NowVideoIE
from .npo import (
NPOIE,
NPOLiveIE,
TegenlichtVproIE,
)
from .nrk import (
NRKIE,
NRKTVIE,
)
from .ntv import NTVIE
from .nytimes import NYTimesIE
from .nuvid import NuvidIE
from .oktoberfesttv import OktoberfestTVIE
from .ooyala import OoyalaIE
from .openfilm import OpenFilmIE
from .orf import (
ORFTVthekIE,
ORFOE1IE,
ORFFM4IE,
)
from .parliamentliveuk import ParliamentLiveUKIE
from .patreon import PatreonIE
from .pbs import PBSIE
from .phoenix import PhoenixIE
from .photobucket import PhotobucketIE
from .planetaplay import PlanetaPlayIE
from .played import PlayedIE
from .playfm import PlayFMIE
from .playvid import PlayvidIE
from .podomatic import PodomaticIE
from .pornhd import PornHdIE
from .pornhub import PornHubIE
from .pornotube import PornotubeIE
from .pornoxo import PornoXOIE
from .promptfile import PromptFileIE
from .prosiebensat1 import ProSiebenSat1IE
from .pyvideo import PyvideoIE
from .quickvid import QuickVidIE
from .radiode import RadioDeIE
from .radiobremen import RadioBremenIE
from .radiofrance import RadioFranceIE
from .rai import RaiIE
from .rbmaradio import RBMARadioIE
from .redtube import RedTubeIE
from .restudy import RestudyIE
from .reverbnation import ReverbNationIE
from .ringtv import RingTVIE
from .ro220 import Ro220IE
from .rottentomatoes import RottenTomatoesIE
from .roxwel import RoxwelIE
from .rtbf import RTBFIE
from .rte import RteIE
from .rtllu import RtlluIE
from .rtlnl import RtlXlIE
from .rtlnow import RTLnowIE
from .rtp import RTPIE
from .rts import RTSIE
from .rtve import RTVEALaCartaIE, RTVELiveIE
from .ruhd import RUHDIE
from .rutube import (
RutubeIE,
RutubeChannelIE,
RutubeEmbedIE,
RutubeMovieIE,
RutubePersonIE,
)
from .rutv import RUTVIE
from .sapo import SapoIE
from .savefrom import SaveFromIE
from .sbs import SBSIE
from .scivee import SciVeeIE
from .screencast import ScreencastIE
from .screencastomatic import ScreencastOMaticIE
from .screenwavemedia import CinemassacreIE, ScreenwaveMediaIE, TeamFourIE
from .servingsys import ServingSysIE
from .sexu import SexuIE
from .sexykarma import SexyKarmaIE
from .shared import SharedIE
from .sharesix import ShareSixIE
from .sina import SinaIE
from .slideshare import SlideshareIE
from .slutload import SlutloadIE
from .smotri import (
SmotriIE,
SmotriCommunityIE,
SmotriUserIE,
SmotriBroadcastIE,
)
from .snotr import SnotrIE
from .sockshare import SockshareIE
from .sohu import SohuIE
from .soundcloud import (
SoundcloudIE,
SoundcloudSetIE,
SoundcloudUserIE,
SoundcloudPlaylistIE
)
from .soundgasm import SoundgasmIE
from .southpark import (
SouthParkIE,
SouthparkDeIE,
)
from .space import SpaceIE
from .spankwire import SpankwireIE
from .spiegel import SpiegelIE, SpiegelArticleIE
from .spiegeltv import SpiegeltvIE
from .spike import SpikeIE
from .sport5 import Sport5IE
from .sportbox import SportBoxIE
from .sportdeutschland import SportDeutschlandIE
from .srmediathek import SRMediathekIE
from .stanfordoc import StanfordOpenClassroomIE
from .steam import SteamIE
from .streamcloud import StreamcloudIE
from .streamcz import StreamCZIE
from .sunporno import SunPornoIE
from .swrmediathek import SWRMediathekIE
from .syfy import SyfyIE
from .sztvhu import SztvHuIE
from .tagesschau import TagesschauIE
from .tapely import TapelyIE
from .tass import TassIE
from .teachertube import (
TeacherTubeIE,
TeacherTubeUserIE,
)
from .teachingchannel import TeachingChannelIE
from .teamcoco import TeamcocoIE
from .techtalks import TechTalksIE
from .ted import TEDIE
from .telebruxelles import TeleBruxellesIE
from .telecinco import TelecincoIE
from .telemb import TeleMBIE
from .teletask import TeleTaskIE
from .tenplay import TenPlayIE
from .testurl import TestURLIE
from .tf1 import TF1IE
from .theonion import TheOnionIE
from .theplatform import ThePlatformIE
from .thesixtyone import TheSixtyOneIE
from .thisav import ThisAVIE
from .tinypic import TinyPicIE
from .tlc import TlcIE, TlcDeIE
from .tmz import TMZIE
from .tnaflix import TNAFlixIE
from .thvideo import (
THVideoIE,
THVideoPlaylistIE
)
from .toutv import TouTvIE
from .toypics import ToypicsUserIE, ToypicsIE
from .traileraddict import TrailerAddictIE
from .trilulilu import TriluliluIE
from .trutube import TruTubeIE
from .tube8 import Tube8IE
from .tudou import TudouIE
from .tumblr import TumblrIE
from .tunein import TuneInIE
from .turbo import TurboIE
from .tutv import TutvIE
from .tvigle import TvigleIE
from .tvp import TvpIE, TvpSeriesIE
from .tvplay import TVPlayIE
from .twentyfourvideo import TwentyFourVideoIE
from .twitch import TwitchIE
from .ubu import UbuIE
from .udemy import (
UdemyIE,
UdemyCourseIE
)
from .unistra import UnistraIE
from .urort import UrortIE
from .ustream import UstreamIE, UstreamChannelIE
from .vbox7 import Vbox7IE
from .veehd import VeeHDIE
from .veoh import VeohIE
from .vesti import VestiIE
from .vevo import VevoIE
from .vgtv import VGTVIE
from .vh1 import VH1IE
from .vice import ViceIE
from .viddler import ViddlerIE
from .videobam import VideoBamIE
from .videodetective import VideoDetectiveIE
from .videolecturesnet import VideoLecturesNetIE
from .videofyme import VideofyMeIE
from .videomega import VideoMegaIE
from .videopremium import VideoPremiumIE
from .videott import VideoTtIE
from .videoweed import VideoWeedIE
from .vidme import VidmeIE
from .vidzi import VidziIE
from .vier import VierIE, VierVideosIE
from .vimeo import (
VimeoIE,
VimeoAlbumIE,
VimeoChannelIE,
VimeoGroupsIE,
VimeoLikesIE,
VimeoReviewIE,
VimeoUserIE,
VimeoWatchLaterIE,
)
from .vimple import VimpleIE
from .vine import (
VineIE,
VineUserIE,
)
from .viki import VikiIE
from .vk import (
VKIE,
VKUserVideosIE,
)
from .vodlocker import VodlockerIE
from .vporn import VpornIE
from .vrt import VRTIE
from .vube import VubeIE
from .vuclip import VuClipIE
from .vulture import VultureIE
from .walla import WallaIE
from .washingtonpost import WashingtonPostIE
from .wat import WatIE
from .wayofthemaster import WayOfTheMasterIE
from .wdr import (
WDRIE,
WDRMobileIE,
WDRMausIE,
)
from .webofstories import WebOfStoriesIE
from .weibo import WeiboIE
from .wimp import WimpIE
from .wistia import WistiaIE
from .worldstarhiphop import WorldStarHipHopIE
from .wrzuta import WrzutaIE
from .xbef import XBefIE
from .xboxclips import XboxClipsIE
from .xhamster import XHamsterIE
from .xminus import XMinusIE
from .xnxx import XNXXIE
from .xvideos import XVideosIE
from .xtube import XTubeUserIE, XTubeIE
from .xxxymovies import XXXYMoviesIE
from .yahoo import (
YahooIE,
YahooSearchIE,
)
from .yesjapan import YesJapanIE
from .ynet import YnetIE
from .youjizz import YouJizzIE
from .youku import YoukuIE
from .youporn import YouPornIE
from .yourupload import YourUploadIE
from .youtube import (
YoutubeIE,
YoutubeChannelIE,
YoutubeFavouritesIE,
YoutubeHistoryIE,
YoutubePlaylistIE,
YoutubeRecommendedIE,
YoutubeSearchDateIE,
YoutubeSearchIE,
YoutubeSearchURLIE,
YoutubeShowIE,
YoutubeSubscriptionsIE,
YoutubeTruncatedIDIE,
YoutubeTruncatedURLIE,
YoutubeUserIE,
YoutubeWatchLaterIE,
)
from .zdf import ZDFIE, ZDFChannelIE
from .zingmp3 import (
ZingMp3SongIE,
ZingMp3AlbumIE,
)
try:
from .lazy_extractors import *
from .lazy_extractors import _ALL_CLASSES
_LAZY_LOADER = True
except ImportError:
_LAZY_LOADER = False
from .extractors import *
_ALL_CLASSES = [
klass
for name, klass in globals().items()
if name.endswith('IE') and name != 'GenericIE'
]
_ALL_CLASSES.append(GenericIE)
_ALL_CLASSES = [
klass
for name, klass in globals().items()
if name.endswith('IE') and name != 'GenericIE'
]
_ALL_CLASSES.append(GenericIE)
def gen_extractor_classes():
""" Return a list of supported extractors.
The order does matter; the first extractor matched is the one handling the URL.
"""
return _ALL_CLASSES
def gen_extractors():
""" Return a list of an instance of every supported extractor.
The order does matter; the first extractor matched is the one handling the URL.
"""
return [klass() for klass in _ALL_CLASSES]
return [klass() for klass in gen_extractor_classes()]
def list_extractors(age_limit):

129
youtube_dl/extractor/abc.py
View File

@ -1,16 +1,21 @@
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..utils import (
ExtractorError,
js_to_json,
int_or_none,
parse_iso8601,
)
class ABCIE(InfoExtractor):
IE_NAME = 'abc.net.au'
_VALID_URL = r'http://www\.abc\.net\.au/news/[^/]+/[^/]+/(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
_TEST = {
_TESTS = [{
'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
'md5': 'cb3dd03b18455a661071ee1e28344d9f',
'info_dict': {
@ -19,23 +24,67 @@ class ABCIE(InfoExtractor):
'title': 'Australia to help staff Ebola treatment centre in Sierra Leone',
'description': 'md5:809ad29c67a05f54eb41f2a105693a67',
},
}
'skip': 'this video has expired',
}, {
'url': 'http://www.abc.net.au/news/2015-08-17/warren-entsch-introduces-same-sex-marriage-bill/6702326',
'md5': 'db2a5369238b51f9811ad815b69dc086',
'info_dict': {
'id': 'NvqvPeNZsHU',
'ext': 'mp4',
'upload_date': '20150816',
'uploader': 'ABC News (Australia)',
'description': 'Government backbencher Warren Entsch introduces a cross-party sponsored bill to legalise same-sex marriage, saying the bill is designed to promote "an inclusive Australia, not a divided one.". Read more here: http://ab.co/1Mwc6ef',
'uploader_id': 'NewsOnABC',
'title': 'Marriage Equality: Warren Entsch introduces same sex marriage bill',
},
'add_ie': ['Youtube'],
'skip': 'Not accessible from Travis CI server',
}, {
'url': 'http://www.abc.net.au/news/2015-10-23/nab-lifts-interest-rates-following-westpac-and-cba/6880080',
'md5': 'b96eee7c9edf4fc5a358a0252881cc1f',
'info_dict': {
'id': '6880080',
'ext': 'mp3',
'title': 'NAB lifts interest rates, following Westpac and CBA',
'description': 'md5:f13d8edc81e462fce4a0437c7dc04728',
},
}, {
'url': 'http://www.abc.net.au/news/2015-10-19/6866214',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
urls_info_json = self._search_regex(
r'inlineVideoData\.push\((.*?)\);', webpage, 'video urls',
flags=re.DOTALL)
urls_info = json.loads(urls_info_json.replace('\'', '"'))
mobj = re.search(
r'inline(?P<type>Video|Audio|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
webpage)
if mobj is None:
expired = self._html_search_regex(r'(?s)class="expired-(?:video|audio)".+?<span>(.+?)</span>', webpage, 'expired', None)
if expired:
raise ExtractorError('%s said: %s' % (self.IE_NAME, expired), expected=True)
raise ExtractorError('Unable to extract video urls')
urls_info = self._parse_json(
mobj.group('json_data'), video_id, transform_source=js_to_json)
if not isinstance(urls_info, list):
urls_info = [urls_info]
if mobj.group('type') == 'YouTube':
return self.playlist_result([
self.url_result(url_info['url']) for url_info in urls_info])
formats = [{
'url': url_info['url'],
'width': int(url_info['width']),
'height': int(url_info['height']),
'tbr': int(url_info['bitrate']),
'filesize': int(url_info['filesize']),
'vcodec': url_info.get('codec') if mobj.group('type') == 'Video' else 'none',
'width': int_or_none(url_info.get('width')),
'height': int_or_none(url_info.get('height')),
'tbr': int_or_none(url_info.get('bitrate')),
'filesize': int_or_none(url_info.get('filesize')),
} for url_info in urls_info]
self._sort_formats(formats)
return {
@ -45,3 +94,59 @@ class ABCIE(InfoExtractor):
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
}
class ABCIViewIE(InfoExtractor):
IE_NAME = 'abc.net.au:iview'
_VALID_URL = r'https?://iview\.abc\.net\.au/programs/[^/]+/(?P<id>[^/?#]+)'
# ABC iview programs are normally available for 14 days only.
_TESTS = [{
'url': 'http://iview.abc.net.au/programs/gardening-australia/FA1505V024S00',
'md5': '979d10b2939101f0d27a06b79edad536',
'info_dict': {
'id': 'FA1505V024S00',
'ext': 'mp4',
'title': 'Series 27 Ep 24',
'description': 'md5:b28baeae7504d1148e1d2f0e3ed3c15d',
'upload_date': '20160820',
'uploader_id': 'abc1',
'timestamp': 1471719600,
},
'skip': 'Video gone',
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_params = self._parse_json(self._search_regex(
r'videoParams\s*=\s*({.+?});', webpage, 'video params'), video_id)
title = video_params['title']
stream = next(s for s in video_params['playlist'] if s.get('type') == 'program')
formats = self._extract_akamai_formats(stream['hds-unmetered'], video_id)
self._sort_formats(formats)
subtitles = {}
src_vtt = stream.get('captions', {}).get('src-vtt')
if src_vtt:
subtitles['en'] = [{
'url': src_vtt,
'ext': 'vtt',
}]
return {
'id': video_id,
'title': title,
'description': self._html_search_meta(['og:description', 'twitter:description'], webpage),
'thumbnail': self._html_search_meta(['og:image', 'twitter:image:src'], webpage),
'duration': int_or_none(video_params.get('eventDuration')),
'timestamp': parse_iso8601(video_params.get('pubDate'), ' '),
'series': video_params.get('seriesTitle'),
'series_id': video_params.get('seriesHouseNumber') or video_id[:7],
'episode_number': int_or_none(self._html_search_meta('episodeNumber', webpage)),
'episode': self._html_search_meta('episode_title', webpage),
'uploader_id': video_params.get('channel'),
'formats': formats,
'subtitles': subtitles,
}

135
youtube_dl/extractor/abcnews.py Normal file
View File

@ -0,0 +1,135 @@
# coding: utf-8
from __future__ import unicode_literals
import calendar
import re
import time
from .amp import AMPIE
from .common import InfoExtractor
from ..compat import compat_urlparse
class AbcNewsVideoIE(AMPIE):
IE_NAME = 'abcnews:video'
_VALID_URL = r'https?://abcnews\.go\.com/[^/]+/video/(?P<display_id>[0-9a-z-]+)-(?P<id>\d+)'
_TESTS = [{
'url': 'http://abcnews.go.com/ThisWeek/video/week-exclusive-irans-foreign-minister-zarif-20411932',
'info_dict': {
'id': '20411932',
'ext': 'mp4',
'display_id': 'week-exclusive-irans-foreign-minister-zarif',
'title': '\'This Week\' Exclusive: Iran\'s Foreign Minister Zarif',
'description': 'George Stephanopoulos goes one-on-one with Iranian Foreign Minister Dr. Javad Zarif.',
'duration': 180,
'thumbnail': 're:^https?://.*\.jpg$',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://abcnews.go.com/2020/video/2020-husband-stands-teacher-jail-student-affairs-26119478',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('display_id')
video_id = mobj.group('id')
info_dict = self._extract_feed_info(
'http://abcnews.go.com/video/itemfeed?id=%s' % video_id)
info_dict.update({
'id': video_id,
'display_id': display_id,
})
return info_dict
class AbcNewsIE(InfoExtractor):
IE_NAME = 'abcnews'
_VALID_URL = r'https?://abcnews\.go\.com/(?:[^/]+/)+(?P<display_id>[0-9a-z-]+)/story\?id=(?P<id>\d+)'
_TESTS = [{
'url': 'http://abcnews.go.com/Blotter/News/dramatic-video-rare-death-job-america/story?id=10498713#.UIhwosWHLjY',
'info_dict': {
'id': '10498713',
'ext': 'flv',
'display_id': 'dramatic-video-rare-death-job-america',
'title': 'Occupational Hazards',
'description': 'Nightline investigates the dangers that lurk at various jobs.',
'thumbnail': 're:^https?://.*\.jpg$',
'upload_date': '20100428',
'timestamp': 1272412800,
},
'add_ie': ['AbcNewsVideo'],
}, {
'url': 'http://abcnews.go.com/Entertainment/justin-timberlake-performs-stop-feeling-eurovision-2016/story?id=39125818',
'info_dict': {
'id': '39125818',
'ext': 'mp4',
'display_id': 'justin-timberlake-performs-stop-feeling-eurovision-2016',
'title': 'Justin Timberlake Drops Hints For Secret Single',
'description': 'Lara Spencer reports the buzziest stories of the day in "GMA" Pop News.',
'upload_date': '20160515',
'timestamp': 1463329500,
},
'params': {
# m3u8 download
'skip_download': True,
# The embedded YouTube video is blocked due to copyright issues
'playlist_items': '1',
},
'add_ie': ['AbcNewsVideo'],
}, {
'url': 'http://abcnews.go.com/Technology/exclusive-apple-ceo-tim-cook-iphone-cracking-software/story?id=37173343',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('display_id')
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(
r'window\.abcnvideo\.url\s*=\s*"([^"]+)"', webpage, 'video URL')
full_video_url = compat_urlparse.urljoin(url, video_url)
youtube_url = self._html_search_regex(
r'<iframe[^>]+src="(https://www\.youtube\.com/embed/[^"]+)"',
webpage, 'YouTube URL', default=None)
timestamp = None
date_str = self._html_search_regex(
r'<span[^>]+class="timestamp">([^<]+)</span>',
webpage, 'timestamp', fatal=False)
if date_str:
tz_offset = 0
if date_str.endswith(' ET'): # Eastern Time
tz_offset = -5
date_str = date_str[:-3]
date_formats = ['%b. %d, %Y', '%b %d, %Y, %I:%M %p']
for date_format in date_formats:
try:
timestamp = calendar.timegm(time.strptime(date_str.strip(), date_format))
except ValueError:
continue
if timestamp is not None:
timestamp -= tz_offset * 3600
entry = {
'_type': 'url_transparent',
'ie_key': AbcNewsVideoIE.ie_key(),
'url': full_video_url,
'id': video_id,
'display_id': display_id,
'timestamp': timestamp,
}
if youtube_url:
entries = [entry, self.url_result(youtube_url, 'Youtube')]
return self.playlist_result(entries)
return entry

112
youtube_dl/extractor/abcotvs.py Normal file
View File

@ -0,0 +1,112 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_iso8601,
)
class ABCOTVSIE(InfoExtractor):
IE_NAME = 'abcotvs'
IE_DESC = 'ABC Owned Television Stations'
_VALID_URL = r'https?://(?:abc(?:7(?:news|ny|chicago)?|11|13|30)|6abc)\.com(?:/[^/]+/(?P<display_id>[^/]+))?/(?P<id>\d+)'
_TESTS = [
{
'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/',
'info_dict': {
'id': '472581',
'display_id': 'east-bay-museum-celebrates-vintage-synthesizers',
'ext': 'mp4',
'title': 'East Bay museum celebrates vintage synthesizers',
'description': 'md5:a4f10fb2f2a02565c1749d4adbab4b10',
'thumbnail': 're:^https?://.*\.jpg$',
'timestamp': 1421123075,
'upload_date': '20150113',
'uploader': 'Jonathan Bloom',
},
'params': {
# m3u8 download
'skip_download': True,
},
},
{
'url': 'http://abc7news.com/472581',
'only_matching': True,
},
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id') or video_id
webpage = self._download_webpage(url, display_id)
m3u8 = self._html_search_meta(
'contentURL', webpage, 'm3u8 url', fatal=True).split('?')[0]
formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4')
self._sort_formats(formats)
title = self._og_search_title(webpage).strip()
description = self._og_search_description(webpage).strip()
thumbnail = self._og_search_thumbnail(webpage)
timestamp = parse_iso8601(self._search_regex(
r'<div class="meta">\s*<time class="timeago" datetime="([^"]+)">',
webpage, 'upload date', fatal=False))
uploader = self._search_regex(
r'rel="author">([^<]+)</a>',
webpage, 'uploader', default=None)
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'timestamp': timestamp,
'uploader': uploader,
'formats': formats,
}
class ABCOTVSClipsIE(InfoExtractor):
IE_NAME = 'abcotvs:clips'
_VALID_URL = r'https?://clips\.abcotvs\.com/(?:[^/]+/)*video/(?P<id>\d+)'
_TEST = {
'url': 'https://clips.abcotvs.com/kabc/video/214814',
'info_dict': {
'id': '214814',
'ext': 'mp4',
'title': 'SpaceX launch pad explosion destroys rocket, satellite',
'description': 'md5:9f186e5ad8f490f65409965ee9c7be1b',
'upload_date': '20160901',
'timestamp': 1472756695,
},
'params': {
# m3u8 download
'skip_download': True,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
video_data = self._download_json('https://clips.abcotvs.com/vogo/video/getByIds?ids=' + video_id, video_id)['results'][0]
title = video_data['title']
formats = self._extract_m3u8_formats(
video_data['videoURL'].split('?')[0], video_id, 'mp4')
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': video_data.get('description'),
'thumbnail': video_data.get('thumbnailURL'),
'duration': int_or_none(video_data.get('duration')),
'timestamp': int_or_none(video_data.get('pubDate')),
'formats': formats,
}

2
youtube_dl/extractor/academicearth.py
View File

@ -15,7 +15,7 @@ class AcademicEarthCourseIE(InfoExtractor):
'title': 'Laws of Nature',
'description': 'Introduce yourself to the laws of nature with these free online college lectures from Yale, Harvard, and MIT.',
},
'playlist_count': 4,
'playlist_count': 3,
}
def _real_extract(self, url):

82
youtube_dl/extractor/acast.py Normal file
View File

@ -0,0 +1,82 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import functools
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
OnDemandPagedList,
)
class ACastIE(InfoExtractor):
IE_NAME = 'acast'
_VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<channel>[^/]+)/(?P<id>[^/#?]+)'
_TEST = {
'url': 'https://www.acast.com/condenasttraveler/-where-are-you-taipei-101-taiwan',
'md5': 'ada3de5a1e3a2a381327d749854788bb',
'info_dict': {
'id': '57de3baa-4bb0-487e-9418-2692c1277a34',
'ext': 'mp3',
'title': '"Where Are You?": Taipei 101, Taiwan',
'timestamp': 1196172000000,
'description': 'md5:a0b4ef3634e63866b542e5b1199a1a0e',
'duration': 211,
}
}
def _real_extract(self, url):
channel, display_id = re.match(self._VALID_URL, url).groups()
cast_data = self._download_json(
'https://embed.acast.com/api/acasts/%s/%s' % (channel, display_id), display_id)
return {
'id': compat_str(cast_data['id']),
'display_id': display_id,
'url': cast_data['blings'][0]['audio'],
'title': cast_data['name'],
'description': cast_data.get('description'),
'thumbnail': cast_data.get('image'),
'timestamp': int_or_none(cast_data.get('publishingDate')),
'duration': int_or_none(cast_data.get('duration')),
}
class ACastChannelIE(InfoExtractor):
IE_NAME = 'acast:channel'
_VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<id>[^/#?]+)'
_TEST = {
'url': 'https://www.acast.com/condenasttraveler',
'info_dict': {
'id': '50544219-29bb-499e-a083-6087f4cb7797',
'title': 'Condé Nast Traveler Podcast',
'description': 'md5:98646dee22a5b386626ae31866638fbd',
},
'playlist_mincount': 20,
}
_API_BASE_URL = 'https://www.acast.com/api/'
_PAGE_SIZE = 10
@classmethod
def suitable(cls, url):
return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
def _fetch_page(self, channel_slug, page):
casts = self._download_json(
self._API_BASE_URL + 'channels/%s/acasts?page=%s' % (channel_slug, page),
channel_slug, note='Download page %d of channel data' % page)
for cast in casts:
yield self.url_result(
'https://www.acast.com/%s/%s' % (channel_slug, cast['url']),
'ACast', cast['id'])
def _real_extract(self, url):
channel_slug = self._match_id(url)
channel_data = self._download_json(
self._API_BASE_URL + 'channels/%s' % channel_slug, channel_slug)
entries = OnDemandPagedList(functools.partial(
self._fetch_page, channel_slug), self._PAGE_SIZE)
return self.playlist_result(entries, compat_str(
channel_data['id']), channel_data['name'], channel_data.get('description'))

19
youtube_dl/extractor/addanime.py
View File

@ -6,17 +6,18 @@ from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
compat_str,
compat_urllib_parse,
compat_urllib_parse_urlencode,
compat_urllib_parse_urlparse,
)
from ..utils import (
ExtractorError,
qualities,
)
class AddAnimeIE(InfoExtractor):
_VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video\.php\?(?:.*?)v=(?P<id>[\w_]+)(?:.*)'
_TEST = {
_VALID_URL = r'https?://(?:\w+\.)?add-anime\.net/(?:watch_video\.php\?(?:.*?)v=|video/)(?P<id>[\w_]+)'
_TESTS = [{
'url': 'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
'md5': '72954ea10bc979ab5e2eb288b21425a0',
'info_dict': {
@ -25,7 +26,10 @@ class AddAnimeIE(InfoExtractor):
'description': 'One Piece 606',
'title': 'One Piece 606',
}
}
}, {
'url': 'http://add-anime.net/video/MDUGWYKNGBD8/One-Piece-687',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
@ -56,15 +60,17 @@ class AddAnimeIE(InfoExtractor):
confirm_url = (
parsed_url.scheme + '://' + parsed_url.netloc +
action + '?' +
compat_urllib_parse.urlencode({
compat_urllib_parse_urlencode({
'jschl_vc': vc, 'jschl_answer': compat_str(av_val)}))
self._download_webpage(
confirm_url, video_id,
note='Confirming after redirect')
webpage = self._download_webpage(url, video_id)
FORMATS = ('normal', 'hq')
quality = qualities(FORMATS)
formats = []
for format_id in ('normal', 'hq'):
for format_id in FORMATS:
rex = r"var %s_video_file = '(.*?)';" % re.escape(format_id)
video_url = self._search_regex(rex, webpage, 'video file URLx',
fatal=False)
@ -73,6 +79,7 @@ class AddAnimeIE(InfoExtractor):
formats.append({
'format_id': format_id,
'url': video_url,
'quality': quality(format_id),
})
self._sort_formats(formats)
video_title = self._og_search_title(webpage)

1428
youtube_dl/extractor/adobepass.py Normal file
View File

File diff suppressed because it is too large Load Diff

199
youtube_dl/extractor/adobetv.py
View File

@ -1,21 +1,32 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
parse_duration,
unified_strdate,
str_to_int,
int_or_none,
float_or_none,
ISO639Utils,
determine_ext,
)
class AdobeTVIE(InfoExtractor):
_VALID_URL = r'https?://tv\.adobe\.com/watch/[^/]+/(?P<id>[^/]+)'
class AdobeTVBaseIE(InfoExtractor):
_API_BASE_URL = 'http://tv.adobe.com/api/v4/'
class AdobeTVIE(AdobeTVBaseIE):
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?watch/(?P<show_urlname>[^/]+)/(?P<id>[^/]+)'
_TEST = {
'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/',
'md5': '9bc5727bcdd55251f35ad311ca74fa1e',
'info_dict': {
'id': 'quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop',
'id': '10981',
'ext': 'mp4',
'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop',
'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311',
@ -27,44 +38,160 @@ class AdobeTVIE(InfoExtractor):
}
def _real_extract(self, url):
video_id = self._match_id(url)
language, show_urlname, urlname = re.match(self._VALID_URL, url).groups()
if not language:
language = 'en'
webpage = self._download_webpage(url, video_id)
player = self._parse_json(
self._search_regex(r'html5player:\s*({.+?})\s*\n', webpage, 'player'),
video_id)
title = player.get('title') or self._search_regex(
r'data-title="([^"]+)"', webpage, 'title')
description = self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage)
upload_date = unified_strdate(
self._html_search_meta('datepublished', webpage, 'upload date'))
duration = parse_duration(
self._html_search_meta('duration', webpage, 'duration')
or self._search_regex(r'Runtime:\s*(\d{2}:\d{2}:\d{2})', webpage, 'duration'))
view_count = str_to_int(self._search_regex(
r'<div class="views">\s*Views?:\s*([\d,.]+)\s*</div>',
webpage, 'view count'))
video_data = self._download_json(
self._API_BASE_URL + 'episode/get/?language=%s&show_urlname=%s&urlname=%s&disclosure=standard' % (language, show_urlname, urlname),
urlname)['data'][0]
formats = [{
'url': source['src'],
'format_id': source.get('quality') or source['src'].split('-')[-1].split('.')[0] or None,
'tbr': source.get('bitrate'),
} for source in player['sources']]
'url': source['url'],
'format_id': source.get('quality_level') or source['url'].split('-')[-1].split('.')[0] or None,
'width': int_or_none(source.get('width')),
'height': int_or_none(source.get('height')),
'tbr': int_or_none(source.get('video_data_rate')),
} for source in video_data['videos']]
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'upload_date': upload_date,
'duration': duration,
'view_count': view_count,
'id': compat_str(video_data['id']),
'title': video_data['title'],
'description': video_data.get('description'),
'thumbnail': video_data.get('thumbnail'),
'upload_date': unified_strdate(video_data.get('start_date')),
'duration': parse_duration(video_data.get('duration')),
'view_count': str_to_int(video_data.get('playcount')),
'formats': formats,
}
class AdobeTVPlaylistBaseIE(AdobeTVBaseIE):
def _parse_page_data(self, page_data):
return [self.url_result(self._get_element_url(element_data)) for element_data in page_data]
def _extract_playlist_entries(self, url, display_id):
page = self._download_json(url, display_id)
entries = self._parse_page_data(page['data'])
for page_num in range(2, page['paging']['pages'] + 1):
entries.extend(self._parse_page_data(
self._download_json(url + '&page=%d' % page_num, display_id)['data']))
return entries
class AdobeTVShowIE(AdobeTVPlaylistBaseIE):
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?show/(?P<id>[^/]+)'
_TEST = {
'url': 'http://tv.adobe.com/show/the-complete-picture-with-julieanne-kost',
'info_dict': {
'id': '36',
'title': 'The Complete Picture with Julieanne Kost',
'description': 'md5:fa50867102dcd1aa0ddf2ab039311b27',
},
'playlist_mincount': 136,
}
def _get_element_url(self, element_data):
return element_data['urls'][0]
def _real_extract(self, url):
language, show_urlname = re.match(self._VALID_URL, url).groups()
if not language:
language = 'en'
query = 'language=%s&show_urlname=%s' % (language, show_urlname)
show_data = self._download_json(self._API_BASE_URL + 'show/get/?%s' % query, show_urlname)['data'][0]
return self.playlist_result(
self._extract_playlist_entries(self._API_BASE_URL + 'episode/?%s' % query, show_urlname),
compat_str(show_data['id']),
show_data['show_name'],
show_data['show_description'])
class AdobeTVChannelIE(AdobeTVPlaylistBaseIE):
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?channel/(?P<id>[^/]+)(?:/(?P<category_urlname>[^/]+))?'
_TEST = {
'url': 'http://tv.adobe.com/channel/development',
'info_dict': {
'id': 'development',
},
'playlist_mincount': 96,
}
def _get_element_url(self, element_data):
return element_data['url']
def _real_extract(self, url):
language, channel_urlname, category_urlname = re.match(self._VALID_URL, url).groups()
if not language:
language = 'en'
query = 'language=%s&channel_urlname=%s' % (language, channel_urlname)
if category_urlname:
query += '&category_urlname=%s' % category_urlname
return self.playlist_result(
self._extract_playlist_entries(self._API_BASE_URL + 'show/?%s' % query, channel_urlname),
channel_urlname)
class AdobeTVVideoIE(InfoExtractor):
_VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)'
_TEST = {
# From https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners
'url': 'https://video.tv.adobe.com/v/2456/',
'md5': '43662b577c018ad707a63766462b1e87',
'info_dict': {
'id': '2456',
'ext': 'mp4',
'title': 'New experience with Acrobat DC',
'description': 'New experience with Acrobat DC',
'duration': 248.667,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_data = self._parse_json(self._search_regex(
r'var\s+bridge\s*=\s*([^;]+);', webpage, 'bridged data'), video_id)
formats = [{
'format_id': '%s-%s' % (determine_ext(source['src']), source.get('height')),
'url': source['src'],
'width': int_or_none(source.get('width')),
'height': int_or_none(source.get('height')),
'tbr': int_or_none(source.get('bitrate')),
} for source in video_data['sources']]
self._sort_formats(formats)
# For both metadata and downloaded files the duration varies among
# formats. I just pick the max one
duration = max(filter(None, [
float_or_none(source.get('duration'), scale=1000)
for source in video_data['sources']]))
subtitles = {}
for translation in video_data.get('translations', []):
lang_id = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium'])
if lang_id not in subtitles:
subtitles[lang_id] = []
subtitles[lang_id].append({
'url': translation['vttPath'],
'ext': 'vtt',
})
return {
'id': video_id,
'formats': formats,
'title': video_data['title'],
'description': video_data.get('description'),
'thumbnail': video_data['video'].get('poster'),
'duration': duration,
'subtitles': subtitles,
}

142
youtube_dl/extractor/adultswim.py
View File

@ -2,17 +2,15 @@
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from .turner import TurnerBaseIE
from ..utils import (
ExtractorError,
xpath_text,
float_or_none,
int_or_none,
)
class AdultSwimIE(InfoExtractor):
class AdultSwimIE(TurnerBaseIE):
_VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<is_playlist>playlists/)?(?P<show_path>[^/]+)/(?P<episode_path>[^/?#]+)/?'
_TESTS = [{
@ -38,9 +36,11 @@ class AdultSwimIE(InfoExtractor):
},
],
'info_dict': {
'id': 'rQxZvXQ4ROaSOqq-or2Mow',
'title': 'Rick and Morty - Pilot',
'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
}
},
'skip': 'This video is only available for registered users',
}, {
'url': 'http://www.adultswim.com/videos/playlists/american-parenting/putting-francine-out-of-business/',
'playlist': [
@ -55,9 +55,47 @@ class AdultSwimIE(InfoExtractor):
}
],
'info_dict': {
'id': '-t8CamQlQ2aYZ49ItZCFog',
'title': 'American Dad - Putting Francine Out of Business',
'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
},
}, {
'url': 'http://www.adultswim.com/videos/tim-and-eric-awesome-show-great-job/dr-steve-brule-for-your-wine/',
'playlist': [
{
'md5': '3e346a2ab0087d687a05e1e7f3b3e529',
'info_dict': {
'id': 'sY3cMUR_TbuE4YmdjzbIcQ-0',
'ext': 'mp4',
'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
'description': 'Dr. Brule reports live from Wine Country with a special report on wines. \r\nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.\r\n\r\n',
},
}
],
'info_dict': {
'id': 'sY3cMUR_TbuE4YmdjzbIcQ',
'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
'description': 'Dr. Brule reports live from Wine Country with a special report on wines. \r\nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.\r\n\r\n',
},
'params': {
# m3u8 download
'skip_download': True,
}
}, {
# heroMetadata.trailer
'url': 'http://www.adultswim.com/videos/decker/inside-decker-a-new-hero/',
'info_dict': {
'id': 'I0LQFQkaSUaFp8PnAWHhoQ',
'ext': 'mp4',
'title': 'Decker - Inside Decker: A New Hero',
'description': 'md5:c916df071d425d62d70c86d4399d3ee0',
'duration': 249.008,
},
'params': {
# m3u8 download
'skip_download': True,
},
'expected_warnings': ['Unable to download f4m manifest'],
}]
@staticmethod
@ -78,6 +116,7 @@ class AdultSwimIE(InfoExtractor):
for video in collection.get('videos'):
if video.get('slug') == slug:
return collection, video
return None, None
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
@ -88,75 +127,75 @@ class AdultSwimIE(InfoExtractor):
webpage = self._download_webpage(url, episode_path)
# Extract the value of `bootstrappedData` from the Javascript in the page.
bootstrappedDataJS = self._search_regex(r'var bootstrappedData = ({.*});', webpage, episode_path)
try:
bootstrappedData = json.loads(bootstrappedDataJS)
except ValueError as ve:
errmsg = '%s: Failed to parse JSON ' % episode_path
raise ExtractorError(errmsg, cause=ve)
bootstrapped_data = self._parse_json(self._search_regex(
r'var bootstrappedData = ({.*});', webpage, 'bootstraped data'), episode_path)
# Downloading videos from a /videos/playlist/ URL needs to be handled differently.
# NOTE: We are only downloading one video (the current one) not the playlist
if is_playlist:
collections = bootstrappedData['playlists']['collections']
collections = bootstrapped_data['playlists']['collections']
collection = self.find_collection_by_linkURL(collections, show_path)
video_info = self.find_video_info(collection, episode_path)
show_title = video_info['showTitle']
segment_ids = [video_info['videoPlaybackID']]
else:
collections = bootstrappedData['show']['collections']
collections = bootstrapped_data['show']['collections']
collection, video_info = self.find_collection_containing_video(collections, episode_path)
# Video wasn't found in the collections, let's try `slugged_video`.
if video_info is None:
if bootstrapped_data.get('slugged_video', {}).get('slug') == episode_path:
video_info = bootstrapped_data['slugged_video']
if not video_info:
video_info = bootstrapped_data.get(
'heroMetadata', {}).get('trailer', {}).get('video')
if not video_info:
video_info = bootstrapped_data.get('onlineOriginals', [None])[0]
if not video_info:
raise ExtractorError('Unable to find video info')
show = bootstrappedData['show']
show = bootstrapped_data['show']
show_title = show['title']
segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']]
stream = video_info.get('stream')
if stream and stream.get('videoPlaybackID'):
segment_ids = [stream['videoPlaybackID']]
elif video_info.get('clips'):
segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']]
elif video_info.get('videoPlaybackID'):
segment_ids = [video_info['videoPlaybackID']]
else:
if video_info.get('auth') is True:
raise ExtractorError(
'This video is only available via cable service provider subscription that'
' is not currently supported. You may want to use --cookies.', expected=True)
else:
raise ExtractorError('Unable to find stream or clips')
episode_id = video_info['id']
episode_title = video_info['title']
episode_description = video_info['description']
episode_duration = video_info.get('duration')
episode_description = video_info.get('description')
episode_duration = int_or_none(video_info.get('duration'))
view_count = int_or_none(video_info.get('views'))
entries = []
for part_num, segment_id in enumerate(segment_ids):
segment_url = 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=mobile' % segment_id
segement_info = self._extract_cvp_info(
'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=desktop' % segment_id,
segment_id, {
'secure': {
'media_src': 'http://androidhls-secure.cdn.turner.com/adultswim/big',
'tokenizer_src': 'http://www.adultswim.com/astv/mvpd/processors/services/token_ipadAdobe.do',
},
})
segment_title = '%s - %s' % (show_title, episode_title)
if len(segment_ids) > 1:
segment_title += ' Part %d' % (part_num + 1)
idoc = self._download_xml(
segment_url, segment_title,
'Downloading segment information', 'Unable to download segment information')
segment_duration = float_or_none(
xpath_text(idoc, './/trt', 'segment duration').strip())
formats = []
file_els = idoc.findall('.//files/file')
for file_el in file_els:
bitrate = file_el.attrib.get('bitrate')
ftype = file_el.attrib.get('type')
formats.append({
'format_id': '%s_%s' % (bitrate, ftype),
'url': file_el.text.strip(),
# The bitrate may not be a number (for example: 'iphone')
'tbr': int(bitrate) if bitrate.isdigit() else None,
'quality': 1 if ftype == 'hd' else -1
})
self._sort_formats(formats)
entries.append({
segement_info.update({
'id': segment_id,
'title': segment_title,
'formats': formats,
'duration': segment_duration,
'description': episode_description
'description': episode_description,
})
entries.append(segement_info)
return {
'_type': 'playlist',
@ -165,5 +204,6 @@ class AdultSwimIE(InfoExtractor):
'entries': entries,
'title': '%s - %s' % (show_title, episode_title),
'description': episode_description,
'duration': episode_duration
'duration': episode_duration,
'view_count': view_count,
}

208
youtube_dl/extractor/aenetworks.py Normal file
View File

@ -0,0 +1,208 @@
from __future__ import unicode_literals
import re
from .theplatform import ThePlatformIE
from ..utils import (
smuggle_url,
update_url_query,
unescapeHTML,
extract_attributes,
get_element_by_attribute,
)
from ..compat import (
compat_urlparse,
)
class AENetworksBaseIE(ThePlatformIE):
_THEPLATFORM_KEY = 'crazyjava'
_THEPLATFORM_SECRET = 's3cr3t'
class AENetworksIE(AENetworksBaseIE):
IE_NAME = 'aenetworks'
IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network'
_VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?:shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|movies/(?P<movie_display_id>[^/]+)/full-movie)'
_TESTS = [{
'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
'md5': '8ff93eb073449f151d6b90c0ae1ef0c7',
'info_dict': {
'id': '22253814',
'ext': 'mp4',
'title': 'Winter Is Coming',
'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
'timestamp': 1338306241,
'upload_date': '20120529',
'uploader': 'AENE-NEW',
},
'add_ie': ['ThePlatform'],
}, {
'url': 'http://www.history.com/shows/ancient-aliens/season-1',
'info_dict': {
'id': '71889446852',
},
'playlist_mincount': 5,
}, {
'url': 'http://www.mylifetime.com/shows/atlanta-plastic',
'info_dict': {
'id': 'SERIES4317',
'title': 'Atlanta Plastic',
},
'playlist_mincount': 2,
}, {
'url': 'http://www.aetv.com/shows/duck-dynasty/season-9/episode-1',
'only_matching': True
}, {
'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8',
'only_matching': True
}, {
'url': 'http://www.mylifetime.com/shows/project-runway-junior/season-1/episode-6',
'only_matching': True
}, {
'url': 'http://www.mylifetime.com/movies/center-stage-on-pointe/full-movie',
'only_matching': True
}]
_DOMAIN_TO_REQUESTOR_ID = {
'history.com': 'HISTORY',
'aetv.com': 'AETV',
'mylifetime.com': 'LIFETIME',
'fyi.tv': 'FYI',
}
def _real_extract(self, url):
domain, show_path, movie_display_id = re.match(self._VALID_URL, url).groups()
display_id = show_path or movie_display_id
webpage = self._download_webpage(url, display_id)
if show_path:
url_parts = show_path.split('/')
url_parts_len = len(url_parts)
if url_parts_len == 1:
entries = []
for season_url_path in re.findall(r'(?s)<li[^>]+data-href="(/shows/%s/season-\d+)"' % url_parts[0], webpage):
entries.append(self.url_result(
compat_urlparse.urljoin(url, season_url_path), 'AENetworks'))
return self.playlist_result(
entries, self._html_search_meta('aetn:SeriesId', webpage),
self._html_search_meta('aetn:SeriesTitle', webpage))
elif url_parts_len == 2:
entries = []
for episode_item in re.findall(r'(?s)<div[^>]+class="[^"]*episode-item[^"]*"[^>]*>', webpage):
episode_attributes = extract_attributes(episode_item)
episode_url = compat_urlparse.urljoin(
url, episode_attributes['data-canonical'])
entries.append(self.url_result(
episode_url, 'AENetworks',
episode_attributes['data-videoid']))
return self.playlist_result(
entries, self._html_search_meta('aetn:SeasonId', webpage))
query = {
'mbr': 'true',
'assetTypes': 'medium_video_s3'
}
video_id = self._html_search_meta('aetn:VideoID', webpage)
media_url = self._search_regex(
r"media_url\s*=\s*'([^']+)'", webpage, 'video url')
theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
r'https?://link.theplatform.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
info = self._parse_theplatform_metadata(theplatform_metadata)
if theplatform_metadata.get('AETN$isBehindWall'):
requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain]
resource = self._get_mvpd_resource(
requestor_id, theplatform_metadata['title'],
theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
theplatform_metadata['ratings'][0]['rating'])
query['auth'] = self._extract_mvpd_auth(
url, video_id, requestor_id, resource)
info.update(self._search_json_ld(webpage, video_id, fatal=False))
media_url = update_url_query(media_url, query)
media_url = self._sign_url(media_url, self._THEPLATFORM_KEY, self._THEPLATFORM_SECRET)
formats, subtitles = self._extract_theplatform_smil(media_url, video_id)
self._sort_formats(formats)
info.update({
'id': video_id,
'formats': formats,
'subtitles': subtitles,
})
return info
class HistoryTopicIE(AENetworksBaseIE):
IE_NAME = 'history:topic'
IE_DESC = 'History.com Topic'
_VALID_URL = r'https?://(?:www\.)?history\.com/topics/(?:[^/]+/)?(?P<topic_id>[^/]+)(?:/[^/]+(?:/(?P<video_display_id>[^/?#]+))?)?'
_TESTS = [{
'url': 'http://www.history.com/topics/valentines-day/history-of-valentines-day/videos/bet-you-didnt-know-valentines-day?m=528e394da93ae&s=undefined&f=1&free=false',
'info_dict': {
'id': '40700995724',
'ext': 'mp4',
'title': "Bet You Didn't Know: Valentine's Day",
'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
'timestamp': 1375819729,
'upload_date': '20130806',
'uploader': 'AENE-NEW',
},
'params': {
# m3u8 download
'skip_download': True,
},
'add_ie': ['ThePlatform'],
}, {
'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/videos',
'info_dict':
{
'id': 'world-war-i-history',
'title': 'World War I History',
},
'playlist_mincount': 24,
}, {
'url': 'http://www.history.com/topics/world-war-i-history/videos',
'only_matching': True,
}, {
'url': 'http://www.history.com/topics/world-war-i/world-war-i-history',
'only_matching': True,
}, {
'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/speeches',
'only_matching': True,
}]
def theplatform_url_result(self, theplatform_url, video_id, query):
return {
'_type': 'url_transparent',
'id': video_id,
'url': smuggle_url(
update_url_query(theplatform_url, query),
{
'sig': {
'key': self._THEPLATFORM_KEY,
'secret': self._THEPLATFORM_SECRET,
},
'force_smil_url': True
}),
'ie_key': 'ThePlatform',
}
def _real_extract(self, url):
topic_id, video_display_id = re.match(self._VALID_URL, url).groups()
if video_display_id:
webpage = self._download_webpage(url, video_display_id)
release_url, video_id = re.search(r"_videoPlayer.play\('([^']+)'\s*,\s*'[^']+'\s*,\s*'(\d+)'\)", webpage).groups()
release_url = unescapeHTML(release_url)
return self.theplatform_url_result(
release_url, video_id, {
'mbr': 'true',
'switch': 'hls'
})
else:
webpage = self._download_webpage(url, topic_id)
entries = []
for episode_item in re.findall(r'<a.+?data-release-url="[^"]+"[^>]*>', webpage):
video_attributes = extract_attributes(episode_item)
entries.append(self.theplatform_url_result(
video_attributes['data-release-url'], video_attributes['data-id'], {
'mbr': 'true',
'switch': 'hls'
}))
return self.playlist_result(entries, topic_id, get_element_by_attribute('class', 'show-title', webpage))

133
youtube_dl/extractor/afreecatv.py Normal file
View File

@ -0,0 +1,133 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlparse,
compat_urlparse,
)
from ..utils import (
ExtractorError,
int_or_none,
xpath_element,
xpath_text,
)
class AfreecaTVIE(InfoExtractor):
IE_DESC = 'afreecatv.com'
_VALID_URL = r'''(?x)^
https?://(?:(live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)?
(?:
/app/(?:index|read_ucc_bbs)\.cgi|
/player/[Pp]layer\.(?:swf|html))
\?.*?\bnTitleNo=(?P<id>\d+)'''
_TESTS = [{
'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=',
'md5': 'f72c89fe7ecc14c1b5ce506c4996046e',
'info_dict': {
'id': '36164052',
'ext': 'mp4',
'title': '데일리 에이프릴 요정들의 시상식!',
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': 'dailyapril',
'uploader_id': 'dailyapril',
'upload_date': '20160503',
}
}, {
'url': 'http://afbbs.afreecatv.com:8080/app/read_ucc_bbs.cgi?nStationNo=16711924&nTitleNo=36153164&szBjId=dailyapril&nBbsNo=18605867',
'info_dict': {
'id': '36153164',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': 'dailyapril',
'uploader_id': 'dailyapril',
},
'playlist_count': 2,
'playlist': [{
'md5': 'd8b7c174568da61d774ef0203159bf97',
'info_dict': {
'id': '36153164_1',
'ext': 'mp4',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
'upload_date': '20160502',
},
}, {
'md5': '58f2ce7f6044e34439ab2d50612ab02b',
'info_dict': {
'id': '36153164_2',
'ext': 'mp4',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
'upload_date': '20160502',
},
}],
}, {
'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652',
'only_matching': True,
}]
@staticmethod
def parse_video_key(key):
video_key = {}
m = re.match(r'^(?P<upload_date>\d{8})_\w+_(?P<part>\d+)$', key)
if m:
video_key['upload_date'] = m.group('upload_date')
video_key['part'] = m.group('part')
return video_key
def _real_extract(self, url):
video_id = self._match_id(url)
parsed_url = compat_urllib_parse_urlparse(url)
info_url = compat_urlparse.urlunparse(parsed_url._replace(
netloc='afbbs.afreecatv.com:8080',
path='/api/video/get_video_info.php'))
video_xml = self._download_xml(info_url, video_id)
if xpath_element(video_xml, './track/video/file') is None:
raise ExtractorError('Specified AfreecaTV video does not exist',
expected=True)
title = xpath_text(video_xml, './track/title', 'title')
uploader = xpath_text(video_xml, './track/nickname', 'uploader')
uploader_id = xpath_text(video_xml, './track/bj_id', 'uploader id')
duration = int_or_none(xpath_text(video_xml, './track/duration',
'duration'))
thumbnail = xpath_text(video_xml, './track/titleImage', 'thumbnail')
entries = []
for i, video_file in enumerate(video_xml.findall('./track/video/file')):
video_key = self.parse_video_key(video_file.get('key', ''))
if not video_key:
continue
entries.append({
'id': '%s_%s' % (video_id, video_key.get('part', i + 1)),
'title': title,
'upload_date': video_key.get('upload_date'),
'duration': int_or_none(video_file.get('duration')),
'url': video_file.text,
})
info = {
'id': video_id,
'title': title,
'uploader': uploader,
'uploader_id': uploader_id,
'duration': duration,
'thumbnail': thumbnail,
}
if len(entries) > 1:
info['_type'] = 'multi_video'
info['entries'] = entries
elif len(entries) == 1:
info['url'] = entries[0]['url']
info['upload_date'] = entries[0].get('upload_date')
else:
raise ExtractorError(
'No files found for the specified AfreecaTV video, either'
' the URL is incorrect or the video has been made private.',
expected=True)
return info

66
youtube_dl/extractor/aftonbladet.py
View File

@ -1,66 +0,0 @@
# encoding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class AftonbladetIE(InfoExtractor):
_VALID_URL = r'^http://tv\.aftonbladet\.se/webbtv.+?(?P<video_id>article[0-9]+)\.ab(?:$|[?#])'
_TEST = {
'url': 'http://tv.aftonbladet.se/webbtv/nyheter/vetenskap/rymden/article36015.ab',
'info_dict': {
'id': 'article36015',
'ext': 'mp4',
'title': 'Vulkanutbrott i rymden - nu släpper NASA bilderna',
'description': 'Jupiters måne mest aktiv av alla himlakroppar',
'timestamp': 1394142732,
'upload_date': '20140306',
},
}
def _real_extract(self, url):
mobj = re.search(self._VALID_URL, url)
video_id = mobj.group('video_id')
webpage = self._download_webpage(url, video_id)
# find internal video meta data
meta_url = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json'
internal_meta_id = self._html_search_regex(
r'data-aptomaId="([\w\d]+)"', webpage, 'internal_meta_id')
internal_meta_url = meta_url % internal_meta_id
internal_meta_json = self._download_json(
internal_meta_url, video_id, 'Downloading video meta data')
# find internal video formats
format_url = 'http://aftonbladet-play.videodata.drvideo.aptoma.no/actions/video/?id=%s'
internal_video_id = internal_meta_json['videoId']
internal_formats_url = format_url % internal_video_id
internal_formats_json = self._download_json(
internal_formats_url, video_id, 'Downloading video formats')
formats = []
for fmt in internal_formats_json['formats']['http']['pseudostreaming']['mp4']:
p = fmt['paths'][0]
formats.append({
'url': 'http://%s:%d/%s/%s' % (p['address'], p['port'], p['path'], p['filename']),
'ext': 'mp4',
'width': fmt['width'],
'height': fmt['height'],
'tbr': fmt['bitrate'],
'protocol': 'http',
})
self._sort_formats(formats)
return {
'id': video_id,
'title': internal_meta_json['title'],
'formats': formats,
'thumbnail': internal_meta_json['imageUrl'],
'description': internal_meta_json['shortPreamble'],
'timestamp': internal_meta_json['timePublished'],
'duration': internal_meta_json['duration'],
'view_count': internal_meta_json['views'],
}

74
youtube_dl/extractor/airmozilla.py Normal file
View File

@ -0,0 +1,74 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_duration,
parse_iso8601,
)
class AirMozillaIE(InfoExtractor):
_VALID_URL = r'https?://air\.mozilla\.org/(?P<id>[0-9a-z-]+)/?'
_TEST = {
'url': 'https://air.mozilla.org/privacy-lab-a-meetup-for-privacy-minded-people-in-san-francisco/',
'md5': '2e3e7486ba5d180e829d453875b9b8bf',
'info_dict': {
'id': '6x4q2w',
'ext': 'mp4',
'title': 'Privacy Lab - a meetup for privacy minded people in San Francisco',
'thumbnail': 're:https?://vid\.ly/(?P<id>[0-9a-z-]+)/poster',
'description': 'Brings together privacy professionals and others interested in privacy at for-profits, non-profits, and NGOs in an effort to contribute to the state of the ecosystem...',
'timestamp': 1422487800,
'upload_date': '20150128',
'location': 'SFO Commons',
'duration': 3780,
'view_count': int,
'categories': ['Main', 'Privacy'],
}
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._html_search_regex(r'//vid.ly/(.*?)/embed', webpage, 'id')
embed_script = self._download_webpage('https://vid.ly/{0}/embed'.format(video_id), video_id)
jwconfig = self._search_regex(r'\svar jwconfig = (\{.*?\});\s', embed_script, 'metadata')
metadata = self._parse_json(jwconfig, video_id)
formats = [{
'url': source['file'],
'ext': source['type'],
'format_id': self._search_regex(r'&format=(.*)$', source['file'], 'video format'),
'format': source['label'],
'height': int(source['label'].rstrip('p')),
} for source in metadata['playlist'][0]['sources']]
self._sort_formats(formats)
view_count = int_or_none(self._html_search_regex(
r'Views since archived: ([0-9]+)',
webpage, 'view count', fatal=False))
timestamp = parse_iso8601(self._html_search_regex(
r'<time datetime="(.*?)"', webpage, 'timestamp', fatal=False))
duration = parse_duration(self._search_regex(
r'Duration:\s*(\d+\s*hours?\s*\d+\s*minutes?)',
webpage, 'duration', fatal=False))
return {
'id': video_id,
'title': self._og_search_title(webpage),
'formats': formats,
'url': self._og_search_url(webpage),
'display_id': display_id,
'thumbnail': metadata['playlist'][0].get('image'),
'description': self._og_search_description(webpage),
'timestamp': timestamp,
'location': self._html_search_regex(r'Location: (.*)', webpage, 'location', default=None),
'duration': duration,
'view_count': view_count,
'categories': re.findall(r'<a href=".*?" class="channel">(.*?)</a>', webpage),
}

21
youtube_dl/extractor/aljazeera.py
View File

@ -4,7 +4,7 @@ from .common import InfoExtractor
class AlJazeeraIE(InfoExtractor):
_VALID_URL = r'http://www\.aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html'
_VALID_URL = r'https?://(?:www\.)?aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html'
_TEST = {
'url': 'http://www.aljazeera.com/programmes/the-slum/2014/08/deliverance-201482883754237240.html',
@ -13,23 +13,18 @@ class AlJazeeraIE(InfoExtractor):
'ext': 'mp4',
'title': 'The Slum - Episode 1: Deliverance',
'description': 'As a birth attendant advocating for family planning, Remy is on the frontline of Tondo\'s battle with overcrowding.',
'uploader': 'Al Jazeera English',
'uploader_id': '665003303001',
'timestamp': 1411116829,
'upload_date': '20140919',
},
'add_ie': ['Brightcove'],
'add_ie': ['BrightcoveNew'],
'skip': 'Not accessible from Travis CI server',
}
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/665003303001/default_default/index.html?videoId=%s'
def _real_extract(self, url):
program_name = self._match_id(url)
webpage = self._download_webpage(url, program_name)
brightcove_id = self._search_regex(
r'RenderPagesVideo\(\'(.+?)\'', webpage, 'brightcove id')
return {
'_type': 'url',
'url': (
'brightcove:'
'playerKey=AQ~~%2CAAAAmtVJIFk~%2CTVGOQ5ZTwJbeMWnq5d_H4MOM57xfzApc'
'&%40videoPlayer={0}'.format(brightcove_id)
),
'ie_key': 'Brightcove',
}
return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)

20
youtube_dl/extractor/allocine.py
View File

@ -8,6 +8,8 @@ from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
qualities,
unescapeHTML,
xpath_element,
)
@ -31,7 +33,7 @@ class AllocineIE(InfoExtractor):
'id': '19540403',
'ext': 'mp4',
'title': 'Planes 2 Bande-annonce VF',
'description': 'md5:eeaffe7c2d634525e21159b93acf3b1e',
'description': 'Regardez la bande annonce du film Planes 2 (Planes 2 Bande-annonce VF). Planes 2, un film de Roberts Gannaway',
'thumbnail': 're:http://.*\.jpg',
},
}, {
@ -41,7 +43,7 @@ class AllocineIE(InfoExtractor):
'id': '19544709',
'ext': 'mp4',
'title': 'Dragons 2 - Bande annonce finale VF',
'description': 'md5:71742e3a74b0d692c7fce0dd2017a4ac',
'description': 'md5:601d15393ac40f249648ef000720e7e3',
'thumbnail': 're:http://.*\.jpg',
},
}, {
@ -59,14 +61,18 @@ class AllocineIE(InfoExtractor):
if typ == 'film':
video_id = self._search_regex(r'href="/video/player_gen_cmedia=([0-9]+).+"', webpage, 'video id')
else:
player = self._search_regex(r'data-player=\'([^\']+)\'>', webpage, 'data player')
player_data = json.loads(player)
video_id = compat_str(player_data['refMedia'])
player = self._search_regex(r'data-player=\'([^\']+)\'>', webpage, 'data player', default=None)
if player:
player_data = json.loads(player)
video_id = compat_str(player_data['refMedia'])
else:
model = self._search_regex(r'data-model="([^"]+)">', webpage, 'data model')
model_data = self._parse_json(unescapeHTML(model), display_id)
video_id = compat_str(model_data['id'])
xml = self._download_xml('http://www.allocine.fr/ws/AcVisiondataV4.ashx?media=%s' % video_id, display_id)
video = xml.find('.//AcVisionVideo').attrib
video = xpath_element(xml, './/AcVisionVideo').attrib
quality = qualities(['ld', 'md', 'hd'])
formats = []

92
youtube_dl/extractor/amcnetworks.py Normal file
View File

@ -0,0 +1,92 @@
# coding: utf-8
from __future__ import unicode_literals
from .theplatform import ThePlatformIE
from ..utils import (
update_url_query,
parse_age_limit,
int_or_none,
)
class AMCNetworksIE(ThePlatformIE):
_VALID_URL = r'https?://(?:www\.)?(?:amc|bbcamerica|ifc|wetv)\.com/(?:movies/|shows/[^/]+/(?:full-episodes/)?season-\d+/episode-\d+(?:-(?:[^/]+/)?|/))(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'http://www.ifc.com/shows/maron/season-04/episode-01/step-1',
'md5': '',
'info_dict': {
'id': 's3MX01Nl4vPH',
'ext': 'mp4',
'title': 'Maron - Season 4 - Step 1',
'description': 'In denial about his current situation, Marc is reluctantly convinced by his friends to enter rehab. Starring Marc Maron and Constance Zimmer.',
'age_limit': 17,
'upload_date': '20160505',
'timestamp': 1462468831,
'uploader': 'AMCN',
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': 'Requires TV provider accounts',
}, {
'url': 'http://www.bbcamerica.com/shows/the-hunt/full-episodes/season-1/episode-01-the-hardest-challenge',
'only_matching': True,
}, {
'url': 'http://www.amc.com/shows/preacher/full-episodes/season-01/episode-00/pilot',
'only_matching': True,
}, {
'url': 'http://www.wetv.com/shows/million-dollar-matchmaker/season-01/episode-06-the-dumped-dj-and-shallow-hal',
'only_matching': True,
}, {
'url': 'http://www.ifc.com/movies/chaos',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
query = {
'mbr': 'true',
'manifest': 'm3u',
}
media_url = self._search_regex(r'window\.platformLinkURL\s*=\s*[\'"]([^\'"]+)', webpage, 'media url')
theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
r'https?://link.theplatform.com/s/([^?]+)', media_url, 'theplatform_path'), display_id)
info = self._parse_theplatform_metadata(theplatform_metadata)
video_id = theplatform_metadata['pid']
title = theplatform_metadata['title']
rating = theplatform_metadata['ratings'][0]['rating']
auth_required = self._search_regex(r'window\.authRequired\s*=\s*(true|false);', webpage, 'auth required')
if auth_required == 'true':
requestor_id = self._search_regex(r'window\.requestor_id\s*=\s*[\'"]([^\'"]+)', webpage, 'requestor id')
resource = self._get_mvpd_resource(requestor_id, title, video_id, rating)
query['auth'] = self._extract_mvpd_auth(url, video_id, requestor_id, resource)
media_url = update_url_query(media_url, query)
formats, subtitles = self._extract_theplatform_smil(media_url, video_id)
self._sort_formats(formats)
info.update({
'id': video_id,
'subtitles': subtitles,
'formats': formats,
'age_limit': parse_age_limit(parse_age_limit(rating)),
})
ns_keys = theplatform_metadata.get('$xmlns', {}).keys()
if ns_keys:
ns = list(ns_keys)[0]
series = theplatform_metadata.get(ns + '$show')
season_number = int_or_none(theplatform_metadata.get(ns + '$season'))
episode = theplatform_metadata.get(ns + '$episodeTitle')
episode_number = int_or_none(theplatform_metadata.get(ns + '$episode'))
if season_number:
title = 'Season %d - %s' % (season_number, title)
if series:
title = '%s - %s' % (series, title)
info.update({
'title': title,
'series': series,
'season_number': season_number,
'episode': episode,
'episode_number': episode_number,
})
return info

89
youtube_dl/extractor/amp.py Normal file
View File

@ -0,0 +1,89 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_iso8601,
mimetype2ext,
determine_ext,
)
class AMPIE(InfoExtractor):
# parse Akamai Adaptive Media Player feed
def _extract_feed_info(self, url):
item = self._download_json(
url, None, 'Downloading Akamai AMP feed',
'Unable to download Akamai AMP feed')['channel']['item']
video_id = item['guid']
def get_media_node(name, default=None):
media_name = 'media-%s' % name
media_group = item.get('media-group') or item
return media_group.get(media_name) or item.get(media_name) or item.get(name, default)
thumbnails = []
media_thumbnail = get_media_node('thumbnail')
if media_thumbnail:
if isinstance(media_thumbnail, dict):
media_thumbnail = [media_thumbnail]
for thumbnail_data in media_thumbnail:
thumbnail = thumbnail_data['@attributes']
thumbnails.append({
'url': self._proto_relative_url(thumbnail['url'], 'http:'),
'width': int_or_none(thumbnail.get('width')),
'height': int_or_none(thumbnail.get('height')),
})
subtitles = {}
media_subtitle = get_media_node('subTitle')
if media_subtitle:
if isinstance(media_subtitle, dict):
media_subtitle = [media_subtitle]
for subtitle_data in media_subtitle:
subtitle = subtitle_data['@attributes']
lang = subtitle.get('lang') or 'en'
subtitles[lang] = [{'url': subtitle['href']}]
formats = []
media_content = get_media_node('content')
if isinstance(media_content, dict):
media_content = [media_content]
for media_data in media_content:
media = media_data.get('@attributes', {})
media_url = media.get('url')
if not media_url:
continue
ext = mimetype2ext(media.get('type')) or determine_ext(media_url)
if ext == 'f4m':
formats.extend(self._extract_f4m_formats(
media_url + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124',
video_id, f4m_id='hds', fatal=False))
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
media_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
else:
formats.append({
'format_id': media_data.get('media-category', {}).get('@attributes', {}).get('label'),
'url': media['url'],
'tbr': int_or_none(media.get('bitrate')),
'filesize': int_or_none(media.get('fileSize')),
'ext': ext,
})
self._sort_formats(formats)
timestamp = parse_iso8601(item.get('pubDate'), ' ') or parse_iso8601(item.get('dc-date'))
return {
'id': video_id,
'title': get_media_node('title'),
'description': get_media_node('description'),
'thumbnails': thumbnails,
'timestamp': timestamp,
'duration': int_or_none(media_content[0].get('@attributes', {}).get('duration')),
'subtitles': subtitles,
'formats': formats,
}

270
youtube_dl/extractor/animeondemand.py Normal file
View File

@ -0,0 +1,270 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_urlparse,
compat_str,
)
from ..utils import (
determine_ext,
extract_attributes,
ExtractorError,
sanitized_Request,
urlencode_postdata,
)
class AnimeOnDemandIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?anime-on-demand\.de/anime/(?P<id>\d+)'
_LOGIN_URL = 'https://www.anime-on-demand.de/users/sign_in'
_APPLY_HTML5_URL = 'https://www.anime-on-demand.de/html5apply'
_NETRC_MACHINE = 'animeondemand'
_TESTS = [{
# jap, OmU
'url': 'https://www.anime-on-demand.de/anime/161',
'info_dict': {
'id': '161',
'title': 'Grimgar, Ashes and Illusions (OmU)',
'description': 'md5:6681ce3c07c7189d255ac6ab23812d31',
},
'playlist_mincount': 4,
}, {
# Film wording is used instead of Episode, ger/jap, Dub/OmU
'url': 'https://www.anime-on-demand.de/anime/39',
'only_matching': True,
}, {
# Episodes without titles, jap, OmU
'url': 'https://www.anime-on-demand.de/anime/162',
'only_matching': True,
}, {
# ger/jap, Dub/OmU, account required
'url': 'https://www.anime-on-demand.de/anime/169',
'only_matching': True,
}, {
# Full length film, non-series, ger/jap, Dub/OmU, account required
'url': 'https://www.anime-on-demand.de/anime/185',
'only_matching': True,
}]
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
login_page = self._download_webpage(
self._LOGIN_URL, None, 'Downloading login page')
if '>Our licensing terms allow the distribution of animes only to German-speaking countries of Europe' in login_page:
self.raise_geo_restricted(
'%s is only available in German-speaking countries of Europe' % self.IE_NAME)
login_form = self._form_hidden_inputs('new_user', login_page)
login_form.update({
'user[login]': username,
'user[password]': password,
})
post_url = self._search_regex(
r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
'post url', default=self._LOGIN_URL, group='url')
if not post_url.startswith('http'):
post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
request = sanitized_Request(
post_url, urlencode_postdata(login_form))
request.add_header('Referer', self._LOGIN_URL)
response = self._download_webpage(
request, None, 'Logging in as %s' % username)
if all(p not in response for p in ('>Logout<', 'href="/users/sign_out"')):
error = self._search_regex(
r'<p class="alert alert-danger">(.+?)</p>',
response, 'error', default=None)
if error:
raise ExtractorError('Unable to login: %s' % error, expected=True)
raise ExtractorError('Unable to log in')
def _real_initialize(self):
self._login()
def _real_extract(self, url):
anime_id = self._match_id(url)
webpage = self._download_webpage(url, anime_id)
if 'data-playlist=' not in webpage:
self._download_webpage(
self._APPLY_HTML5_URL, anime_id,
'Activating HTML5 beta', 'Unable to apply HTML5 beta')
webpage = self._download_webpage(url, anime_id)
csrf_token = self._html_search_meta(
'csrf-token', webpage, 'csrf token', fatal=True)
anime_title = self._html_search_regex(
r'(?s)<h1[^>]+itemprop="name"[^>]*>(.+?)</h1>',
webpage, 'anime name')
anime_description = self._html_search_regex(
r'(?s)<div[^>]+itemprop="description"[^>]*>(.+?)</div>',
webpage, 'anime description', default=None)
entries = []
def extract_info(html, video_id, num=None):
title, description = [None] * 2
formats = []
for input_ in re.findall(
r'<input[^>]+class=["\'].*?streamstarter_html5[^>]+>', html):
attributes = extract_attributes(input_)
playlist_urls = []
for playlist_key in ('data-playlist', 'data-otherplaylist'):
playlist_url = attributes.get(playlist_key)
if isinstance(playlist_url, compat_str) and re.match(
r'/?[\da-zA-Z]+', playlist_url):
playlist_urls.append(attributes[playlist_key])
if not playlist_urls:
continue
lang = attributes.get('data-lang')
lang_note = attributes.get('value')
for playlist_url in playlist_urls:
kind = self._search_regex(
r'videomaterialurl/\d+/([^/]+)/',
playlist_url, 'media kind', default=None)
format_id_list = []
if lang:
format_id_list.append(lang)
if kind:
format_id_list.append(kind)
if not format_id_list and num is not None:
format_id_list.append(compat_str(num))
format_id = '-'.join(format_id_list)
format_note = ', '.join(filter(None, (kind, lang_note)))
request = sanitized_Request(
compat_urlparse.urljoin(url, playlist_url),
headers={
'X-Requested-With': 'XMLHttpRequest',
'X-CSRF-Token': csrf_token,
'Referer': url,
'Accept': 'application/json, text/javascript, */*; q=0.01',
})
playlist = self._download_json(
request, video_id, 'Downloading %s playlist JSON' % format_id,
fatal=False)
if not playlist:
continue
start_video = playlist.get('startvideo', 0)
playlist = playlist.get('playlist')
if not playlist or not isinstance(playlist, list):
continue
playlist = playlist[start_video]
title = playlist.get('title')
if not title:
continue
description = playlist.get('description')
for source in playlist.get('sources', []):
file_ = source.get('file')
if not file_:
continue
ext = determine_ext(file_)
format_id_list = [lang, kind]
if ext == 'm3u8':
format_id_list.append('hls')
elif source.get('type') == 'video/dash' or ext == 'mpd':
format_id_list.append('dash')
format_id = '-'.join(filter(None, format_id_list))
if ext == 'm3u8':
file_formats = self._extract_m3u8_formats(
file_, video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id=format_id, fatal=False)
elif source.get('type') == 'video/dash' or ext == 'mpd':
continue
file_formats = self._extract_mpd_formats(
file_, video_id, mpd_id=format_id, fatal=False)
else:
continue
for f in file_formats:
f.update({
'language': lang,
'format_note': format_note,
})
formats.extend(file_formats)
return {
'title': title,
'description': description,
'formats': formats,
}
def extract_entries(html, video_id, common_info, num=None):
info = extract_info(html, video_id, num)
if info['formats']:
self._sort_formats(info['formats'])
f = common_info.copy()
f.update(info)
entries.append(f)
# Extract teaser/trailer only when full episode is not available
if not info['formats']:
m = re.search(
r'data-dialog-header=(["\'])(?P<title>.+?)\1[^>]+href=(["\'])(?P<href>.+?)\3[^>]*>(?P<kind>Teaser|Trailer)<',
html)
if m:
f = common_info.copy()
f.update({
'id': '%s-%s' % (f['id'], m.group('kind').lower()),
'title': m.group('title'),
'url': compat_urlparse.urljoin(url, m.group('href')),
})
entries.append(f)
def extract_episodes(html):
for num, episode_html in enumerate(re.findall(
r'(?s)<h3[^>]+class="episodebox-title".+?>Episodeninhalt<', html), 1):
episodebox_title = self._search_regex(
(r'class="episodebox-title"[^>]+title=(["\'])(?P<title>.+?)\1',
r'class="episodebox-title"[^>]+>(?P<title>.+?)<'),
episode_html, 'episodebox title', default=None, group='title')
if not episodebox_title:
continue
episode_number = int(self._search_regex(
r'(?:Episode|Film)\s*(\d+)',
episodebox_title, 'episode number', default=num))
episode_title = self._search_regex(
r'(?:Episode|Film)\s*\d+\s*-\s*(.+)',
episodebox_title, 'episode title', default=None)
video_id = 'episode-%d' % episode_number
common_info = {
'id': video_id,
'series': anime_title,
'episode': episode_title,
'episode_number': episode_number,
}
extract_entries(episode_html, video_id, common_info)
def extract_film(html, video_id):
common_info = {
'id': anime_id,
'title': anime_title,
'description': anime_description,
}
extract_entries(html, video_id, common_info)
extract_episodes(webpage)
if not entries:
extract_film(webpage, anime_id)
return self.playlist_result(entries, anime_id, anime_title, anime_description)

43
youtube_dl/extractor/anitube.py
View File

@ -1,11 +1,9 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .nuevo import NuevoBaseIE
class AnitubeIE(InfoExtractor):
class AnitubeIE(NuevoBaseIE):
IE_NAME = 'anitube.se'
_VALID_URL = r'https?://(?:www\.)?anitube\.se/video/(?P<id>\d+)'
@ -22,38 +20,11 @@ class AnitubeIE(InfoExtractor):
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
key = self._html_search_regex(
r'http://www\.anitube\.se/embed/([A-Za-z0-9_-]*)', webpage, 'key')
key = self._search_regex(
r'src=["\']https?://[^/]+/embed/([A-Za-z0-9_-]+)', webpage, 'key')
config_xml = self._download_xml(
'http://www.anitube.se/nuevo/econfig.php?key=%s' % key, key)
video_title = config_xml.find('title').text
thumbnail = config_xml.find('image').text
duration = float(config_xml.find('duration').text)
formats = []
video_url = config_xml.find('file')
if video_url is not None:
formats.append({
'format_id': 'sd',
'url': video_url.text,
})
video_url = config_xml.find('filehd')
if video_url is not None:
formats.append({
'format_id': 'hd',
'url': video_url.text,
})
return {
'id': video_id,
'title': video_title,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats
}
return self._extract_nuevo(
'http://www.anitube.se/nuevo/econfig.php?key=%s' % key, video_id)

224
youtube_dl/extractor/anvato.py Normal file
View File

@ -0,0 +1,224 @@
# coding: utf-8
from __future__ import unicode_literals
import base64
import hashlib
import json
import random
import time
from .common import InfoExtractor
from ..aes import aes_encrypt
from ..compat import compat_str
from ..utils import (
bytes_to_intlist,
determine_ext,
intlist_to_bytes,
int_or_none,
strip_jsonp,
)
def md5_text(s):
if not isinstance(s, compat_str):
s = compat_str(s)
return hashlib.md5(s.encode('utf-8')).hexdigest()
class AnvatoIE(InfoExtractor):
# Copied from anvplayer.min.js
_ANVACK_TABLE = {
'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ',
'nbcu_nbcd_desktop_web_qa_1a6f01bdd0dc45a439043b694c8a031d': 'eSxJUbA2UUKBTXryyQ2d6NuM8oEqaPySvaPzfKNA',
'nbcu_nbcd_desktop_web_acc_eb2ff240a5d4ae9a63d4c297c32716b6c523a129': '89JR3RtUGbvKuuJIiKOMK0SoarLb5MUx8v89RcbP',
'nbcu_nbcd_watchvod_web_prod_e61107507180976724ec8e8319fe24ba5b4b60e1': 'Uc7dFt7MJ9GsBWB5T7iPvLaMSOt8BBxv4hAXk5vv',
'nbcu_nbcd_watchvod_web_qa_42afedba88a36203db5a4c09a5ba29d045302232': 'T12oDYVFP2IaFvxkmYMy5dKxswpLHtGZa4ZAXEi7',
'nbcu_nbcd_watchvod_web_acc_9193214448e2e636b0ffb78abacfd9c4f937c6ca': 'MmobcxUxMedUpohNWwXaOnMjlbiyTOBLL6d46ZpR',
'nbcu_local_monitor_web_acc_f998ad54eaf26acd8ee033eb36f39a7b791c6335': 'QvfIoPYrwsjUCcASiw3AIkVtQob2LtJHfidp9iWg',
'nbcu_cable_monitor_web_acc_a413759603e8bedfcd3c61b14767796e17834077': 'uwVPJLShvJWSs6sWEIuVem7MTF8A4IknMMzIlFto',
'nbcu_nbcd_mcpstage_web_qa_4c43a8f6e95a88dbb40276c0630ba9f693a63a4e': 'PxVYZVwjhgd5TeoPRxL3whssb5OUPnM3zyAzq8GY',
'nbcu_comcast_comcast_web_prod_074080762ad4ce956b26b43fb22abf153443a8c4': 'afnaRZfDyg1Z3WZHdupKfy6xrbAG2MHqe3VfuSwh',
'nbcu_comcast_comcast_web_qa_706103bb93ead3ef70b1de12a0e95e3c4481ade0': 'DcjsVbX9b3uoPlhdriIiovgFQZVxpISZwz0cx1ZK',
'nbcu_comcast_comcastcable_web_prod_669f04817536743563d7331c9293e59fbdbe3d07': '0RwMN2cWy10qhAhOscq3eK7aEe0wqnKt3vJ0WS4D',
'nbcu_comcast_comcastcable_web_qa_3d9d2d66219094127f0f6b09cc3c7bb076e3e1ca': '2r8G9DEya7PCqBceKZgrn2XkXgASjwLMuaFE1Aad',
'hearst_hearst_demo_web_stage_960726dfef3337059a01a78816e43b29ec04dfc7': 'cuZBPXTR6kSdoTCVXwk5KGA8rk3NrgGn4H6e9Dsp',
'anvato_mcpqa_demo_web_stage_18b55e00db5a13faa8d03ae6e41f6f5bcb15b922': 'IOaaLQ8ymqVyem14QuAvE5SndQynTcH5CrLkU2Ih',
'anvato_nextmedia_demo_web_stage_9787d56a02ff6b9f43e9a2b0920d8ca88beb5818': 'Pqu9zVzI1ApiIzbVA3VkGBEQHvdKSUuKpD6s2uaR',
'anvato_scripps_app_web_prod_0837996dbe373629133857ae9eb72e740424d80a': 'du1ccmn7RxzgizwbWU7hyUaGodNlJn7HtXI0WgXW',
'anvato_scripps_app_web_stage_360797e00fe2826be142155c4618cc52fce6c26c': '2PMrQ0BRoqCWl7nzphj0GouIMEh2mZYivAT0S1Su',
'fs2go_fs2go_go_all_prod_21934911ccfafc03a075894ead2260d11e2ddd24': 'RcuHlKikW2IJw6HvVoEkqq2UsuEJlbEl11pWXs4Q',
'fs2go_fs2go_go_web_prod_ead4b0eec7460c1a07783808db21b49cf1f2f9a7': '4K0HTT2u1zkQA2MaGaZmkLa1BthGSBdr7jllrhk5',
'fs2go_fs2go_go_web_stage_407585454a4400355d4391691c67f361': 'ftnc37VKRJBmHfoGGi3kT05bHyeJzilEzhKJCyl3',
'fs2go_fs2go_go_android_stage_44b714db6f8477f29afcba15a41e1d30': 'CtxpPvVpo6AbZGomYUhkKs7juHZwNml9b9J0J2gI',
'anvato_cbslocal_app_web_prod_547f3e49241ef0e5d30c79b2efbca5d92c698f67': 'Pw0XX5KBDsyRnPS0R2JrSrXftsy8Jnz5pAjaYC8s',
'anvato_cbslocal_app_web_stage_547a5f096594cd3e00620c6f825cad1096d28c80': '37OBUhX2uwNyKhhrNzSSNHSRPZpApC3trdqDBpuz',
'fs2go_att_att_web_prod_1042dddd089a05438b6a08f972941176f699ffd8': 'JLcF20JwYvpv6uAGcLWIaV12jKwaL1R8us4b6Zkg',
'fs2go_att_att_web_stage_807c5001955fc114a3331fe027ddc76e': 'gbu1oO1y0JiOFh4SUipt86P288JHpyjSqolrrT1x',
'fs2go_fs2go_tudor_web_prod_a7dd8e5a7cdc830cae55eae6f3e9fee5ee49eb9b': 'ipcp87VCEZXPPe868j3orLqzc03oTy7DXsGkAXXH',
'anvato_mhz_app_web_prod_b808218b30de7fdf60340cbd9831512bc1bf6d37': 'Stlm5Gs6BEhJLRTZHcNquyzxGqr23EuFmE5DCgjX',
'fs2go_charter_charter_web_stage_c2c6e5a68375a1bf00fff213d3ff8f61a835a54c': 'Lz4hbJp1fwL6jlcz4M2PMzghM4jp4aAmybtT5dPc',
'fs2go_charter_charter_web_prod_ebfe3b10f1af215a7321cd3d629e0b81dfa6fa8c': 'vUJsK345A1bVmyYDRhZX0lqFIgVXuqhmuyp1EtPK',
'anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b': 'GDKq1ixvX3MoBNdU5IOYmYa2DTUXYOozPjrCJnW7',
'anvato_epfox_app_web_stage_a3c2ce60f8f83ef374a88b68ee73a950f8ab87ce': '2jz2NH4BsXMaDsoJ5qkHMbcczAfIReo2eFYuVC1C',
'fs2go_verizon_verizon_web_stage_08e6df0354a4803f1b1f2428b5a9a382e8dbcd62': 'rKTVapNaAcmnUbGL4ZcuOoY4SE7VmZSQsblPFr7e',
'fs2go_verizon_verizon_web_prod_f909564cb606eff1f731b5e22e0928676732c445': 'qLSUuHerM3u9eNPzaHyUK52obai5MvE4XDJfqYe1',
'fs2go_foxcom_synd_web_stage_f7b9091f00ea25a4fdaaae77fca5b54cdc7e7043': '96VKF2vLd24fFiDfwPFpzM5llFN4TiIGAlodE0Re',
'fs2go_foxcom_synd_web_prod_0f2cdd64d87e4ab6a1d54aada0ff7a7c8387a064': 'agiPjbXEyEZUkbuhcnmVPhe9NNVbDjCFq2xkcx51',
'anvato_own_app_web_stage_1214ade5d28422c4dae9d03c1243aba0563c4dba': 'mzhamNac3swG4WsJAiUTacnGIODi6SWeVWk5D7ho',
'anvato_own_app_web_prod_944e162ed927ec3e9ed13eb68ed2f1008ee7565e': '9TSxh6G2TXOLBoYm9ro3LdNjjvnXpKb8UR8KoIP9',
'anvato_scripps_app_ftv_prod_a10a10468edd5afb16fb48171c03b956176afad1': 'COJ2i2UIPK7xZqIWswxe7FaVBOVgRkP1F6O6qGoH',
'anvato_scripps_app_ftv_stage_77d3ad2bdb021ec37ca2e35eb09acd396a974c9a': 'Q7nnopNLe2PPfGLOTYBqxSaRpl209IhqaEuDZi1F',
'anvato_univision_app_web_stage_551236ef07a0e17718c3995c35586b5ed8cb5031': 'D92PoLS6UitwxDRA191HUGT9OYcOjV6mPMa5wNyo',
'anvato_univision_app_web_prod_039a5c0a6009e637ae8ac906718a79911e0e65e1': '5mVS5u4SQjtw6NGw2uhMbKEIONIiLqRKck5RwQLR',
'nbcu_cnbc_springfield_ios_prod_670207fae43d6e9a94c351688851a2ce': 'M7fqCCIP9lW53oJbHs19OlJlpDrVyc2OL8gNeuTa',
'nbcu_cnbc_springfieldvod_ios_prod_7a5f04b1ceceb0e9c9e2264a44aa236e08e034c2': 'Yia6QbJahW0S7K1I0drksimhZb4UFq92xLBmmMvk',
'anvato_cox_app_web_prod_ce45cda237969f93e7130f50ee8bb6280c1484ab': 'cc0miZexpFtdoqZGvdhfXsLy7FXjRAOgb9V0f5fZ',
'anvato_cox_app_web_stage_c23dbe016a8e9d8c7101d10172b92434f6088bf9': 'yivU3MYHd2eDZcOfmLbINVtqxyecKTOp8OjOuoGJ',
'anvato_chnzero_app_web_stage_b1164d1352b579e792e542fddf13ee34c0eeb46b': 'A76QkXMmVH8lTCfU15xva1mZnSVcqeY4Xb22Kp7m',
'anvato_chnzero_app_web_prod_253d358928dc08ec161eda2389d53707288a730c': 'OA5QI3ZWZZkdtUEDqh28AH8GedsF6FqzJI32596b',
'anvato_discovery_vodpoc_web_stage_9fa7077b5e8af1f8355f65d4fb8d2e0e9d54e2b7': 'q3oT191tTQ5g3JCP67PkjLASI9s16DuWZ6fYmry3',
'anvato_discovery_vodpoc_web_prod_688614983167a1af6cdf6d76343fda10a65223c1': 'qRvRQCTVHd0VVOHsMvvfidyWmlYVrTbjby7WqIuK',
'nbcu_cnbc_springfieldvod_ftv_stage_826040aad1925a46ac5dfb4b3c5143e648c6a30d': 'JQaSb5a8Tz0PT4ti329DNmzDO30TnngTHmvX8Vua',
'nbcu_cnbc_springfield_ftv_stage_826040aad1925a46ac5dfb4b3c5143e648c6a30d': 'JQaSb5a8Tz0PT4ti329DNmzDO30TnngTHmvX8Vua',
'nbcu_nbcd_capture_web_stage_4dd9d585bfb984ebf856dee35db027b2465cc4ae': '0j1Ov4Vopyi2HpBZJYdL2m8ERJVGYh3nNpzPiO8F',
'nbcu_nbcd_watch3_android_prod_7712ca5fcf1c22f19ec1870a9650f9c37db22dcf': '3LN2UB3rPUAMu7ZriWkHky9vpLMXYha8JbSnxBlx',
'nbcu_nbcd_watchvod3_android_prod_0910a3a4692d57c0b5ff4316075bc5d096be45b9': 'mJagcQ2II30vUOAauOXne7ERwbf5S9nlB3IP17lQ',
'anvato_scripps_app_atv_prod_790deda22e16e71e83df58f880cd389908a45d52': 'CB6trI1mpoDIM5o54DNTsji90NDBQPZ4z4RqBNSH',
'nbcu_nbcd_watchv4_android_prod_ff67cef9cb409158c6f8c3533edddadd0b750507': 'j8CHQCUWjlYERj4NFRmUYOND85QNbHViH09UwuKm',
'nbcu_nbcd_watchvodv4_android_prod_a814d781609989dea6a629d50ae4c7ad8cc8e907': 'rkVnUXxdA9rawVLUlDQtMue9Y4Q7lFEaIotcUhjt',
'rvVKpA50qlOPLFxMjrCGf5pdkdQDm7qn': '1J7ZkY5Qz5lMLi93QOH9IveE7EYB3rLl',
'nbcu_dtv_local_web_prod_b266cf49defe255fd4426a97e27c09e513e9f82f': 'HuLnJDqzLa4saCzYMJ79zDRSQpEduw1TzjMNQu2b',
'nbcu_att_local_web_prod_4cef038b2d969a6b7d700a56a599040b6a619f67': 'Q0Em5VDc2KpydUrVwzWRXAwoNBulWUxCq2faK0AV',
'nbcu_dish_local_web_prod_c56dcaf2da2e9157a4266c82a78195f1dd570f6b': 'bC1LWmRz9ayj2AlzizeJ1HuhTfIaJGsDBnZNgoRg',
'nbcu_verizon_local_web_prod_88bebd2ce006d4ed980de8133496f9a74cb9b3e1': 'wzhDKJZpgvUSS1EQvpCQP8Q59qVzcPixqDGJefSk',
'nbcu_charter_local_web_prod_9ad90f7fc4023643bb718f0fe0fd5beea2382a50': 'PyNbxNhEWLzy1ZvWEQelRuIQY88Eub7xbSVRMdfT',
'nbcu_suddenlink_local_web_prod_20fb711725cac224baa1c1cb0b1c324d25e97178': '0Rph41lPXZbb3fqeXtHjjbxfSrNbtZp1Ygq7Jypa',
'nbcu_wow_local_web_prod_652d9ce4f552d9c2e7b5b1ed37b8cb48155174ad': 'qayIBZ70w1dItm2zS42AptXnxW15mkjRrwnBjMPv',
'nbcu_centurylink_local_web_prod_2034402b029bf3e837ad46814d9e4b1d1345ccd5': 'StePcPMkjsX51PcizLdLRMzxMEl5k2FlsMLUNV4k',
'nbcu_atlanticbrd_local_web_prod_8d5f5ecbf7f7b2f5e6d908dd75d90ae3565f682e': 'NtYLb4TFUS0pRs3XTkyO5sbVGYjVf17bVbjaGscI',
'nbcu_nbcd_watchvod_web_dev_08bc05699be47c4f31d5080263a8cfadc16d0f7c': 'hwxi2dgDoSWgfmVVXOYZm14uuvku4QfopstXckhr',
'anvato_nextmedia_app_web_prod_a4fa8c7204aa65e71044b57aaf63711980cfe5a0': 'tQN1oGPYY1nM85rJYePWGcIb92TG0gSqoVpQTWOw',
'anvato_mcp_lin_web_prod_4c36fbfd4d8d8ecae6488656e21ac6d1ac972749': 'GUXNf5ZDX2jFUpu4WT2Go4DJ5nhUCzpnwDRRUx1K',
'anvato_mcp_univision_web_prod_37fe34850c99a3b5cdb71dab10a417dd5cdecafa': 'bLDYF8JqfG42b7bwKEgQiU9E2LTIAtnKzSgYpFUH',
'anvato_mcp_fs2go_web_prod_c7b90a93e171469cdca00a931211a2f556370d0a': 'icgGoYGipQMMSEvhplZX1pwbN69srwKYWksz3xWK',
'anvato_mcp_sps_web_prod_54bdc90dd6ba21710e9f7074338365bba28da336': 'fA2iQdI7RDpynqzQYIpXALVS83NTPr8LLFK4LFsu',
'anvato_mcp_anv_web_prod_791407490f4c1ef2a4bcb21103e0cb1bcb3352b3': 'rMOUZqe9lwcGq2mNgG3EDusm6lKgsUnczoOX3mbg',
'anvato_mcp_gray_web_prod_4c10f067c393ed8fc453d3930f8ab2b159973900': 'rMOUZqe9lwcGq2mNgG3EDusm6lKgsUnczoOX3mbg',
'anvato_mcp_hearst_web_prod_5356c3de0fc7c90a3727b4863ca7fec3a4524a99': 'P3uXJ0fXXditBPCGkfvlnVScpPEfKmc64Zv7ZgbK',
'anvato_mcp_cbs_web_prod_02f26581ff80e5bda7aad28226a8d369037f2cbe': 'mGPvo5ZA5SgjOFAPEPXv7AnOpFUICX8hvFQVz69n',
'anvato_mcp_telemundo_web_prod_c5278d51ad46fda4b6ca3d0ea44a7846a054f582': 'qyT6PXXLjVNCrHaRVj0ugAhalNRS7Ee9BP7LUokD',
'nbcu_nbcd_watchvodv4_web_stage_4108362fba2d4ede21f262fea3c4162cbafd66c7': 'DhaU5lj0W2gEdcSSsnxURq8t7KIWtJfD966crVDk',
'anvato_scripps_app_ios_prod_409c41960c60b308db43c3cc1da79cab9f1c3d93': 'WPxj5GraLTkYCyj3M7RozLqIycjrXOEcDGFMIJPn',
'EZqvRyKBJLrgpClDPDF8I7Xpdp40Vx73': '4OxGd2dEakylntVKjKF0UK9PDPYB6A9W',
'M2v78QkpleXm9hPp9jUXI63x5vA6BogR': 'ka6K32k7ZALmpINkjJUGUo0OE42Md1BQ',
'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6_secure': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ'
}
_AUTH_KEY = b'\x31\xc2\x42\x84\x9e\x73\xa0\xce'
def __init__(self, *args, **kwargs):
super(AnvatoIE, self).__init__(*args, **kwargs)
self.__server_time = None
def _server_time(self, access_key, video_id):
if self.__server_time is not None:
return self.__server_time
self.__server_time = int(self._download_json(
self._api_prefix(access_key) + 'server_time?anvack=' + access_key, video_id,
note='Fetching server time')['server_time'])
return self.__server_time
def _api_prefix(self, access_key):
return 'https://tkx2-%s.anvato.net/rest/v2/' % ('prod' if 'prod' in access_key else 'stage')
def _get_video_json(self, access_key, video_id):
# See et() in anvplayer.min.js, which is an alias of getVideoJSON()
video_data_url = self._api_prefix(access_key) + 'mcp/video/%s?anvack=%s' % (video_id, access_key)
server_time = self._server_time(access_key, video_id)
input_data = '%d~%s~%s' % (server_time, md5_text(video_data_url), md5_text(server_time))
auth_secret = intlist_to_bytes(aes_encrypt(
bytes_to_intlist(input_data[:64]), bytes_to_intlist(self._AUTH_KEY)))
video_data_url += '&X-Anvato-Adst-Auth=' + base64.b64encode(auth_secret).decode('ascii')
anvrid = md5_text(time.time() * 1000 * random.random())[:30]
payload = {
'api': {
'anvrid': anvrid,
'anvstk': md5_text('%s|%s|%d|%s' % (
access_key, anvrid, server_time, self._ANVACK_TABLE[access_key])),
'anvts': server_time,
},
}
return self._download_json(
video_data_url, video_id, transform_source=strip_jsonp,
data=json.dumps(payload).encode('utf-8'))
def _extract_anvato_videos(self, webpage, video_id):
anvplayer_data = self._parse_json(self._html_search_regex(
r'<script[^>]+data-anvp=\'([^\']+)\'', webpage,
'Anvato player data'), video_id)
video_id = anvplayer_data['video']
access_key = anvplayer_data['accessKey']
video_data = self._get_video_json(access_key, video_id)
formats = []
for published_url in video_data['published_urls']:
video_url = published_url['embed_url']
ext = determine_ext(video_url)
if ext == 'smil':
formats.extend(self._extract_smil_formats(video_url, video_id))
continue
tbr = int_or_none(published_url.get('kbps'))
a_format = {
'url': video_url,
'format_id': ('-'.join(filter(None, ['http', published_url.get('cdn_name')]))).lower(),
'tbr': tbr if tbr != 0 else None,
}
if ext == 'm3u8':
# Not using _extract_m3u8_formats here as individual media
# playlists are also included in published_urls.
if tbr is None:
formats.append(self._m3u8_meta_format(video_url, ext='mp4', m3u8_id='hls'))
continue
else:
a_format.update({
'format_id': '-'.join(filter(None, ['hls', compat_str(tbr)])),
'ext': 'mp4',
})
elif ext == 'mp3':
a_format['vcodec'] = 'none'
else:
a_format.update({
'width': int_or_none(published_url.get('width')),
'height': int_or_none(published_url.get('height')),
})
formats.append(a_format)
self._sort_formats(formats)
subtitles = {}
for caption in video_data.get('captions', []):
a_caption = {
'url': caption['url'],
'ext': 'tt' if caption.get('format') == 'SMPTE-TT' else None
}
subtitles.setdefault(caption['language'], []).append(a_caption)
return {
'id': video_id,
'formats': formats,
'title': video_data.get('def_title'),
'description': video_data.get('def_description'),
'categories': video_data.get('categories'),
'thumbnail': video_data.get('thumbnail'),
'subtitles': subtitles,
}

149
youtube_dl/extractor/aol.py
View File

@ -1,70 +1,137 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
)
class AolIE(InfoExtractor):
IE_NAME = 'on.aol.com'
_VALID_URL = r'''(?x)
(?:
aol-video:|
http://on\.aol\.com/
(?:
video/.*-|
playlist/(?P<playlist_display_id>[^/?#]+?)-(?P<playlist_id>[0-9]+)[?#].*_videoid=
)
)
(?P<id>[0-9]+)
(?:$|\?)
'''
_VALID_URL = r'(?:aol-video:|https?://on\.aol\.com/(?:[^/]+/)*(?:[^/?#&]+-)?)(?P<id>[^/?#&]+)'
_TESTS = [{
# video with 5min ID
'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img',
'md5': '18ef68f48740e86ae94b98da815eec42',
'info_dict': {
'id': '518167793',
'ext': 'mp4',
'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam',
'description': 'A major phone scam has cost thousands of taxpayers more than $1 million, with less than a month until income tax returns are due to the IRS.',
'timestamp': 1395405060,
'upload_date': '20140321',
'uploader': 'Newsy Studio',
},
'add_ie': ['FiveMin'],
'params': {
# m3u8 download
'skip_download': True,
}
}, {
'url': 'http://on.aol.com/playlist/brace-yourself---todays-weirdest-news-152147?icid=OnHomepageC4_Omg_Img#_videoid=518184316',
# video with vidible ID
'url': 'http://on.aol.com/video/netflix-is-raising-rates-5707d6b8e4b090497b04f706?context=PC:homepage:PL1944:1460189336183',
'info_dict': {
'id': '152147',
'title': 'Brace Yourself - Today\'s Weirdest News',
'id': '5707d6b8e4b090497b04f706',
'ext': 'mp4',
'title': 'Netflix is Raising Rates',
'description': 'Netflix is rewarding millions of it’s long-standing members with an increase in cost. Veuer’s Carly Figueroa has more.',
'upload_date': '20160408',
'timestamp': 1460123280,
'uploader': 'Veuer',
},
'playlist_mincount': 10,
'params': {
# m3u8 download
'skip_download': True,
}
}, {
'url': 'http://on.aol.com/partners/abc-551438d309eab105804dbfe8/sneak-peek-was-haley-really-framed-570eaebee4b0448640a5c944',
'only_matching': True,
}, {
'url': 'http://on.aol.com/shows/park-bench-shw518173474-559a1b9be4b0c3bfad3357a7?context=SH:SHW518173474:PL4327:1460619712763',
'only_matching': True,
}, {
'url': 'http://on.aol.com/video/519442220',
'only_matching': True,
}, {
'url': 'aol-video:5707d6b8e4b090497b04f706',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
playlist_id = mobj.group('playlist_id')
if not playlist_id or self._downloader.params.get('noplaylist'):
return self.url_result('5min:%s' % video_id)
video_id = self._match_id(url)
self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
response = self._download_json(
'https://feedapi.b2c.on.aol.com/v1.0/app/videos/aolon/%s/details' % video_id,
video_id)['response']
if response['statusText'] != 'Ok':
raise ExtractorError('%s said: %s' % (self.IE_NAME, response['statusText']), expected=True)
webpage = self._download_webpage(url, playlist_id)
title = self._html_search_regex(
r'<h1 class="video-title[^"]*">(.+?)</h1>', webpage, 'title')
playlist_html = self._search_regex(
r"(?s)<ul\s+class='video-related[^']*'>(.*?)</ul>", webpage,
'playlist HTML')
entries = [{
'_type': 'url',
'url': 'aol-video:%s' % m.group('id'),
'ie_key': 'Aol',
} for m in re.finditer(
r"<a\s+href='.*videoid=(?P<id>[0-9]+)'\s+class='video-thumb'>",
playlist_html)]
video_data = response['data']
formats = []
m3u8_url = video_data.get('videoMasterPlaylist')
if m3u8_url:
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
for rendition in video_data.get('renditions', []):
video_url = rendition.get('url')
if not video_url:
continue
ext = rendition.get('format')
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
else:
f = {
'url': video_url,
'format_id': rendition.get('quality'),
}
mobj = re.search(r'(\d+)x(\d+)', video_url)
if mobj:
f.update({
'width': int(mobj.group(1)),
'height': int(mobj.group(2)),
})
formats.append(f)
self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id'))
return {
'_type': 'playlist',
'id': playlist_id,
'display_id': mobj.group('playlist_display_id'),
'title': title,
'entries': entries,
'id': video_id,
'title': video_data['title'],
'duration': int_or_none(video_data.get('duration')),
'timestamp': int_or_none(video_data.get('publishDate')),
'view_count': int_or_none(video_data.get('views')),
'description': video_data.get('description'),
'uploader': video_data.get('videoOwner'),
'formats': formats,
}
class AolFeaturesIE(InfoExtractor):
IE_NAME = 'features.aol.com'
_VALID_URL = r'https?://features\.aol\.com/video/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'http://features.aol.com/video/behind-secret-second-careers-late-night-talk-show-hosts',
'md5': '7db483bb0c09c85e241f84a34238cc75',
'info_dict': {
'id': '519507715',
'ext': 'mp4',
'title': 'What To Watch - February 17, 2016',
},
'add_ie': ['FiveMin'],
'params': {
# encrypted m3u8 download
'skip_download': True,
},
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
return self.url_result(self._search_regex(
r'<script type="text/javascript" src="(https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js[^"]+)"',
webpage, '5min embed url'), 'FiveMin')

17
youtube_dl/extractor/aparat.py
View File

@ -1,8 +1,6 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
@ -15,11 +13,12 @@ class AparatIE(InfoExtractor):
_TEST = {
'url': 'http://www.aparat.com/v/wP8On',
'md5': '6714e0af7e0d875c5a39c4dc4ab46ad1',
'md5': '131aca2e14fe7c4dcb3c4877ba300c89',
'info_dict': {
'id': 'wP8On',
'ext': 'mp4',
'title': 'تیم گلکسی 11 - زومیت',
'age_limit': 0,
},
# 'skip': 'Extremely unreliable',
}
@ -30,12 +29,13 @@ class AparatIE(InfoExtractor):
# Note: There is an easier-to-parse configuration at
# http://www.aparat.com/video/video/config/videohash/%video_id
# but the URL in there does not work
embed_url = ('http://www.aparat.com/video/video/embed/videohash/' +
video_id + '/vt/frame')
embed_url = 'http://www.aparat.com/video/video/embed/vt/frame/showvideo/yes/videohash/' + video_id
webpage = self._download_webpage(embed_url, video_id)
video_urls = re.findall(r'fileList\[[0-9]+\]\s*=\s*"([^"]+)"', webpage)
for i, video_url in enumerate(video_urls):
file_list = self._parse_json(self._search_regex(
r'fileList\s*=\s*JSON\.parse\(\'([^\']+)\'\)', webpage, 'file list'), video_id)
for i, item in enumerate(file_list[0]):
video_url = item['file']
req = HEADRequest(video_url)
res = self._request_webpage(
req, video_id, note='Testing video URL %d' % i, errnote=False)
@ -46,7 +46,7 @@ class AparatIE(InfoExtractor):
title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, 'title')
thumbnail = self._search_regex(
r'\s+image:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False)
r'image:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False)
return {
'id': video_id,
@ -54,4 +54,5 @@ class AparatIE(InfoExtractor):
'url': video_url,
'ext': 'mp4',
'thumbnail': thumbnail,
'age_limit': self._family_friendly_search(webpage),
}

50
youtube_dl/extractor/appleconnect.py Normal file
View File

@ -0,0 +1,50 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
str_to_int,
ExtractorError
)
class AppleConnectIE(InfoExtractor):
_VALID_URL = r'https?://itunes\.apple\.com/\w{0,2}/?post/idsa\.(?P<id>[\w-]+)'
_TEST = {
'url': 'https://itunes.apple.com/us/post/idsa.4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
'md5': '10d0f2799111df4cb1c924520ca78f98',
'info_dict': {
'id': '4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
'ext': 'm4v',
'title': 'Energy',
'uploader': 'Drake',
'thumbnail': 'http://is5.mzstatic.com/image/thumb/Video5/v4/78/61/c5/7861c5fa-ad6d-294b-1464-cf7605b911d6/source/1920x1080sr.jpg',
'upload_date': '20150710',
'timestamp': 1436545535,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
try:
video_json = self._html_search_regex(
r'class="auc-video-data">(\{.*?\})', webpage, 'json')
except ExtractorError:
raise ExtractorError('This post doesn\'t contain a video', expected=True)
video_data = self._parse_json(video_json, video_id)
timestamp = str_to_int(self._html_search_regex(r'data-timestamp="(\d+)"', webpage, 'timestamp'))
like_count = str_to_int(self._html_search_regex(r'(\d+) Loves', webpage, 'like count'))
return {
'id': video_id,
'url': video_data['sslSrc'],
'title': video_data['title'],
'description': video_data['description'],
'uploader': video_data['artistName'],
'thumbnail': video_data['artworkUrl'],
'timestamp': timestamp,
'like_count': like_count,
}

225
youtube_dl/extractor/appletrailers.py
View File

@ -7,60 +7,88 @@ from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
int_or_none,
parse_duration,
unified_strdate,
)
class AppleTrailersIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/trailers/(?P<company>[^/]+)/(?P<movie>[^/]+)'
_TEST = {
"url": "http://trailers.apple.com/trailers/wb/manofsteel/",
"playlist": [
IE_NAME = 'appletrailers'
_VALID_URL = r'https?://(?:www\.|movie)?trailers\.apple\.com/(?:trailers|ca)/(?P<company>[^/]+)/(?P<movie>[^/]+)'
_TESTS = [{
'url': 'http://trailers.apple.com/trailers/wb/manofsteel/',
'info_dict': {
'id': '5111',
'title': 'Man of Steel',
},
'playlist': [
{
"md5": "d97a8e575432dbcb81b7c3acb741f8a8",
"info_dict": {
"id": "manofsteel-trailer4",
"ext": "mov",
"duration": 111,
"title": "Trailer 4",
"upload_date": "20130523",
"uploader_id": "wb",
'md5': 'd97a8e575432dbcb81b7c3acb741f8a8',
'info_dict': {
'id': 'manofsteel-trailer4',
'ext': 'mov',
'duration': 111,
'title': 'Trailer 4',
'upload_date': '20130523',
'uploader_id': 'wb',
},
},
{
"md5": "b8017b7131b721fb4e8d6f49e1df908c",
"info_dict": {
"id": "manofsteel-trailer3",
"ext": "mov",
"duration": 182,
"title": "Trailer 3",
"upload_date": "20130417",
"uploader_id": "wb",
'md5': 'b8017b7131b721fb4e8d6f49e1df908c',
'info_dict': {
'id': 'manofsteel-trailer3',
'ext': 'mov',
'duration': 182,
'title': 'Trailer 3',
'upload_date': '20130417',
'uploader_id': 'wb',
},
},
{
"md5": "d0f1e1150989b9924679b441f3404d48",
"info_dict": {
"id": "manofsteel-trailer",
"ext": "mov",
"duration": 148,
"title": "Trailer",
"upload_date": "20121212",
"uploader_id": "wb",
'md5': 'd0f1e1150989b9924679b441f3404d48',
'info_dict': {
'id': 'manofsteel-trailer',
'ext': 'mov',
'duration': 148,
'title': 'Trailer',
'upload_date': '20121212',
'uploader_id': 'wb',
},
},
{
"md5": "5fe08795b943eb2e757fa95cb6def1cb",
"info_dict": {
"id": "manofsteel-teaser",
"ext": "mov",
"duration": 93,
"title": "Teaser",
"upload_date": "20120721",
"uploader_id": "wb",
'md5': '5fe08795b943eb2e757fa95cb6def1cb',
'info_dict': {
'id': 'manofsteel-teaser',
'ext': 'mov',
'duration': 93,
'title': 'Teaser',
'upload_date': '20120721',
'uploader_id': 'wb',
},
},
]
}
}, {
'url': 'http://trailers.apple.com/trailers/magnolia/blackthorn/',
'info_dict': {
'id': 'blackthorn',
},
'playlist_mincount': 2,
'expected_warnings': ['Unable to download JSON metadata'],
}, {
# json data only available from http://trailers.apple.com/trailers/feeds/data/15881.json
'url': 'http://trailers.apple.com/trailers/fox/kungfupanda3/',
'info_dict': {
'id': '15881',
'title': 'Kung Fu Panda 3',
},
'playlist_mincount': 4,
}, {
'url': 'http://trailers.apple.com/ca/metropole/autrui/',
'only_matching': True,
}, {
'url': 'http://movietrailers.apple.com/trailers/focus_features/kuboandthetwostrings/',
'only_matching': True,
}]
_JSON_RE = r'iTunes.playURL\((.*?)\);'
@ -69,11 +97,50 @@ class AppleTrailersIE(InfoExtractor):
movie = mobj.group('movie')
uploader_id = mobj.group('company')
webpage = self._download_webpage(url, movie)
film_id = self._search_regex(r"FilmId\s*=\s*'(\d+)'", webpage, 'film id')
film_data = self._download_json(
'http://trailers.apple.com/trailers/feeds/data/%s.json' % film_id,
film_id, fatal=False)
if film_data:
entries = []
for clip in film_data.get('clips', []):
clip_title = clip['title']
formats = []
for version, version_data in clip.get('versions', {}).items():
for size, size_data in version_data.get('sizes', {}).items():
src = size_data.get('src')
if not src:
continue
formats.append({
'format_id': '%s-%s' % (version, size),
'url': re.sub(r'_(\d+p.mov)', r'_h\1', src),
'width': int_or_none(size_data.get('width')),
'height': int_or_none(size_data.get('height')),
'language': version[:2],
})
self._sort_formats(formats)
entries.append({
'id': movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', clip_title).lower(),
'formats': formats,
'title': clip_title,
'thumbnail': clip.get('screen') or clip.get('thumb'),
'duration': parse_duration(clip.get('runtime') or clip.get('faded')),
'upload_date': unified_strdate(clip.get('posted')),
'uploader_id': uploader_id,
})
page_data = film_data.get('page', {})
return self.playlist_result(entries, film_id, page_data.get('movie_title'))
playlist_url = compat_urlparse.urljoin(url, 'includes/playlists/itunes.inc')
def fix_html(s):
s = re.sub(r'(?s)<script[^<]*?>.*?</script>', '', s)
s = re.sub(r'<img ([^<]*?)>', r'<img \1/>', s)
s = re.sub(r'<img ([^<]*?)/?>', r'<img \1/>', s)
# The ' in the onClick attributes are not escaped, it couldn't be parsed
# like: http://trailers.apple.com/trailers/wb/gravity/
@ -90,6 +157,9 @@ class AppleTrailersIE(InfoExtractor):
trailer_info_json = self._search_regex(self._JSON_RE,
on_click, 'trailer info')
trailer_info = json.loads(trailer_info_json)
first_url = trailer_info.get('url')
if not first_url:
continue
title = trailer_info['title']
video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower()
thumbnail = li.find('.//img').attrib['src']
@ -101,7 +171,6 @@ class AppleTrailersIE(InfoExtractor):
if m:
duration = 60 * int(m.group('minutes')) + int(m.group('seconds'))
first_url = trailer_info['url']
trailer_id = first_url.split('/')[-1].rpartition('_')[0].lower()
settings_json_url = compat_urlparse.urljoin(url, 'includes/settings/%s.json' % trailer_id)
settings = self._download_json(settings_json_url, trailer_id, 'Downloading settings json')
@ -122,14 +191,15 @@ class AppleTrailersIE(InfoExtractor):
playlist.append({
'_type': 'video',
'id': video_id,
'title': title,
'formats': formats,
'title': title,
'duration': duration,
'thumbnail': thumbnail,
'upload_date': upload_date,
'uploader_id': uploader_id,
'user_agent': 'QuickTime compatible (youtube-dl)',
'http_headers': {
'User-Agent': 'QuickTime compatible (youtube-dl)',
},
})
return {
@ -137,3 +207,76 @@ class AppleTrailersIE(InfoExtractor):
'id': movie,
'entries': playlist,
}
class AppleTrailersSectionIE(InfoExtractor):
IE_NAME = 'appletrailers:section'
_SECTIONS = {
'justadded': {
'feed_path': 'just_added',
'title': 'Just Added',
},
'exclusive': {
'feed_path': 'exclusive',
'title': 'Exclusive',
},
'justhd': {
'feed_path': 'just_hd',
'title': 'Just HD',
},
'mostpopular': {
'feed_path': 'most_pop',
'title': 'Most Popular',
},
'moviestudios': {
'feed_path': 'studios',
'title': 'Movie Studios',
},
}
_VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/#section=(?P<id>%s)' % '|'.join(_SECTIONS)
_TESTS = [{
'url': 'http://trailers.apple.com/#section=justadded',
'info_dict': {
'title': 'Just Added',
'id': 'justadded',
},
'playlist_mincount': 80,
}, {
'url': 'http://trailers.apple.com/#section=exclusive',
'info_dict': {
'title': 'Exclusive',
'id': 'exclusive',
},
'playlist_mincount': 80,
}, {
'url': 'http://trailers.apple.com/#section=justhd',
'info_dict': {
'title': 'Just HD',
'id': 'justhd',
},
'playlist_mincount': 80,
}, {
'url': 'http://trailers.apple.com/#section=mostpopular',
'info_dict': {
'title': 'Most Popular',
'id': 'mostpopular',
},
'playlist_mincount': 80,
}, {
'url': 'http://trailers.apple.com/#section=moviestudios',
'info_dict': {
'title': 'Movie Studios',
'id': 'moviestudios',
},
'playlist_mincount': 80,
}]
def _real_extract(self, url):
section = self._match_id(url)
section_data = self._download_json(
'http://trailers.apple.com/trailers/home/feeds/%s.json' % self._SECTIONS[section]['feed_path'],
section)
entries = [
self.url_result('http://trailers.apple.com' + e['location'])
for e in section_data]
return self.playlist_result(entries, section, self._SECTIONS[section]['title'])

78
youtube_dl/extractor/archiveorg.py
View File

@ -1,67 +1,65 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import unified_strdate
from .jwplatform import JWPlatformBaseIE
from ..utils import (
unified_strdate,
clean_html,
)
class ArchiveOrgIE(InfoExtractor):
class ArchiveOrgIE(JWPlatformBaseIE):
IE_NAME = 'archive.org'
IE_DESC = 'archive.org videos'
_VALID_URL = r'https?://(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
_VALID_URL = r'https?://(?:www\.)?archive\.org/(?:details|embed)/(?P<id>[^/?#]+)(?:[?].*)?$'
_TESTS = [{
'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
'md5': '8af1d4cf447933ed3c7f4871162602db',
'info_dict': {
'id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect',
'ext': 'ogv',
'ext': 'ogg',
'title': '1968 Demo - FJCC Conference Presentation Reel #1',
'description': 'md5:1780b464abaca9991d8968c877bb53ed',
'description': 'md5:da45c349df039f1cc8075268eb1b5c25',
'upload_date': '19681210',
'uploader': 'SRI International'
}
}, {
'url': 'https://archive.org/details/Cops1922',
'md5': '18f2a19e6d89af8425671da1cf3d4e04',
'md5': 'bc73c8ab3838b5a8fc6c6651fa7b58ba',
'info_dict': {
'id': 'Cops1922',
'ext': 'ogv',
'ext': 'mp4',
'title': 'Buster Keaton\'s "Cops" (1922)',
'description': 'md5:70f72ee70882f713d4578725461ffcc3',
'description': 'md5:b4544662605877edd99df22f9620d858',
}
}, {
'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'http://archive.org/embed/' + video_id, video_id)
jwplayer_playlist = self._parse_json(self._search_regex(
r"(?s)Play\('[^']+'\s*,\s*(\[.+\])\s*,\s*{.*?}\);",
webpage, 'jwplayer playlist'), video_id)
info = self._parse_jwplayer_data(
{'playlist': jwplayer_playlist}, video_id, base_url=url)
json_url = url + ('?' if '?' in url else '&') + 'output=json'
data = self._download_json(json_url, video_id)
def get_optional(metadata, field):
return metadata.get(field, [None])[0]
def get_optional(data_dict, field):
return data_dict['metadata'].get(field, [None])[0]
title = get_optional(data, 'title')
description = get_optional(data, 'description')
uploader = get_optional(data, 'creator')
upload_date = unified_strdate(get_optional(data, 'date'))
formats = [
{
'format': fdata['format'],
'url': 'http://' + data['server'] + data['dir'] + fn,
'file_size': int(fdata['size']),
}
for fn, fdata in data['files'].items()
if 'Video' in fdata['format']]
self._sort_formats(formats)
return {
'_type': 'video',
'id': video_id,
'title': title,
'formats': formats,
'description': description,
'uploader': uploader,
'upload_date': upload_date,
'thumbnail': data.get('misc', {}).get('image'),
}
metadata = self._download_json(
'http://archive.org/details/' + video_id, video_id, query={
'output': 'json',
})['metadata']
info.update({
'title': get_optional(metadata, 'title') or info.get('title'),
'description': clean_html(get_optional(metadata, 'description')),
})
if info.get('_type') != 'playlist':
info.update({
'uploader': get_optional(metadata, 'creator'),
'upload_date': unified_strdate(get_optional(metadata, 'date')),
})
return info

207
youtube_dl/extractor/ard.py
View File

@ -13,34 +13,155 @@ from ..utils import (
parse_duration,
unified_strdate,
xpath_text,
parse_xml,
update_url_query,
)
from ..compat import compat_etree_fromstring
class ARDMediathekIE(InfoExtractor):
IE_NAME = 'ARD:mediathek'
_VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
_VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
_TESTS = [{
'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht',
'file': '22429276.mp4',
'md5': '469751912f1de0816a9fc9df8336476c',
'url': 'http://www.ardmediathek.de/tv/Dokumentation-und-Reportage/Ich-liebe-das-Leben-trotzdem/rbb-Fernsehen/Video?documentId=29582122&bcastId=3822114',
'info_dict': {
'title': 'Vertrauen ist gut, Spionieren ist besser - Geht so deutsch-amerikanische Freundschaft?',
'description': 'Das Erste Mediathek [ARD]: Vertrauen ist gut, Spionieren ist besser - Geht so deutsch-amerikanische Freundschaft?, Anne Will, Über die Spionage-Affäre diskutieren Clemens Binninger, Katrin Göring-Eckardt, Georg Mascolo, Andrew B. Denison und Constanze Kurz.. Das Video zur Sendung Anne Will am Mittwoch, 16.07.2014',
},
'skip': 'Blocked outside of Germany',
}, {
'url': 'http://www.ardmediathek.de/tv/Tatort/Das-Wunder-von-Wolbeck-Video-tgl-ab-20/Das-Erste/Video?documentId=22490580&bcastId=602916',
'info_dict': {
'id': '22490580',
'id': '29582122',
'ext': 'mp4',
'title': 'Das Wunder von Wolbeck (Video tgl. ab 20 Uhr)',
'description': 'Auf einem restaurierten Hof bei Wolbeck wird der Heilpraktiker Raffael Lembeck eines morgens von seiner Frau Stella tot aufgefunden. Das Opfer war offensichtlich in seiner Praxis zu Fall gekommen und ist dann verblutet, erklärt Prof. Boerne am Tatort.',
'title': 'Ich liebe das Leben trotzdem',
'description': 'md5:45e4c225c72b27993314b31a84a5261c',
'duration': 4557,
},
'skip': 'Blocked outside of Germany',
'params': {
# m3u8 download
'skip_download': True,
},
'skip': 'HTTP Error 404: Not Found',
}, {
'url': 'http://www.ardmediathek.de/tv/Tatort/Tatort-Scheinwelten-H%C3%B6rfassung-Video/Das-Erste/Video?documentId=29522730&bcastId=602916',
'md5': 'f4d98b10759ac06c0072bbcd1f0b9e3e',
'info_dict': {
'id': '29522730',
'ext': 'mp4',
'title': 'Tatort: Scheinwelten - Hörfassung (Video tgl. ab 20 Uhr)',
'description': 'md5:196392e79876d0ac94c94e8cdb2875f1',
'duration': 5252,
},
'skip': 'HTTP Error 404: Not Found',
}, {
# audio
'url': 'http://www.ardmediathek.de/tv/WDR-H%C3%B6rspiel-Speicher/Tod-eines-Fu%C3%9Fballers/WDR-3/Audio-Podcast?documentId=28488308&bcastId=23074086',
'md5': '219d94d8980b4f538c7fcb0865eb7f2c',
'info_dict': {
'id': '28488308',
'ext': 'mp3',
'title': 'Tod eines Fußballers',
'description': 'md5:f6e39f3461f0e1f54bfa48c8875c86ef',
'duration': 3240,
},
'skip': 'HTTP Error 404: Not Found',
}, {
'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht',
'only_matching': True,
}, {
# audio
'url': 'http://mediathek.rbb-online.de/radio/Hörspiel/Vor-dem-Fest/kulturradio/Audio?documentId=30796318&topRessort=radio&bcastId=9839158',
'md5': '4e8f00631aac0395fee17368ac0e9867',
'info_dict': {
'id': '30796318',
'ext': 'mp3',
'title': 'Vor dem Fest',
'description': 'md5:c0c1c8048514deaed2a73b3a60eecacb',
'duration': 3287,
},
'skip': 'Video is no longer available',
}]
def _extract_media_info(self, media_info_url, webpage, video_id):
media_info = self._download_json(
media_info_url, video_id, 'Downloading media JSON')
formats = self._extract_formats(media_info, video_id)
if not formats:
if '"fsk"' in webpage:
raise ExtractorError(
'This video is only available after 20:00', expected=True)
elif media_info.get('_geoblocked'):
raise ExtractorError('This video is not available due to geo restriction', expected=True)
self._sort_formats(formats)
duration = int_or_none(media_info.get('_duration'))
thumbnail = media_info.get('_previewImage')
subtitles = {}
subtitle_url = media_info.get('_subtitleUrl')
if subtitle_url:
subtitles['de'] = [{
'ext': 'ttml',
'url': subtitle_url,
}]
return {
'id': video_id,
'duration': duration,
'thumbnail': thumbnail,
'formats': formats,
'subtitles': subtitles,
}
def _extract_formats(self, media_info, video_id):
type_ = media_info.get('_type')
media_array = media_info.get('_mediaArray', [])
formats = []
for num, media in enumerate(media_array):
for stream in media.get('_mediaStreamArray', []):
stream_urls = stream.get('_stream')
if not stream_urls:
continue
if not isinstance(stream_urls, list):
stream_urls = [stream_urls]
quality = stream.get('_quality')
server = stream.get('_server')
for stream_url in stream_urls:
ext = determine_ext(stream_url)
if quality != 'auto' and ext in ('f4m', 'm3u8'):
continue
if ext == 'f4m':
formats.extend(self._extract_f4m_formats(
update_url_query(stream_url, {
'hdcore': '3.1.1',
'plugin': 'aasp-3.1.1.69.124'
}),
video_id, f4m_id='hds', fatal=False))
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
else:
if server and server.startswith('rtmp'):
f = {
'url': server,
'play_path': stream_url,
'format_id': 'a%s-rtmp-%s' % (num, quality),
}
elif stream_url.startswith('http'):
f = {
'url': stream_url,
'format_id': 'a%s-%s-%s' % (num, ext, quality)
}
else:
continue
m = re.search(r'_(?P<width>\d+)x(?P<height>\d+)\.mp4$', stream_url)
if m:
f.update({
'width': int(m.group('width')),
'height': int(m.group('height')),
})
if type_ == 'audio':
f['vcodec'] = 'none'
formats.append(f)
return formats
def _real_extract(self, url):
# determine video id from url
m = re.match(self._VALID_URL, url)
@ -56,8 +177,11 @@ class ARDMediathekIE(InfoExtractor):
if '>Der gewünschte Beitrag ist nicht mehr verfügbar.<' in webpage:
raise ExtractorError('Video %s is no longer available' % video_id, expected=True)
if 'Diese Sendung ist für Jugendliche unter 12 Jahren nicht geeignet. Der Clip ist deshalb nur von 20 bis 6 Uhr verfügbar.' in webpage:
raise ExtractorError('This program is only suitable for those aged 12 and older. Video %s is therefore only available between 20 pm and 6 am.' % video_id, expected=True)
if re.search(r'[\?&]rss($|[=&])', url):
doc = parse_xml(webpage)
doc = compat_etree_fromstring(webpage.encode('utf-8'))
if doc.tag == 'rss':
return GenericIE()._extract_rss(url, video_id, doc)
@ -95,50 +219,26 @@ class ARDMediathekIE(InfoExtractor):
'format_id': fid,
'url': furl,
})
self._sort_formats(formats)
info = {
'formats': formats,
}
else: # request JSON file
media_info = self._download_json(
'http://www.ardmediathek.de/play/media/%s' % video_id, video_id)
# The second element of the _mediaArray contains the standard http urls
streams = media_info['_mediaArray'][1]['_mediaStreamArray']
if not streams:
if '"fsk"' in webpage:
raise ExtractorError('This video is only available after 20:00')
info = self._extract_media_info(
'http://www.ardmediathek.de/play/media/%s' % video_id, webpage, video_id)
formats = []
for s in streams:
if type(s['_stream']) == list:
for index, url in enumerate(s['_stream'][::-1]):
quality = s['_quality'] + index
formats.append({
'quality': quality,
'url': url,
'format_id': '%s-%s' % (determine_ext(url), quality)
})
continue
format = {
'quality': s['_quality'],
'url': s['_stream'],
}
format['format_id'] = '%s-%s' % (
determine_ext(format['url']), format['quality'])
formats.append(format)
self._sort_formats(formats)
return {
info.update({
'id': video_id,
'title': title,
'description': description,
'formats': formats,
'thumbnail': thumbnail,
}
})
return info
class ARDIE(InfoExtractor):
_VALID_URL = '(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html'
_VALID_URL = r'(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html'
_TEST = {
'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html',
'md5': 'd216c3a86493f9322545e045ddc3eb35',
@ -150,7 +250,8 @@ class ARDIE(InfoExtractor):
'title': 'Die Story im Ersten: Mission unter falscher Flagge',
'upload_date': '20140804',
'thumbnail': 're:^https?://.*\.jpg$',
}
},
'skip': 'HTTP Error 404: Not Found',
}
def _real_extract(self, url):

115
youtube_dl/extractor/arkena.py Normal file
View File

@ -0,0 +1,115 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
float_or_none,
int_or_none,
mimetype2ext,
parse_iso8601,
strip_jsonp,
)
class ArkenaIE(InfoExtractor):
_VALID_URL = r'https?://play\.arkena\.com/(?:config|embed)/avp/v\d/player/media/(?P<id>[^/]+)/[^/]+/(?P<account_id>\d+)'
_TESTS = [{
'url': 'https://play.arkena.com/embed/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411',
'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
'info_dict': {
'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
'ext': 'mp4',
'title': 'Big Buck Bunny',
'description': 'Royalty free test video',
'timestamp': 1432816365,
'upload_date': '20150528',
'is_live': False,
},
}, {
'url': 'https://play.arkena.com/config/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411/?callbackMethod=jQuery1111023664739129262213_1469227693893',
'only_matching': True,
}, {
'url': 'http://play.arkena.com/config/avp/v1/player/media/327336/darkmatter/131064/?callbackMethod=jQuery1111002221189684892677_1469227595972',
'only_matching': True,
}, {
'url': 'http://play.arkena.com/embed/avp/v1/player/media/327336/darkmatter/131064/',
'only_matching': True,
}]
@staticmethod
def _extract_url(webpage):
# See https://support.arkena.com/display/PLAY/Ways+to+embed+your+video
mobj = re.search(
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//play\.arkena\.com/embed/avp/.+?)\1',
webpage)
if mobj:
return mobj.group('url')
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
account_id = mobj.group('account_id')
playlist = self._download_json(
'https://play.arkena.com/config/avp/v2/player/media/%s/0/%s/?callbackMethod=_'
% (video_id, account_id),
video_id, transform_source=strip_jsonp)['Playlist'][0]
media_info = playlist['MediaInfo']
title = media_info['Title']
media_files = playlist['MediaFiles']
is_live = False
formats = []
for kind_case, kind_formats in media_files.items():
kind = kind_case.lower()
for f in kind_formats:
f_url = f.get('Url')
if not f_url:
continue
is_live = f.get('Live') == 'true'
exts = (mimetype2ext(f.get('Type')), determine_ext(f_url, None))
if kind == 'm3u8' or 'm3u8' in exts:
formats.extend(self._extract_m3u8_formats(
f_url, video_id, 'mp4',
entry_protocol='m3u8' if is_live else 'm3u8_native',
m3u8_id=kind, fatal=False, live=is_live))
elif kind == 'flash' or 'f4m' in exts:
formats.extend(self._extract_f4m_formats(
f_url, video_id, f4m_id=kind, fatal=False))
elif kind == 'dash' or 'mpd' in exts:
formats.extend(self._extract_mpd_formats(
f_url, video_id, mpd_id=kind, fatal=False))
elif kind == 'silverlight':
# TODO: process when ism is supported (see
# https://github.com/rg3/youtube-dl/issues/8118)
continue
else:
tbr = float_or_none(f.get('Bitrate'), 1000)
formats.append({
'url': f_url,
'format_id': '%s-%d' % (kind, tbr) if tbr else kind,
'tbr': tbr,
})
self._sort_formats(formats)
description = media_info.get('Description')
video_id = media_info.get('VideoId') or video_id
timestamp = parse_iso8601(media_info.get('PublishDate'))
thumbnails = [{
'url': thumbnail['Url'],
'width': int_or_none(thumbnail.get('Size')),
} for thumbnail in (media_info.get('Poster') or []) if thumbnail.get('Url')]
return {
'id': video_id,
'title': title,
'description': description,
'timestamp': timestamp,
'is_live': is_live,
'thumbnails': thumbnails,
'formats': formats,
}

Some files were not shown because too many files have changed in this diff Show More