Merge branch 'master' of https://github.com/rg3/youtube-dl
This commit is contained in:
Gilles Habran
commit
255142eec5
6
.github/ISSUE_TEMPLATE.md
vendored
6
.github/ISSUE_TEMPLATE.md
vendored
@ -6,8 +6,8 @@
|
||||
|
||||
---
|
||||
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.06.03*. 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 Issues with outdated version will be rejected.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 **2016.06.03**
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.06.12*. 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 Issues with outdated version will be rejected.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 **2016.06.12**
|
||||
|
||||
### 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
|
||||
@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
|
||||
[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 2016.06.03
|
||||
[debug] youtube-dl version 2016.06.12
|
||||
[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: {}
|
||||
|
||||
17
README.md
17
README.md
@ -255,7 +255,7 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
--write-info-json Write video metadata to a .info.json file
|
||||
--write-annotations Write video annotations to a
|
||||
.annotations.xml file
|
||||
--load-info FILE JSON file containing the video information
|
||||
--load-info-json FILE JSON file containing the video information
|
||||
(created with the "--write-info-json"
|
||||
option)
|
||||
--cookies FILE File to read cookies from and dump cookie
|
||||
@ -511,6 +511,9 @@ The basic usage is not to set any template arguments when downloading a single f
|
||||
- `autonumber`: Five-digit number that will be increased with each download, starting at zero
|
||||
- `playlist`: Name or id of the playlist that contains the video
|
||||
- `playlist_index`: Index of the video in the playlist padded with leading zeros according to the total length of the playlist
|
||||
- `playlist_id`: Playlist identifier
|
||||
- `playlist_title`: Playlist title
|
||||
|
||||
|
||||
Available for the video that belongs to some logical chapter or section:
|
||||
- `chapter`: Name or title of the chapter the video belongs to
|
||||
@ -550,6 +553,10 @@ The current default template is `%(title)s-%(id)s.%(ext)s`.
|
||||
|
||||
In some cases, you don't want special characters such as 中, spaces, or &, such as when transferring the downloaded filename to a Windows system or the filename through an 8bit-unsafe channel. In these cases, add the `--restrict-filenames` flag to get a shorter title:
|
||||
|
||||
#### Output template and Windows batch files
|
||||
|
||||
If you are using output template inside a Windows batch file then you must escape plain percent characters (`%`) by doubling, so that `-o "%(title)s-%(id)s.%(ext)s"` should become `-o "%%(title)s-%%(id)s.%%(ext)s"`. However you should not touch `%`'s that are not plain characters, e.g. environment variables for expansion should stay intact: `-o "C:\%HOMEPATH%\Desktop\%%(title)s.%%(ext)s"`.
|
||||
|
||||
#### Output template examples
|
||||
|
||||
Note on Windows you may need to use double quotes instead of single.
|
||||
@ -928,9 +935,9 @@ After you have ensured this site is distributing it's content legally, you can f
|
||||
```
|
||||
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/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L68-L226). Add tests and code for as many as you want.
|
||||
8. Keep in mind that the only mandatory fields in info dict for successful extraction process are `id`, `title` and either `url` or `formats`, i.e. these are the critical data the extraction does not make any sense without. This means that [any field](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L138-L226) apart from aforementioned mandatory ones should be treated **as optional** and extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. For example, if you have some intermediate dict `meta` that is a source of metadata and it has a key `summary` that you want to extract and put into resulting info dict as `description`, you should be ready that this key may be missing from the `meta` dict, i.e. you should extract it as `meta.get('summary')` and not `meta['summary']`. Similarly, you should pass `fatal=False` when extracting data from a webpage with `_search_regex/_html_search_regex`.
|
||||
9. Check the code with [flake8](https://pypi.python.org/pypi/flake8).
|
||||
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. Keep in mind that the only mandatory fields in info dict for successful extraction process are `id`, `title` and either `url` or `formats`, i.e. these are the critical data the extraction does not make any sense without. This means that [any field](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L148-L252) apart from aforementioned mandatory ones should be treated **as optional** and extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. For example, if you have some intermediate dict `meta` that is a source of metadata and it has a key `summary` that you want to extract and put into resulting info dict as `description`, you should be ready that this key may be missing from the `meta` dict, i.e. you should extract it as `meta.get('summary')` and not `meta['summary']`. Similarly, you should pass `fatal=False` when extracting data from a webpage with `_search_regex/_html_search_regex`.
|
||||
9. 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+.
|
||||
10. 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/extractors.py
|
||||
@ -957,7 +964,7 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl:
|
||||
ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc'])
|
||||
```
|
||||
|
||||
Most likely, you'll want to use various options. For a list of what can be done, have a look at [`youtube_dl/YoutubeDL.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L121-L269). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
|
||||
Most likely, you'll want to use various options. For a list of options available, have a look at [`youtube_dl/YoutubeDL.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L128-L278). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
|
||||
|
||||
Here's a more complete example of a program that outputs only errors (and a short message after the download is finished), and downloads/converts the video to an mp3 file:
|
||||
|
||||
|
||||
@ -28,6 +28,7 @@
|
||||
- **AdobeTVVideo**
|
||||
- **AdultSwim**
|
||||
- **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network
|
||||
- **AfreecaTV**: afreecatv.com
|
||||
- **Aftonbladet**
|
||||
- **AirMozilla**
|
||||
- **AlJazeera**
|
||||
@ -253,6 +254,7 @@
|
||||
- **Globo**
|
||||
- **GloboArticle**
|
||||
- **GodTube**
|
||||
- **GodTV**
|
||||
- **GoldenMoustache**
|
||||
- **Golem**
|
||||
- **GoogleDrive**
|
||||
@ -645,6 +647,7 @@
|
||||
- **Telegraaf**
|
||||
- **TeleMB**
|
||||
- **TeleTask**
|
||||
- **Telewebion**
|
||||
- **TF1**
|
||||
- **TheIntercept**
|
||||
- **ThePlatform**
|
||||
@ -738,6 +741,7 @@
|
||||
- **VideoPremium**
|
||||
- **VideoTt**: video.tt - Your True Tube (Currently broken)
|
||||
- **videoweed**: VideoWeed
|
||||
- **Vidio**
|
||||
- **vidme**
|
||||
- **vidme:user**
|
||||
- **vidme:user:likes**
|
||||
@ -773,7 +777,6 @@
|
||||
- **VRT**
|
||||
- **vube**: Vube.com
|
||||
- **VuClip**
|
||||
- **vulture.com**
|
||||
- **Walla**
|
||||
- **washingtonpost**
|
||||
- **washingtonpost:article**
|
||||
@ -781,10 +784,8 @@
|
||||
- **WatchIndianPorn**: Watch Indian Porn
|
||||
- **WDR**
|
||||
- **wdr:mobile**
|
||||
- **WDRMaus**: Sendung mit der Maus
|
||||
- **WebOfStories**
|
||||
- **WebOfStoriesPlaylist**
|
||||
- **Weibo**
|
||||
- **WeiqiTV**: WQTV
|
||||
- **wholecloud**: WholeCloud
|
||||
- **Wimp**
|
||||
@ -820,6 +821,7 @@
|
||||
- **Ynet**
|
||||
- **YouJizz**
|
||||
- **youku**: 优酷
|
||||
- **youku:show**
|
||||
- **YouPorn**
|
||||
- **YourUpload**
|
||||
- **youtube**: YouTube.com
|
||||
|
||||
1
setup.py
1
setup.py
@ -122,6 +122,7 @@ setup(
|
||||
"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},
|
||||
|
||||
@ -249,6 +249,8 @@ class TestUtil(unittest.TestCase):
|
||||
self.assertEqual(unescapeHTML('/'), '/')
|
||||
self.assertEqual(unescapeHTML('é'), 'é')
|
||||
self.assertEqual(unescapeHTML('�'), '�')
|
||||
# HTML5 entities
|
||||
self.assertEqual(unescapeHTML('.''), '.\'')
|
||||
|
||||
def test_date_from_str(self):
|
||||
self.assertEqual(date_from_str('yesterday'), date_from_str('now-1day'))
|
||||
|
||||
@ -1223,6 +1223,10 @@ class YoutubeDL(object):
|
||||
if 'title' not in info_dict:
|
||||
raise ExtractorError('Missing "title" field in extractor result')
|
||||
|
||||
if not isinstance(info_dict['id'], compat_str):
|
||||
self.report_warning('"id" field is not a string - forcing string conversion')
|
||||
info_dict['id'] = compat_str(info_dict['id'])
|
||||
|
||||
if 'playlist' not in info_dict:
|
||||
# It isn't part of a playlist
|
||||
info_dict['playlist'] = None
|
||||
|
||||
2240
youtube_dl/compat.py
2240
youtube_dl/compat.py
File diff suppressed because it is too large
Load Diff
@ -85,7 +85,7 @@ class ExternalFD(FileDownloader):
|
||||
cmd, stderr=subprocess.PIPE)
|
||||
_, stderr = p.communicate()
|
||||
if p.returncode != 0:
|
||||
self.to_stderr(stderr)
|
||||
self.to_stderr(stderr.decode('utf-8', 'replace'))
|
||||
return p.returncode
|
||||
|
||||
|
||||
@ -210,6 +210,7 @@ class FFmpegFD(ExternalFD):
|
||||
# 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')
|
||||
|
||||
|
||||
133
youtube_dl/extractor/afreecatv.py
Normal file
133
youtube_dl/extractor/afreecatv.py
Normal 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
|
||||
@ -6,6 +6,7 @@ import time
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .soundcloud import SoundcloudIE
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
url_basename,
|
||||
@ -136,7 +137,7 @@ class AudiomackAlbumIE(InfoExtractor):
|
||||
result[resultkey] = api_response[apikey]
|
||||
song_id = url_basename(api_response['url']).rpartition('.')[0]
|
||||
result['entries'].append({
|
||||
'id': api_response.get('id', song_id),
|
||||
'id': compat_str(api_response.get('id', song_id)),
|
||||
'uploader': api_response.get('artist'),
|
||||
'title': api_response.get('title', song_id),
|
||||
'url': api_response['url'],
|
||||
|
||||
@ -102,6 +102,22 @@ class BiliBiliIE(InfoExtractor):
|
||||
'uploader_id': '151066',
|
||||
},
|
||||
}],
|
||||
}, {
|
||||
# Missing upload time
|
||||
'url': 'http://www.bilibili.com/video/av1867637/',
|
||||
'info_dict': {
|
||||
'id': '2880301',
|
||||
'ext': 'flv',
|
||||
'title': '【HDTV】【喜剧】岳父岳母真难当 （2014）【法国票房冠军】',
|
||||
'description': '一个信奉天主教的法国旧式传统资产阶级家庭中有四个女儿。三个女儿却分别找了阿拉伯、犹太、中国丈夫，老夫老妻唯独期盼剩下未嫁的小女儿能找一个信奉天主教的法国白人，结果没想到小女儿找了一位非裔黑人……【这次应该不会跳帧了】',
|
||||
'uploader': '黑夜为猫',
|
||||
'uploader_id': '610729',
|
||||
},
|
||||
'params': {
|
||||
# Just to test metadata extraction
|
||||
'skip_download': True,
|
||||
},
|
||||
'expected_warnings': ['upload time'],
|
||||
}]
|
||||
|
||||
# BiliBili blocks keys from time to time. The current key is extracted from
|
||||
@ -172,6 +188,7 @@ class BiliBiliIE(InfoExtractor):
|
||||
description = self._html_search_meta('description', webpage)
|
||||
datetime_str = self._html_search_regex(
|
||||
r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', fatal=False)
|
||||
timestamp = None
|
||||
if datetime_str:
|
||||
timestamp = calendar.timegm(datetime.datetime.strptime(datetime_str, '%Y-%m-%dT%H:%M').timetuple())
|
||||
|
||||
|
||||
@ -35,6 +35,7 @@ class DWIE(InfoExtractor):
|
||||
'upload_date': '20160311',
|
||||
}
|
||||
}, {
|
||||
# DW documentaries, only last for one or two weeks
|
||||
'url': 'http://www.dw.com/en/documentaries-welcome-to-the-90s-2016-05-21/e-19220158-9798',
|
||||
'md5': '56b6214ef463bfb9a3b71aeb886f3cf1',
|
||||
'info_dict': {
|
||||
@ -44,6 +45,7 @@ class DWIE(InfoExtractor):
|
||||
'description': 'Welcome to the 90s - The Golden Decade of Hip Hop',
|
||||
'upload_date': '20160521',
|
||||
},
|
||||
'skip': 'Video removed',
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@ -21,6 +21,7 @@ from .adobetv import (
|
||||
)
|
||||
from .adultswim import AdultSwimIE
|
||||
from .aenetworks import AENetworksIE
|
||||
from .afreecatv import AfreecaTVIE
|
||||
from .aftonbladet import AftonbladetIE
|
||||
from .airmozilla import AirMozillaIE
|
||||
from .aljazeera import AlJazeeraIE
|
||||
@ -291,6 +292,7 @@ from .globo import (
|
||||
GloboArticleIE,
|
||||
)
|
||||
from .godtube import GodTubeIE
|
||||
from .godtv import GodTVIE
|
||||
from .goldenmoustache import GoldenMoustacheIE
|
||||
from .golem import GolemIE
|
||||
from .googledrive import GoogleDriveIE
|
||||
@ -775,6 +777,7 @@ from .telecinco import TelecincoIE
|
||||
from .telegraaf import TelegraafIE
|
||||
from .telemb import TeleMBIE
|
||||
from .teletask import TeleTaskIE
|
||||
from .telewebion import TelewebionIE
|
||||
from .testurl import TestURLIE
|
||||
from .tf1 import TF1IE
|
||||
from .theintercept import TheInterceptIE
|
||||
@ -956,7 +959,6 @@ 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,
|
||||
@ -972,7 +974,6 @@ from .webofstories import (
|
||||
WebOfStoriesIE,
|
||||
WebOfStoriesPlaylistIE,
|
||||
)
|
||||
from .weibo import WeiboIE
|
||||
from .weiqitv import WeiqiTVIE
|
||||
from .wimp import WimpIE
|
||||
from .wistia import WistiaIE
|
||||
@ -1013,7 +1014,10 @@ from .yesjapan import YesJapanIE
|
||||
from .yinyuetai import YinYueTaiIE
|
||||
from .ynet import YnetIE
|
||||
from .youjizz import YouJizzIE
|
||||
from .youku import YoukuIE
|
||||
from .youku import (
|
||||
YoukuIE,
|
||||
YoukuShowIE,
|
||||
)
|
||||
from .youporn import YouPornIE
|
||||
from .yourupload import YourUploadIE
|
||||
from .youtube import (
|
||||
|
||||
@ -63,6 +63,7 @@ from .instagram import InstagramIE
|
||||
from .liveleak import LiveLeakIE
|
||||
from .threeqsdn import ThreeQSDNIE
|
||||
from .theplatform import ThePlatformIE
|
||||
from .vessel import VesselIE
|
||||
|
||||
|
||||
class GenericIE(InfoExtractor):
|
||||
@ -626,13 +627,13 @@ class GenericIE(InfoExtractor):
|
||||
},
|
||||
# MTVSercices embed
|
||||
{
|
||||
'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
|
||||
'md5': '35727f82f58c76d996fc188f9755b0d5',
|
||||
'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
|
||||
'md5': 'ca1aef97695ef2c1d6973256a57e5252',
|
||||
'info_dict': {
|
||||
'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
|
||||
'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
|
||||
'ext': 'mp4',
|
||||
'title': 'Review',
|
||||
'description': 'Mario\'s life in the fast lane has never looked so good.',
|
||||
'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
|
||||
'description': 'Two valets share their love for movie star Liam Neesons.',
|
||||
},
|
||||
},
|
||||
# YouTube embed via <data-embed-url="">
|
||||
@ -1031,6 +1032,17 @@ class GenericIE(InfoExtractor):
|
||||
'timestamp': 1389118457,
|
||||
},
|
||||
},
|
||||
# NBC News embed
|
||||
{
|
||||
'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
|
||||
'md5': '1aa589c675898ae6d37a17913cf68d66',
|
||||
'info_dict': {
|
||||
'id': '701714499682',
|
||||
'ext': 'mp4',
|
||||
'title': 'PREVIEW: On Assignment: David Letterman',
|
||||
'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.',
|
||||
},
|
||||
},
|
||||
# UDN embed
|
||||
{
|
||||
'url': 'https://video.udn.com/news/300346',
|
||||
@ -1061,20 +1073,6 @@ class GenericIE(InfoExtractor):
|
||||
'skip_download': True,
|
||||
}
|
||||
},
|
||||
# Contains a SMIL manifest
|
||||
{
|
||||
'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
|
||||
'info_dict': {
|
||||
'id': 'file',
|
||||
'ext': 'flv',
|
||||
'title': '+ Football: Lottery Champions League Europe',
|
||||
'uploader': 'www.telewebion.com',
|
||||
},
|
||||
'params': {
|
||||
# rtmpe downloads
|
||||
'skip_download': True,
|
||||
}
|
||||
},
|
||||
# Brightcove URL in single quotes
|
||||
{
|
||||
'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
|
||||
@ -1533,6 +1531,11 @@ class GenericIE(InfoExtractor):
|
||||
if tp_urls:
|
||||
return _playlist_from_matches(tp_urls, ie='ThePlatform')
|
||||
|
||||
# Look for Vessel embeds
|
||||
vessel_urls = VesselIE._extract_urls(webpage)
|
||||
if vessel_urls:
|
||||
return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
|
||||
|
||||
# Look for embedded rtl.nl player
|
||||
matches = re.findall(
|
||||
r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
|
||||
@ -1840,14 +1843,6 @@ class GenericIE(InfoExtractor):
|
||||
url = unescapeHTML(mobj.group('url'))
|
||||
return self.url_result(url)
|
||||
|
||||
# Look for embedded vulture.com player
|
||||
mobj = re.search(
|
||||
r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
|
||||
webpage)
|
||||
if mobj is not None:
|
||||
url = unescapeHTML(mobj.group('url'))
|
||||
return self.url_result(url, ie='Vulture')
|
||||
|
||||
# Look for embedded mtvservices player
|
||||
mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
|
||||
if mtvservices_url:
|
||||
@ -1960,6 +1955,12 @@ class GenericIE(InfoExtractor):
|
||||
if nbc_sports_url:
|
||||
return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
|
||||
|
||||
# Look for NBC News embeds
|
||||
nbc_news_embed_url = re.search(
|
||||
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
|
||||
if nbc_news_embed_url:
|
||||
return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
|
||||
|
||||
# Look for Google Drive embeds
|
||||
google_drive_url = GoogleDriveIE._extract_url(webpage)
|
||||
if google_drive_url:
|
||||
|
||||
66
youtube_dl/extractor/godtv.py
Normal file
66
youtube_dl/extractor/godtv.py
Normal file
@ -0,0 +1,66 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .ooyala import OoyalaIE
|
||||
from ..utils import js_to_json
|
||||
|
||||
|
||||
class GodTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?god\.tv(?:/[^/]+)*/(?P<id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://god.tv/jesus-image/video/jesus-conference-2016/randy-needham',
|
||||
'info_dict': {
|
||||
'id': 'lpd3g2MzE6D1g8zFAKz8AGpxWcpu6o_3',
|
||||
'ext': 'mp4',
|
||||
'title': 'Randy Needham',
|
||||
'duration': 3615.08,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
}
|
||||
}, {
|
||||
'url': 'http://god.tv/playlist/bible-study',
|
||||
'info_dict': {
|
||||
'id': 'bible-study',
|
||||
},
|
||||
'playlist_mincount': 37,
|
||||
}, {
|
||||
'url': 'http://god.tv/node/15097',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://god.tv/live/africa',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://god.tv/liveevents',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
settings = self._parse_json(
|
||||
self._search_regex(
|
||||
r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
|
||||
webpage, 'settings', default='{}'),
|
||||
display_id, transform_source=js_to_json, fatal=False)
|
||||
|
||||
ooyala_id = None
|
||||
|
||||
if settings:
|
||||
playlist = settings.get('playlist')
|
||||
if playlist and isinstance(playlist, list):
|
||||
entries = [
|
||||
OoyalaIE._build_url_result(video['content_id'])
|
||||
for video in playlist if video.get('content_id')]
|
||||
if entries:
|
||||
return self.playlist_result(entries, display_id)
|
||||
ooyala_id = settings.get('ooyala', {}).get('content_id')
|
||||
|
||||
if not ooyala_id:
|
||||
ooyala_id = self._search_regex(
|
||||
r'["\']content_id["\']\s*:\s*(["\'])(?P<id>[\w-]+)\1',
|
||||
webpage, 'ooyala id', group='id')
|
||||
|
||||
return OoyalaIE._build_url_result(ooyala_id)
|
||||
@ -60,7 +60,8 @@ class IndavideoEmbedIE(InfoExtractor):
|
||||
|
||||
formats = [{
|
||||
'url': video_url,
|
||||
'height': self._search_regex(r'\.(\d{3,4})\.mp4$', video_url, 'height', default=None),
|
||||
'height': int_or_none(self._search_regex(
|
||||
r'\.(\d{3,4})\.mp4(?:\?|$)', video_url, 'height', default=None)),
|
||||
} for video_url in video_urls]
|
||||
self._sort_formats(formats)
|
||||
|
||||
|
||||
@ -8,6 +8,7 @@ from ..utils import (
|
||||
int_or_none,
|
||||
limit_length,
|
||||
lowercase_escape,
|
||||
try_get,
|
||||
)
|
||||
|
||||
|
||||
@ -19,10 +20,16 @@ class InstagramIE(InfoExtractor):
|
||||
'info_dict': {
|
||||
'id': 'aye83DjauH',
|
||||
'ext': 'mp4',
|
||||
'uploader_id': 'naomipq',
|
||||
'title': 'Video by naomipq',
|
||||
'description': 'md5:1f17f0ab29bd6fe2bfad705f58de3cb8',
|
||||
}
|
||||
'thumbnail': 're:^https?://.*\.jpg',
|
||||
'timestamp': 1371748545,
|
||||
'upload_date': '20130620',
|
||||
'uploader_id': 'naomipq',
|
||||
'uploader': 'Naomi Leonor Phan-Quang',
|
||||
'like_count': int,
|
||||
'comment_count': int,
|
||||
},
|
||||
}, {
|
||||
# missing description
|
||||
'url': 'https://www.instagram.com/p/BA-pQFBG8HZ/?taken-by=britneyspears',
|
||||
@ -31,6 +38,13 @@ class InstagramIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'uploader_id': 'britneyspears',
|
||||
'title': 'Video by britneyspears',
|
||||
'thumbnail': 're:^https?://.*\.jpg',
|
||||
'timestamp': 1453760977,
|
||||
'upload_date': '20160125',
|
||||
'uploader_id': 'britneyspears',
|
||||
'uploader': 'Britney Spears',
|
||||
'like_count': int,
|
||||
'comment_count': int,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
@ -67,21 +81,57 @@ class InstagramIE(InfoExtractor):
|
||||
url = mobj.group('url')
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"',
|
||||
|
||||
(video_url, description, thumbnail, timestamp, uploader,
|
||||
uploader_id, like_count, comment_count) = [None] * 8
|
||||
|
||||
shared_data = self._parse_json(
|
||||
self._search_regex(
|
||||
r'window\._sharedData\s*=\s*({.+?});',
|
||||
webpage, 'shared data', default='{}'),
|
||||
video_id, fatal=False)
|
||||
if shared_data:
|
||||
media = try_get(
|
||||
shared_data, lambda x: x['entry_data']['PostPage'][0]['media'], dict)
|
||||
if media:
|
||||
video_url = media.get('video_url')
|
||||
description = media.get('caption')
|
||||
thumbnail = media.get('display_src')
|
||||
timestamp = int_or_none(media.get('date'))
|
||||
uploader = media.get('owner', {}).get('full_name')
|
||||
uploader_id = media.get('owner', {}).get('username')
|
||||
like_count = int_or_none(media.get('likes', {}).get('count'))
|
||||
comment_count = int_or_none(media.get('comments', {}).get('count'))
|
||||
|
||||
if not video_url:
|
||||
video_url = self._og_search_video_url(webpage, secure=False)
|
||||
|
||||
if not uploader_id:
|
||||
uploader_id = self._search_regex(
|
||||
r'"owner"\s*:\s*{\s*"username"\s*:\s*"(.+?)"',
|
||||
webpage, 'uploader id', fatal=False)
|
||||
desc = self._search_regex(
|
||||
r'"caption":"(.+?)"', webpage, 'description', default=None)
|
||||
if desc is not None:
|
||||
desc = lowercase_escape(desc)
|
||||
|
||||
if not description:
|
||||
description = self._search_regex(
|
||||
r'"caption"\s*:\s*"(.+?)"', webpage, 'description', default=None)
|
||||
if description is not None:
|
||||
description = lowercase_escape(description)
|
||||
|
||||
if not thumbnail:
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'url': self._og_search_video_url(webpage, secure=False),
|
||||
'url': video_url,
|
||||
'ext': 'mp4',
|
||||
'title': 'Video by %s' % uploader_id,
|
||||
'thumbnail': self._og_search_thumbnail(webpage),
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'timestamp': timestamp,
|
||||
'uploader_id': uploader_id,
|
||||
'description': desc,
|
||||
'uploader': uploader,
|
||||
'like_count': like_count,
|
||||
'comment_count': comment_count,
|
||||
}
|
||||
|
||||
|
||||
|
||||
@ -148,8 +148,8 @@ class KuwoAlbumIE(InfoExtractor):
|
||||
'url': 'http://www.kuwo.cn/album/502294/',
|
||||
'info_dict': {
|
||||
'id': '502294',
|
||||
'title': 'M',
|
||||
'description': 'md5:6a7235a84cc6400ec3b38a7bdaf1d60c',
|
||||
'title': 'Made\xa0Series\xa0《M》',
|
||||
'description': 'md5:d463f0d8a0ff3c3ea3d6ed7452a9483f',
|
||||
},
|
||||
'playlist_count': 2,
|
||||
}
|
||||
@ -209,7 +209,7 @@ class KuwoSingerIE(InfoExtractor):
|
||||
'url': 'http://www.kuwo.cn/mingxing/bruno+mars/',
|
||||
'info_dict': {
|
||||
'id': 'bruno+mars',
|
||||
'title': 'Bruno Mars',
|
||||
'title': 'Bruno\xa0Mars',
|
||||
},
|
||||
'playlist_mincount': 329,
|
||||
}, {
|
||||
@ -306,7 +306,7 @@ class KuwoMvIE(KuwoBaseIE):
|
||||
'id': '6480076',
|
||||
'ext': 'mp4',
|
||||
'title': 'My HouseMV',
|
||||
'creator': '2PM',
|
||||
'creator': 'PM02:00',
|
||||
},
|
||||
# In this video, music URLs (anti.s) are blocked outside China and
|
||||
# USA, while the MV URL (mvurl) is available globally, so force the MV
|
||||
|
||||
@ -28,7 +28,7 @@ from ..utils import (
|
||||
|
||||
class LeIE(InfoExtractor):
|
||||
IE_DESC = '乐视网'
|
||||
_VALID_URL = r'https?://www\.le\.com/ptv/vplay/(?P<id>\d+)\.html'
|
||||
_VALID_URL = r'https?://(?:www\.le\.com/ptv/vplay|sports\.le\.com/video)/(?P<id>\d+)\.html'
|
||||
|
||||
_URL_TEMPLATE = 'http://www.le.com/ptv/vplay/%s.html'
|
||||
|
||||
@ -69,6 +69,9 @@ class LeIE(InfoExtractor):
|
||||
'hls_prefer_native': True,
|
||||
},
|
||||
'skip': 'Only available in China',
|
||||
}, {
|
||||
'url': 'http://sports.le.com/video/25737697.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
@ -196,7 +199,7 @@ class LeIE(InfoExtractor):
|
||||
|
||||
|
||||
class LePlaylistIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://[a-z]+\.le\.com/[a-z]+/(?P<id>[a-z0-9_]+)'
|
||||
_VALID_URL = r'https?://[a-z]+\.le\.com/(?!video)[a-z]+/(?P<id>[a-z0-9_]+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.le.com/tv/46177.html',
|
||||
|
||||
@ -98,13 +98,19 @@ class LimelightBaseIE(InfoExtractor):
|
||||
} for thumbnail in properties.get('thumbnails', []) if thumbnail.get('url')]
|
||||
|
||||
subtitles = {}
|
||||
for caption in properties.get('captions', {}):
|
||||
for caption in properties.get('captions', []):
|
||||
lang = caption.get('language_code')
|
||||
subtitles_url = caption.get('url')
|
||||
if lang and subtitles_url:
|
||||
subtitles[lang] = [{
|
||||
subtitles.setdefault(lang, []).append({
|
||||
'url': subtitles_url,
|
||||
}]
|
||||
})
|
||||
closed_captions_url = properties.get('closed_captions_url')
|
||||
if closed_captions_url:
|
||||
subtitles.setdefault('en', []).append({
|
||||
'url': closed_captions_url,
|
||||
'ext': 'ttml',
|
||||
})
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
@ -123,7 +129,18 @@ class LimelightBaseIE(InfoExtractor):
|
||||
|
||||
class LimelightMediaIE(LimelightBaseIE):
|
||||
IE_NAME = 'limelight'
|
||||
_VALID_URL = r'(?:limelight:media:|https?://link\.videoplatform\.limelight\.com/media/\??\bmediaId=)(?P<id>[a-z0-9]{32})'
|
||||
_VALID_URL = r'''(?x)
|
||||
(?:
|
||||
limelight:media:|
|
||||
https?://
|
||||
(?:
|
||||
link\.videoplatform\.limelight\.com/media/|
|
||||
assets\.delvenetworks\.com/player/loader\.swf
|
||||
)
|
||||
\?.*?\bmediaId=
|
||||
)
|
||||
(?P<id>[a-z0-9]{32})
|
||||
'''
|
||||
_TESTS = [{
|
||||
'url': 'http://link.videoplatform.limelight.com/media/?mediaId=3ffd040b522b4485b6d84effc750cd86',
|
||||
'info_dict': {
|
||||
@ -158,6 +175,9 @@ class LimelightMediaIE(LimelightBaseIE):
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://assets.delvenetworks.com/player/loader.swf?mediaId=8018a574f08d416e95ceaccae4ba0452',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_PLAYLIST_SERVICE_PATH = 'media'
|
||||
_API_PATH = 'media'
|
||||
@ -176,15 +196,29 @@ class LimelightMediaIE(LimelightBaseIE):
|
||||
|
||||
class LimelightChannelIE(LimelightBaseIE):
|
||||
IE_NAME = 'limelight:channel'
|
||||
_VALID_URL = r'(?:limelight:channel:|https?://link\.videoplatform\.limelight\.com/media/\??\bchannelId=)(?P<id>[a-z0-9]{32})'
|
||||
_TEST = {
|
||||
_VALID_URL = r'''(?x)
|
||||
(?:
|
||||
limelight:channel:|
|
||||
https?://
|
||||
(?:
|
||||
link\.videoplatform\.limelight\.com/media/|
|
||||
assets\.delvenetworks\.com/player/loader\.swf
|
||||
)
|
||||
\?.*?\bchannelId=
|
||||
)
|
||||
(?P<id>[a-z0-9]{32})
|
||||
'''
|
||||
_TESTS = [{
|
||||
'url': 'http://link.videoplatform.limelight.com/media/?channelId=ab6a524c379342f9b23642917020c082',
|
||||
'info_dict': {
|
||||
'id': 'ab6a524c379342f9b23642917020c082',
|
||||
'title': 'Javascript Sample Code',
|
||||
},
|
||||
'playlist_mincount': 3,
|
||||
}
|
||||
}, {
|
||||
'url': 'http://assets.delvenetworks.com/player/loader.swf?channelId=ab6a524c379342f9b23642917020c082',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_PLAYLIST_SERVICE_PATH = 'channel'
|
||||
_API_PATH = 'channels'
|
||||
|
||||
@ -207,15 +241,29 @@ class LimelightChannelIE(LimelightBaseIE):
|
||||
|
||||
class LimelightChannelListIE(LimelightBaseIE):
|
||||
IE_NAME = 'limelight:channel_list'
|
||||
_VALID_URL = r'(?:limelight:channel_list:|https?://link\.videoplatform\.limelight\.com/media/\?.*?\bchannelListId=)(?P<id>[a-z0-9]{32})'
|
||||
_TEST = {
|
||||
_VALID_URL = r'''(?x)
|
||||
(?:
|
||||
limelight:channel_list:|
|
||||
https?://
|
||||
(?:
|
||||
link\.videoplatform\.limelight\.com/media/|
|
||||
assets\.delvenetworks\.com/player/loader\.swf
|
||||
)
|
||||
\?.*?\bchannelListId=
|
||||
)
|
||||
(?P<id>[a-z0-9]{32})
|
||||
'''
|
||||
_TESTS = [{
|
||||
'url': 'http://link.videoplatform.limelight.com/media/?channelListId=301b117890c4465c8179ede21fd92e2b',
|
||||
'info_dict': {
|
||||
'id': '301b117890c4465c8179ede21fd92e2b',
|
||||
'title': 'Website - Hero Player',
|
||||
},
|
||||
'playlist_mincount': 2,
|
||||
}
|
||||
}, {
|
||||
'url': 'https://assets.delvenetworks.com/player/loader.swf?channelListId=301b117890c4465c8179ede21fd92e2b',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_PLAYLIST_SERVICE_PATH = 'channel_list'
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@ -1,93 +1,94 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..compat import (
|
||||
compat_HTTPError,
|
||||
compat_str,
|
||||
compat_urlparse,
|
||||
)
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
clean_html,
|
||||
int_or_none,
|
||||
sanitized_Request,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
|
||||
class LyndaBaseIE(InfoExtractor):
|
||||
_LOGIN_URL = 'https://www.lynda.com/login/login.aspx'
|
||||
_SIGNIN_URL = 'https://www.lynda.com/signin'
|
||||
_PASSWORD_URL = 'https://www.lynda.com/signin/password'
|
||||
_USER_URL = 'https://www.lynda.com/signin/user'
|
||||
_ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to provide lynda.com account credentials.'
|
||||
_NETRC_MACHINE = 'lynda'
|
||||
|
||||
def _real_initialize(self):
|
||||
self._login()
|
||||
|
||||
@staticmethod
|
||||
def _check_error(json_string, key_or_keys):
|
||||
keys = [key_or_keys] if isinstance(key_or_keys, compat_str) else key_or_keys
|
||||
for key in keys:
|
||||
error = json_string.get(key)
|
||||
if error:
|
||||
raise ExtractorError('Unable to login: %s' % error, expected=True)
|
||||
|
||||
def _login_step(self, form_html, fallback_action_url, extra_form_data, note, referrer_url):
|
||||
action_url = self._search_regex(
|
||||
r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_html,
|
||||
'post url', default=fallback_action_url, group='url')
|
||||
|
||||
if not action_url.startswith('http'):
|
||||
action_url = compat_urlparse.urljoin(self._SIGNIN_URL, action_url)
|
||||
|
||||
form_data = self._hidden_inputs(form_html)
|
||||
form_data.update(extra_form_data)
|
||||
|
||||
try:
|
||||
response = self._download_json(
|
||||
action_url, None, note,
|
||||
data=urlencode_postdata(form_data),
|
||||
headers={
|
||||
'Referer': referrer_url,
|
||||
'X-Requested-With': 'XMLHttpRequest',
|
||||
})
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 500:
|
||||
response = self._parse_json(e.cause.read().decode('utf-8'), None)
|
||||
self._check_error(response, ('email', 'password'))
|
||||
raise
|
||||
|
||||
self._check_error(response, 'ErrorMessage')
|
||||
|
||||
return response, action_url
|
||||
|
||||
def _login(self):
|
||||
username, password = self._get_login_info()
|
||||
if username is None:
|
||||
return
|
||||
|
||||
login_form = {
|
||||
'username': username,
|
||||
'password': password,
|
||||
'remember': 'false',
|
||||
'stayPut': 'false'
|
||||
}
|
||||
request = sanitized_Request(
|
||||
self._LOGIN_URL, urlencode_postdata(login_form))
|
||||
login_page = self._download_webpage(
|
||||
request, None, 'Logging in as %s' % username)
|
||||
# Step 1: download signin page
|
||||
signin_page = self._download_webpage(
|
||||
self._SIGNIN_URL, None, 'Downloading signin page')
|
||||
|
||||
# Not (yet) logged in
|
||||
m = re.search(r'loginResultJson\s*=\s*\'(?P<json>[^\']+)\';', login_page)
|
||||
if m is not None:
|
||||
response = m.group('json')
|
||||
response_json = json.loads(response)
|
||||
state = response_json['state']
|
||||
|
||||
if state == 'notlogged':
|
||||
raise ExtractorError(
|
||||
'Unable to login, incorrect username and/or password',
|
||||
expected=True)
|
||||
|
||||
# This is when we get popup:
|
||||
# > You're already logged in to lynda.com on two devices.
|
||||
# > If you log in here, we'll log you out of another device.
|
||||
# So, we need to confirm this.
|
||||
if state == 'conflicted':
|
||||
confirm_form = {
|
||||
'username': '',
|
||||
'password': '',
|
||||
'resolve': 'true',
|
||||
'remember': 'false',
|
||||
'stayPut': 'false',
|
||||
}
|
||||
request = sanitized_Request(
|
||||
self._LOGIN_URL, urlencode_postdata(confirm_form))
|
||||
login_page = self._download_webpage(
|
||||
request, None,
|
||||
'Confirming log in and log out from another device')
|
||||
|
||||
if all(not re.search(p, login_page) for p in ('isLoggedIn\s*:\s*true', r'logout\.aspx', r'>Log out<')):
|
||||
if 'login error' in login_page:
|
||||
mobj = re.search(
|
||||
r'(?s)<h1[^>]+class="topmost">(?P<title>[^<]+)</h1>\s*<div>(?P<description>.+?)</div>',
|
||||
login_page)
|
||||
if mobj:
|
||||
raise ExtractorError(
|
||||
'lynda returned error: %s - %s'
|
||||
% (mobj.group('title'), clean_html(mobj.group('description'))),
|
||||
expected=True)
|
||||
raise ExtractorError('Unable to log in')
|
||||
|
||||
def _logout(self):
|
||||
username, _ = self._get_login_info()
|
||||
if username is None:
|
||||
# Already logged in
|
||||
if any(re.search(p, signin_page) for p in (
|
||||
'isLoggedIn\s*:\s*true', r'logout\.aspx', r'>Log out<')):
|
||||
return
|
||||
|
||||
self._download_webpage(
|
||||
'http://www.lynda.com/ajax/logout.aspx', None,
|
||||
'Logging out', 'Unable to log out', fatal=False)
|
||||
# Step 2: submit email
|
||||
signin_form = self._search_regex(
|
||||
r'(?s)(<form[^>]+data-form-name=["\']signin["\'][^>]*>.+?</form>)',
|
||||
signin_page, 'signin form')
|
||||
signin_page, signin_url = self._login_step(
|
||||
signin_form, self._PASSWORD_URL, {'email': username},
|
||||
'Submitting email', self._SIGNIN_URL)
|
||||
|
||||
# Step 3: submit password
|
||||
password_form = signin_page['body']
|
||||
self._login_step(
|
||||
password_form, self._USER_URL, {'email': username, 'password': password},
|
||||
'Submitting password', signin_url)
|
||||
|
||||
|
||||
class LyndaIE(LyndaBaseIE):
|
||||
@ -212,8 +213,6 @@ class LyndaCourseIE(LyndaBaseIE):
|
||||
'http://www.lynda.com/ajax/player?courseId=%s&type=course' % course_id,
|
||||
course_id, 'Downloading course JSON')
|
||||
|
||||
self._logout()
|
||||
|
||||
if course.get('Status') == 'NotFound':
|
||||
raise ExtractorError(
|
||||
'Course %s does not exist' % course_id, expected=True)
|
||||
@ -246,5 +245,6 @@ class LyndaCourseIE(LyndaBaseIE):
|
||||
% unaccessible_videos + self._ACCOUNT_CREDENTIALS_HINT)
|
||||
|
||||
course_title = course.get('Title')
|
||||
course_description = course.get('Description')
|
||||
|
||||
return self.playlist_result(entries, course_id, course_title)
|
||||
return self.playlist_result(entries, course_id, course_title, course_description)
|
||||
|
||||
@ -4,16 +4,12 @@ from __future__ import unicode_literals
|
||||
import random
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_urllib_parse_urlencode
|
||||
from ..utils import (
|
||||
sanitized_Request,
|
||||
xpath_text,
|
||||
)
|
||||
from ..utils import xpath_text
|
||||
|
||||
|
||||
class MatchTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://matchtv\.ru/?#live-player'
|
||||
_TEST = {
|
||||
_VALID_URL = r'https?://matchtv\.ru(?:/on-air|/?#live-player)'
|
||||
_TESTS = [{
|
||||
'url': 'http://matchtv.ru/#live-player',
|
||||
'info_dict': {
|
||||
'id': 'matchtv-live',
|
||||
@ -24,12 +20,16 @@ class MatchTVIE(InfoExtractor):
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}
|
||||
}, {
|
||||
'url': 'http://matchtv.ru/on-air/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = 'matchtv-live'
|
||||
request = sanitized_Request(
|
||||
'http://player.matchtv.ntvplus.tv/player/smil?%s' % compat_urllib_parse_urlencode({
|
||||
video_url = self._download_json(
|
||||
'http://player.matchtv.ntvplus.tv/player/smil', video_id,
|
||||
query={
|
||||
'ts': '',
|
||||
'quality': 'SD',
|
||||
'contentId': '561d2c0df7159b37178b4567',
|
||||
@ -40,11 +40,10 @@ class MatchTVIE(InfoExtractor):
|
||||
'contentType': 'channel',
|
||||
'timeShift': '0',
|
||||
'platform': 'portal',
|
||||
}),
|
||||
},
|
||||
headers={
|
||||
'Referer': 'http://player.matchtv.ntvplus.tv/embed-player/NTVEmbedPlayer.swf',
|
||||
})
|
||||
video_url = self._download_json(request, video_id)['data']['videoUrl']
|
||||
})['data']['videoUrl']
|
||||
f4m_url = xpath_text(self._download_xml(video_url, video_id), './to')
|
||||
formats = self._extract_f4m_formats(f4m_url, video_id)
|
||||
self._sort_formats(formats)
|
||||
|
||||
@ -67,6 +67,23 @@ class NBCIE(InfoExtractor):
|
||||
# This video has expired but with an escaped embedURL
|
||||
'url': 'http://www.nbc.com/parenthood/episode-guide/season-5/just-like-at-home/515',
|
||||
'only_matching': True,
|
||||
},
|
||||
{
|
||||
# HLS streams requires the 'hdnea3' cookie
|
||||
'url': 'http://www.nbc.com/Kings/video/goliath/n1806',
|
||||
'info_dict': {
|
||||
'id': 'n1806',
|
||||
'ext': 'mp4',
|
||||
'title': 'Goliath',
|
||||
'description': 'When an unknown soldier saves the life of the King\'s son in battle, he\'s thrust into the limelight and politics of the kingdom.',
|
||||
'timestamp': 1237100400,
|
||||
'upload_date': '20090315',
|
||||
'uploader': 'NBCU-COM',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'skip': 'Only works from US',
|
||||
}
|
||||
]
|
||||
|
||||
@ -249,6 +266,11 @@ class NBCNewsIE(ThePlatformIE):
|
||||
'url': 'http://www.nbcnews.com/watch/dateline/full-episode--deadly-betrayal-386250819952',
|
||||
'only_matching': True,
|
||||
},
|
||||
{
|
||||
# From http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html
|
||||
'url': 'http://www.nbcnews.com/widget/video-embed/701714499682',
|
||||
'only_matching': True,
|
||||
},
|
||||
]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -272,18 +294,17 @@ class NBCNewsIE(ThePlatformIE):
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
info = None
|
||||
bootstrap_json = self._search_regex(
|
||||
r'(?m)var\s+(?:bootstrapJson|playlistData)\s*=\s*({.+});?\s*$',
|
||||
[r'(?m)(?:var\s+(?:bootstrapJson|playlistData)|NEWS\.videoObj)\s*=\s*({.+});?\s*$',
|
||||
r'videoObj\s*:\s*({.+})', r'data-video="([^"]+)"'],
|
||||
webpage, 'bootstrap json', default=None)
|
||||
if bootstrap_json:
|
||||
bootstrap = self._parse_json(bootstrap_json, display_id)
|
||||
bootstrap = self._parse_json(
|
||||
bootstrap_json, display_id, transform_source=unescapeHTML)
|
||||
if 'results' in bootstrap:
|
||||
info = bootstrap['results'][0]['video']
|
||||
elif 'video' in bootstrap:
|
||||
info = bootstrap['video']
|
||||
else:
|
||||
player_instance_json = self._search_regex(
|
||||
r'videoObj\s*:\s*({.+})', webpage, 'player instance', default=None)
|
||||
if not player_instance_json:
|
||||
player_instance_json = self._html_search_regex(
|
||||
r'data-video="([^"]+)"', webpage, 'video json')
|
||||
info = self._parse_json(player_instance_json, display_id)
|
||||
info = bootstrap
|
||||
video_id = info['mpxId']
|
||||
title = info['title']
|
||||
|
||||
|
||||
@ -163,7 +163,7 @@ class NRKTVIE(NRKBaseIE):
|
||||
'ext': 'mp4',
|
||||
'title': '20 spørsmål 23.05.2014',
|
||||
'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
|
||||
'duration': 1741.52,
|
||||
'duration': 1741,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://tv.nrk.no/program/mdfp15000514',
|
||||
@ -173,7 +173,7 @@ class NRKTVIE(NRKBaseIE):
|
||||
'ext': 'mp4',
|
||||
'title': 'Grunnlovsjubiléet - Stor ståhei for ingenting 24.05.2014',
|
||||
'description': 'md5:89290c5ccde1b3a24bb8050ab67fe1db',
|
||||
'duration': 4605.08,
|
||||
'duration': 4605,
|
||||
},
|
||||
}, {
|
||||
# single playlist video
|
||||
@ -260,30 +260,34 @@ class NRKPlaylistIE(InfoExtractor):
|
||||
|
||||
class NRKSkoleIE(InfoExtractor):
|
||||
IE_DESC = 'NRK Skole'
|
||||
_VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/klippdetalj?.*\btopic=(?P<id>[^/?#&]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/?\?.*\bmediaId=(?P<id>\d+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://nrk.no/skole/klippdetalj?topic=nrk:klipp/616532',
|
||||
'md5': '04cd85877cc1913bce73c5d28a47e00f',
|
||||
'url': 'https://www.nrk.no/skole/?page=search&q=&mediaId=14099',
|
||||
'md5': '6bc936b01f9dd8ed45bc58b252b2d9b6',
|
||||
'info_dict': {
|
||||
'id': '6021',
|
||||
'ext': 'flv',
|
||||
'ext': 'mp4',
|
||||
'title': 'Genetikk og eneggede tvillinger',
|
||||
'description': 'md5:3aca25dcf38ec30f0363428d2b265f8d',
|
||||
'duration': 399,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.nrk.no/skole/klippdetalj?topic=nrk%3Aklipp%2F616532#embed',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.nrk.no/skole/klippdetalj?topic=urn:x-mediadb:21379',
|
||||
'url': 'https://www.nrk.no/skole/?page=objectives&subject=naturfag&objective=K15114&mediaId=19355',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = compat_urllib_parse_unquote(self._match_id(url))
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
webpage = self._download_webpage(
|
||||
'https://mimir.nrk.no/plugin/1.0/static?mediaId=%s' % video_id,
|
||||
video_id)
|
||||
|
||||
nrk_id = self._parse_json(
|
||||
self._search_regex(
|
||||
r'<script[^>]+type=["\']application/json["\'][^>]*>({.+?})</script>',
|
||||
webpage, 'application json'),
|
||||
video_id)['activeMedia']['psId']
|
||||
|
||||
nrk_id = self._search_regex(r'data-nrk-id=["\'](\d+)', webpage, 'nrk id')
|
||||
return self.url_result('nrk:%s' % nrk_id)
|
||||
|
||||
@ -14,7 +14,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class OpenloadIE(InfoExtractor):
|
||||
_VALID_URL = r'https://openload.(?:co|io)/(?:f|embed)/(?P<id>[a-zA-Z0-9-]+)'
|
||||
_VALID_URL = r'https://openload.(?:co|io)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://openload.co/f/kUEfGclsU9o',
|
||||
@ -31,6 +31,9 @@ class OpenloadIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'https://openload.io/f/ZAn6oz-VZGE/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://openload.co/f/_-ztPaZtMhM/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# unavailable via https://openload.co/f/Sxz5sADo82g/, different layout
|
||||
# for title and ext
|
||||
@ -100,7 +103,7 @@ class OpenloadIE(InfoExtractor):
|
||||
raise ExtractorError('File not found', expected=True)
|
||||
|
||||
code = self._search_regex(
|
||||
r'</video>\s*</div>\s*<script[^>]+>([^<]+)</script>',
|
||||
r'</video>\s*</div>\s*<script[^>]+>[^>]+</script>\s*<script[^>]+>([^<]+)</script>',
|
||||
webpage, 'JS code')
|
||||
|
||||
decoded = self.openload_decode(code)
|
||||
|
||||
@ -5,6 +5,7 @@ import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
sanitized_Request,
|
||||
urlencode_postdata,
|
||||
)
|
||||
@ -14,7 +15,7 @@ class StreamcloudIE(InfoExtractor):
|
||||
IE_NAME = 'streamcloud.eu'
|
||||
_VALID_URL = r'https?://streamcloud\.eu/(?P<id>[a-zA-Z0-9_-]+)(?:/(?P<fname>[^#?]*)\.html)?'
|
||||
|
||||
_TEST = {
|
||||
_TESTS = [{
|
||||
'url': 'http://streamcloud.eu/skp9j99s4bpz/youtube-dl_test_video_____________-BaW_jenozKc.mp4.html',
|
||||
'md5': '6bea4c7fa5daaacc2a946b7146286686',
|
||||
'info_dict': {
|
||||
@ -23,7 +24,10 @@ class StreamcloudIE(InfoExtractor):
|
||||
'title': 'youtube-dl test video \'/\\ ä ↭',
|
||||
},
|
||||
'skip': 'Only available from the EU'
|
||||
}
|
||||
}, {
|
||||
'url': 'http://streamcloud.eu/ua8cmfh1nbe6/NSHIP-148--KUC-NG--H264-.mp4.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
@ -31,6 +35,10 @@ class StreamcloudIE(InfoExtractor):
|
||||
|
||||
orig_webpage = self._download_webpage(url, video_id)
|
||||
|
||||
if '>File Not Found<' in orig_webpage:
|
||||
raise ExtractorError(
|
||||
'Video %s does not exist' % video_id, expected=True)
|
||||
|
||||
fields = re.findall(r'''(?x)<input\s+
|
||||
type="(?:hidden|submit)"\s+
|
||||
name="([^"]+)"\s+
|
||||
|
||||
55
youtube_dl/extractor/telewebion.py
Normal file
55
youtube_dl/extractor/telewebion.py
Normal file
@ -0,0 +1,55 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class TelewebionIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.telewebion\.com/#!/episode/(?P<id>\d+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.telewebion.com/#!/episode/1263668/',
|
||||
'info_dict': {
|
||||
'id': '1263668',
|
||||
'ext': 'mp4',
|
||||
'title': 'قرعه\u200cکشی لیگ قهرمانان اروپا',
|
||||
'thumbnail': 're:^https?://.*\.jpg',
|
||||
'view_count': int,
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
secure_token = self._download_webpage(
|
||||
'http://m.s2.telewebion.com/op/op?action=getSecurityToken', video_id)
|
||||
episode_details = self._download_json(
|
||||
'http://m.s2.telewebion.com/op/op', video_id,
|
||||
query={'action': 'getEpisodeDetails', 'episode_id': video_id})
|
||||
|
||||
m3u8_url = 'http://m.s1.telewebion.com/smil/%s.m3u8?filepath=%s&m3u8=1&secure_token=%s' % (
|
||||
video_id, episode_details['file_path'], secure_token)
|
||||
formats = self._extract_m3u8_formats(
|
||||
m3u8_url, video_id, ext='mp4', m3u8_id='hls')
|
||||
|
||||
picture_paths = [
|
||||
episode_details.get('picture_path'),
|
||||
episode_details.get('large_picture_path'),
|
||||
]
|
||||
|
||||
thumbnails = [{
|
||||
'url': picture_path,
|
||||
'preference': idx,
|
||||
} for idx, picture_path in enumerate(picture_paths) if picture_path is not None]
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': episode_details['title'],
|
||||
'formats': formats,
|
||||
'thumbnails': thumbnails,
|
||||
'view_count': episode_details.get('view_count'),
|
||||
}
|
||||
@ -14,11 +14,13 @@ from ..compat import (
|
||||
compat_urllib_parse_urlparse,
|
||||
)
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
sanitized_Request,
|
||||
unsmuggle_url,
|
||||
update_url_query,
|
||||
xpath_with_ns,
|
||||
mimetype2ext,
|
||||
find_xpath_attr,
|
||||
@ -48,6 +50,12 @@ class ThePlatformBaseIE(OnceIE):
|
||||
if OnceIE.suitable(_format['url']):
|
||||
formats.extend(self._extract_once_formats(_format['url']))
|
||||
else:
|
||||
media_url = _format['url']
|
||||
if determine_ext(media_url) == 'm3u8':
|
||||
hdnea2 = self._get_cookies(media_url).get('hdnea2')
|
||||
if hdnea2:
|
||||
_format['url'] = update_url_query(media_url, {'hdnea3': hdnea2.value})
|
||||
|
||||
formats.append(_format)
|
||||
|
||||
subtitles = self._parse_smil_subtitles(meta, default_ns)
|
||||
|
||||
@ -5,6 +5,7 @@ import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
float_or_none,
|
||||
xpath_text,
|
||||
remove_end,
|
||||
@ -52,7 +53,7 @@ class TwitterCardIE(TwitterBaseIE):
|
||||
'id': 'dq4Oj5quskI',
|
||||
'ext': 'mp4',
|
||||
'title': 'Ubuntu 11.10 Overview',
|
||||
'description': 'Take a quick peek at what\'s new and improved in Ubuntu 11.10.\n\nOnce installed take a look at 10 Things to Do After Installing: http://www.omgubuntu.co.uk/2011/10/10-things-to-do-after-installing-ubuntu-11-10/',
|
||||
'description': 'Take a quick peek at what\'s new and improved in Ubuntu 11.10.\n\nOnce installed take a look at 10 Things to Do After Installing: http://www.omgubuntu.co.uk/2011/10/10...',
|
||||
'upload_date': '20111013',
|
||||
'uploader': 'OMG! Ubuntu!',
|
||||
'uploader_id': 'omgubuntu',
|
||||
@ -116,6 +117,9 @@ class TwitterCardIE(TwitterBaseIE):
|
||||
video_url = config.get('video_url') or config.get('playlist', [{}])[0].get('source')
|
||||
|
||||
if video_url:
|
||||
if determine_ext(video_url) == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(video_url, video_id, ext='mp4', m3u8_id='hls'))
|
||||
else:
|
||||
f = {
|
||||
'url': video_url,
|
||||
}
|
||||
@ -207,6 +211,7 @@ class TwitterIE(InfoExtractor):
|
||||
'uploader_id': 'giphz',
|
||||
},
|
||||
'expected_warnings': ['height', 'width'],
|
||||
'skip': 'Account suspended',
|
||||
}, {
|
||||
'url': 'https://twitter.com/starwars/status/665052190608723968',
|
||||
'md5': '39b7199856dee6cd4432e72c74bc69d4',
|
||||
@ -239,10 +244,10 @@ class TwitterIE(InfoExtractor):
|
||||
'info_dict': {
|
||||
'id': '700207533655363584',
|
||||
'ext': 'mp4',
|
||||
'title': 'jay - BEAT PROD: @suhmeduh #Damndaniel',
|
||||
'description': 'jay on Twitter: "BEAT PROD: @suhmeduh https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ"',
|
||||
'title': 'Donte The Dumbass - BEAT PROD: @suhmeduh #Damndaniel',
|
||||
'description': 'Donte The Dumbass on Twitter: "BEAT PROD: @suhmeduh https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ"',
|
||||
'thumbnail': 're:^https?://.*\.jpg',
|
||||
'uploader': 'jay',
|
||||
'uploader': 'Donte The Dumbass',
|
||||
'uploader_id': 'jaydingeer',
|
||||
},
|
||||
'params': {
|
||||
@ -262,7 +267,6 @@ class TwitterIE(InfoExtractor):
|
||||
'add_ie': ['Vine'],
|
||||
}, {
|
||||
'url': 'https://twitter.com/captainamerica/status/719944021058060289',
|
||||
# md5 constantly changes
|
||||
'info_dict': {
|
||||
'id': '719944021058060289',
|
||||
'ext': 'mp4',
|
||||
@ -271,6 +275,9 @@ class TwitterIE(InfoExtractor):
|
||||
'uploader_id': 'captainamerica',
|
||||
'uploader': 'Captain America',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True, # requires ffmpeg
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -278,7 +285,11 @@ class TwitterIE(InfoExtractor):
|
||||
user_id = mobj.group('user_id')
|
||||
twid = mobj.group('id')
|
||||
|
||||
webpage = self._download_webpage(self._TEMPLATE_URL % (user_id, twid), twid)
|
||||
webpage, urlh = self._download_webpage_handle(
|
||||
self._TEMPLATE_URL % (user_id, twid), twid)
|
||||
|
||||
if 'twitter.com/account/suspended' in urlh.geturl():
|
||||
raise ExtractorError('Account suspended by Twitter.', expected=True)
|
||||
|
||||
username = remove_end(self._og_search_title(webpage), ' on Twitter')
|
||||
|
||||
|
||||
@ -2,6 +2,7 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
@ -12,11 +13,11 @@ from ..utils import (
|
||||
|
||||
|
||||
class VesselIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?vessel\.com/videos/(?P<id>[0-9a-zA-Z]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?vessel\.com/(?:videos|embed)/(?P<id>[0-9a-zA-Z]+)'
|
||||
_API_URL_TEMPLATE = 'https://www.vessel.com/api/view/items/%s'
|
||||
_LOGIN_URL = 'https://www.vessel.com/api/account/login'
|
||||
_NETRC_MACHINE = 'vessel'
|
||||
_TEST = {
|
||||
_TESTS = [{
|
||||
'url': 'https://www.vessel.com/videos/HDN7G5UMs',
|
||||
'md5': '455cdf8beb71c6dd797fd2f3818d05c4',
|
||||
'info_dict': {
|
||||
@ -28,7 +29,16 @@ class VesselIE(InfoExtractor):
|
||||
'description': 'Did Nvidia pull out all the stops on the Titan X, or does its performance leave something to be desired?',
|
||||
'timestamp': int,
|
||||
},
|
||||
}
|
||||
}, {
|
||||
'url': 'https://www.vessel.com/embed/G4U7gUJ6a?w=615&h=346',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _extract_urls(webpage):
|
||||
return [url for _, url in re.findall(
|
||||
r'<iframe[^>]+src=(["\'])((?:https?:)?//(?:www\.)?vessel\.com/embed/[0-9a-zA-Z]+.*?)\1',
|
||||
webpage)]
|
||||
|
||||
@staticmethod
|
||||
def make_json_request(url, data):
|
||||
@ -98,16 +108,24 @@ class VesselIE(InfoExtractor):
|
||||
|
||||
formats = []
|
||||
for f in video_asset.get('sources', []):
|
||||
if f['name'] == 'hls-index':
|
||||
location = f.get('location')
|
||||
if not location:
|
||||
continue
|
||||
name = f.get('name')
|
||||
if name == 'hls-index':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
f['location'], video_id, ext='mp4', m3u8_id='m3u8'))
|
||||
location, video_id, ext='mp4',
|
||||
entry_protocol='m3u8_native', m3u8_id='m3u8', fatal=False))
|
||||
elif name == 'dash-index':
|
||||
formats.extend(self._extract_mpd_formats(
|
||||
location, video_id, mpd_id='dash', fatal=False))
|
||||
else:
|
||||
formats.append({
|
||||
'format_id': f['name'],
|
||||
'format_id': name,
|
||||
'tbr': f.get('bitrate'),
|
||||
'height': f.get('height'),
|
||||
'width': f.get('width'),
|
||||
'url': f['location'],
|
||||
'url': location,
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
|
||||
@ -101,10 +101,13 @@ class VikiBaseIE(InfoExtractor):
|
||||
self.report_warning('Unable to get session token, login has probably failed')
|
||||
|
||||
@staticmethod
|
||||
def dict_selection(dict_obj, preferred_key):
|
||||
def dict_selection(dict_obj, preferred_key, allow_fallback=True):
|
||||
if preferred_key in dict_obj:
|
||||
return dict_obj.get(preferred_key)
|
||||
|
||||
if not allow_fallback:
|
||||
return
|
||||
|
||||
filtered_dict = list(filter(None, [dict_obj.get(k) for k in dict_obj.keys()]))
|
||||
return filtered_dict[0] if filtered_dict else None
|
||||
|
||||
@ -127,7 +130,7 @@ class VikiIE(VikiBaseIE):
|
||||
}, {
|
||||
# clip
|
||||
'url': 'http://www.viki.com/videos/1067139v-the-avengers-age-of-ultron-press-conference',
|
||||
'md5': '86c0b5dbd4d83a6611a79987cc7a1989',
|
||||
'md5': 'feea2b1d7b3957f70886e6dfd8b8be84',
|
||||
'info_dict': {
|
||||
'id': '1067139v',
|
||||
'ext': 'mp4',
|
||||
@ -156,17 +159,18 @@ class VikiIE(VikiBaseIE):
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
}
|
||||
},
|
||||
'skip': 'Blocked in the US',
|
||||
}, {
|
||||
# episode
|
||||
'url': 'http://www.viki.com/videos/44699v-boys-over-flowers-episode-1',
|
||||
'md5': '190f3ef426005ba3a080a63325955bc3',
|
||||
'md5': '1f54697dabc8f13f31bf06bb2e4de6db',
|
||||
'info_dict': {
|
||||
'id': '44699v',
|
||||
'ext': 'mp4',
|
||||
'title': 'Boys Over Flowers - Episode 1',
|
||||
'description': 'md5:52617e4f729c7d03bfd4bcbbb6e946f2',
|
||||
'duration': 4155,
|
||||
'description': 'md5:b89cf50038b480b88b5b3c93589a9076',
|
||||
'duration': 4204,
|
||||
'timestamp': 1270496524,
|
||||
'upload_date': '20100405',
|
||||
'uploader': 'group8',
|
||||
@ -196,7 +200,7 @@ class VikiIE(VikiBaseIE):
|
||||
}, {
|
||||
# non-English description
|
||||
'url': 'http://www.viki.com/videos/158036v-love-in-magic',
|
||||
'md5': '1713ae35df5a521b31f6dc40730e7c9c',
|
||||
'md5': '013dc282714e22acf9447cad14ff1208',
|
||||
'info_dict': {
|
||||
'id': '158036v',
|
||||
'ext': 'mp4',
|
||||
@ -217,7 +221,7 @@ class VikiIE(VikiBaseIE):
|
||||
|
||||
self._check_errors(video)
|
||||
|
||||
title = self.dict_selection(video.get('titles', {}), 'en')
|
||||
title = self.dict_selection(video.get('titles', {}), 'en', allow_fallback=False)
|
||||
if not title:
|
||||
title = 'Episode %d' % video.get('number') if video.get('type') == 'episode' else video.get('id') or video_id
|
||||
container_titles = video.get('container', {}).get('titles', {})
|
||||
@ -302,7 +306,7 @@ class VikiChannelIE(VikiBaseIE):
|
||||
'title': 'Boys Over Flowers',
|
||||
'description': 'md5:ecd3cff47967fe193cff37c0bec52790',
|
||||
},
|
||||
'playlist_count': 70,
|
||||
'playlist_mincount': 71,
|
||||
}, {
|
||||
'url': 'http://www.viki.com/tv/1354c-poor-nastya-complete',
|
||||
'info_dict': {
|
||||
|
||||
@ -66,6 +66,69 @@ class VimeoBaseInfoExtractor(InfoExtractor):
|
||||
def _set_vimeo_cookie(self, name, value):
|
||||
self._set_cookie('vimeo.com', name, value)
|
||||
|
||||
def _vimeo_sort_formats(self, formats):
|
||||
# Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
|
||||
# at the same time without actual units specified. This lead to wrong sorting.
|
||||
self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'format_id'))
|
||||
|
||||
def _parse_config(self, config, video_id):
|
||||
# Extract title
|
||||
video_title = config['video']['title']
|
||||
|
||||
# Extract uploader, uploader_url and uploader_id
|
||||
video_uploader = config['video'].get('owner', {}).get('name')
|
||||
video_uploader_url = config['video'].get('owner', {}).get('url')
|
||||
video_uploader_id = video_uploader_url.split('/')[-1] if video_uploader_url else None
|
||||
|
||||
# Extract video thumbnail
|
||||
video_thumbnail = config['video'].get('thumbnail')
|
||||
if video_thumbnail is None:
|
||||
video_thumbs = config['video'].get('thumbs')
|
||||
if video_thumbs and isinstance(video_thumbs, dict):
|
||||
_, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
|
||||
|
||||
# Extract video duration
|
||||
video_duration = int_or_none(config['video'].get('duration'))
|
||||
|
||||
formats = []
|
||||
config_files = config['video'].get('files') or config['request'].get('files', {})
|
||||
for f in config_files.get('progressive', []):
|
||||
video_url = f.get('url')
|
||||
if not video_url:
|
||||
continue
|
||||
formats.append({
|
||||
'url': video_url,
|
||||
'format_id': 'http-%s' % f.get('quality'),
|
||||
'width': int_or_none(f.get('width')),
|
||||
'height': int_or_none(f.get('height')),
|
||||
'fps': int_or_none(f.get('fps')),
|
||||
'tbr': int_or_none(f.get('bitrate')),
|
||||
})
|
||||
m3u8_url = config_files.get('hls', {}).get('url')
|
||||
if m3u8_url:
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
|
||||
|
||||
subtitles = {}
|
||||
text_tracks = config['request'].get('text_tracks')
|
||||
if text_tracks:
|
||||
for tt in text_tracks:
|
||||
subtitles[tt['lang']] = [{
|
||||
'ext': 'vtt',
|
||||
'url': 'https://vimeo.com' + tt['url'],
|
||||
}]
|
||||
|
||||
return {
|
||||
'title': video_title,
|
||||
'uploader': video_uploader,
|
||||
'uploader_id': video_uploader_id,
|
||||
'uploader_url': video_uploader_url,
|
||||
'thumbnail': video_thumbnail,
|
||||
'duration': video_duration,
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
}
|
||||
|
||||
|
||||
class VimeoIE(VimeoBaseInfoExtractor):
|
||||
"""Information extractor for vimeo.com."""
|
||||
@ -153,7 +216,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
||||
'uploader_id': 'user18948128',
|
||||
'uploader': 'Jaime Marquínez Ferrándiz',
|
||||
'duration': 10,
|
||||
'description': 'This is "youtube-dl password protected test video" by Jaime Marquínez Ferrándiz on Vimeo, the home for high quality videos and the people\u2026',
|
||||
'description': 'This is "youtube-dl password protected test video" by on Vimeo, the home for high quality videos and the people who love them.',
|
||||
},
|
||||
'params': {
|
||||
'videopassword': 'youtube-dl',
|
||||
@ -389,21 +452,6 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
||||
'https://player.vimeo.com/player/%s' % feature_id,
|
||||
{'force_feature_id': True}), 'Vimeo')
|
||||
|
||||
# Extract title
|
||||
video_title = config['video']['title']
|
||||
|
||||
# Extract uploader, uploader_url and uploader_id
|
||||
video_uploader = config['video'].get('owner', {}).get('name')
|
||||
video_uploader_url = config['video'].get('owner', {}).get('url')
|
||||
video_uploader_id = video_uploader_url.split('/')[-1] if video_uploader_url else None
|
||||
|
||||
# Extract video thumbnail
|
||||
video_thumbnail = config['video'].get('thumbnail')
|
||||
if video_thumbnail is None:
|
||||
video_thumbs = config['video'].get('thumbs')
|
||||
if video_thumbs and isinstance(video_thumbs, dict):
|
||||
_, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
|
||||
|
||||
# Extract video description
|
||||
|
||||
video_description = self._html_search_regex(
|
||||
@ -423,9 +471,6 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
||||
if not video_description and not mobj.group('player'):
|
||||
self._downloader.report_warning('Cannot find video description')
|
||||
|
||||
# Extract video duration
|
||||
video_duration = int_or_none(config['video'].get('duration'))
|
||||
|
||||
# Extract upload date
|
||||
video_upload_date = None
|
||||
mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage)
|
||||
@ -463,53 +508,22 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
||||
'format_id': source_name,
|
||||
'preference': 1,
|
||||
})
|
||||
config_files = config['video'].get('files') or config['request'].get('files', {})
|
||||
for f in config_files.get('progressive', []):
|
||||
video_url = f.get('url')
|
||||
if not video_url:
|
||||
continue
|
||||
formats.append({
|
||||
'url': video_url,
|
||||
'format_id': 'http-%s' % f.get('quality'),
|
||||
'width': int_or_none(f.get('width')),
|
||||
'height': int_or_none(f.get('height')),
|
||||
'fps': int_or_none(f.get('fps')),
|
||||
'tbr': int_or_none(f.get('bitrate')),
|
||||
})
|
||||
m3u8_url = config_files.get('hls', {}).get('url')
|
||||
if m3u8_url:
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
|
||||
# Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
|
||||
# at the same time without actual units specified. This lead to wrong sorting.
|
||||
self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'format_id'))
|
||||
|
||||
subtitles = {}
|
||||
text_tracks = config['request'].get('text_tracks')
|
||||
if text_tracks:
|
||||
for tt in text_tracks:
|
||||
subtitles[tt['lang']] = [{
|
||||
'ext': 'vtt',
|
||||
'url': 'https://vimeo.com' + tt['url'],
|
||||
}]
|
||||
|
||||
return {
|
||||
info_dict = self._parse_config(config, video_id)
|
||||
formats.extend(info_dict['formats'])
|
||||
self._vimeo_sort_formats(formats)
|
||||
info_dict.update({
|
||||
'id': video_id,
|
||||
'uploader': video_uploader,
|
||||
'uploader_url': video_uploader_url,
|
||||
'uploader_id': video_uploader_id,
|
||||
'upload_date': video_upload_date,
|
||||
'title': video_title,
|
||||
'thumbnail': video_thumbnail,
|
||||
'description': video_description,
|
||||
'duration': video_duration,
|
||||
'formats': formats,
|
||||
'upload_date': video_upload_date,
|
||||
'description': video_description,
|
||||
'webpage_url': url,
|
||||
'view_count': view_count,
|
||||
'like_count': like_count,
|
||||
'comment_count': comment_count,
|
||||
'subtitles': subtitles,
|
||||
}
|
||||
})
|
||||
|
||||
return info_dict
|
||||
|
||||
|
||||
class VimeoOndemandIE(VimeoBaseInfoExtractor):
|
||||
@ -692,7 +706,7 @@ class VimeoGroupsIE(VimeoAlbumIE):
|
||||
return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)
|
||||
|
||||
|
||||
class VimeoReviewIE(InfoExtractor):
|
||||
class VimeoReviewIE(VimeoBaseInfoExtractor):
|
||||
IE_NAME = 'vimeo:review'
|
||||
IE_DESC = 'Review pages on vimeo'
|
||||
_VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
|
||||
@ -704,6 +718,7 @@ class VimeoReviewIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': "DICK HARDWICK 'Comedian'",
|
||||
'uploader': 'Richard Hardwick',
|
||||
'uploader_id': 'user21297594',
|
||||
}
|
||||
}, {
|
||||
'note': 'video player needs Referer',
|
||||
@ -716,14 +731,18 @@ class VimeoReviewIE(InfoExtractor):
|
||||
'uploader': 'DevWeek Events',
|
||||
'duration': 2773,
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'uploader_id': 'user22258446',
|
||||
}
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
player_url = 'https://player.vimeo.com/player/' + video_id
|
||||
return self.url_result(player_url, 'Vimeo', video_id)
|
||||
video_id = self._match_id(url)
|
||||
config = self._download_json(
|
||||
'https://player.vimeo.com/video/%s/config' % video_id, video_id)
|
||||
info_dict = self._parse_config(config, video_id)
|
||||
self._vimeo_sort_formats(info_dict['formats'])
|
||||
info_dict['id'] = video_id
|
||||
return info_dict
|
||||
|
||||
|
||||
class VimeoWatchLaterIE(VimeoChannelIE):
|
||||
|
||||
@ -3,7 +3,10 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_urlparse
|
||||
from ..compat import (
|
||||
compat_str,
|
||||
compat_urlparse,
|
||||
)
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
determine_ext,
|
||||
@ -16,13 +19,13 @@ class VoiceRepublicIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://voicerepublic\.com/(?:talks|embed)/(?P<id>[0-9a-z-]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://voicerepublic.com/talks/watching-the-watchers-building-a-sousveillance-state',
|
||||
'md5': '0554a24d1657915aa8e8f84e15dc9353',
|
||||
'md5': 'b9174d651323f17783000876347116e3',
|
||||
'info_dict': {
|
||||
'id': '2296',
|
||||
'display_id': 'watching-the-watchers-building-a-sousveillance-state',
|
||||
'ext': 'm4a',
|
||||
'title': 'Watching the Watchers: Building a Sousveillance State',
|
||||
'description': 'md5:715ba964958afa2398df615809cfecb1',
|
||||
'description': 'Secret surveillance programs have metadata too. The people and companies that operate secret surveillance programs can be surveilled.',
|
||||
'thumbnail': 're:^https?://.*\.(?:png|jpg)$',
|
||||
'duration': 1800,
|
||||
'view_count': int,
|
||||
@ -52,7 +55,7 @@ class VoiceRepublicIE(InfoExtractor):
|
||||
if data:
|
||||
title = data['title']
|
||||
description = data.get('teaser')
|
||||
talk_id = data.get('talk_id') or display_id
|
||||
talk_id = compat_str(data.get('talk_id') or display_id)
|
||||
talk = data['talk']
|
||||
duration = int_or_none(talk.get('duration'))
|
||||
formats = [{
|
||||
|
||||
@ -4,6 +4,7 @@ import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
parse_duration,
|
||||
str_to_int,
|
||||
)
|
||||
@ -27,7 +28,8 @@ class VpornIE(InfoExtractor):
|
||||
'duration': 393,
|
||||
'age_limit': 18,
|
||||
'view_count': int,
|
||||
}
|
||||
},
|
||||
'skip': 'video removed',
|
||||
},
|
||||
{
|
||||
'url': 'http://www.vporn.com/female/hana-shower/523564/',
|
||||
@ -40,7 +42,7 @@ class VpornIE(InfoExtractor):
|
||||
'description': 'Hana showers at the bathroom.',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'uploader': 'Hmmmmm',
|
||||
'categories': ['Big Boobs', 'Erotic', 'Teen', 'Female'],
|
||||
'categories': ['Big Boobs', 'Erotic', 'Teen', 'Female', '720p'],
|
||||
'duration': 588,
|
||||
'age_limit': 18,
|
||||
'view_count': int,
|
||||
@ -55,6 +57,10 @@ class VpornIE(InfoExtractor):
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
errmsg = 'This video has been deleted due to Copyright Infringement or by the account owner!'
|
||||
if errmsg in webpage:
|
||||
raise ExtractorError('%s said: %s' % (self.IE_NAME, errmsg), expected=True)
|
||||
|
||||
title = self._html_search_regex(
|
||||
r'videoname\s*=\s*\'([^\']+)\'', webpage, 'title').strip()
|
||||
description = self._html_search_regex(
|
||||
|
||||
@ -1,69 +0,0 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import os.path
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
)
|
||||
|
||||
|
||||
class VultureIE(InfoExtractor):
|
||||
IE_NAME = 'vulture.com'
|
||||
_VALID_URL = r'https?://video\.vulture\.com/video/(?P<display_id>[^/]+)/'
|
||||
_TEST = {
|
||||
'url': 'http://video.vulture.com/video/Mindy-Kaling-s-Harvard-Speech/player?layout=compact&read_more=1',
|
||||
'md5': '8d997845642a2b5152820f7257871bc8',
|
||||
'info_dict': {
|
||||
'id': '6GHRQL3RV7MSD1H4',
|
||||
'ext': 'mp4',
|
||||
'title': 'kaling-speech-2-MAGNIFY STANDARD CONTAINER REVISED',
|
||||
'uploader_id': 'Sarah',
|
||||
'thumbnail': 're:^http://.*\.jpg$',
|
||||
'timestamp': 1401288564,
|
||||
'upload_date': '20140528',
|
||||
'description': 'Uplifting and witty, as predicted.',
|
||||
'duration': 1015,
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
display_id = mobj.group('display_id')
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
query_string = self._search_regex(
|
||||
r"queryString\s*=\s*'([^']+)'", webpage, 'query string')
|
||||
video_id = self._search_regex(
|
||||
r'content=([^&]+)', query_string, 'video ID')
|
||||
query_url = 'http://video.vulture.com/embed/player/container/1000/1000/?%s' % query_string
|
||||
|
||||
query_webpage = self._download_webpage(
|
||||
query_url, display_id, note='Downloading query page')
|
||||
params_json = self._search_regex(
|
||||
r'(?sm)new MagnifyEmbeddablePlayer\({.*?contentItem:\s*(\{.*?\})\n?,\n',
|
||||
query_webpage,
|
||||
'player params')
|
||||
params = json.loads(params_json)
|
||||
|
||||
upload_timestamp = parse_iso8601(params['posted'].replace(' ', 'T'))
|
||||
uploader_id = params.get('user', {}).get('handle')
|
||||
|
||||
media_item = params['media_item']
|
||||
title = os.path.splitext(media_item['title'])[0]
|
||||
duration = int_or_none(media_item.get('duration_seconds'))
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'url': media_item['pipeline_xid'],
|
||||
'title': title,
|
||||
'timestamp': upload_timestamp,
|
||||
'thumbnail': params.get('thumbnail_url'),
|
||||
'uploader_id': uploader_id,
|
||||
'description': params.get('description'),
|
||||
'duration': duration,
|
||||
}
|
||||
@ -6,16 +6,18 @@ import re
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
ExtractorError,
|
||||
js_to_json,
|
||||
strip_jsonp,
|
||||
unified_strdate,
|
||||
ExtractorError,
|
||||
update_url_query,
|
||||
urlhandle_detect_ext,
|
||||
)
|
||||
|
||||
|
||||
class WDRIE(InfoExtractor):
|
||||
_CURRENT_MAUS_URL = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/){1,2}[^/?#]+\.php5'
|
||||
_PAGE_REGEX = r'/mediathek/(?P<media_type>[^/]+)/(?P<type>[^/]+)/(?P<display_id>.+)\.html'
|
||||
_PAGE_REGEX = r'/(?:mediathek/)?[^/]+/(?P<type>[^/]+)/(?P<display_id>.+)\.html'
|
||||
_VALID_URL = r'(?P<page_url>https?://(?:www\d\.)?wdr\d?\.de)' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL
|
||||
|
||||
_TESTS = [
|
||||
@ -32,7 +34,8 @@ class WDRIE(InfoExtractor):
|
||||
'description': 'md5:87be8ff14d8dfd7a7ee46f0299b52318',
|
||||
'is_live': False,
|
||||
'subtitles': {'de': [{
|
||||
'url': 'http://ondemand-ww.wdr.de/medp/fsk0/105/1058683/1058683_12220974.xml'
|
||||
'url': 'http://ondemand-ww.wdr.de/medp/fsk0/105/1058683/1058683_12220974.xml',
|
||||
'ext': 'ttml',
|
||||
}]},
|
||||
},
|
||||
},
|
||||
@ -97,6 +100,17 @@ class WDRIE(InfoExtractor):
|
||||
'description': '- Die Sendung mit der Maus -',
|
||||
},
|
||||
},
|
||||
{
|
||||
'url': 'http://www1.wdr.de/radio/player/radioplayer116~_layout-popupVersion.html',
|
||||
# Live stream, MD5 unstable
|
||||
'info_dict': {
|
||||
'id': 'mdb-869971',
|
||||
'ext': 'flv',
|
||||
'title': 'Funkhaus Europa Livestream',
|
||||
'description': 'md5:2309992a6716c347891c045be50992e4',
|
||||
'upload_date': '20160101',
|
||||
},
|
||||
}
|
||||
]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -107,9 +121,10 @@ class WDRIE(InfoExtractor):
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
# for wdr.de the data-extension is in a tag with the class "mediaLink"
|
||||
# for wdr.de radio players, in a tag with the class "wdrrPlayerPlayBtn"
|
||||
# for wdrmaus its in a link to the page in a multiline "videoLink"-tag
|
||||
json_metadata = self._html_search_regex(
|
||||
r'class=(?:"mediaLink\b[^"]*"[^>]+|"videoLink\b[^"]*"[\s]*>\n[^\n]*)data-extension="([^"]+)"',
|
||||
r'class=(?:"(?:mediaLink|wdrrPlayerPlayBtn)\b[^"]*"[^>]+|"videoLink\b[^"]*"[\s]*>\n[^\n]*)data-extension="([^"]+)"',
|
||||
webpage, 'media link', default=None, flags=re.MULTILINE)
|
||||
|
||||
if not json_metadata:
|
||||
@ -138,35 +153,46 @@ class WDRIE(InfoExtractor):
|
||||
formats = []
|
||||
|
||||
# check if the metadata contains a direct URL to a file
|
||||
metadata_media_alt = metadata_media_resource.get('alt')
|
||||
if metadata_media_alt:
|
||||
for tag_name in ['videoURL', 'audioURL']:
|
||||
if tag_name in metadata_media_alt:
|
||||
alt_url = metadata_media_alt[tag_name]
|
||||
if determine_ext(alt_url) == 'm3u8':
|
||||
m3u_fmt = self._extract_m3u8_formats(
|
||||
alt_url, display_id, 'mp4', 'm3u8_native',
|
||||
m3u8_id='hls')
|
||||
formats.extend(m3u_fmt)
|
||||
else:
|
||||
formats.append({
|
||||
'url': alt_url
|
||||
})
|
||||
for kind, media_resource in metadata_media_resource.items():
|
||||
if kind not in ('dflt', 'alt'):
|
||||
continue
|
||||
|
||||
# check if there are flash-streams for this video
|
||||
if 'dflt' in metadata_media_resource and 'videoURL' in metadata_media_resource['dflt']:
|
||||
video_url = metadata_media_resource['dflt']['videoURL']
|
||||
if video_url.endswith('.f4m'):
|
||||
full_video_url = video_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18'
|
||||
formats.extend(self._extract_f4m_formats(full_video_url, display_id, f4m_id='hds', fatal=False))
|
||||
elif video_url.endswith('.smil'):
|
||||
formats.extend(self._extract_smil_formats(video_url, 'stream', fatal=False))
|
||||
for tag_name, medium_url in media_resource.items():
|
||||
if tag_name not in ('videoURL', 'audioURL'):
|
||||
continue
|
||||
|
||||
ext = determine_ext(medium_url)
|
||||
if ext == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
medium_url, display_id, 'mp4', 'm3u8_native',
|
||||
m3u8_id='hls'))
|
||||
elif ext == 'f4m':
|
||||
manifest_url = update_url_query(
|
||||
medium_url, {'hdcore': '3.2.0', 'plugin': 'aasp-3.2.0.77.18'})
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
manifest_url, display_id, f4m_id='hds', fatal=False))
|
||||
elif ext == 'smil':
|
||||
formats.extend(self._extract_smil_formats(
|
||||
medium_url, 'stream', fatal=False))
|
||||
else:
|
||||
a_format = {
|
||||
'url': medium_url
|
||||
}
|
||||
if ext == 'unknown_video':
|
||||
urlh = self._request_webpage(
|
||||
medium_url, display_id, note='Determining extension')
|
||||
ext = urlhandle_detect_ext(urlh)
|
||||
a_format['ext'] = ext
|
||||
formats.append(a_format)
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
subtitles = {}
|
||||
caption_url = metadata_media_resource.get('captionURL')
|
||||
if caption_url:
|
||||
subtitles['de'] = [{
|
||||
'url': caption_url
|
||||
'url': caption_url,
|
||||
'ext': 'ttml',
|
||||
}]
|
||||
|
||||
title = metadata_tracker_data.get('trackerClipTitle')
|
||||
@ -183,8 +209,6 @@ class WDRIE(InfoExtractor):
|
||||
if upload_date:
|
||||
upload_date = unified_strdate(upload_date)
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': metadata_tracker_data.get('trackerClipId', display_id),
|
||||
'display_id': display_id,
|
||||
|
||||
@ -1,49 +0,0 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class WeiboIE(InfoExtractor):
|
||||
"""
|
||||
The videos in Weibo come from different sites, this IE just finds the link
|
||||
to the external video and returns it.
|
||||
"""
|
||||
_VALID_URL = r'https?://video\.weibo\.com/v/weishipin/t_(?P<id>.+?)\.htm'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://video.weibo.com/v/weishipin/t_zjUw2kZ.htm',
|
||||
'info_dict': {
|
||||
'id': '98322879',
|
||||
'ext': 'flv',
|
||||
'title': '魔声耳机最新广告“All Eyes On Us”',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'add_ie': ['Sina'],
|
||||
}
|
||||
|
||||
# Additional example videos from different sites
|
||||
# Youku: http://video.weibo.com/v/weishipin/t_zQGDWQ8.htm
|
||||
# 56.com: http://video.weibo.com/v/weishipin/t_zQ44HxN.htm
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
|
||||
video_id = mobj.group('id')
|
||||
info_url = 'http://video.weibo.com/?s=v&a=play_list&format=json&mix_video_id=t_%s' % video_id
|
||||
info = self._download_json(info_url, video_id)
|
||||
|
||||
videos_urls = map(lambda v: v['play_page_url'], info['result']['data'])
|
||||
# Prefer sina video since they have thumbnails
|
||||
videos_urls = sorted(videos_urls, key=lambda u: 'video.sina.com' in u)
|
||||
player_url = videos_urls[-1]
|
||||
m_sina = re.match(r'https?://video\.sina\.com\.cn/v/b/(\d+)-\d+\.html',
|
||||
player_url)
|
||||
if m_sina is not None:
|
||||
self.to_screen('Sina video detected')
|
||||
sina_id = m_sina.group(1)
|
||||
player_url = 'http://you.video.sina.com.cn/swf/quotePlayer.swf?vid=%s' % sina_id
|
||||
return self.url_result(player_url)
|
||||
@ -5,8 +5,10 @@ import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
decode_packed_codes,
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
NO_DEFAULT,
|
||||
sanitized_Request,
|
||||
urlencode_postdata,
|
||||
)
|
||||
@ -23,20 +25,24 @@ class XFileShareIE(InfoExtractor):
|
||||
('thevideobee.to', 'TheVideoBee'),
|
||||
('vidto.me', 'Vidto'),
|
||||
('streamin.to', 'Streamin.To'),
|
||||
('xvidstage.com', 'XVIDSTAGE'),
|
||||
)
|
||||
|
||||
IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1])
|
||||
_VALID_URL = (r'https?://(?P<host>(?:www\.)?(?:%s))/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
|
||||
% '|'.join(re.escape(site) for site in list(zip(*_SITES))[0]))
|
||||
|
||||
_FILE_NOT_FOUND_REGEX = r'>(?:404 - )?File Not Found<'
|
||||
_FILE_NOT_FOUND_REGEXES = (
|
||||
r'>(?:404 - )?File Not Found<',
|
||||
r'>The file was removed by administrator<',
|
||||
)
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://gorillavid.in/06y9juieqpmi',
|
||||
'md5': '5ae4a3580620380619678ee4875893ba',
|
||||
'info_dict': {
|
||||
'id': '06y9juieqpmi',
|
||||
'ext': 'flv',
|
||||
'ext': 'mp4',
|
||||
'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ',
|
||||
'thumbnail': 're:http://.*\.jpg',
|
||||
},
|
||||
@ -62,7 +68,8 @@ class XFileShareIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'youtube-dl test video \'äBaW_jenozKc.mp4.mp4',
|
||||
'thumbnail': 're:http://.*\.jpg',
|
||||
}
|
||||
},
|
||||
'skip': 'Video removed',
|
||||
}, {
|
||||
'url': 'http://vidto.me/ku5glz52nqe1.html',
|
||||
'info_dict': {
|
||||
@ -77,6 +84,17 @@ class XFileShareIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'Big Buck Bunny trailer',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://xvidstage.com/e0qcnl03co6z',
|
||||
'info_dict': {
|
||||
'id': 'e0qcnl03co6z',
|
||||
'ext': 'mp4',
|
||||
'title': 'Chucky Prank 2015.mp4',
|
||||
},
|
||||
}, {
|
||||
# removed by administrator
|
||||
'url': 'http://xvidstage.com/amfy7atlkx25',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -86,7 +104,7 @@ class XFileShareIE(InfoExtractor):
|
||||
url = 'http://%s/%s' % (mobj.group('host'), video_id)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
|
||||
if any(re.search(p, webpage) for p in self._FILE_NOT_FOUND_REGEXES):
|
||||
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
|
||||
|
||||
fields = self._hidden_inputs(webpage)
|
||||
@ -112,10 +130,23 @@ class XFileShareIE(InfoExtractor):
|
||||
r'>Watch (.+) ',
|
||||
r'<h2 class="video-page-head">([^<]+)</h2>'],
|
||||
webpage, 'title', default=None) or self._og_search_title(webpage)).strip()
|
||||
video_url = self._search_regex(
|
||||
[r'file\s*:\s*["\'](http[^"\']+)["\'],',
|
||||
r'file_link\s*=\s*\'(https?:\/\/[0-9a-zA-z.\/\-_]+)'],
|
||||
webpage, 'file url')
|
||||
|
||||
def extract_video_url(default=NO_DEFAULT):
|
||||
return self._search_regex(
|
||||
(r'file\s*:\s*(["\'])(?P<url>http.+?)\1,',
|
||||
r'file_link\s*=\s*(["\'])(?P<url>http.+?)\1',
|
||||
r'addVariable\((\\?["\'])file\1\s*,\s*(\\?["\'])(?P<url>http.+?)\2\)',
|
||||
r'<embed[^>]+src=(["\'])(?P<url>http.+?)\1'),
|
||||
webpage, 'file url', default=default, group='url')
|
||||
|
||||
video_url = extract_video_url(default=None)
|
||||
|
||||
if not video_url:
|
||||
webpage = decode_packed_codes(self._search_regex(
|
||||
r"(}\('(.+)',(\d+),(\d+),'[^']*\b(?:file|embed)\b[^']*'\.split\('\|'\))",
|
||||
webpage, 'packed code'))
|
||||
video_url = extract_video_url()
|
||||
|
||||
thumbnail = self._search_regex(
|
||||
r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None)
|
||||
|
||||
|
||||
@ -66,6 +66,7 @@ class XuiteIE(InfoExtractor):
|
||||
'uploader_id': '242127761',
|
||||
'categories': ['電玩動漫'],
|
||||
},
|
||||
'skip': 'Video removed',
|
||||
}, {
|
||||
'url': 'http://vlog.xuite.net/play/S1dDUjdyLTMyOTc3NjcuZmx2/%E5%AD%AB%E7%87%95%E5%A7%BF-%E7%9C%BC%E6%B7%9A%E6%88%90%E8%A9%A9',
|
||||
'only_matching': True,
|
||||
|
||||
@ -343,7 +343,7 @@ class YahooIE(InfoExtractor):
|
||||
webpage, 'region', fatal=False, default='US')
|
||||
data = compat_urllib_parse_urlencode({
|
||||
'protocol': 'http',
|
||||
'region': region,
|
||||
'region': region.upper(),
|
||||
})
|
||||
query_url = (
|
||||
'https://video.media.yql.yahoo.com/v1/video/sapi/streams/'
|
||||
|
||||
@ -2,7 +2,9 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import base64
|
||||
import itertools
|
||||
import random
|
||||
import re
|
||||
import string
|
||||
import time
|
||||
|
||||
@ -13,6 +15,7 @@ from ..compat import (
|
||||
)
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
get_element_by_attribute,
|
||||
sanitized_Request,
|
||||
)
|
||||
|
||||
@ -285,3 +288,52 @@ class YoukuIE(InfoExtractor):
|
||||
'title': title,
|
||||
'entries': entries,
|
||||
}
|
||||
|
||||
|
||||
class YoukuShowIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?youku\.com/show_page/id_(?P<id>[0-9a-z]+)\.html'
|
||||
IE_NAME = 'youku:show'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.youku.com/show_page/id_zc7c670be07ff11e48b3f.html',
|
||||
'info_dict': {
|
||||
'id': 'zc7c670be07ff11e48b3f',
|
||||
'title': '花千骨 未删减版',
|
||||
'description': 'md5:578d4f2145ae3f9128d9d4d863312910',
|
||||
},
|
||||
'playlist_count': 50,
|
||||
}
|
||||
|
||||
_PAGE_SIZE = 40
|
||||
|
||||
def _find_videos_in_page(self, webpage):
|
||||
videos = re.findall(
|
||||
r'<li><a[^>]+href="(?P<url>https?://v\.youku\.com/[^"]+)"[^>]+title="(?P<title>[^"]+)"', webpage)
|
||||
return [
|
||||
self.url_result(video_url, YoukuIE.ie_key(), title)
|
||||
for video_url, title in videos]
|
||||
|
||||
def _real_extract(self, url):
|
||||
show_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, show_id)
|
||||
|
||||
entries = self._find_videos_in_page(webpage)
|
||||
|
||||
playlist_title = self._html_search_regex(
|
||||
r'<span[^>]+class="name">([^<]+)</span>', webpage, 'playlist title', fatal=False)
|
||||
detail_div = get_element_by_attribute('class', 'detail', webpage) or ''
|
||||
playlist_description = self._html_search_regex(
|
||||
r'<span[^>]+style="display:none"[^>]*>([^<]+)</span>',
|
||||
detail_div, 'playlist description', fatal=False)
|
||||
|
||||
for idx in itertools.count(1):
|
||||
episodes_page = self._download_webpage(
|
||||
'http://www.youku.com/show_episode/id_%s.html' % show_id,
|
||||
show_id, query={'divid': 'reload_%d' % (idx * self._PAGE_SIZE + 1)},
|
||||
note='Downloading episodes page %d' % idx)
|
||||
new_entries = self._find_videos_in_page(episodes_page)
|
||||
entries.extend(new_entries)
|
||||
if len(new_entries) < self._PAGE_SIZE:
|
||||
break
|
||||
|
||||
return self.playlist_result(entries, show_id, playlist_title, playlist_description)
|
||||
|
||||
@ -17,7 +17,7 @@ class YouPornIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?youporn\.com/watch/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
|
||||
'md5': '71ec5fcfddacf80f495efa8b6a8d9a89',
|
||||
'md5': '3744d24c50438cf5b6f6d59feb5055c2',
|
||||
'info_dict': {
|
||||
'id': '505835',
|
||||
'display_id': 'sex-ed-is-it-safe-to-masturbate-daily',
|
||||
@ -121,21 +121,21 @@ class YouPornIE(InfoExtractor):
|
||||
webpage, 'thumbnail', fatal=False, group='thumbnail')
|
||||
|
||||
uploader = self._html_search_regex(
|
||||
r'(?s)<div[^>]+class=["\']videoInfoBy(?:\s+[^"\']+)?["\'][^>]*>\s*By:\s*</div>(.+?)</(?:a|div)>',
|
||||
r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>',
|
||||
webpage, 'uploader', fatal=False)
|
||||
upload_date = unified_strdate(self._html_search_regex(
|
||||
r'(?s)<div[^>]+class=["\']videoInfoTime["\'][^>]*>(.+?)</div>',
|
||||
r'(?s)<div[^>]+class=["\']videoInfo(?:Date|Time)["\'][^>]*>(.+?)</div>',
|
||||
webpage, 'upload date', fatal=False))
|
||||
|
||||
age_limit = self._rta_search(webpage)
|
||||
|
||||
average_rating = int_or_none(self._search_regex(
|
||||
r'<div[^>]+class=["\']videoInfoRating["\'][^>]*>\s*<div[^>]+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%</div>',
|
||||
r'<div[^>]+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%</div>',
|
||||
webpage, 'average rating', fatal=False))
|
||||
|
||||
view_count = str_to_int(self._search_regex(
|
||||
r'(?s)<div[^>]+class=["\']videoInfoViews["\'][^>]*>.*?([\d,.]+)\s*</div>',
|
||||
webpage, 'view count', fatal=False))
|
||||
r'(?s)<div[^>]+class=(["\']).*?\bvideoInfoViews\b.*?\1[^>]*>.*?(?P<count>[\d,.]+)<',
|
||||
webpage, 'view count', fatal=False, group='count'))
|
||||
comment_count = str_to_int(self._search_regex(
|
||||
r'>All [Cc]omments? \(([\d,.]+)\)',
|
||||
webpage, 'comment count', fatal=False))
|
||||
|
||||
@ -1988,7 +1988,7 @@ class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
|
||||
|
||||
class YoutubeUserIE(YoutubeChannelIE):
|
||||
IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
|
||||
_VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:user/)?(?!(?:attribution_link|watch|results)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)'
|
||||
_VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:user/|c/)?(?!(?:attribution_link|watch|results)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)'
|
||||
_TEMPLATE_URL = 'https://www.youtube.com/user/%s/videos'
|
||||
IE_NAME = 'youtube:user'
|
||||
|
||||
@ -2001,6 +2001,9 @@ class YoutubeUserIE(YoutubeChannelIE):
|
||||
}, {
|
||||
'url': 'ytuser:phihag',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.youtube.com/c/gametrailers',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
|
||||
@ -39,6 +39,7 @@ from .compat import (
|
||||
compat_chr,
|
||||
compat_etree_fromstring,
|
||||
compat_html_entities,
|
||||
compat_html_entities_html5,
|
||||
compat_http_client,
|
||||
compat_kwargs,
|
||||
compat_parse_qs,
|
||||
@ -75,7 +76,7 @@ def register_socks_protocols():
|
||||
compiled_regex_type = type(re.compile(''))
|
||||
|
||||
std_headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/44.0 (Chrome)',
|
||||
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/47.0 (Chrome)',
|
||||
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
|
||||
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
|
||||
'Accept-Encoding': 'gzip, deflate',
|
||||
@ -456,12 +457,19 @@ def orderedSet(iterable):
|
||||
return res
|
||||
|
||||
|
||||
def _htmlentity_transform(entity):
|
||||
def _htmlentity_transform(entity_with_semicolon):
|
||||
"""Transforms an HTML entity to a character."""
|
||||
entity = entity_with_semicolon[:-1]
|
||||
|
||||
# Known non-numeric HTML entity
|
||||
if entity in compat_html_entities.name2codepoint:
|
||||
return compat_chr(compat_html_entities.name2codepoint[entity])
|
||||
|
||||
# TODO: HTML5 allows entities without a semicolon. For example,
|
||||
# 'Éric' should be decoded as 'Éric'.
|
||||
if entity_with_semicolon in compat_html_entities_html5:
|
||||
return compat_html_entities_html5[entity_with_semicolon]
|
||||
|
||||
mobj = re.match(r'#(x[0-9a-fA-F]+|[0-9]+)', entity)
|
||||
if mobj is not None:
|
||||
numstr = mobj.group(1)
|
||||
@ -486,7 +494,7 @@ def unescapeHTML(s):
|
||||
assert type(s) == compat_str
|
||||
|
||||
return re.sub(
|
||||
r'&([^;]+);', lambda m: _htmlentity_transform(m.group(1)), s)
|
||||
r'&([^;]+;)', lambda m: _htmlentity_transform(m.group(1)), s)
|
||||
|
||||
|
||||
def get_subprocess_encoding():
|
||||
@ -1893,6 +1901,16 @@ def dict_get(d, key_or_keys, default=None, skip_false_values=True):
|
||||
return d.get(key_or_keys, default)
|
||||
|
||||
|
||||
def try_get(src, getter, expected_type=None):
|
||||
try:
|
||||
v = getter(src)
|
||||
except (AttributeError, KeyError, TypeError, IndexError):
|
||||
pass
|
||||
else:
|
||||
if expected_type is None or isinstance(v, expected_type):
|
||||
return v
|
||||
|
||||
|
||||
def encode_compat_str(string, encoding=preferredencoding(), errors='strict'):
|
||||
return string if isinstance(string, compat_str) else compat_str(string, encoding, errors)
|
||||
|
||||
@ -2020,6 +2038,9 @@ def mimetype2ext(mt):
|
||||
|
||||
ext = {
|
||||
'audio/mp4': 'm4a',
|
||||
# Per RFC 3003, audio/mpeg can be .mp1, .mp2 or .mp3. Here use .mp3 as
|
||||
# it's the most popular one
|
||||
'audio/mpeg': 'mp3',
|
||||
}.get(mt)
|
||||
if ext is not None:
|
||||
return ext
|
||||
|
||||
@ -1,3 +1,3 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
__version__ = '2016.06.03'
|
||||
__version__ = '2016.06.12'
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user