diff --git a/.gitignore b/.gitignore index 7e2490c44..bd7d11f26 100644 --- a/.gitignore +++ b/.gitignore @@ -23,6 +23,8 @@ updates_key.pem *.vtt *.flv *.mp4 +*.m4a +*.m4v *.part test/testdata .tox diff --git a/README.md b/README.md index 6632e5865..aafdd3e51 100644 --- a/README.md +++ b/README.md @@ -30,13 +30,20 @@ which means you can modify it, redistribute it or use it however you like. --list-extractors List all supported extractors and the URLs they would handle --extractor-descriptions Output descriptions of all supported extractors - --proxy URL Use the specified HTTP/HTTPS proxy + --proxy URL Use the specified HTTP/HTTPS proxy. Pass in an + empty string (--proxy "") for direct connection --no-check-certificate Suppress HTTPS certificate validation. --cache-dir DIR Location in the filesystem where youtube-dl can - store downloaded information permanently. By + store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl or ~/.cache - /youtube-dl . + /youtube-dl . At the moment, only YouTube player + files (for videos with obfuscated signatures) are + cached, but that may change. --no-cache-dir Disable filesystem caching + --socket-timeout None Time to wait before giving up, in seconds + --bidi-workaround Work around terminals that lack bidirectional + text support. Requires bidiv or fribidi + executable in PATH ## Video Selection: --playlist-start NUMBER playlist video to start at (default is 1) @@ -51,12 +58,20 @@ which means you can modify it, redistribute it or use it however you like. --max-filesize SIZE Do not download any videos larger than SIZE (e.g. 50k or 44.6m) --date DATE download only videos uploaded in this date - --datebefore DATE download only videos uploaded before this date - --dateafter DATE download only videos uploaded after this date + --datebefore DATE download only videos uploaded on or before this + date (i.e. inclusive) + --dateafter DATE download only videos uploaded on or after this + date (i.e. inclusive) + --min-views COUNT Do not download any videos with less than COUNT + views + --max-views COUNT Do not download any videos with more than COUNT + views --no-playlist download only the currently playing video --age-limit YEARS download only videos suitable for the given age - --download-archive FILE Download only videos not present in the archive - file. Record all downloaded videos in it. + --download-archive FILE Download only videos not listed in the archive + file. Record the IDs of all downloaded videos in + it. + --include-ads Download advertisements as well (experimental) ## Download Options: -r, --rate-limit LIMIT maximum download rate in bytes per second (e.g. @@ -79,13 +94,13 @@ which means you can modify it, redistribute it or use it however you like. different, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(format)s for the format description - (like "22 - 1280x720" or "HD"),%(format_id)s for + (like "22 - 1280x720" or "HD"), %(format_id)s for the unique id of the format (like Youtube's - itags: "137"),%(upload_date)s for the upload date - (YYYYMMDD), %(extractor)s for the provider - (youtube, metacafe, etc), %(id)s for the video id - , %(playlist)s for the playlist the video is in, - %(playlist_index)s for the position in the + itags: "137"), %(upload_date)s for the upload + date (YYYYMMDD), %(extractor)s for the provider + (youtube, metacafe, etc), %(id)s for the video + id, %(playlist)s for the playlist the video is + in, %(playlist_index)s for the position in the playlist and %% for a literal percent. Use - to output to stdout. Can also be used to download to a different directory, for example with -o '/my/d @@ -96,6 +111,8 @@ which means you can modify it, redistribute it or use it however you like. --restrict-filenames Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames -a, --batch-file FILE file containing URLs to download ('-' for stdin) + --load-info FILE json file containing the video information + (created with the "--write-json" option) -w, --no-overwrites do not overwrite files -c, --continue force resume of partially downloaded files. By default, youtube-dl will resume downloads if @@ -121,27 +138,28 @@ which means you can modify it, redistribute it or use it however you like. --get-id simulate, quiet but print id --get-thumbnail simulate, quiet but print thumbnail URL --get-description simulate, quiet but print video description + --get-duration simulate, quiet but print video length --get-filename simulate, quiet but print output filename --get-format simulate, quiet but print output format + -j, --dump-json simulate, quiet but print JSON information --newline output progress bar as new lines --no-progress do not print progress bar --console-title display progress in console titlebar -v, --verbose print various debugging information - --dump-intermediate-pages print downloaded pages to debug problems(very + --dump-intermediate-pages print downloaded pages to debug problems (very verbose) - --write-pages Write downloaded pages to files in the current - directory + --write-pages Write downloaded intermediary pages to files in + the current directory to debug problems ## Video Format Options: - -f, --format FORMAT video format code, specifiy the order of + -f, --format FORMAT video format code, specify the order of preference using slashes: "-f 22/17/18". "-f mp4" and "-f flv" are also supported --all-formats download all available video formats --prefer-free-formats prefer free video formats unless a specific one is requested --max-quality FORMAT highest quality format to download - -F, --list-formats list all available formats (currently youtube - only) + -F, --list-formats list all available formats ## Subtitle Options: --write-sub write subtitle file @@ -159,7 +177,7 @@ which means you can modify it, redistribute it or use it however you like. -u, --username USERNAME account username -p, --password PASSWORD account password -n, --netrc use .netrc authentication data - --video-password PASSWORD video password (vimeo only) + --video-password PASSWORD video password (vimeo, smotri) ## Post-processing Options: -x, --extract-audio convert video files to audio-only files (requires @@ -177,11 +195,17 @@ which means you can modify it, redistribute it or use it however you like. processed files are overwritten by default --embed-subs embed subtitles in the video (only for mp4 videos) - --add-metadata add metadata to the files + --add-metadata write metadata to the video file + --xattrs write metadata to the video file's xattrs (using + dublin core and xdg standards) + --prefer-avconv Prefer avconv over ffmpeg for running the + postprocessors (default) + --prefer-ffmpeg Prefer ffmpeg over avconv for running the + postprocessors # CONFIGURATION -You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl.conf`. +You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl.conf`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\\youtube-dl.conf`. # OUTPUT TEMPLATE @@ -216,9 +240,12 @@ Videos can be filtered by their upload date using the options `--date`, `--dateb Examples: - $ youtube-dl --dateafter now-6months #will only download the videos uploaded in the last 6 months - $ youtube-dl --date 19700101 #will only download the videos uploaded in January 1, 1970 - $ youtube-dl --dateafter 20000101 --datebefore 20100101 #will only download the videos uploaded between 2000 and 2010 + $ # Download only the videos uploaded in the last 6 months + $ youtube-dl --dateafter now-6months + $ # Download only the videos uploaded on January 1, 1970 + $ youtube-dl --date 19700101 + $ # will only download the videos uploaded in the 200x decade + $ youtube-dl --dateafter 20000101 --datebefore 20091231 # FAQ @@ -271,14 +298,58 @@ This README file was originally written by Daniel Bolton ( +Bugs and suggestions should be reported at: . Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. -Please include: - -* Your exact command line, like `youtube-dl -t "http://www.youtube.com/watch?v=uHlDtZ6Oc3s&feature=channel_video_title"`. A common mistake is not to escape the `&`. Putting URLs in quotes should solve this problem. -* If possible re-run the command with `--verbose`, and include the full output, it is really helpful to us. -* The output of `youtube-dl --version` -* The output of `python --version` -* The name and version of your Operating System ("Ubuntu 11.04 x64" or "Windows 7 x64" is usually enough). +Please include the full output of the command when run with `--verbose`. The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever. For discussions, join us in the irc channel #youtube-dl on freenode. + +When you submit a request, please re-read it once to avoid a couple of mistakes (you can and should use this as a checklist): + +### Is the description of the issue itself sufficient? + +We often get issue reports that we cannot really decipher. While in most cases we eventually get the required information after asking back multiple times, this poses an unnecessary drain on our resources. Many contributors, including myself, are also not native speakers, so we may misread some parts. + +So please elaborate on what feature you are requesting, or what bug you want to be fixed. Make sure that it's obvious + +- What the problem is +- How it could be fixed +- How your proposed solution would look like + +If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We're often too polite to close the issue outright, but the missing info makes misinterpretation likely. As a commiter myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over. + +For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the -v flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information. + +Site support requests must contain an example URL. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL. + +### Are you using the latest version? + +Before reporting any issue, type youtube-dl -U. This should report that you're up-to-date. About 20% of the reports we receive are already fixed, but people are using outdated versions. This goes for feature requests as well. + +### Is the issue already documented? + +Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or at https://github.com/rg3/youtube-dl/search?type=Issues . If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity. + +### Why are existing options not enough? + +Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#synopsis). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem. + +### Is there enough context in your bug report? + +People want to solve problems, and often think they do us a favor by breaking down their larger problems (e.g. wanting to skip already downloaded files) to a specific request (e.g. requesting us to look whether the file exists before downloading the info page). However, what often happens is that they break down the problem into two steps: One simple, and one impossible (or extremely complicated one). + +We are then presented with a very complicated request when the original problem could be solved far easier, e.g. by recording the downloaded video IDs in a separate file. To avoid this, you must include the greater context where it is non-obvious. In particular, every feature request that does not consist of adding support for a new site should contain a use case scenario that explains in what situation the missing feature would be useful. + +### Does the issue involve one problem, and one problem only? + +Some of our users seem to think there is a limit of issues they can or should open. There is no limit of issues they can or should open. While it may seem appealing to be able to dump all your issues into one ticket, that means that someone who solves one of your issues cannot mark the issue as closed. Typically, reporting a bunch of issues leads to the ticket lingering since nobody wants to attack that behemoth, until someone mercifully splits the issue into multiple ones. + +In particular, every site support request issue should only pertain to services at one site (generally under a common domain, but always using the same backend technology). Do not request support for vimeo user videos, Whitehouse podcasts, and Google Plus pages in the same issue. Also, make sure that you don't post bug reports alongside feature requests. As a rule of thumb, a feature request does not include outputs of youtube-dl that are not immediately related to the feature at hand. Do not post reports of a network error alongside the request for a new video service. + +### Is anyone going to need the feature? + +Only post features that you (or an incapicated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them. + +### Is your question about youtube-dl? + +It may sound strange, but some bug reports we receive are completely unrelated to youtube-dl and relate to a different or even the reporter's own application. Please make sure that you are actually using youtube-dl. If you are using a UI for youtube-dl, report the bug to the maintainer of the actual application providing the UI. On the other hand, if your UI for youtube-dl fails in some way you believe is related to youtube-dl, by all means, go ahead and report the bug. diff --git a/devscripts/bash-completion.in b/devscripts/bash-completion.in index ce893fcbe..28bd23727 100644 --- a/devscripts/bash-completion.in +++ b/devscripts/bash-completion.in @@ -1,10 +1,21 @@ __youtube_dl() { - local cur prev opts + local cur prev opts fileopts diropts keywords COMPREPLY=() cur="${COMP_WORDS[COMP_CWORD]}" + prev="${COMP_WORDS[COMP_CWORD-1]}" opts="{{flags}}" - keywords=":ytfavorites :ytrecommended :ytsubscriptions :ytwatchlater" + keywords=":ytfavorites :ytrecommended :ytsubscriptions :ytwatchlater :ythistory" + fileopts="-a|--batch-file|--download-archive|--cookies|--load-info" + diropts="--cache-dir" + + if [[ ${prev} =~ ${fileopts} ]]; then + COMPREPLY=( $(compgen -f -- ${cur}) ) + return 0 + elif [[ ${prev} =~ ${diropts} ]]; then + COMPREPLY=( $(compgen -d -- ${cur}) ) + return 0 + fi if [[ ${cur} =~ : ]]; then COMPREPLY=( $(compgen -W "${keywords}" -- ${cur}) ) diff --git a/devscripts/check-porn.py b/devscripts/check-porn.py index 63401fe18..86aa37b5f 100644 --- a/devscripts/check-porn.py +++ b/devscripts/check-porn.py @@ -3,6 +3,9 @@ """ This script employs a VERY basic heuristic ('porn' in webpage.lower()) to check if we are not 'age_limit' tagging some porn site + +A second approach implemented relies on a list of porn domains, to activate it +pass the list filename as the only argument """ # Allow direct execution @@ -11,25 +14,42 @@ import sys sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) from test.helper import get_testcases +from youtube_dl.utils import compat_urllib_parse_urlparse from youtube_dl.utils import compat_urllib_request +if len(sys.argv) > 1: + METHOD = 'LIST' + LIST = open(sys.argv[1]).read().decode('utf8').strip() +else: + METHOD = 'EURISTIC' + for test in get_testcases(): - try: - webpage = compat_urllib_request.urlopen(test['url'], timeout=10).read() - except: - print('\nFail: {0}'.format(test['name'])) - continue + if METHOD == 'EURISTIC': + try: + webpage = compat_urllib_request.urlopen(test['url'], timeout=10).read() + except: + print('\nFail: {0}'.format(test['name'])) + continue - webpage = webpage.decode('utf8', 'replace') + webpage = webpage.decode('utf8', 'replace') - if 'porn' in webpage.lower() and ('info_dict' not in test - or 'age_limit' not in test['info_dict'] - or test['info_dict']['age_limit'] != 18): + RESULT = 'porn' in webpage.lower() + + elif METHOD == 'LIST': + domain = compat_urllib_parse_urlparse(test['url']).netloc + if not domain: + print('\nFail: {0}'.format(test['name'])) + continue + domain = '.'.join(domain.split('.')[-2:]) + + RESULT = ('.' + domain + '\n' in LIST or '\n' + domain + '\n' in LIST) + + if RESULT and ('info_dict' not in test or 'age_limit' not in test['info_dict'] + or test['info_dict']['age_limit'] != 18): print('\nPotential missing age_limit check: {0}'.format(test['name'])) - elif 'porn' not in webpage.lower() and ('info_dict' in test and - 'age_limit' in test['info_dict'] and - test['info_dict']['age_limit'] == 18): + elif not RESULT and ('info_dict' in test and 'age_limit' in test['info_dict'] + and test['info_dict']['age_limit'] == 18): print('\nPotential false negative: {0}'.format(test['name'])) else: diff --git a/devscripts/gh-pages/update-feed.py b/devscripts/gh-pages/update-feed.py index 16571a924..0ba15ae0f 100755 --- a/devscripts/gh-pages/update-feed.py +++ b/devscripts/gh-pages/update-feed.py @@ -1,56 +1,76 @@ #!/usr/bin/env python3 import datetime - +import io +import json import textwrap -import json -atom_template=textwrap.dedent("""\ - - - youtube-dl releases - youtube-dl-updates-feed - @TIMESTAMP@ - @ENTRIES@ - """) +atom_template = textwrap.dedent("""\ + + + + youtube-dl releases + https://yt-dl.org/feed/youtube-dl-updates-feed + @TIMESTAMP@ + @ENTRIES@ + """) -entry_template=textwrap.dedent(""" - - youtube-dl-@VERSION@ - New version @VERSION@ - - -
- Downloads available at https://yt-dl.org/downloads/@VERSION@/ -
- - - The youtube-dl maintainers - - @TIMESTAMP@ - - """) +entry_template = textwrap.dedent(""" + + https://yt-dl.org/feed/youtube-dl-updates-feed/youtube-dl-@VERSION@ + New version @VERSION@ + + +
+ Downloads available at https://yt-dl.org/downloads/@VERSION@/ +
+ + + The youtube-dl maintainers + + @TIMESTAMP@ + + """) now = datetime.datetime.now() -now_iso = now.isoformat() +now_iso = now.isoformat() + 'Z' -atom_template = atom_template.replace('@TIMESTAMP@',now_iso) - -entries=[] +atom_template = atom_template.replace('@TIMESTAMP@', now_iso) versions_info = json.load(open('update/versions.json')) versions = list(versions_info['versions'].keys()) versions.sort() +entries = [] for v in versions: - entry = entry_template.replace('@TIMESTAMP@',v.replace('.','-')) - entry = entry.replace('@VERSION@',v) - entries.append(entry) + fields = v.split('.') + year, month, day = map(int, fields[:3]) + faked = 0 + patchlevel = 0 + while True: + try: + datetime.date(year, month, day) + except ValueError: + day -= 1 + faked += 1 + assert day > 0 + continue + break + if len(fields) >= 4: + try: + patchlevel = int(fields[3]) + except ValueError: + patchlevel = 1 + timestamp = '%04d-%02d-%02dT00:%02d:%02dZ' % (year, month, day, faked, patchlevel) + + entry = entry_template.replace('@TIMESTAMP@', timestamp) + entry = entry.replace('@VERSION@', v) + entries.append(entry) entries_str = textwrap.indent(''.join(entries), '\t') atom_template = atom_template.replace('@ENTRIES@', entries_str) -with open('update/releases.atom','w',encoding='utf-8') as atom_file: - atom_file.write(atom_template) +with io.open('update/releases.atom', 'w', encoding='utf-8') as atom_file: + atom_file.write(atom_template) diff --git a/devscripts/make_readme.py b/devscripts/make_readme.py index 7f2ea319c..cae1fa4f2 100755 --- a/devscripts/make_readme.py +++ b/devscripts/make_readme.py @@ -1,20 +1,24 @@ +import io import sys import re README_FILE = 'README.md' helptext = sys.stdin.read() -with open(README_FILE) as f: +if isinstance(helptext, bytes): + helptext = helptext.decode('utf-8') + +with io.open(README_FILE, encoding='utf-8') as f: oldreadme = f.read() header = oldreadme[:oldreadme.index('# OPTIONS')] footer = oldreadme[oldreadme.index('# CONFIGURATION'):] -options = helptext[helptext.index(' General Options:')+19:] +options = helptext[helptext.index(' General Options:') + 19:] options = re.sub(r'^ (\w.+)$', r'## \1', options, flags=re.M) options = '# OPTIONS\n' + options + '\n' -with open(README_FILE, 'w') as f: +with io.open(README_FILE, 'w', encoding='utf-8') as f: f.write(header) f.write(options) f.write(footer) diff --git a/devscripts/release.sh b/devscripts/release.sh index 2766174c1..323acf8cf 100755 --- a/devscripts/release.sh +++ b/devscripts/release.sh @@ -24,6 +24,8 @@ if [ -z "$1" ]; then echo "ERROR: specify version number like this: $0 1994.09.0 version="$1" if [ ! -z "`git tag | grep "$version"`" ]; then echo 'ERROR: version already present'; exit 1; fi if [ ! -z "`git status --porcelain | grep -v CHANGELOG`" ]; then echo 'ERROR: the working directory is not clean; commit or stash changes'; exit 1; fi +useless_files=$(find youtube_dl -type f -not -name '*.py') +if [ ! -z "$useless_files" ]; then echo "ERROR: Non-.py files in youtube_dl: $useless_files"; exit 1; fi if [ ! -f "updates_key.pem" ]; then echo 'ERROR: updates_key.pem missing'; exit 1; fi /bin/echo -e "\n### First of all, testing..." diff --git a/setup.py b/setup.py index aa7cfca08..1f45159cd 100644 --- a/setup.py +++ b/setup.py @@ -48,7 +48,7 @@ else: 'data_files': [ # Installing system-wide would require sudo... ('etc/bash_completion.d', ['youtube-dl.bash-completion']), ('share/doc/youtube_dl', ['README.txt']), - ('share/man/man1/', ['youtube-dl.1']) + ('share/man/man1', ['youtube-dl.1']) ] } if setuptools_available: @@ -71,7 +71,10 @@ setup( author_email='ytdl@yt-dl.org', maintainer='Philipp Hagemeister', maintainer_email='phihag@phihag.de', - packages=['youtube_dl', 'youtube_dl.extractor'], + packages=[ + 'youtube_dl', + 'youtube_dl.extractor', 'youtube_dl.downloader', + 'youtube_dl.postprocessor'], # Provokes warning on most systems (why?!) # test_suite = 'nose.collector', diff --git a/test/helper.py b/test/helper.py index d7bf7a828..b1f421ac5 100644 --- a/test/helper.py +++ b/test/helper.py @@ -12,10 +12,6 @@ from youtube_dl import YoutubeDL from youtube_dl.utils import preferredencoding -def global_setup(): - youtube_dl._setup_opener(timeout=10) - - def get_params(override=None): PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json") diff --git a/test/parameters.json b/test/parameters.json index f042880ed..487a46d56 100644 --- a/test/parameters.json +++ b/test/parameters.json @@ -39,5 +39,6 @@ "writeinfojson": true, "writesubtitles": false, "allsubtitles": false, - "listssubtitles": false + "listssubtitles": false, + "socket_timeout": 20 } diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index 58cf9c313..01de10e31 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -7,6 +7,8 @@ import unittest sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) from test.helper import FakeYDL +from youtube_dl import YoutubeDL +from youtube_dl.extractor import YoutubeIE class YDL(FakeYDL): @@ -32,6 +34,8 @@ class TestFormatSelection(unittest.TestCase): {u'ext': u'mp4', u'height': 460}, ] info_dict = {u'formats': formats, u'extractor': u'test'} + yie = YoutubeIE(ydl) + yie._sort_formats(info_dict['formats']) ydl.process_ie_result(info_dict) downloaded = ydl.downloaded_info_dicts[0] self.assertEqual(downloaded[u'ext'], u'webm') @@ -44,28 +48,46 @@ class TestFormatSelection(unittest.TestCase): {u'ext': u'mp4', u'height': 1080}, ] info_dict[u'formats'] = formats + yie = YoutubeIE(ydl) + yie._sort_formats(info_dict['formats']) ydl.process_ie_result(info_dict) downloaded = ydl.downloaded_info_dicts[0] self.assertEqual(downloaded[u'ext'], u'mp4') - # No prefer_free_formats => keep original formats order + # No prefer_free_formats => prefer mp4 and flv for greater compatibilty ydl = YDL() ydl.params['prefer_free_formats'] = False formats = [ {u'ext': u'webm', u'height': 720}, + {u'ext': u'mp4', u'height': 720}, {u'ext': u'flv', u'height': 720}, ] info_dict[u'formats'] = formats + yie = YoutubeIE(ydl) + yie._sort_formats(info_dict['formats']) + ydl.process_ie_result(info_dict) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded[u'ext'], u'mp4') + + ydl = YDL() + ydl.params['prefer_free_formats'] = False + formats = [ + {u'ext': u'flv', u'height': 720}, + {u'ext': u'webm', u'height': 720}, + ] + info_dict[u'formats'] = formats + yie = YoutubeIE(ydl) + yie._sort_formats(info_dict['formats']) ydl.process_ie_result(info_dict) downloaded = ydl.downloaded_info_dicts[0] self.assertEqual(downloaded[u'ext'], u'flv') def test_format_limit(self): formats = [ - {u'format_id': u'meh', u'url': u'http://example.com/meh'}, - {u'format_id': u'good', u'url': u'http://example.com/good'}, - {u'format_id': u'great', u'url': u'http://example.com/great'}, - {u'format_id': u'excellent', u'url': u'http://example.com/exc'}, + {u'format_id': u'meh', u'url': u'http://example.com/meh', 'preference': 1}, + {u'format_id': u'good', u'url': u'http://example.com/good', 'preference': 2}, + {u'format_id': u'great', u'url': u'http://example.com/great', 'preference': 3}, + {u'format_id': u'excellent', u'url': u'http://example.com/exc', 'preference': 4}, ] info_dict = { u'formats': formats, u'extractor': u'test', 'id': 'testvid'} @@ -77,12 +99,12 @@ class TestFormatSelection(unittest.TestCase): ydl = YDL({'format_limit': 'good'}) assert ydl.params['format_limit'] == 'good' - ydl.process_ie_result(info_dict) + ydl.process_ie_result(info_dict.copy()) downloaded = ydl.downloaded_info_dicts[0] self.assertEqual(downloaded[u'format_id'], u'good') ydl = YDL({'format_limit': 'great', 'format': 'all'}) - ydl.process_ie_result(info_dict) + ydl.process_ie_result(info_dict.copy()) self.assertEqual(ydl.downloaded_info_dicts[0][u'format_id'], u'meh') self.assertEqual(ydl.downloaded_info_dicts[1][u'format_id'], u'good') self.assertEqual(ydl.downloaded_info_dicts[2][u'format_id'], u'great') @@ -90,44 +112,80 @@ class TestFormatSelection(unittest.TestCase): ydl = YDL() ydl.params['format_limit'] = 'excellent' - ydl.process_ie_result(info_dict) + ydl.process_ie_result(info_dict.copy()) downloaded = ydl.downloaded_info_dicts[0] self.assertEqual(downloaded[u'format_id'], u'excellent') def test_format_selection(self): formats = [ - {u'format_id': u'35', u'ext': u'mp4'}, - {u'format_id': u'45', u'ext': u'webm'}, - {u'format_id': u'47', u'ext': u'webm'}, - {u'format_id': u'2', u'ext': u'flv'}, + {u'format_id': u'35', u'ext': u'mp4', 'preference': 1}, + {u'format_id': u'45', u'ext': u'webm', 'preference': 2}, + {u'format_id': u'47', u'ext': u'webm', 'preference': 3}, + {u'format_id': u'2', u'ext': u'flv', 'preference': 4}, ] info_dict = {u'formats': formats, u'extractor': u'test'} ydl = YDL({'format': u'20/47'}) - ydl.process_ie_result(info_dict) + ydl.process_ie_result(info_dict.copy()) downloaded = ydl.downloaded_info_dicts[0] self.assertEqual(downloaded['format_id'], u'47') ydl = YDL({'format': u'20/71/worst'}) - ydl.process_ie_result(info_dict) + ydl.process_ie_result(info_dict.copy()) downloaded = ydl.downloaded_info_dicts[0] self.assertEqual(downloaded['format_id'], u'35') ydl = YDL() - ydl.process_ie_result(info_dict) + ydl.process_ie_result(info_dict.copy()) downloaded = ydl.downloaded_info_dicts[0] self.assertEqual(downloaded['format_id'], u'2') ydl = YDL({'format': u'webm/mp4'}) - ydl.process_ie_result(info_dict) + ydl.process_ie_result(info_dict.copy()) downloaded = ydl.downloaded_info_dicts[0] self.assertEqual(downloaded['format_id'], u'47') ydl = YDL({'format': u'3gp/40/mp4'}) - ydl.process_ie_result(info_dict) + ydl.process_ie_result(info_dict.copy()) downloaded = ydl.downloaded_info_dicts[0] self.assertEqual(downloaded['format_id'], u'35') + def test_youtube_format_selection(self): + order = [ + '38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '36', '17', '13', + # Apple HTTP Live Streaming + '96', '95', '94', '93', '92', '132', '151', + # 3D + '85', '84', '102', '83', '101', '82', '100', + # Dash video + '138', '137', '248', '136', '247', '135', '246', + '245', '244', '134', '243', '133', '242', '160', + # Dash audio + '141', '172', '140', '139', '171', + ] + + for f1id, f2id in zip(order, order[1:]): + f1 = YoutubeIE._formats[f1id].copy() + f1['format_id'] = f1id + f2 = YoutubeIE._formats[f2id].copy() + f2['format_id'] = f2id + + info_dict = {'formats': [f1, f2], 'extractor': 'youtube'} + ydl = YDL() + yie = YoutubeIE(ydl) + yie._sort_formats(info_dict['formats']) + ydl.process_ie_result(info_dict) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], f1id) + + info_dict = {'formats': [f2, f1], 'extractor': 'youtube'} + ydl = YDL() + yie = YoutubeIE(ydl) + yie._sort_formats(info_dict['formats']) + ydl.process_ie_result(info_dict) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], f1id) + def test_add_extra_info(self): test_dict = { 'extractor': 'Foo', @@ -140,6 +198,20 @@ class TestFormatSelection(unittest.TestCase): self.assertEqual(test_dict['extractor'], 'Foo') self.assertEqual(test_dict['playlist'], 'funny videos') + def test_prepare_filename(self): + info = { + u'id': u'1234', + u'ext': u'mp4', + u'width': None, + } + def fname(templ): + ydl = YoutubeDL({'outtmpl': templ}) + return ydl.prepare_filename(info) + self.assertEqual(fname(u'%(id)s.%(ext)s'), u'1234.mp4') + self.assertEqual(fname(u'%(id)s-%(width)s.%(ext)s'), u'1234-NA.mp4') + # Replace missing fields with 'NA' + self.assertEqual(fname(u'%(uploader_date)s-%(id)s.%(ext)s'), u'NA-1234.mp4') + if __name__ == '__main__': unittest.main() diff --git a/test/test_age_restriction.py b/test/test_age_restriction.py index d500c6edc..c9cdb96cb 100644 --- a/test/test_age_restriction.py +++ b/test/test_age_restriction.py @@ -6,8 +6,7 @@ import sys import unittest sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) -from test.helper import global_setup, try_rm -global_setup() +from test.helper import try_rm from youtube_dl import YoutubeDL @@ -24,7 +23,7 @@ def _download_restricted(url, filename, age): } ydl = YoutubeDL(params) ydl.add_default_info_extractors() - json_filename = filename + '.info.json' + json_filename = os.path.splitext(filename)[0] + '.info.json' try_rm(json_filename) ydl.download([url]) res = os.path.exists(json_filename) diff --git a/test/test_all_urls.py b/test/test_all_urls.py index 56e5f80e1..75547f42a 100644 --- a/test/test_all_urls.py +++ b/test/test_all_urls.py @@ -10,6 +10,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) from test.helper import get_testcases from youtube_dl.extractor import ( + FacebookIE, gen_extractors, JustinTVIE, YoutubeIE, @@ -87,12 +88,15 @@ class TestAllURLsMatching(unittest.TestCase): assertExtractId('http://www.youtube.com/watch?v=BaW_jenozKcsharePLED17F32AD9753930', 'BaW_jenozKc') assertExtractId('BaW_jenozKc', 'BaW_jenozKc') + def test_facebook_matching(self): + self.assertTrue(FacebookIE.suitable(u'https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268')) + def test_no_duplicates(self): ies = gen_extractors() for tc in get_testcases(): url = tc['url'] for ie in ies: - if type(ie).__name__ in ['GenericIE', tc['name'] + 'IE']: + if type(ie).__name__ in ('GenericIE', tc['name'] + 'IE'): self.assertTrue(ie.suitable(url), '%s should match URL %r' % (type(ie).__name__, url)) else: self.assertFalse(ie.suitable(url), '%s should not match URL %r' % (type(ie).__name__, url)) @@ -100,11 +104,21 @@ class TestAllURLsMatching(unittest.TestCase): def test_keywords(self): self.assertMatch(':ytsubs', ['youtube:subscriptions']) self.assertMatch(':ytsubscriptions', ['youtube:subscriptions']) - self.assertMatch(':thedailyshow', ['ComedyCentral']) - self.assertMatch(':tds', ['ComedyCentral']) - self.assertMatch(':colbertreport', ['ComedyCentral']) - self.assertMatch(':cr', ['ComedyCentral']) + self.assertMatch(':ythistory', ['youtube:history']) + self.assertMatch(':thedailyshow', ['ComedyCentralShows']) + self.assertMatch(':tds', ['ComedyCentralShows']) + self.assertMatch(':colbertreport', ['ComedyCentralShows']) + self.assertMatch(':cr', ['ComedyCentralShows']) + def test_vimeo_matching(self): + self.assertMatch('http://vimeo.com/channels/tributes', ['vimeo:channel']) + self.assertMatch('http://vimeo.com/user7108434', ['vimeo:user']) + self.assertMatch('http://vimeo.com/user7108434/videos', ['vimeo:user']) + self.assertMatch('https://vimeo.com/user21297594/review/75524534/3c257a1b5d', ['vimeo:review']) + + # https://github.com/rg3/youtube-dl/issues/1930 + def test_soundcloud_not_matching_sets(self): + self.assertMatch('http://soundcloud.com/floex/sets/gone-ep', ['soundcloud:set']) if __name__ == '__main__': unittest.main() diff --git a/test/test_download.py b/test/test_download.py index 16f200809..0d925ae69 100644 --- a/test/test_download.py +++ b/test/test_download.py @@ -9,12 +9,10 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) from test.helper import ( get_params, get_testcases, - global_setup, try_rm, md5, report_warning ) -global_setup() import hashlib @@ -92,7 +90,7 @@ def generator(test_case): def _hook(status): if status['status'] == 'finished': finished_hook_called.add(status['filename']) - ydl.fd.add_progress_hook(_hook) + ydl.add_progress_hook(_hook) def get_tc_filename(tc): return tc.get('file') or ydl.prepare_filename(tc.get('info_dict', {})) @@ -103,7 +101,7 @@ def generator(test_case): tc_filename = get_tc_filename(tc) try_rm(tc_filename) try_rm(tc_filename + '.part') - try_rm(tc_filename + '.info.json') + try_rm(os.path.splitext(tc_filename)[0] + '.info.json') try_rm_tcs_files() try: try_num = 1 @@ -130,11 +128,12 @@ def generator(test_case): if not test_case.get('params', {}).get('skip_download', False): self.assertTrue(os.path.exists(tc_filename), msg='Missing file ' + tc_filename) self.assertTrue(tc_filename in finished_hook_called) - self.assertTrue(os.path.exists(tc_filename + '.info.json')) + info_json_fn = os.path.splitext(tc_filename)[0] + '.info.json' + self.assertTrue(os.path.exists(info_json_fn)) if 'md5' in tc: md5_for_file = _file_md5(tc_filename) self.assertEqual(md5_for_file, tc['md5']) - with io.open(tc_filename + '.info.json', encoding='utf-8') as infof: + with io.open(info_json_fn, encoding='utf-8') as infof: info_dict = json.load(infof) for (info_field, expected) in tc.get('info_dict', {}).items(): if isinstance(expected, compat_str) and expected.startswith('md5:'): @@ -149,7 +148,7 @@ def generator(test_case): for key, value in info_dict.items() if value and key in ('title', 'description', 'uploader', 'upload_date', 'uploader_id', 'location')) if not all(key in tc.get('info_dict', {}).keys() for key in test_info_dict.keys()): - sys.stderr.write(u'\n"info_dict": ' + json.dumps(test_info_dict, ensure_ascii=False, indent=2) + u'\n') + sys.stderr.write(u'\n"info_dict": ' + json.dumps(test_info_dict, ensure_ascii=False, indent=4) + u'\n') # Check for the presence of mandatory fields for key in ('id', 'url', 'title', 'ext'): diff --git a/test/test_playlists.py b/test/test_playlists.py index 706b6bdca..5eeba091e 100644 --- a/test/test_playlists.py +++ b/test/test_playlists.py @@ -1,6 +1,7 @@ #!/usr/bin/env python # encoding: utf-8 +from __future__ import unicode_literals # Allow direct execution import os @@ -8,20 +9,30 @@ import sys import unittest sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) -from test.helper import FakeYDL, global_setup -global_setup() +from test.helper import FakeYDL from youtube_dl.extractor import ( + AcademicEarthCourseIE, DailymotionPlaylistIE, DailymotionUserIE, VimeoChannelIE, + VimeoUserIE, + VimeoAlbumIE, + VimeoGroupsIE, UstreamChannelIE, SoundcloudSetIE, SoundcloudUserIE, LivestreamIE, NHLVideocenterIE, BambuserChannelIE, + BandcampAlbumIE, + SmotriCommunityIE, + SmotriUserIE, + IviCompilationIE, + ImdbListIE, + KhanAcademyIE, + EveryonesMixtapeIE, ) @@ -35,7 +46,7 @@ class TestPlaylists(unittest.TestCase): ie = DailymotionPlaylistIE(dl) result = ie.extract('http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q') self.assertIsPlaylist(result) - self.assertEqual(result['title'], u'SPORT') + self.assertEqual(result['title'], 'SPORT') self.assertTrue(len(result['entries']) > 20) def test_dailymotion_user(self): @@ -43,7 +54,7 @@ class TestPlaylists(unittest.TestCase): ie = DailymotionUserIE(dl) result = ie.extract('http://www.dailymotion.com/user/generation-quoi/') self.assertIsPlaylist(result) - self.assertEqual(result['title'], u'Génération Quoi') + self.assertEqual(result['title'], 'Génération Quoi') self.assertTrue(len(result['entries']) >= 26) def test_vimeo_channel(self): @@ -51,15 +62,39 @@ class TestPlaylists(unittest.TestCase): ie = VimeoChannelIE(dl) result = ie.extract('http://vimeo.com/channels/tributes') self.assertIsPlaylist(result) - self.assertEqual(result['title'], u'Vimeo Tributes') + self.assertEqual(result['title'], 'Vimeo Tributes') self.assertTrue(len(result['entries']) > 24) + def test_vimeo_user(self): + dl = FakeYDL() + ie = VimeoUserIE(dl) + result = ie.extract('http://vimeo.com/nkistudio/videos') + self.assertIsPlaylist(result) + self.assertEqual(result['title'], 'Nki') + self.assertTrue(len(result['entries']) > 65) + + def test_vimeo_album(self): + dl = FakeYDL() + ie = VimeoAlbumIE(dl) + result = ie.extract('http://vimeo.com/album/2632481') + self.assertIsPlaylist(result) + self.assertEqual(result['title'], 'Staff Favorites: November 2013') + self.assertTrue(len(result['entries']) > 12) + + def test_vimeo_groups(self): + dl = FakeYDL() + ie = VimeoGroupsIE(dl) + result = ie.extract('http://vimeo.com/groups/rolexawards') + self.assertIsPlaylist(result) + self.assertEqual(result['title'], 'Rolex Awards for Enterprise') + self.assertTrue(len(result['entries']) > 72) + def test_ustream_channel(self): dl = FakeYDL() ie = UstreamChannelIE(dl) result = ie.extract('http://www.ustream.tv/channel/young-americans-for-liberty') self.assertIsPlaylist(result) - self.assertEqual(result['id'], u'5124905') + self.assertEqual(result['id'], '5124905') self.assertTrue(len(result['entries']) >= 11) def test_soundcloud_set(self): @@ -67,7 +102,7 @@ class TestPlaylists(unittest.TestCase): ie = SoundcloudSetIE(dl) result = ie.extract('https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep') self.assertIsPlaylist(result) - self.assertEqual(result['title'], u'The Royal Concept EP') + self.assertEqual(result['title'], 'The Royal Concept EP') self.assertTrue(len(result['entries']) >= 6) def test_soundcloud_user(self): @@ -75,7 +110,7 @@ class TestPlaylists(unittest.TestCase): ie = SoundcloudUserIE(dl) result = ie.extract('https://soundcloud.com/the-concept-band') self.assertIsPlaylist(result) - self.assertEqual(result['id'], u'9615865') + self.assertEqual(result['id'], '9615865') self.assertTrue(len(result['entries']) >= 12) def test_livestream_event(self): @@ -83,7 +118,7 @@ class TestPlaylists(unittest.TestCase): ie = LivestreamIE(dl) result = ie.extract('http://new.livestream.com/tedx/cityenglish') self.assertIsPlaylist(result) - self.assertEqual(result['title'], u'TEDCity2.0 (English)') + self.assertEqual(result['title'], 'TEDCity2.0 (English)') self.assertTrue(len(result['entries']) >= 4) def test_nhl_videocenter(self): @@ -91,8 +126,8 @@ class TestPlaylists(unittest.TestCase): ie = NHLVideocenterIE(dl) result = ie.extract('http://video.canucks.nhl.com/videocenter/console?catid=999') self.assertIsPlaylist(result) - self.assertEqual(result['id'], u'999') - self.assertEqual(result['title'], u'Highlights') + self.assertEqual(result['id'], '999') + self.assertEqual(result['title'], 'Highlights') self.assertEqual(len(result['entries']), 12) def test_bambuser_channel(self): @@ -100,8 +135,91 @@ class TestPlaylists(unittest.TestCase): ie = BambuserChannelIE(dl) result = ie.extract('http://bambuser.com/channel/pixelversity') self.assertIsPlaylist(result) - self.assertEqual(result['title'], u'pixelversity') - self.assertTrue(len(result['entries']) >= 66) + self.assertEqual(result['title'], 'pixelversity') + self.assertTrue(len(result['entries']) >= 60) + + def test_bandcamp_album(self): + dl = FakeYDL() + ie = BandcampAlbumIE(dl) + result = ie.extract('http://mpallante.bandcamp.com/album/nightmare-night-ep') + self.assertIsPlaylist(result) + self.assertEqual(result['title'], 'Nightmare Night EP') + self.assertTrue(len(result['entries']) >= 4) + + def test_smotri_community(self): + dl = FakeYDL() + ie = SmotriCommunityIE(dl) + result = ie.extract('http://smotri.com/community/video/kommuna') + self.assertIsPlaylist(result) + self.assertEqual(result['id'], 'kommuna') + self.assertEqual(result['title'], 'КПРФ') + self.assertTrue(len(result['entries']) >= 4) + + def test_smotri_user(self): + dl = FakeYDL() + ie = SmotriUserIE(dl) + result = ie.extract('http://smotri.com/user/inspector') + self.assertIsPlaylist(result) + self.assertEqual(result['id'], 'inspector') + self.assertEqual(result['title'], 'Inspector') + self.assertTrue(len(result['entries']) >= 9) + + def test_AcademicEarthCourse(self): + dl = FakeYDL() + ie = AcademicEarthCourseIE(dl) + result = ie.extract('http://academicearth.org/courses/building-dynamic-websites/') + self.assertIsPlaylist(result) + self.assertEqual(result['id'], 'building-dynamic-websites') + self.assertEqual(result['title'], 'Building Dynamic Websites') + self.assertEqual(result['description'], u"Today's websites are increasingly dynamic. Pages are no longer static HTML files but instead generated by scripts and database calls. User interfaces are more seamless, with technologies like Ajax replacing traditional page reloads. This course teaches students how to build dynamic websites with Ajax and with Linux, Apache, MySQL, and PHP (LAMP), one of today's most popular frameworks. Students learn how to set up domain names with DNS, how to structure pages with XHTML and CSS, how to program in JavaScript and PHP, how to configure Apache and MySQL, how to design and query databases with SQL, how to use Ajax with both XML and JSON, and how to build mashups. The course explores issues of security, scalability, and cross-browser support and also discusses enterprise-level deployments of websites, including third-party hosting, virtualization, colocation in data centers, firewalling, and load-balancing.") + self.assertEqual(len(result['entries']), 10) + + def test_ivi_compilation(self): + dl = FakeYDL() + ie = IviCompilationIE(dl) + result = ie.extract('http://www.ivi.ru/watch/dezhurnyi_angel') + self.assertIsPlaylist(result) + self.assertEqual(result['id'], 'dezhurnyi_angel') + self.assertEqual(result['title'], 'Дежурный ангел (2010 - 2012)') + self.assertTrue(len(result['entries']) >= 36) + + def test_ivi_compilation_season(self): + dl = FakeYDL() + ie = IviCompilationIE(dl) + result = ie.extract('http://www.ivi.ru/watch/dezhurnyi_angel/season2') + self.assertIsPlaylist(result) + self.assertEqual(result['id'], 'dezhurnyi_angel/season2') + self.assertEqual(result['title'], 'Дежурный ангел (2010 - 2012) 2 сезон') + self.assertTrue(len(result['entries']) >= 20) + + def test_imdb_list(self): + dl = FakeYDL() + ie = ImdbListIE(dl) + result = ie.extract('http://www.imdb.com/list/sMjedvGDd8U') + self.assertIsPlaylist(result) + self.assertEqual(result['id'], 'sMjedvGDd8U') + self.assertEqual(result['title'], 'Animated and Family Films') + self.assertTrue(len(result['entries']) >= 48) + + def test_khanacademy_topic(self): + dl = FakeYDL() + ie = KhanAcademyIE(dl) + result = ie.extract('https://www.khanacademy.org/math/applied-math/cryptography') + self.assertIsPlaylist(result) + self.assertEqual(result['id'], 'cryptography') + self.assertEqual(result['title'], 'Journey into cryptography') + self.assertEqual(result['description'], 'How have humans protected their secret messages through history? What has changed today?') + self.assertTrue(len(result['entries']) >= 3) + + def test_EveryonesMixtape(self): + dl = FakeYDL() + ie = EveryonesMixtapeIE(dl) + result = ie.extract('http://everyonesmixtape.com/#/mix/m7m0jJAbMQi') + self.assertIsPlaylist(result) + self.assertEqual(result['id'], 'm7m0jJAbMQi') + self.assertEqual(result['title'], 'Driving') + self.assertEqual(len(result['entries']), 24) + if __name__ == '__main__': unittest.main() diff --git a/test/test_subtitles.py b/test/test_subtitles.py index 06a304879..1e4e62faa 100644 --- a/test/test_subtitles.py +++ b/test/test_subtitles.py @@ -6,8 +6,7 @@ import sys import unittest sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) -from test.helper import FakeYDL, global_setup, md5 -global_setup() +from test.helper import FakeYDL, md5 from youtube_dl.extractor import ( @@ -37,10 +36,6 @@ class TestYoutubeSubtitles(BaseTestSubtitles): url = 'QRS8MkLhQmM' IE = YoutubeIE - def getSubtitles(self): - info_dict = self.getInfoDict() - return info_dict[0]['subtitles'] - def test_youtube_no_writesubtitles(self): self.DL.params['writesubtitles'] = False subtitles = self.getSubtitles() @@ -73,7 +68,7 @@ class TestYoutubeSubtitles(BaseTestSubtitles): self.DL.params['writesubtitles'] = True self.DL.params['subtitlesformat'] = 'vtt' subtitles = self.getSubtitles() - self.assertEqual(md5(subtitles['en']), '356cdc577fde0c6783b9b822e7206ff7') + self.assertEqual(md5(subtitles['en']), '3cb210999d3e021bd6c7f0ea751eab06') def test_youtube_list_subtitles(self): self.DL.expect_warning(u'Video doesn\'t have automatic captions') @@ -172,13 +167,13 @@ class TestTedSubtitles(BaseTestSubtitles): def test_subtitles(self): self.DL.params['writesubtitles'] = True subtitles = self.getSubtitles() - self.assertEqual(md5(subtitles['en']), '2154f31ff9b9f89a0aa671537559c21d') + self.assertEqual(md5(subtitles['en']), '4262c1665ff928a2dada178f62cb8d14') def test_subtitles_lang(self): self.DL.params['writesubtitles'] = True self.DL.params['subtitleslangs'] = ['fr'] subtitles = self.getSubtitles() - self.assertEqual(md5(subtitles['fr']), '7616cbc6df20ec2c1204083c83871cf6') + self.assertEqual(md5(subtitles['fr']), '66a63f7f42c97a50f8c0e90bc7797bb5') def test_allsubtitles(self): self.DL.params['writesubtitles'] = True diff --git a/test/test_unicode_literals.py b/test/test_unicode_literals.py new file mode 100644 index 000000000..a4ba7bad0 --- /dev/null +++ b/test/test_unicode_literals.py @@ -0,0 +1,47 @@ +from __future__ import unicode_literals + +import io +import os +import re +import unittest + +rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) + +IGNORED_FILES = [ + 'setup.py', # http://bugs.python.org/issue13943 +] + + +class TestUnicodeLiterals(unittest.TestCase): + def test_all_files(self): + print('Skipping this test (not yet fully implemented)') + return + + for dirpath, _, filenames in os.walk(rootDir): + for basename in filenames: + if not basename.endswith('.py'): + continue + if basename in IGNORED_FILES: + continue + + fn = os.path.join(dirpath, basename) + with io.open(fn, encoding='utf-8') as inf: + code = inf.read() + + if "'" not in code and '"' not in code: + continue + imps = 'from __future__ import unicode_literals' + self.assertTrue( + imps in code, + ' %s missing in %s' % (imps, fn)) + + m = re.search(r'(?<=\s)u[\'"](?!\)|,|$)', code) + if m is not None: + self.assertTrue( + m is None, + 'u present in %s, around %s' % ( + fn, code[m.start() - 10:m.end() + 10])) + + +if __name__ == '__main__': + unittest.main() diff --git a/test/test_utils.py b/test/test_utils.py index f3fbff042..a17483ada 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -13,17 +13,23 @@ import xml.etree.ElementTree #from youtube_dl.utils import htmlentity_transform from youtube_dl.utils import ( - timeconvert, - sanitize_filename, - unescapeHTML, - orderedSet, DateRange, - unified_strdate, + encodeFilename, find_xpath_attr, + fix_xml_ampersands, get_meta_content, - xpath_with_ns, + orderedSet, + parse_duration, + sanitize_filename, + shell_quote, smuggle_url, + str_to_int, + timeconvert, + unescapeHTML, + unified_strdate, unsmuggle_url, + url_basename, + xpath_with_ns, ) if sys.version_info < (3, 0): @@ -170,6 +176,43 @@ class TestUtil(unittest.TestCase): self.assertEqual(res_url, url) self.assertEqual(res_data, None) + def test_shell_quote(self): + args = ['ffmpeg', '-i', encodeFilename(u'ñ€ß\'.mp4')] + self.assertEqual(shell_quote(args), u"""ffmpeg -i 'ñ€ß'"'"'.mp4'""") + + def test_str_to_int(self): + self.assertEqual(str_to_int('123,456'), 123456) + self.assertEqual(str_to_int('123.456'), 123456) + + def test_url_basename(self): + self.assertEqual(url_basename(u'http://foo.de/'), u'') + self.assertEqual(url_basename(u'http://foo.de/bar/baz'), u'baz') + self.assertEqual(url_basename(u'http://foo.de/bar/baz?x=y'), u'baz') + self.assertEqual(url_basename(u'http://foo.de/bar/baz#x=y'), u'baz') + self.assertEqual(url_basename(u'http://foo.de/bar/baz/'), u'baz') + self.assertEqual( + url_basename(u'http://media.w3.org/2010/05/sintel/trailer.mp4'), + u'trailer.mp4') + + def test_parse_duration(self): + self.assertEqual(parse_duration(None), None) + self.assertEqual(parse_duration('1'), 1) + self.assertEqual(parse_duration('1337:12'), 80232) + self.assertEqual(parse_duration('9:12:43'), 33163) + self.assertEqual(parse_duration('x:y'), None) + + def test_fix_xml_ampersands(self): + self.assertEqual( + fix_xml_ampersands('"&x=y&z=a'), '"&x=y&z=a') + self.assertEqual( + fix_xml_ampersands('"&x=y&wrong;&z=a'), + '"&x=y&wrong;&z=a') + self.assertEqual( + fix_xml_ampersands('&'><"'), + '&'><"') + self.assertEqual( + fix_xml_ampersands('Ӓ᪼'), 'Ӓ᪼') + self.assertEqual(fix_xml_ampersands('&#&#'), '&#&#') if __name__ == '__main__': unittest.main() diff --git a/test/test_write_annotations.py b/test/test_write_annotations.py index 35defb895..eac53b285 100644 --- a/test/test_write_annotations.py +++ b/test/test_write_annotations.py @@ -7,8 +7,7 @@ import sys import unittest sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) -from test.helper import get_params, global_setup, try_rm -global_setup() +from test.helper import get_params, try_rm import io diff --git a/test/test_write_info_json.py b/test/test_write_info_json.py index a5b6f6972..90426a559 100644 --- a/test/test_write_info_json.py +++ b/test/test_write_info_json.py @@ -7,8 +7,7 @@ import sys import unittest sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) -from test.helper import get_params, global_setup -global_setup() +from test.helper import get_params import io @@ -31,9 +30,10 @@ params = get_params({ TEST_ID = 'BaW_jenozKc' -INFO_JSON_FILE = TEST_ID + '.mp4.info.json' +INFO_JSON_FILE = TEST_ID + '.info.json' DESCRIPTION_FILE = TEST_ID + '.mp4.description' EXPECTED_DESCRIPTION = u'''test chars: "'/\ä↭𝕐 +test URL: https://github.com/rg3/youtube-dl/issues/1892 This is a test video for youtube-dl. diff --git a/test/test_youtube_lists.py b/test/test_youtube_lists.py index 4b7a7847b..d9fe5af4e 100644 --- a/test/test_youtube_lists.py +++ b/test/test_youtube_lists.py @@ -6,8 +6,7 @@ import sys import unittest sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) -from test.helper import FakeYDL, global_setup -global_setup() +from test.helper import FakeYDL from youtube_dl.extractor import ( @@ -16,6 +15,7 @@ from youtube_dl.extractor import ( YoutubeIE, YoutubeChannelIE, YoutubeShowIE, + YoutubeTopListIE, ) @@ -27,7 +27,7 @@ class TestYoutubeLists(unittest.TestCase): def test_youtube_playlist(self): dl = FakeYDL() ie = YoutubePlaylistIE(dl) - result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')[0] + result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re') self.assertIsPlaylist(result) self.assertEqual(result['title'], 'ytdl test PL') ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']] @@ -44,13 +44,13 @@ class TestYoutubeLists(unittest.TestCase): def test_issue_673(self): dl = FakeYDL() ie = YoutubePlaylistIE(dl) - result = ie.extract('PLBB231211A4F62143')[0] + result = ie.extract('PLBB231211A4F62143') self.assertTrue(len(result['entries']) > 25) def test_youtube_playlist_long(self): dl = FakeYDL() ie = YoutubePlaylistIE(dl) - result = ie.extract('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')[0] + result = ie.extract('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q') self.assertIsPlaylist(result) self.assertTrue(len(result['entries']) >= 799) @@ -58,7 +58,7 @@ class TestYoutubeLists(unittest.TestCase): #651 dl = FakeYDL() ie = YoutubePlaylistIE(dl) - result = ie.extract('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')[0] + result = ie.extract('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC') ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']] self.assertFalse('pElCt5oNDuI' in ytie_results) self.assertFalse('KdPEApIVdWM' in ytie_results) @@ -66,7 +66,7 @@ class TestYoutubeLists(unittest.TestCase): def test_youtube_playlist_empty(self): dl = FakeYDL() ie = YoutubePlaylistIE(dl) - result = ie.extract('https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx')[0] + result = ie.extract('https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx') self.assertIsPlaylist(result) self.assertEqual(len(result['entries']), 0) @@ -74,7 +74,7 @@ class TestYoutubeLists(unittest.TestCase): dl = FakeYDL() ie = YoutubePlaylistIE(dl) # TODO find a > 100 (paginating?) videos course - result = ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')[0] + result = ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8') entries = result['entries'] self.assertEqual(YoutubeIE()._extract_id(entries[0]['url']), 'j9WZyLZCBzs') self.assertEqual(len(entries), 25) @@ -84,22 +84,22 @@ class TestYoutubeLists(unittest.TestCase): dl = FakeYDL() ie = YoutubeChannelIE(dl) #test paginated channel - result = ie.extract('https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w')[0] + result = ie.extract('https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w') self.assertTrue(len(result['entries']) > 90) #test autogenerated channel - result = ie.extract('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')[0] + result = ie.extract('https://www.youtube.com/channel/HCtnHdj3df7iM/videos') self.assertTrue(len(result['entries']) >= 18) def test_youtube_user(self): dl = FakeYDL() ie = YoutubeUserIE(dl) - result = ie.extract('https://www.youtube.com/user/TheLinuxFoundation')[0] + result = ie.extract('https://www.youtube.com/user/TheLinuxFoundation') self.assertTrue(len(result['entries']) >= 320) def test_youtube_safe_search(self): dl = FakeYDL() ie = YoutubePlaylistIE(dl) - result = ie.extract('PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl')[0] + result = ie.extract('PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl') self.assertEqual(len(result['entries']), 2) def test_youtube_show(self): @@ -108,5 +108,21 @@ class TestYoutubeLists(unittest.TestCase): result = ie.extract('http://www.youtube.com/show/airdisasters') self.assertTrue(len(result) >= 3) + def test_youtube_mix(self): + dl = FakeYDL() + ie = YoutubePlaylistIE(dl) + result = ie.extract('http://www.youtube.com/watch?v=lLJf9qJHR3E&list=RDrjFaenf1T-Y') + entries = result['entries'] + self.assertTrue(len(entries) >= 20) + original_video = entries[0] + self.assertEqual(original_video['id'], 'rjFaenf1T-Y') + + def test_youtube_toplist(self): + dl = FakeYDL() + ie = YoutubeTopListIE(dl) + result = ie.extract('yttoplist:music:Top Tracks') + entries = result['entries'] + self.assertTrue(len(entries) >= 5) + if __name__ == '__main__': unittest.main() diff --git a/test/test_youtube_signature.py b/test/test_youtube_signature.py index 5e1ff5eb0..a3fc53047 100644 --- a/test/test_youtube_signature.py +++ b/test/test_youtube_signature.py @@ -6,9 +6,6 @@ import sys import unittest sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) -from test.helper import global_setup -global_setup() - import io import re @@ -30,12 +27,6 @@ _TESTS = [ 85, u'3456789a0cdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRS[UVWXYZ!"#$%&\'()*+,-./:;<=>?@', ), - ( - u'https://s.ytimg.com/yts/swfbin/watch_as3-vflg5GhxU.swf', - u'swf', - 82, - u':/.-,+*)=\'&%$#"!ZYX0VUTSRQPONMLKJIHGFEDCBAzyxw>utsrqponmlkjihgfedcba987654321' - ), ] diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index e5a542ed5..5c8e676a2 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -1,625 +1,12 @@ -import math -import os -import re -import subprocess -import sys -import time - -from .utils import ( - compat_urllib_error, - compat_urllib_request, - ContentTooShortError, - determine_ext, - encodeFilename, - sanitize_open, - timeconvert, -) - - -class FileDownloader(object): - """File Downloader class. - - File downloader objects are the ones responsible of downloading the - actual video file and writing it to disk. - - File downloaders accept a lot of parameters. In order not to saturate - the object constructor with arguments, it receives a dictionary of - options instead. - - Available options: - - verbose: Print additional info to stdout. - quiet: Do not print messages to stdout. - ratelimit: Download speed limit, in bytes/sec. - retries: Number of times to retry for HTTP error 5xx - buffersize: Size of download buffer in bytes. - noresizebuffer: Do not automatically resize the download buffer. - continuedl: Try to continue downloads if possible. - noprogress: Do not print the progress bar. - logtostderr: Log messages to stderr instead of stdout. - consoletitle: Display progress in console window's titlebar. - nopart: Do not use temporary .part files. - updatetime: Use the Last-modified header to set output file timestamps. - test: Download only first bytes to test the downloader. - min_filesize: Skip files smaller than this size - max_filesize: Skip files larger than this size - """ - - params = None - - def __init__(self, ydl, params): - """Create a FileDownloader object with the given options.""" - self.ydl = ydl - self._progress_hooks = [] - self.params = params - - @staticmethod - def format_bytes(bytes): - if bytes is None: - return 'N/A' - if type(bytes) is str: - bytes = float(bytes) - if bytes == 0.0: - exponent = 0 - else: - exponent = int(math.log(bytes, 1024.0)) - suffix = ['B','KiB','MiB','GiB','TiB','PiB','EiB','ZiB','YiB'][exponent] - converted = float(bytes) / float(1024 ** exponent) - return '%.2f%s' % (converted, suffix) - - @staticmethod - def format_seconds(seconds): - (mins, secs) = divmod(seconds, 60) - (hours, mins) = divmod(mins, 60) - if hours > 99: - return '--:--:--' - if hours == 0: - return '%02d:%02d' % (mins, secs) - else: - return '%02d:%02d:%02d' % (hours, mins, secs) - - @staticmethod - def calc_percent(byte_counter, data_len): - if data_len is None: - return None - return float(byte_counter) / float(data_len) * 100.0 - - @staticmethod - def format_percent(percent): - if percent is None: - return '---.-%' - return '%6s' % ('%3.1f%%' % percent) - - @staticmethod - def calc_eta(start, now, total, current): - if total is None: - return None - dif = now - start - if current == 0 or dif < 0.001: # One millisecond - return None - rate = float(current) / dif - return int((float(total) - float(current)) / rate) - - @staticmethod - def format_eta(eta): - if eta is None: - return '--:--' - return FileDownloader.format_seconds(eta) - - @staticmethod - def calc_speed(start, now, bytes): - dif = now - start - if bytes == 0 or dif < 0.001: # One millisecond - return None - return float(bytes) / dif - - @staticmethod - def format_speed(speed): - if speed is None: - return '%10s' % '---b/s' - return '%10s' % ('%s/s' % FileDownloader.format_bytes(speed)) - - @staticmethod - def best_block_size(elapsed_time, bytes): - new_min = max(bytes / 2.0, 1.0) - new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB - if elapsed_time < 0.001: - return int(new_max) - rate = bytes / elapsed_time - if rate > new_max: - return int(new_max) - if rate < new_min: - return int(new_min) - return int(rate) - - @staticmethod - def parse_bytes(bytestr): - """Parse a string indicating a byte quantity into an integer.""" - matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr) - if matchobj is None: - return None - number = float(matchobj.group(1)) - multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower()) - return int(round(number * multiplier)) - - def to_screen(self, *args, **kargs): - self.ydl.to_screen(*args, **kargs) - - def to_stderr(self, message): - self.ydl.to_screen(message) - - def to_console_title(self, message): - self.ydl.to_console_title(message) - - def trouble(self, *args, **kargs): - self.ydl.trouble(*args, **kargs) - - def report_warning(self, *args, **kargs): - self.ydl.report_warning(*args, **kargs) - - def report_error(self, *args, **kargs): - self.ydl.report_error(*args, **kargs) - - def slow_down(self, start_time, byte_counter): - """Sleep if the download speed is over the rate limit.""" - rate_limit = self.params.get('ratelimit', None) - if rate_limit is None or byte_counter == 0: - return - now = time.time() - elapsed = now - start_time - if elapsed <= 0.0: - return - speed = float(byte_counter) / elapsed - if speed > rate_limit: - time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) - - def temp_name(self, filename): - """Returns a temporary filename for the given filename.""" - if self.params.get('nopart', False) or filename == u'-' or \ - (os.path.exists(encodeFilename(filename)) and not os.path.isfile(encodeFilename(filename))): - return filename - return filename + u'.part' - - def undo_temp_name(self, filename): - if filename.endswith(u'.part'): - return filename[:-len(u'.part')] - return filename - - def try_rename(self, old_filename, new_filename): - try: - if old_filename == new_filename: - return - os.rename(encodeFilename(old_filename), encodeFilename(new_filename)) - except (IOError, OSError): - self.report_error(u'unable to rename file') - - def try_utime(self, filename, last_modified_hdr): - """Try to set the last-modified time of the given file.""" - if last_modified_hdr is None: - return - if not os.path.isfile(encodeFilename(filename)): - return - timestr = last_modified_hdr - if timestr is None: - return - filetime = timeconvert(timestr) - if filetime is None: - return filetime - # Ignore obviously invalid dates - if filetime == 0: - return - try: - os.utime(filename, (time.time(), filetime)) - except: - pass - return filetime - - def report_destination(self, filename): - """Report destination filename.""" - self.to_screen(u'[download] Destination: ' + filename) - - def report_progress(self, percent, data_len_str, speed, eta): - """Report download progress.""" - if self.params.get('noprogress', False): - return - clear_line = (u'\x1b[K' if sys.stderr.isatty() and os.name != 'nt' else u'') - if eta is not None: - eta_str = self.format_eta(eta) - else: - eta_str = 'Unknown ETA' - if percent is not None: - percent_str = self.format_percent(percent) - else: - percent_str = 'Unknown %' - speed_str = self.format_speed(speed) - if self.params.get('progress_with_newline', False): - self.to_screen(u'[download] %s of %s at %s ETA %s' % - (percent_str, data_len_str, speed_str, eta_str)) - else: - self.to_screen(u'\r%s[download] %s of %s at %s ETA %s' % - (clear_line, percent_str, data_len_str, speed_str, eta_str), skip_eol=True) - self.to_console_title(u'youtube-dl - %s of %s at %s ETA %s' % - (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip())) - - def report_resuming_byte(self, resume_len): - """Report attempt to resume at given byte.""" - self.to_screen(u'[download] Resuming download at byte %s' % resume_len) - - def report_retry(self, count, retries): - """Report retry in case of HTTP error 5xx""" - self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries)) - - def report_file_already_downloaded(self, file_name): - """Report file has already been fully downloaded.""" - try: - self.to_screen(u'[download] %s has already been downloaded' % file_name) - except UnicodeEncodeError: - self.to_screen(u'[download] The file has already been downloaded') - - def report_unable_to_resume(self): - """Report it was impossible to resume download.""" - self.to_screen(u'[download] Unable to resume') - - def report_finish(self, data_len_str, tot_time): - """Report download finished.""" - if self.params.get('noprogress', False): - self.to_screen(u'[download] Download completed') - else: - clear_line = (u'\x1b[K' if sys.stderr.isatty() and os.name != 'nt' else u'') - self.to_screen(u'\r%s[download] 100%% of %s in %s' % - (clear_line, data_len_str, self.format_seconds(tot_time))) - - def _download_with_rtmpdump(self, filename, url, player_url, page_url, play_path, tc_url, live): - self.report_destination(filename) - tmpfilename = self.temp_name(filename) - test = self.params.get('test', False) - - # Check for rtmpdump first - try: - subprocess.call(['rtmpdump', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT) - except (OSError, IOError): - self.report_error(u'RTMP download detected but "rtmpdump" could not be run') - return False - verbosity_option = '--verbose' if self.params.get('verbose', False) else '--quiet' - - # Download using rtmpdump. rtmpdump returns exit code 2 when - # the connection was interrumpted and resuming appears to be - # possible. This is part of rtmpdump's normal usage, AFAIK. - basic_args = ['rtmpdump', verbosity_option, '-r', url, '-o', tmpfilename] - if player_url is not None: - basic_args += ['--swfVfy', player_url] - if page_url is not None: - basic_args += ['--pageUrl', page_url] - if play_path is not None: - basic_args += ['--playpath', play_path] - if tc_url is not None: - basic_args += ['--tcUrl', url] - if test: - basic_args += ['--stop', '1'] - if live: - basic_args += ['--live'] - args = basic_args + [[], ['--resume', '--skip', '1']][self.params.get('continuedl', False)] - if self.params.get('verbose', False): - try: - import pipes - shell_quote = lambda args: ' '.join(map(pipes.quote, args)) - except ImportError: - shell_quote = repr - self.to_screen(u'[debug] rtmpdump command line: ' + shell_quote(args)) - retval = subprocess.call(args) - while (retval == 2 or retval == 1) and not test: - prevsize = os.path.getsize(encodeFilename(tmpfilename)) - self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True) - time.sleep(5.0) # This seems to be needed - retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1]) - cursize = os.path.getsize(encodeFilename(tmpfilename)) - if prevsize == cursize and retval == 1: - break - # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those - if prevsize == cursize and retval == 2 and cursize > 1024: - self.to_screen(u'\r[rtmpdump] Could not download the whole video. This can happen for some advertisements.') - retval = 0 - break - if retval == 0 or (test and retval == 2): - fsize = os.path.getsize(encodeFilename(tmpfilename)) - self.to_screen(u'\r[rtmpdump] %s bytes' % fsize) - self.try_rename(tmpfilename, filename) - self._hook_progress({ - 'downloaded_bytes': fsize, - 'total_bytes': fsize, - 'filename': filename, - 'status': 'finished', - }) - return True - else: - self.to_stderr(u"\n") - self.report_error(u'rtmpdump exited with code %d' % retval) - return False - - def _download_with_mplayer(self, filename, url): - self.report_destination(filename) - tmpfilename = self.temp_name(filename) - - args = ['mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy', '-dumpstream', '-dumpfile', tmpfilename, url] - # Check for mplayer first - try: - subprocess.call(['mplayer', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT) - except (OSError, IOError): - self.report_error(u'MMS or RTSP download detected but "%s" could not be run' % args[0] ) - return False - - # Download using mplayer. - retval = subprocess.call(args) - if retval == 0: - fsize = os.path.getsize(encodeFilename(tmpfilename)) - self.to_screen(u'\r[%s] %s bytes' % (args[0], fsize)) - self.try_rename(tmpfilename, filename) - self._hook_progress({ - 'downloaded_bytes': fsize, - 'total_bytes': fsize, - 'filename': filename, - 'status': 'finished', - }) - return True - else: - self.to_stderr(u"\n") - self.report_error(u'mplayer exited with code %d' % retval) - return False - - def _download_m3u8_with_ffmpeg(self, filename, url): - self.report_destination(filename) - tmpfilename = self.temp_name(filename) - - args = ['-y', '-i', url, '-f', 'mp4', '-c', 'copy', - '-bsf:a', 'aac_adtstoasc', tmpfilename] - - for program in ['avconv', 'ffmpeg']: - try: - subprocess.call([program, '-version'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT) - break - except (OSError, IOError): - pass - else: - self.report_error(u'm3u8 download detected but ffmpeg or avconv could not be found') - cmd = [program] + args - - retval = subprocess.call(cmd) - if retval == 0: - fsize = os.path.getsize(encodeFilename(tmpfilename)) - self.to_screen(u'\r[%s] %s bytes' % (args[0], fsize)) - self.try_rename(tmpfilename, filename) - self._hook_progress({ - 'downloaded_bytes': fsize, - 'total_bytes': fsize, - 'filename': filename, - 'status': 'finished', - }) - return True - else: - self.to_stderr(u"\n") - self.report_error(u'ffmpeg exited with code %d' % retval) - return False +# Legacy file for backwards compatibility, use youtube_dl.downloader instead! +from .downloader import FileDownloader as RealFileDownloader +from .downloader import get_suitable_downloader +# This class reproduces the old behaviour of FileDownloader +class FileDownloader(RealFileDownloader): def _do_download(self, filename, info_dict): - url = info_dict['url'] - - # Check file already present - if self.params.get('continuedl', False) and os.path.isfile(encodeFilename(filename)) and not self.params.get('nopart', False): - self.report_file_already_downloaded(filename) - self._hook_progress({ - 'filename': filename, - 'status': 'finished', - 'total_bytes': os.path.getsize(encodeFilename(filename)), - }) - return True - - # Attempt to download using rtmpdump - if url.startswith('rtmp'): - return self._download_with_rtmpdump(filename, url, - info_dict.get('player_url', None), - info_dict.get('page_url', None), - info_dict.get('play_path', None), - info_dict.get('tc_url', None), - info_dict.get('rtmp_live', False)) - - # Attempt to download using mplayer - if url.startswith('mms') or url.startswith('rtsp'): - return self._download_with_mplayer(filename, url) - - # m3u8 manifest are downloaded with ffmpeg - if determine_ext(url) == u'm3u8': - return self._download_m3u8_with_ffmpeg(filename, url) - - tmpfilename = self.temp_name(filename) - stream = None - - # Do not include the Accept-Encoding header - headers = {'Youtubedl-no-compression': 'True'} - if 'user_agent' in info_dict: - headers['Youtubedl-user-agent'] = info_dict['user_agent'] - basic_request = compat_urllib_request.Request(url, None, headers) - request = compat_urllib_request.Request(url, None, headers) - - if self.params.get('test', False): - request.add_header('Range','bytes=0-10240') - - # Establish possible resume length - if os.path.isfile(encodeFilename(tmpfilename)): - resume_len = os.path.getsize(encodeFilename(tmpfilename)) - else: - resume_len = 0 - - open_mode = 'wb' - if resume_len != 0: - if self.params.get('continuedl', False): - self.report_resuming_byte(resume_len) - request.add_header('Range','bytes=%d-' % resume_len) - open_mode = 'ab' - else: - resume_len = 0 - - count = 0 - retries = self.params.get('retries', 0) - while count <= retries: - # Establish connection - try: - if count == 0 and 'urlhandle' in info_dict: - data = info_dict['urlhandle'] - data = compat_urllib_request.urlopen(request) - break - except (compat_urllib_error.HTTPError, ) as err: - if (err.code < 500 or err.code >= 600) and err.code != 416: - # Unexpected HTTP error - raise - elif err.code == 416: - # Unable to resume (requested range not satisfiable) - try: - # Open the connection again without the range header - data = compat_urllib_request.urlopen(basic_request) - content_length = data.info()['Content-Length'] - except (compat_urllib_error.HTTPError, ) as err: - if err.code < 500 or err.code >= 600: - raise - else: - # Examine the reported length - if (content_length is not None and - (resume_len - 100 < int(content_length) < resume_len + 100)): - # The file had already been fully downloaded. - # Explanation to the above condition: in issue #175 it was revealed that - # YouTube sometimes adds or removes a few bytes from the end of the file, - # changing the file size slightly and causing problems for some users. So - # I decided to implement a suggested change and consider the file - # completely downloaded if the file size differs less than 100 bytes from - # the one in the hard drive. - self.report_file_already_downloaded(filename) - self.try_rename(tmpfilename, filename) - self._hook_progress({ - 'filename': filename, - 'status': 'finished', - }) - return True - else: - # The length does not match, we start the download over - self.report_unable_to_resume() - open_mode = 'wb' - break - # Retry - count += 1 - if count <= retries: - self.report_retry(count, retries) - - if count > retries: - self.report_error(u'giving up after %s retries' % retries) - return False - - data_len = data.info().get('Content-length', None) - if data_len is not None: - data_len = int(data_len) + resume_len - min_data_len = self.params.get("min_filesize", None) - max_data_len = self.params.get("max_filesize", None) - if min_data_len is not None and data_len < min_data_len: - self.to_screen(u'\r[download] File is smaller than min-filesize (%s bytes < %s bytes). Aborting.' % (data_len, min_data_len)) - return False - if max_data_len is not None and data_len > max_data_len: - self.to_screen(u'\r[download] File is larger than max-filesize (%s bytes > %s bytes). Aborting.' % (data_len, max_data_len)) - return False - - data_len_str = self.format_bytes(data_len) - byte_counter = 0 + resume_len - block_size = self.params.get('buffersize', 1024) - start = time.time() - while True: - # Download and write - before = time.time() - data_block = data.read(block_size) - after = time.time() - if len(data_block) == 0: - break - byte_counter += len(data_block) - - # Open file just in time - if stream is None: - try: - (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode) - assert stream is not None - filename = self.undo_temp_name(tmpfilename) - self.report_destination(filename) - except (OSError, IOError) as err: - self.report_error(u'unable to open for writing: %s' % str(err)) - return False - try: - stream.write(data_block) - except (IOError, OSError) as err: - self.to_stderr(u"\n") - self.report_error(u'unable to write data: %s' % str(err)) - return False - if not self.params.get('noresizebuffer', False): - block_size = self.best_block_size(after - before, len(data_block)) - - # Progress message - speed = self.calc_speed(start, time.time(), byte_counter - resume_len) - if data_len is None: - eta = percent = None - else: - percent = self.calc_percent(byte_counter, data_len) - eta = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len) - self.report_progress(percent, data_len_str, speed, eta) - - self._hook_progress({ - 'downloaded_bytes': byte_counter, - 'total_bytes': data_len, - 'tmpfilename': tmpfilename, - 'filename': filename, - 'status': 'downloading', - 'eta': eta, - 'speed': speed, - }) - - # Apply rate limit - self.slow_down(start, byte_counter - resume_len) - - if stream is None: - self.to_stderr(u"\n") - self.report_error(u'Did not get any data blocks') - return False - stream.close() - self.report_finish(data_len_str, (time.time() - start)) - if data_len is not None and byte_counter != data_len: - raise ContentTooShortError(byte_counter, int(data_len)) - self.try_rename(tmpfilename, filename) - - # Update file modification time - if self.params.get('updatetime', True): - info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None)) - - self._hook_progress({ - 'downloaded_bytes': byte_counter, - 'total_bytes': byte_counter, - 'filename': filename, - 'status': 'finished', - }) - - return True - - def _hook_progress(self, status): + real_fd = get_suitable_downloader(info_dict)(self.ydl, self.params) for ph in self._progress_hooks: - ph(status) - - def add_progress_hook(self, ph): - """ ph gets called on download progress, with a dictionary with the entries - * filename: The final filename - * status: One of "downloading" and "finished" - - It can also have some of the following entries: - - * downloaded_bytes: Bytes on disks - * total_bytes: Total bytes, None if unknown - * tmpfilename: The filename we're currently writing to - * eta: The estimated time in seconds, None if unknown - * speed: The download speed in bytes/second, None if unknown - - Hooks are guaranteed to be called at least once (with status "finished") - if the download is successful. - """ - self._progress_hooks.append(ph) + real_fd.add_progress_hook(ph) + return real_fd.download(filename, info_dict) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 20eed96ca..dc8aa788c 100644 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -1,13 +1,17 @@ #!/usr/bin/env python # -*- coding: utf-8 -*- -from __future__ import absolute_import +from __future__ import absolute_import, unicode_literals +import collections import errno import io +import json import os +import platform import re import shutil +import subprocess import socket import sys import time @@ -17,8 +21,8 @@ if os.name == 'nt': import ctypes from .utils import ( + compat_cookiejar, compat_http_client, - compat_print, compat_str, compat_urllib_error, compat_urllib_request, @@ -29,20 +33,30 @@ from .utils import ( DownloadError, encodeFilename, ExtractorError, + format_bytes, + formatSeconds, + get_term_width, locked_file, + make_HTTPS_handler, MaxDownloadsReached, PostProcessingError, + platform_name, preferredencoding, SameFileError, sanitize_filename, subtitles_filename, takewhile_inclusive, UnavailableVideoError, + url_basename, write_json_file, write_string, + YoutubeDLHandler, + prepend_extension, ) from .extractor import get_info_extractor, gen_extractors -from .FileDownloader import FileDownloader +from .downloader import get_suitable_downloader +from .postprocessor import FFmpegMergerPP +from .version import __version__ class YoutubeDL(object): @@ -84,6 +98,8 @@ class YoutubeDL(object): forcethumbnail: Force printing thumbnail URL. forcedescription: Force printing description. forcefilename: Force printing final filename. + forceduration: Force printing duration. + forcejson: Force printing info_dict as JSON. simulate: Do not download the video files. format: Video format code. format_limit: Highest quality format to try. @@ -95,6 +111,7 @@ class YoutubeDL(object): playlistend: Playlist item to end at. matchtitle: Download only matching titles. rejecttitle: Reject downloads for matching titles. + logger: Log messages to a logging.Logger instance. logtostderr: Log messages to stderr instead of stdout. writedescription: Write the video description to a .description file writeinfojson: Write the video description to a .info.json file @@ -115,14 +132,35 @@ class YoutubeDL(object): noplaylist: Download single video instead of a playlist if in doubt. age_limit: An integer representing the user's age in years. Unsuitable videos for the given age are skipped. - downloadarchive: File name of a file where all downloads are recorded. + min_views: An integer representing the minimum view count the video + must have in order to not be skipped. + Videos without view count information are always + downloaded. None for no limit. + max_views: An integer representing the maximum view count. + Videos that are more popular than that are not + downloaded. + Videos without view count information are always + downloaded. None for no limit. + download_archive: File name of a file where all downloads are recorded. Videos already present in the file are not downloaded again. + cookiefile: File name where cookies should be read from and dumped to. + nocheckcertificate:Do not verify SSL certificates + proxy: URL of the proxy server to use + socket_timeout: Time to wait for unresponsive hosts, in seconds + bidi_workaround: Work around buggy terminals without bidirectional text + support, using fridibi + debug_printtraffic:Print out sent and received HTTP traffic + include_ads: Download ads as well The following parameters are not used by YoutubeDL itself, they are used by the FileDownloader: nopart, updatetime, buffersize, ratelimit, min_filesize, max_filesize, test, noresizebuffer, retries, continuedl, noprogress, consoletitle + + The following options are used by the post processors: + prefer_ffmpeg: If True, use ffmpeg instead of avconv if both are available, + otherwise prefer avconv. """ params = None @@ -132,8 +170,10 @@ class YoutubeDL(object): _num_downloads = None _screen_file = None - def __init__(self, params): + def __init__(self, params=None): """Create a FileDownloader object with the given options.""" + if params is None: + params = {} self._ies = [] self._ies_instances = {} self._pps = [] @@ -141,22 +181,50 @@ class YoutubeDL(object): self._download_retcode = 0 self._num_downloads = 0 self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] + self._err_file = sys.stderr + self.params = params + + if params.get('bidi_workaround', False): + try: + import pty + master, slave = pty.openpty() + width = get_term_width() + if width is None: + width_args = [] + else: + width_args = ['-w', str(width)] + sp_kwargs = dict( + stdin=subprocess.PIPE, + stdout=slave, + stderr=self._err_file) + try: + self._output_process = subprocess.Popen( + ['bidiv'] + width_args, **sp_kwargs + ) + except OSError: + self._output_process = subprocess.Popen( + ['fribidi', '-c', 'UTF-8'] + width_args, **sp_kwargs) + self._output_channel = os.fdopen(master, 'rb') + except OSError as ose: + if ose.errno == 2: + self.report_warning('Could not find fribidi executable, ignoring --bidi-workaround . Make sure that fribidi is an executable file in one of the directories in your $PATH.') + else: + raise if (sys.version_info >= (3,) and sys.platform != 'win32' and sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968'] and not params['restrictfilenames']): # On Python 3, the Unicode filesystem API will throw errors (#1474) self.report_warning( - u'Assuming --restrict-filenames since file system encoding ' - u'cannot encode all charactes. ' - u'Set the LC_ALL environment variable to fix this.') - params['restrictfilenames'] = True + 'Assuming --restrict-filenames since file system encoding ' + 'cannot encode all charactes. ' + 'Set the LC_ALL environment variable to fix this.') + self.params['restrictfilenames'] = True - self.params = params - self.fd = FileDownloader(self, self.params) + if '%(stitle)s' in self.params.get('outtmpl', ''): + self.report_warning('%(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.') - if '%(stitle)s' in self.params['outtmpl']: - self.report_warning(u'%(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.') + self._setup_opener() def add_info_extractor(self, ie): """Add an InfoExtractor object to the end of the list.""" @@ -188,20 +256,47 @@ class YoutubeDL(object): self._pps.append(pp) pp.set_downloader(self) + def add_progress_hook(self, ph): + """Add the progress hook (currently only for the file downloader)""" + self._progress_hooks.append(ph) + + def _bidi_workaround(self, message): + if not hasattr(self, '_output_channel'): + return message + + assert hasattr(self, '_output_process') + assert type(message) == type('') + line_count = message.count('\n') + 1 + self._output_process.stdin.write((message + '\n').encode('utf-8')) + self._output_process.stdin.flush() + res = ''.join(self._output_channel.readline().decode('utf-8') + for _ in range(line_count)) + return res[:-len('\n')] + def to_screen(self, message, skip_eol=False): """Print message to stdout if not in quiet mode.""" - if not self.params.get('quiet', False): - terminator = [u'\n', u''][skip_eol] + return self.to_stdout(message, skip_eol, check_quiet=True) + + def to_stdout(self, message, skip_eol=False, check_quiet=False): + """Print message to stdout if not in quiet mode.""" + if self.params.get('logger'): + self.params['logger'].debug(message) + elif not check_quiet or not self.params.get('quiet', False): + message = self._bidi_workaround(message) + terminator = ['\n', ''][skip_eol] output = message + terminator + write_string(output, self._screen_file) def to_stderr(self, message): """Print message to stderr.""" - assert type(message) == type(u'') - output = message + u'\n' - if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr - output = output.encode(preferredencoding()) - sys.stderr.write(output) + assert type(message) == type('') + if self.params.get('logger'): + self.params['logger'].error(message) + else: + message = self._bidi_workaround(message) + output = message + '\n' + write_string(output, self._err_file) def to_console_title(self, message): if not self.params.get('consoletitle', False): @@ -211,19 +306,21 @@ class YoutubeDL(object): # already of type unicode() ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message)) elif 'TERM' in os.environ: - write_string(u'\033]0;%s\007' % message, self._screen_file) + write_string('\033]0;%s\007' % message, self._screen_file) def save_console_title(self): if not self.params.get('consoletitle', False): return if 'TERM' in os.environ: - write_string(u'\033[22t', self._screen_file) + # Save the title on stack + write_string('\033[22;0t', self._screen_file) def restore_console_title(self): if not self.params.get('consoletitle', False): return if 'TERM' in os.environ: - write_string(u'\033[23t', self._screen_file) + # Restore the title from stack + write_string('\033[23;0t', self._screen_file) def __enter__(self): self.save_console_title() @@ -231,10 +328,9 @@ class YoutubeDL(object): def __exit__(self, *args): self.restore_console_title() - - def fixed_template(self): - """Checks if the output template is fixed.""" - return (re.search(u'(?u)%\\(.+?\\)s', self.params['outtmpl']) is None) + + if self.params.get('cookiefile') is not None: + self.cookiejar.save() def trouble(self, message=None, tb=None): """Determine action to take when a download problem appears. @@ -250,13 +346,13 @@ class YoutubeDL(object): if self.params.get('verbose'): if tb is None: if sys.exc_info()[0]: # if .trouble has been called from an except block - tb = u'' + tb = '' if hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]: - tb += u''.join(traceback.format_exception(*sys.exc_info()[1].exc_info)) + tb += ''.join(traceback.format_exception(*sys.exc_info()[1].exc_info)) tb += compat_str(traceback.format_exc()) else: tb_data = traceback.format_list(traceback.extract_stack()) - tb = u''.join(tb_data) + tb = ''.join(tb_data) self.to_stderr(tb) if not self.params.get('ignoreerrors', False): if sys.exc_info()[0] and hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]: @@ -271,11 +367,11 @@ class YoutubeDL(object): Print the message to stderr, it will be prefixed with 'WARNING:' If stderr is a tty file the 'WARNING:' will be colored ''' - if sys.stderr.isatty() and os.name != 'nt': - _msg_header = u'\033[0;33mWARNING:\033[0m' + if self._err_file.isatty() and os.name != 'nt': + _msg_header = '\033[0;33mWARNING:\033[0m' else: - _msg_header = u'WARNING:' - warning_message = u'%s %s' % (_msg_header, message) + _msg_header = 'WARNING:' + warning_message = '%s %s' % (_msg_header, message) self.to_stderr(warning_message) def report_error(self, message, tb=None): @@ -283,35 +379,19 @@ class YoutubeDL(object): Do the same as trouble, but prefixes the message with 'ERROR:', colored in red if stderr is a tty file. ''' - if sys.stderr.isatty() and os.name != 'nt': - _msg_header = u'\033[0;31mERROR:\033[0m' + if self._err_file.isatty() and os.name != 'nt': + _msg_header = '\033[0;31mERROR:\033[0m' else: - _msg_header = u'ERROR:' - error_message = u'%s %s' % (_msg_header, message) + _msg_header = 'ERROR:' + error_message = '%s %s' % (_msg_header, message) self.trouble(error_message, tb) - def report_writedescription(self, descfn): - """ Report that the description file is being written """ - self.to_screen(u'[info] Writing video description to: ' + descfn) - - def report_writesubtitles(self, sub_filename): - """ Report that the subtitles file is being written """ - self.to_screen(u'[info] Writing video subtitles to: ' + sub_filename) - - def report_writeinfojson(self, infofn): - """ Report that the metadata file has been written """ - self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn) - - def report_writeannotations(self, annofn): - """ Report that the annotations file has been written. """ - self.to_screen(u'[info] Writing video annotations to: ' + annofn) - def report_file_already_downloaded(self, file_name): """Report file has already been fully downloaded.""" try: - self.to_screen(u'[download] %s has already been downloaded' % file_name) + self.to_screen('[download] %s has already been downloaded' % file_name) except UnicodeEncodeError: - self.to_screen(u'[download] The file has already been downloaded') + self.to_screen('[download] The file has already been downloaded') def increment_downloads(self): """Increment the ordinal that assigns a number to each file.""" @@ -326,52 +406,61 @@ class YoutubeDL(object): autonumber_size = self.params.get('autonumber_size') if autonumber_size is None: autonumber_size = 5 - autonumber_templ = u'%0' + str(autonumber_size) + u'd' + autonumber_templ = '%0' + str(autonumber_size) + 'd' template_dict['autonumber'] = autonumber_templ % self._num_downloads if template_dict.get('playlist_index') is not None: - template_dict['playlist_index'] = u'%05d' % template_dict['playlist_index'] + template_dict['playlist_index'] = '%05d' % template_dict['playlist_index'] sanitize = lambda k, v: sanitize_filename( - u'NA' if v is None else compat_str(v), + compat_str(v), restricted=self.params.get('restrictfilenames'), - is_id=(k == u'id')) + is_id=(k == 'id')) template_dict = dict((k, sanitize(k, v)) - for k, v in template_dict.items()) + for k, v in template_dict.items() + if v is not None) + template_dict = collections.defaultdict(lambda: 'NA', template_dict) tmpl = os.path.expanduser(self.params['outtmpl']) filename = tmpl % template_dict return filename - except KeyError as err: - self.report_error(u'Erroneous output template') - return None except ValueError as err: - self.report_error(u'Error in output template: ' + str(err) + u' (encoding: ' + repr(preferredencoding()) + ')') + self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')') return None def _match_entry(self, info_dict): """ Returns None iff the file should be downloaded """ - title = info_dict['title'] - matchtitle = self.params.get('matchtitle', False) - if matchtitle: - if not re.search(matchtitle, title, re.IGNORECASE): - return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"' - rejecttitle = self.params.get('rejecttitle', False) - if rejecttitle: - if re.search(rejecttitle, title, re.IGNORECASE): - return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"' + video_title = info_dict.get('title', info_dict.get('id', 'video')) + if 'title' in info_dict: + # This can happen when we're just evaluating the playlist + title = info_dict['title'] + matchtitle = self.params.get('matchtitle', False) + if matchtitle: + if not re.search(matchtitle, title, re.IGNORECASE): + return '"' + title + '" title did not match pattern "' + matchtitle + '"' + rejecttitle = self.params.get('rejecttitle', False) + if rejecttitle: + if re.search(rejecttitle, title, re.IGNORECASE): + return '"' + title + '" title matched reject pattern "' + rejecttitle + '"' date = info_dict.get('upload_date', None) if date is not None: dateRange = self.params.get('daterange', DateRange()) if date not in dateRange: - return u'[download] %s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange) + return '%s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange) + view_count = info_dict.get('view_count', None) + if view_count is not None: + min_views = self.params.get('min_views') + if min_views is not None and view_count < min_views: + return 'Skipping %s, because it has not reached minimum view count (%d/%d)' % (video_title, view_count, min_views) + max_views = self.params.get('max_views') + if max_views is not None and view_count > max_views: + return 'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views) age_limit = self.params.get('age_limit') if age_limit is not None: if age_limit < info_dict.get('age_limit', 0): - return u'Skipping "' + title + '" because it is age restricted' + return 'Skipping "' + title + '" because it is age restricted' if self.in_download_archive(info_dict): - return (u'%(title)s has already been recorded in archive' - % info_dict) + return '%s has already been recorded in archive' % video_title return None @staticmethod @@ -380,7 +469,8 @@ class YoutubeDL(object): for key, value in extra_info.items(): info_dict.setdefault(key, value) - def extract_info(self, url, download=True, ie_key=None, extra_info={}): + def extract_info(self, url, download=True, ie_key=None, extra_info={}, + process=True): ''' Returns a list with a dictionary for each video we find. If 'download', also downloads the videos. @@ -397,8 +487,8 @@ class YoutubeDL(object): continue if not ie.working(): - self.report_warning(u'The program functionality for this site has been marked as broken, ' - u'and will probably not work.') + self.report_warning('The program functionality for this site has been marked as broken, ' + 'and will probably not work.') try: ie_result = ie.extract(url) @@ -414,9 +504,13 @@ class YoutubeDL(object): { 'extractor': ie.IE_NAME, 'webpage_url': url, + 'webpage_url_basename': url_basename(url), 'extractor_key': ie.ie_key(), }) - return self.process_ie_result(ie_result, download, extra_info) + if process: + return self.process_ie_result(ie_result, download, extra_info) + else: + return ie_result except ExtractorError as de: # An error we somewhat expected self.report_error(compat_str(de), de.format_traceback()) break @@ -427,7 +521,7 @@ class YoutubeDL(object): else: raise else: - self.report_error(u'no suitable InfoExtractor: %s' % url) + self.report_error('no suitable InfoExtractor: %s' % url) def process_ie_result(self, ie_result, download=True, extra_info={}): """ @@ -449,37 +543,69 @@ class YoutubeDL(object): download, ie_key=ie_result.get('ie_key'), extra_info=extra_info) + elif result_type == 'url_transparent': + # Use the information from the embedding page + info = self.extract_info( + ie_result['url'], ie_key=ie_result.get('ie_key'), + extra_info=extra_info, download=False, process=False) + + def make_result(embedded_info): + new_result = ie_result.copy() + for f in ('_type', 'url', 'ext', 'player_url', 'formats', + 'entries', 'ie_key', 'duration', + 'subtitles', 'annotations', 'format', + 'thumbnail', 'thumbnails'): + if f in new_result: + del new_result[f] + if f in embedded_info: + new_result[f] = embedded_info[f] + return new_result + new_result = make_result(info) + + assert new_result.get('_type') != 'url_transparent' + if new_result.get('_type') == 'compat_list': + new_result['entries'] = [ + make_result(e) for e in new_result['entries']] + + return self.process_ie_result( + new_result, download=download, extra_info=extra_info) elif result_type == 'playlist': - self.add_extra_info(ie_result, extra_info) # We process each entry in the playlist playlist = ie_result.get('title', None) or ie_result.get('id', None) - self.to_screen(u'[download] Downloading playlist: %s' % playlist) + self.to_screen('[download] Downloading playlist: %s' % playlist) playlist_results = [] n_all_entries = len(ie_result['entries']) playliststart = self.params.get('playliststart', 1) - 1 - playlistend = self.params.get('playlistend', -1) - + playlistend = self.params.get('playlistend', None) + # For backwards compatibility, interpret -1 as whole list if playlistend == -1: - entries = ie_result['entries'][playliststart:] - else: - entries = ie_result['entries'][playliststart:playlistend] + playlistend = None + entries = ie_result['entries'][playliststart:playlistend] n_entries = len(entries) - self.to_screen(u"[%s] playlist '%s': Collected %d video ids (downloading %d of them)" % + self.to_screen( + "[%s] playlist '%s': Collected %d video ids (downloading %d of them)" % (ie_result['extractor'], playlist, n_all_entries, n_entries)) for i, entry in enumerate(entries, 1): - self.to_screen(u'[download] Downloading video #%s of %s' % (i, n_entries)) + self.to_screen('[download] Downloading video #%s of %s' % (i, n_entries)) extra = { 'playlist': playlist, 'playlist_index': i + playliststart, 'extractor': ie_result['extractor'], 'webpage_url': ie_result['webpage_url'], + 'webpage_url_basename': url_basename(ie_result['webpage_url']), 'extractor_key': ie_result['extractor_key'], } + + reason = self._match_entry(entry) + if reason is not None: + self.to_screen('[download] ' + reason) + continue + entry_result = self.process_ie_result(entry, download=download, extra_info=extra) @@ -492,6 +618,7 @@ class YoutubeDL(object): { 'extractor': ie_result['extractor'], 'webpage_url': ie_result['webpage_url'], + 'webpage_url_basename': url_basename(ie_result['webpage_url']), 'extractor_key': ie_result['extractor_key'], }) return r @@ -509,7 +636,7 @@ class YoutubeDL(object): elif format_spec == 'worst': return available_formats[0] else: - extensions = [u'mp4', u'flv', u'webm', u'3gp'] + extensions = ['mp4', 'flv', 'webm', '3gp'] if format_spec in extensions: filter_f = lambda f: f['ext'] == format_spec else: @@ -528,7 +655,7 @@ class YoutubeDL(object): info_dict['playlist_index'] = None # This extractors handle format selection themselves - if info_dict['extractor'] in [u'youtube', u'Youku']: + if info_dict['extractor'] in ['Youku']: if download: self.process_info(info_dict) return info_dict @@ -545,33 +672,32 @@ class YoutubeDL(object): if format.get('format_id') is None: format['format_id'] = compat_str(i) if format.get('format') is None: - format['format'] = u'{id} - {res}{note}'.format( + format['format'] = '{id} - {res}{note}'.format( id=format['format_id'], res=self.format_resolution(format), - note=u' ({0})'.format(format['format_note']) if format.get('format_note') is not None else '', + note=' ({0})'.format(format['format_note']) if format.get('format_note') is not None else '', ) # Automatically determine file extension if missing if 'ext' not in format: format['ext'] = determine_ext(format['url']) - if self.params.get('listformats', None): - self.list_formats(info_dict) - return - format_limit = self.params.get('format_limit', None) if format_limit: formats = list(takewhile_inclusive( lambda f: f['format_id'] != format_limit, formats )) - if self.params.get('prefer_free_formats'): - def _free_formats_key(f): - try: - ext_ord = [u'flv', u'mp4', u'webm'].index(f['ext']) - except ValueError: - ext_ord = -1 - # We only compare the extension if they have the same height and width - return (f.get('height'), f.get('width'), ext_ord) - formats = sorted(formats, key=_free_formats_key) + + # TODO Central sorting goes here + + if formats[0] is not info_dict: + # only set the 'formats' fields if the original info_dict list them + # otherwise we end up with a circular reference, the first (and unique) + # element in the 'formats' field in info_dict is info_dict itself, + # wich can't be exported to json + info_dict['formats'] = formats + if self.params.get('listformats', None): + self.list_formats(info_dict) + return req_format = self.params.get('format', 'best') if req_format is None: @@ -581,21 +707,35 @@ class YoutubeDL(object): if req_format in ('-1', 'all'): formats_to_download = formats else: - # We can accept formats requestd in the format: 34/5/best, we pick + # We can accept formats requested in the format: 34/5/best, we pick # the first that is available, starting from left req_formats = req_format.split('/') for rf in req_formats: - selected_format = self.select_format(rf, formats) + if re.match(r'.+?\+.+?', rf) is not None: + # Two formats have been requested like '137+139' + format_1, format_2 = rf.split('+') + formats_info = (self.select_format(format_1, formats), + self.select_format(format_2, formats)) + if all(formats_info): + selected_format = { + 'requested_formats': formats_info, + 'format': rf, + 'ext': formats_info[0]['ext'], + } + else: + selected_format = None + else: + selected_format = self.select_format(rf, formats) if selected_format is not None: formats_to_download = [selected_format] break if not formats_to_download: - raise ExtractorError(u'requested format not available', + raise ExtractorError('requested format not available', expected=True) if download: if len(formats_to_download) > 1: - self.to_screen(u'[info] %s: downloading video in %s formats' % (info_dict['id'], len(formats_to_download))) + self.to_screen('[info] %s: downloading video in %s formats' % (info_dict['id'], len(formats_to_download))) for format in formats_to_download: new_info = dict(info_dict) new_info.update(format) @@ -613,7 +753,7 @@ class YoutubeDL(object): info_dict['fulltitle'] = info_dict['title'] if len(info_dict['title']) > 200: - info_dict['title'] = info_dict['title'][:197] + u'...' + info_dict['title'] = info_dict['title'][:197] + '...' # Keep for backwards compatibility info_dict['stitle'] = info_dict['title'] @@ -623,7 +763,7 @@ class YoutubeDL(object): reason = self._match_entry(info_dict) if reason is not None: - self.to_screen(u'[download] ' + reason) + self.to_screen('[download] ' + reason) return max_downloads = self.params.get('max_downloads') @@ -635,20 +775,25 @@ class YoutubeDL(object): # Forced printings if self.params.get('forcetitle', False): - compat_print(info_dict['title']) + self.to_stdout(info_dict['fulltitle']) if self.params.get('forceid', False): - compat_print(info_dict['id']) + self.to_stdout(info_dict['id']) if self.params.get('forceurl', False): # For RTMP URLs, also include the playpath - compat_print(info_dict['url'] + info_dict.get('play_path', u'')) + self.to_stdout(info_dict['url'] + info_dict.get('play_path', '')) if self.params.get('forcethumbnail', False) and info_dict.get('thumbnail') is not None: - compat_print(info_dict['thumbnail']) + self.to_stdout(info_dict['thumbnail']) if self.params.get('forcedescription', False) and info_dict.get('description') is not None: - compat_print(info_dict['description']) + self.to_stdout(info_dict['description']) if self.params.get('forcefilename', False) and filename is not None: - compat_print(filename) + self.to_stdout(filename) + if self.params.get('forceduration', False) and info_dict.get('duration') is not None: + self.to_stdout(formatSeconds(info_dict['duration'])) if self.params.get('forceformat', False): - compat_print(info_dict['format']) + self.to_stdout(info_dict['format']) + if self.params.get('forcejson', False): + info_dict['_filename'] = filename + self.to_stdout(json.dumps(info_dict)) # Do nothing else if in simulate mode if self.params.get('simulate', False): @@ -662,32 +807,38 @@ class YoutubeDL(object): if dn != '' and not os.path.exists(dn): os.makedirs(dn) except (OSError, IOError) as err: - self.report_error(u'unable to create directory ' + compat_str(err)) + self.report_error('unable to create directory ' + compat_str(err)) return if self.params.get('writedescription', False): - try: - descfn = filename + u'.description' - self.report_writedescription(descfn) - with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile: - descfile.write(info_dict['description']) - except (KeyError, TypeError): - self.report_warning(u'There\'s no description to write.') - except (OSError, IOError): - self.report_error(u'Cannot write description file ' + descfn) - return + descfn = filename + '.description' + if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(descfn)): + self.to_screen('[info] Video description is already present') + else: + try: + self.to_screen('[info] Writing video description to: ' + descfn) + with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile: + descfile.write(info_dict['description']) + except (KeyError, TypeError): + self.report_warning('There\'s no description to write.') + except (OSError, IOError): + self.report_error('Cannot write description file ' + descfn) + return if self.params.get('writeannotations', False): - try: - annofn = filename + u'.annotations.xml' - self.report_writeannotations(annofn) - with io.open(encodeFilename(annofn), 'w', encoding='utf-8') as annofile: - annofile.write(info_dict['annotations']) - except (KeyError, TypeError): - self.report_warning(u'There are no annotations to write.') - except (OSError, IOError): - self.report_error(u'Cannot write annotations file: ' + annofn) - return + annofn = filename + '.annotations.xml' + if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(annofn)): + self.to_screen('[info] Video annotations are already present') + else: + try: + self.to_screen('[info] Writing video annotations to: ' + annofn) + with io.open(encodeFilename(annofn), 'w', encoding='utf-8') as annofile: + annofile.write(info_dict['annotations']) + except (KeyError, TypeError): + self.report_warning('There are no annotations to write.') + except (OSError, IOError): + self.report_error('Cannot write annotations file: ' + annofn) + return subtitles_are_requested = any([self.params.get('writesubtitles', False), self.params.get('writeautomaticsub')]) @@ -703,86 +854,143 @@ class YoutubeDL(object): continue try: sub_filename = subtitles_filename(filename, sub_lang, sub_format) - self.report_writesubtitles(sub_filename) - with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile: - subfile.write(sub) + if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)): + self.to_screen('[info] Video subtitle %s.%s is already_present' % (sub_lang, sub_format)) + else: + self.to_screen('[info] Writing video subtitles to: ' + sub_filename) + with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile: + subfile.write(sub) except (OSError, IOError): - self.report_error(u'Cannot write subtitles file ' + descfn) + self.report_error('Cannot write subtitles file ' + descfn) return if self.params.get('writeinfojson', False): - infofn = filename + u'.info.json' - self.report_writeinfojson(infofn) - try: - json_info_dict = dict((k, v) for k, v in info_dict.items() if not k in ['urlhandle']) - write_json_file(json_info_dict, encodeFilename(infofn)) - except (OSError, IOError): - self.report_error(u'Cannot write metadata to JSON file ' + infofn) - return + infofn = os.path.splitext(filename)[0] + '.info.json' + if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(infofn)): + self.to_screen('[info] Video description metadata is already present') + else: + self.to_screen('[info] Writing video description metadata as JSON to: ' + infofn) + try: + write_json_file(info_dict, encodeFilename(infofn)) + except (OSError, IOError): + self.report_error('Cannot write metadata to JSON file ' + infofn) + return if self.params.get('writethumbnail', False): if info_dict.get('thumbnail') is not None: - thumb_format = determine_ext(info_dict['thumbnail'], u'jpg') - thumb_filename = filename.rpartition('.')[0] + u'.' + thumb_format - self.to_screen(u'[%s] %s: Downloading thumbnail ...' % - (info_dict['extractor'], info_dict['id'])) - try: - uf = compat_urllib_request.urlopen(info_dict['thumbnail']) - with open(thumb_filename, 'wb') as thumbf: - shutil.copyfileobj(uf, thumbf) - self.to_screen(u'[%s] %s: Writing thumbnail to: %s' % - (info_dict['extractor'], info_dict['id'], thumb_filename)) - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self.report_warning(u'Unable to download thumbnail "%s": %s' % - (info_dict['thumbnail'], compat_str(err))) + thumb_format = determine_ext(info_dict['thumbnail'], 'jpg') + thumb_filename = os.path.splitext(filename)[0] + '.' + thumb_format + if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)): + self.to_screen('[%s] %s: Thumbnail is already present' % + (info_dict['extractor'], info_dict['id'])) + else: + self.to_screen('[%s] %s: Downloading thumbnail ...' % + (info_dict['extractor'], info_dict['id'])) + try: + uf = compat_urllib_request.urlopen(info_dict['thumbnail']) + with open(thumb_filename, 'wb') as thumbf: + shutil.copyfileobj(uf, thumbf) + self.to_screen('[%s] %s: Writing thumbnail to: %s' % + (info_dict['extractor'], info_dict['id'], thumb_filename)) + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self.report_warning('Unable to download thumbnail "%s": %s' % + (info_dict['thumbnail'], compat_str(err))) if not self.params.get('skip_download', False): if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)): success = True else: try: - success = self.fd._do_download(filename, info_dict) + def dl(name, info): + fd = get_suitable_downloader(info)(self, self.params) + for ph in self._progress_hooks: + fd.add_progress_hook(ph) + return fd.download(name, info) + if info_dict.get('requested_formats') is not None: + downloaded = [] + success = True + merger = FFmpegMergerPP(self) + if not merger._get_executable(): + postprocessors = [] + self.report_warning('You have requested multiple ' + 'formats but ffmpeg or avconv are not installed.' + ' The formats won\'t be merged') + else: + postprocessors = [merger] + for f in info_dict['requested_formats']: + new_info = dict(info_dict) + new_info.update(f) + fname = self.prepare_filename(new_info) + fname = prepend_extension(fname, 'f%s' % f['format_id']) + downloaded.append(fname) + partial_success = dl(fname, new_info) + success = success and partial_success + info_dict['__postprocessors'] = postprocessors + info_dict['__files_to_merge'] = downloaded + else: + # Just a single file + success = dl(filename, info_dict) except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self.report_error(u'unable to download video data: %s' % str(err)) + self.report_error('unable to download video data: %s' % str(err)) return except (OSError, IOError) as err: raise UnavailableVideoError(err) except (ContentTooShortError, ) as err: - self.report_error(u'content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) + self.report_error('content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) return if success: try: self.post_process(filename, info_dict) except (PostProcessingError) as err: - self.report_error(u'postprocessing: %s' % str(err)) + self.report_error('postprocessing: %s' % str(err)) return self.record_download_archive(info_dict) def download(self, url_list): """Download a given list of URLs.""" - if len(url_list) > 1 and self.fixed_template(): + if (len(url_list) > 1 and + '%' not in self.params['outtmpl'] + and self.params.get('max_downloads') != 1): raise SameFileError(self.params['outtmpl']) for url in url_list: try: #It also downloads the videos - videos = self.extract_info(url) + self.extract_info(url) except UnavailableVideoError: - self.report_error(u'unable to download video') + self.report_error('unable to download video') except MaxDownloadsReached: - self.to_screen(u'[info] Maximum number of downloaded files reached.') + self.to_screen('[info] Maximum number of downloaded files reached.') raise return self._download_retcode + def download_with_info_file(self, info_filename): + with io.open(info_filename, 'r', encoding='utf-8') as f: + info = json.load(f) + try: + self.process_ie_result(info, download=True) + except DownloadError: + webpage_url = info.get('webpage_url') + if webpage_url is not None: + self.report_warning('The info failed to download, trying with "%s"' % webpage_url) + return self.download([webpage_url]) + else: + raise + return self._download_retcode + def post_process(self, filename, ie_info): """Run all the postprocessors on the given file.""" info = dict(ie_info) info['filepath'] = filename keep_video = None - for pp in self._pps: + pps_chain = [] + if ie_info.get('__postprocessors') is not None: + pps_chain.extend(ie_info['__postprocessors']) + pps_chain.extend(self._pps) + for pp in pps_chain: try: keep_video_wish, new_info = pp.run(info) if keep_video_wish is not None: @@ -795,16 +1003,31 @@ class YoutubeDL(object): self.report_error(e.msg) if keep_video is False and not self.params.get('keepvideo', False): try: - self.to_screen(u'Deleting original file %s (pass -k to keep)' % filename) + self.to_screen('Deleting original file %s (pass -k to keep)' % filename) os.remove(encodeFilename(filename)) except (IOError, OSError): - self.report_warning(u'Unable to remove downloaded video file') + self.report_warning('Unable to remove downloaded video file') + + def _make_archive_id(self, info_dict): + # Future-proof against any change in case + # and backwards compatibility with prior versions + extractor = info_dict.get('extractor_key') + if extractor is None: + if 'id' in info_dict: + extractor = info_dict.get('ie_key') # key in a playlist + if extractor is None: + return None # Incomplete video information + return extractor.lower() + ' ' + info_dict['id'] def in_download_archive(self, info_dict): fn = self.params.get('download_archive') if fn is None: return False - vid_id = info_dict['extractor'] + u' ' + info_dict['id'] + + vid_id = self._make_archive_id(info_dict) + if vid_id is None: + return False # Incomplete video information + try: with locked_file(fn, 'r', encoding='utf-8') as archive_file: for line in archive_file: @@ -819,63 +1042,156 @@ class YoutubeDL(object): fn = self.params.get('download_archive') if fn is None: return - vid_id = info_dict['extractor'] + u' ' + info_dict['id'] + vid_id = self._make_archive_id(info_dict) + assert vid_id with locked_file(fn, 'a', encoding='utf-8') as archive_file: - archive_file.write(vid_id + u'\n') + archive_file.write(vid_id + '\n') @staticmethod def format_resolution(format, default='unknown'): - if format.get('_resolution') is not None: - return format['_resolution'] + if format.get('vcodec') == 'none': + return 'audio only' + if format.get('resolution') is not None: + return format['resolution'] if format.get('height') is not None: if format.get('width') is not None: - res = u'%sx%s' % (format['width'], format['height']) + res = '%sx%s' % (format['width'], format['height']) else: - res = u'%sp' % format['height'] + res = '%sp' % format['height'] + elif format.get('width') is not None: + res = '?x%d' % format['width'] else: res = default return res def list_formats(self, info_dict): def format_note(fdict): + res = '' + if fdict.get('ext') in ['f4f', 'f4m']: + res += '(unsupported) ' if fdict.get('format_note') is not None: - return fdict['format_note'] - res = u'' - if fdict.get('vcodec') is not None: - res += u'%-5s' % fdict['vcodec'] - elif fdict.get('vbr') is not None: - res += u'video' + res += fdict['format_note'] + ' ' + if fdict.get('tbr') is not None: + res += '%4dk ' % fdict['tbr'] + if (fdict.get('vcodec') is not None and + fdict.get('vcodec') != 'none'): + res += '%-5s' % fdict['vcodec'] + if fdict.get('vbr') is not None: + res += '@' + elif fdict.get('vbr') is not None and fdict.get('abr') is not None: + res += 'video@' if fdict.get('vbr') is not None: - res += u'@%4dk' % fdict['vbr'] + res += '%4dk' % fdict['vbr'] if fdict.get('acodec') is not None: if res: - res += u', ' - res += u'%-5s' % fdict['acodec'] + res += ', ' + res += '%-5s' % fdict['acodec'] elif fdict.get('abr') is not None: if res: - res += u', ' + res += ', ' res += 'audio' if fdict.get('abr') is not None: - res += u'@%3dk' % fdict['abr'] + res += '@%3dk' % fdict['abr'] + if fdict.get('filesize') is not None: + if res: + res += ', ' + res += format_bytes(fdict['filesize']) return res - def line(format): - return (u'%-20s%-10s%-12s%s' % ( + def line(format, idlen=20): + return (('%-' + compat_str(idlen + 1) + 's%-10s%-12s%s') % ( format['format_id'], format['ext'], self.format_resolution(format), format_note(format), - ) - ) + )) formats = info_dict.get('formats', [info_dict]) - formats_s = list(map(line, formats)) + idlen = max(len('format code'), + max(len(f['format_id']) for f in formats)) + formats_s = [line(f, idlen) for f in formats] if len(formats) > 1: formats_s[0] += (' ' if format_note(formats[0]) else '') + '(worst)' formats_s[-1] += (' ' if format_note(formats[-1]) else '') + '(best)' header_line = line({ - 'format_id': u'format code', 'ext': u'extension', - '_resolution': u'resolution', 'format_note': u'note'}) - self.to_screen(u'[info] Available formats for %s:\n%s\n%s' % - (info_dict['id'], header_line, u"\n".join(formats_s))) + 'format_id': 'format code', 'ext': 'extension', + 'resolution': 'resolution', 'format_note': 'note'}, idlen=idlen) + self.to_screen('[info] Available formats for %s:\n%s\n%s' % + (info_dict['id'], header_line, '\n'.join(formats_s))) + + def urlopen(self, req): + """ Start an HTTP download """ + return self._opener.open(req) + + def print_debug_header(self): + if not self.params.get('verbose'): + return + write_string('[debug] youtube-dl version ' + __version__ + '\n') + try: + sp = subprocess.Popen( + ['git', 'rev-parse', '--short', 'HEAD'], + stdout=subprocess.PIPE, stderr=subprocess.PIPE, + cwd=os.path.dirname(os.path.abspath(__file__))) + out, err = sp.communicate() + out = out.decode().strip() + if re.match('[0-9a-f]+', out): + write_string('[debug] Git HEAD: ' + out + '\n') + except: + try: + sys.exc_clear() + except: + pass + write_string('[debug] Python version %s - %s' % + (platform.python_version(), platform_name()) + '\n') + + proxy_map = {} + for handler in self._opener.handlers: + if hasattr(handler, 'proxies'): + proxy_map.update(handler.proxies) + write_string('[debug] Proxy map: ' + compat_str(proxy_map) + '\n') + + def _setup_opener(self): + timeout_val = self.params.get('socket_timeout') + timeout = 600 if timeout_val is None else float(timeout_val) + + opts_cookiefile = self.params.get('cookiefile') + opts_proxy = self.params.get('proxy') + + if opts_cookiefile is None: + self.cookiejar = compat_cookiejar.CookieJar() + else: + self.cookiejar = compat_cookiejar.MozillaCookieJar( + opts_cookiefile) + if os.access(opts_cookiefile, os.R_OK): + self.cookiejar.load() + + cookie_processor = compat_urllib_request.HTTPCookieProcessor( + self.cookiejar) + if opts_proxy is not None: + if opts_proxy == '': + proxies = {} + else: + proxies = {'http': opts_proxy, 'https': opts_proxy} + else: + proxies = compat_urllib_request.getproxies() + # Set HTTPS proxy to HTTP one if given (https://github.com/rg3/youtube-dl/issues/805) + if 'http' in proxies and 'https' not in proxies: + proxies['https'] = proxies['http'] + proxy_handler = compat_urllib_request.ProxyHandler(proxies) + + debuglevel = 1 if self.params.get('debug_printtraffic') else 0 + https_handler = make_HTTPS_handler( + self.params.get('nocheckcertificate', False), debuglevel=debuglevel) + ydlh = YoutubeDLHandler(debuglevel=debuglevel) + opener = compat_urllib_request.build_opener( + https_handler, proxy_handler, cookie_processor, ydlh) + # Delete the default user-agent header, which would otherwise apply in + # cases where our custom HTTP handler doesn't come into play + # (See https://github.com/rg3/youtube-dl/issues/1309 for details) + opener.addheaders = [] + self._opener = opener + + # TODO remove this global modification + compat_urllib_request.install_opener(opener) + socket.setdefaulttimeout(timeout) diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index af4c9c5c4..a948b1d90 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -34,65 +34,63 @@ __authors__ = ( 'Andras Elso', 'Jelle van der Waa', 'Marcin Cieślak', + 'Anton Larionov', + 'Takuya Tsuchida', + 'Sergey M.', + 'Michael Orlitzky', + 'Chris Gahan', + 'Saimadhav Heblikar', ) __license__ = 'Public Domain' import codecs -import collections import getpass +import locale import optparse import os import random import re import shlex -import socket -import subprocess import sys -import traceback -import platform from .utils import ( - compat_cookiejar, compat_print, - compat_str, - compat_urllib_request, DateRange, decodeOption, - determine_ext, + get_term_width, DownloadError, get_cachedir, - make_HTTPS_handler, MaxDownloadsReached, - platform_name, preferredencoding, SameFileError, + setproctitle, std_headers, write_string, - YoutubeDLHandler, ) from .update import update_self -from .version import __version__ from .FileDownloader import ( FileDownloader, ) from .extractor import gen_extractors +from .version import __version__ from .YoutubeDL import YoutubeDL -from .PostProcessor import ( +from .postprocessor import ( FFmpegMetadataPP, FFmpegVideoConvertor, FFmpegExtractAudioPP, FFmpegEmbedSubtitlePP, + XAttrMetadataPP, ) def parseOpts(overrideArguments=None): - def _readOptions(filename_bytes): + def _readOptions(filename_bytes, default=[]): try: optionf = open(filename_bytes) except IOError: - return [] # silently skip if file is not present + return default # silently skip if file is not present try: res = [] for l in optionf: @@ -120,19 +118,6 @@ def parseOpts(overrideArguments=None): def _comma_separated_values_options_callback(option, opt_str, value, parser): setattr(parser.values, option.dest, value.split(',')) - def _find_term_columns(): - columns = os.environ.get('COLUMNS', None) - if columns: - return int(columns) - - try: - sp = subprocess.Popen(['stty', 'size'], stdout=subprocess.PIPE, stderr=subprocess.PIPE) - out,err = sp.communicate() - return int(out.split()[1]) - except: - pass - return None - def _hide_login_info(opts): opts = list(opts) for private_opt in ['-p', '--password', '-u', '--username', '--video-password']: @@ -147,7 +132,7 @@ def parseOpts(overrideArguments=None): max_help_position = 80 # No need to wrap help messages if we're on a wide console - columns = _find_term_columns() + columns = get_term_width() if columns: max_width = columns fmt = optparse.IndentedHelpFormatter(width=max_width, max_help_position=max_help_position) @@ -198,36 +183,65 @@ def parseOpts(overrideArguments=None): general.add_option('--extractor-descriptions', action='store_true', dest='list_extractor_descriptions', help='Output descriptions of all supported extractors', default=False) - general.add_option('--proxy', dest='proxy', default=None, help='Use the specified HTTP/HTTPS proxy', metavar='URL') + general.add_option( + '--proxy', dest='proxy', default=None, metavar='URL', + help='Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection') general.add_option('--no-check-certificate', action='store_true', dest='no_check_certificate', default=False, help='Suppress HTTPS certificate validation.') general.add_option( '--cache-dir', dest='cachedir', default=get_cachedir(), metavar='DIR', - help='Location in the filesystem where youtube-dl can store downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl or ~/.cache/youtube-dl .') + help='Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may change.') general.add_option( '--no-cache-dir', action='store_const', const=None, dest='cachedir', help='Disable filesystem caching') + general.add_option( + '--socket-timeout', dest='socket_timeout', + type=float, default=None, help=u'Time to wait before giving up, in seconds') + general.add_option( + '--bidi-workaround', dest='bidi_workaround', action='store_true', + help=u'Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH') - selection.add_option('--playlist-start', - dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is %default)', default=1) - selection.add_option('--playlist-end', - dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1) + selection.add_option( + '--playlist-start', + dest='playliststart', metavar='NUMBER', default=1, type=int, + help='playlist video to start at (default is %default)') + selection.add_option( + '--playlist-end', + dest='playlistend', metavar='NUMBER', default=None, type=int, + help='playlist video to end at (default is last)') selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)') selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)') - selection.add_option('--max-downloads', metavar='NUMBER', dest='max_downloads', help='Abort after downloading NUMBER files', default=None) + selection.add_option('--max-downloads', metavar='NUMBER', + dest='max_downloads', type=int, default=None, + help='Abort after downloading NUMBER files') selection.add_option('--min-filesize', metavar='SIZE', dest='min_filesize', help="Do not download any videos smaller than SIZE (e.g. 50k or 44.6m)", default=None) selection.add_option('--max-filesize', metavar='SIZE', dest='max_filesize', help="Do not download any videos larger than SIZE (e.g. 50k or 44.6m)", default=None) selection.add_option('--date', metavar='DATE', dest='date', help='download only videos uploaded in this date', default=None) - selection.add_option('--datebefore', metavar='DATE', dest='datebefore', help='download only videos uploaded before this date', default=None) - selection.add_option('--dateafter', metavar='DATE', dest='dateafter', help='download only videos uploaded after this date', default=None) + selection.add_option( + '--datebefore', metavar='DATE', dest='datebefore', default=None, + help='download only videos uploaded on or before this date (i.e. inclusive)') + selection.add_option( + '--dateafter', metavar='DATE', dest='dateafter', default=None, + help='download only videos uploaded on or after this date (i.e. inclusive)') + selection.add_option( + '--min-views', metavar='COUNT', dest='min_views', + default=None, type=int, + help="Do not download any videos with less than COUNT views",) + selection.add_option( + '--max-views', metavar='COUNT', dest='max_views', + default=None, type=int, + help="Do not download any videos with more than COUNT views",) selection.add_option('--no-playlist', action='store_true', dest='noplaylist', help='download only the currently playing video', default=False) selection.add_option('--age-limit', metavar='YEARS', dest='age_limit', help='download only videos suitable for the given age', default=None, type=int) selection.add_option('--download-archive', metavar='FILE', dest='download_archive', - help='Download only videos not present in the archive file. Record all downloaded videos in it.') - + help='Download only videos not listed in the archive file. Record the IDs of all downloaded videos in it.') + selection.add_option( + '--include-ads', dest='include_ads', + action='store_true', + help='Download advertisements as well (experimental)') authentication.add_option('-u', '--username', dest='username', metavar='USERNAME', help='account username') @@ -236,12 +250,12 @@ def parseOpts(overrideArguments=None): authentication.add_option('-n', '--netrc', action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False) authentication.add_option('--video-password', - dest='videopassword', metavar='PASSWORD', help='video password (vimeo only)') + dest='videopassword', metavar='PASSWORD', help='video password (vimeo, smotri)') video_format.add_option('-f', '--format', action='store', dest='format', metavar='FORMAT', default='best', - help='video format code, specifiy the order of preference using slashes: "-f 22/17/18". "-f mp4" and "-f flv" are also supported') + help='video format code, specify the order of preference using slashes: "-f 22/17/18". "-f mp4" and "-f flv" are also supported') video_format.add_option('--all-formats', action='store_const', dest='format', help='download all available video formats', const='all') video_format.add_option('--prefer-free-formats', @@ -249,7 +263,7 @@ def parseOpts(overrideArguments=None): video_format.add_option('--max-quality', action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download') video_format.add_option('-F', '--list-formats', - action='store_true', dest='listformats', help='list all available formats (currently youtube only)') + action='store_true', dest='listformats', help='list all available formats') subtitles.add_option('--write-sub', '--write-srt', action='store_true', dest='writesubtitles', @@ -300,12 +314,18 @@ def parseOpts(overrideArguments=None): verbosity.add_option('--get-description', action='store_true', dest='getdescription', help='simulate, quiet but print video description', default=False) + verbosity.add_option('--get-duration', + action='store_true', dest='getduration', + help='simulate, quiet but print video length', default=False) verbosity.add_option('--get-filename', action='store_true', dest='getfilename', help='simulate, quiet but print output filename', default=False) verbosity.add_option('--get-format', action='store_true', dest='getformat', help='simulate, quiet but print output format', default=False) + verbosity.add_option('-j', '--dump-json', + action='store_true', dest='dumpjson', + help='simulate, quiet but print JSON information', default=False) verbosity.add_option('--newline', action='store_true', dest='progress_with_newline', help='output progress bar as new lines', default=False) verbosity.add_option('--no-progress', @@ -317,14 +337,16 @@ def parseOpts(overrideArguments=None): action='store_true', dest='verbose', help='print various debugging information', default=False) verbosity.add_option('--dump-intermediate-pages', action='store_true', dest='dump_intermediate_pages', default=False, - help='print downloaded pages to debug problems(very verbose)') + help='print downloaded pages to debug problems (very verbose)') verbosity.add_option('--write-pages', action='store_true', dest='write_pages', default=False, - help='Write downloaded pages to files in the current directory') + help='Write downloaded intermediary pages to files in the current directory to debug problems') verbosity.add_option('--youtube-print-sig-code', action='store_true', dest='youtube_print_sig_code', default=False, help=optparse.SUPPRESS_HELP) - + verbosity.add_option('--print-traffic', + dest='debug_printtraffic', action='store_true', default=False, + help=optparse.SUPPRESS_HELP) filesystem.add_option('-t', '--title', action='store_true', dest='usetitle', help='use title in file name (default)', default=False) @@ -341,11 +363,11 @@ def parseOpts(overrideArguments=None): '%(uploader)s for the uploader name, %(uploader_id)s for the uploader nickname if different, ' '%(autonumber)s to get an automatically incremented number, ' '%(ext)s for the filename extension, ' - '%(format)s for the format description (like "22 - 1280x720" or "HD"),' - '%(format_id)s for the unique id of the format (like Youtube\'s itags: "137"),' + '%(format)s for the format description (like "22 - 1280x720" or "HD"), ' + '%(format_id)s for the unique id of the format (like Youtube\'s itags: "137"), ' '%(upload_date)s for the upload date (YYYYMMDD), ' '%(extractor)s for the provider (youtube, metacafe, etc), ' - '%(id)s for the video id , %(playlist)s for the playlist the video is in, ' + '%(id)s for the video id, %(playlist)s for the playlist the video is in, ' '%(playlist_index)s for the position in the playlist and %% for a literal percent. ' 'Use - to output to stdout. Can also be used to download to a different directory, ' 'for example with -o \'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s\' .')) @@ -357,6 +379,9 @@ def parseOpts(overrideArguments=None): help='Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames', default=False) filesystem.add_option('-a', '--batch-file', dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)') + filesystem.add_option('--load-info', + dest='load_info_filename', metavar='FILE', + help='json file containing the video information (created with the "--write-json" option)') filesystem.add_option('-w', '--no-overwrites', action='store_true', dest='nooverwrites', help='do not overwrite files', default=False) filesystem.add_option('-c', '--continue', @@ -400,7 +425,13 @@ def parseOpts(overrideArguments=None): postproc.add_option('--embed-subs', action='store_true', dest='embedsubtitles', default=False, help='embed subtitles in the video (only for mp4 videos)') postproc.add_option('--add-metadata', action='store_true', dest='addmetadata', default=False, - help='add metadata to the files') + help='write metadata to the video file') + postproc.add_option('--xattrs', action='store_true', dest='xattrs', default=False, + help='write metadata to the video file\'s xattrs (using dublin core and xdg standards)') + postproc.add_option('--prefer-avconv', action='store_false', dest='prefer_ffmpeg', + help='Prefer avconv over ffmpeg for running the postprocessors (default)') + postproc.add_option('--prefer-ffmpeg', action='store_true', dest='prefer_ffmpeg', + help='Prefer ffmpeg over avconv for running the postprocessors') parser.add_option_group(general) @@ -418,6 +449,8 @@ def parseOpts(overrideArguments=None): if opts.verbose: write_string(u'[debug] Override config: ' + repr(overrideArguments) + '\n') else: + systemConf = _readOptions('/etc/youtube-dl.conf') + xdg_config_home = os.environ.get('XDG_CONFIG_HOME') if xdg_config_home: userConfFile = os.path.join(xdg_config_home, 'youtube-dl', 'config') @@ -427,8 +460,31 @@ def parseOpts(overrideArguments=None): userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl', 'config') if not os.path.isfile(userConfFile): userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf') - systemConf = _readOptions('/etc/youtube-dl.conf') - userConf = _readOptions(userConfFile) + userConf = _readOptions(userConfFile, None) + + if userConf is None: + appdata_dir = os.environ.get('appdata') + if appdata_dir: + userConf = _readOptions( + os.path.join(appdata_dir, 'youtube-dl', 'config'), + default=None) + if userConf is None: + userConf = _readOptions( + os.path.join(appdata_dir, 'youtube-dl', 'config.txt'), + default=None) + + if userConf is None: + userConf = _readOptions( + os.path.join(os.path.expanduser('~'), 'youtube-dl.conf'), + default=None) + if userConf is None: + userConf = _readOptions( + os.path.join(os.path.expanduser('~'), 'youtube-dl.conf.txt'), + default=None) + + if userConf is None: + userConf = [] + commandLineConf = sys.argv[1:] argv = systemConf + userConf + commandLineConf opts, args = parser.parse_args(argv) @@ -436,30 +492,22 @@ def parseOpts(overrideArguments=None): write_string(u'[debug] System config: ' + repr(_hide_login_info(systemConf)) + '\n') write_string(u'[debug] User config: ' + repr(_hide_login_info(userConf)) + '\n') write_string(u'[debug] Command-line args: ' + repr(_hide_login_info(commandLineConf)) + '\n') + write_string(u'[debug] Encodings: locale %r, fs %r, out %r, pref: %r\n' % + (locale.getpreferredencoding(), sys.getfilesystemencoding(), sys.stdout.encoding, preferredencoding())) return parser, opts, args + def _real_main(argv=None): # Compatibility fixes for Windows if sys.platform == 'win32': # https://github.com/rg3/youtube-dl/issues/820 codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None) + setproctitle(u'youtube-dl') + parser, opts, args = parseOpts(argv) - # Open appropriate CookieJar - if opts.cookiefile is None: - jar = compat_cookiejar.CookieJar() - else: - try: - jar = compat_cookiejar.MozillaCookieJar(opts.cookiefile) - if os.access(opts.cookiefile, os.R_OK): - jar.load() - except (IOError, OSError) as err: - if opts.verbose: - traceback.print_exc() - write_string(u'ERROR: unable to open cookie file\n') - sys.exit(101) # Set user agent if opts.user_agent is not None: std_headers['User-Agent'] = opts.user_agent @@ -490,8 +538,8 @@ def _real_main(argv=None): sys.exit(u'ERROR: batch file could not be read') all_urls = batchurls + args all_urls = [url.strip() for url in all_urls] - - opener = _setup_opener(jar=jar, opts=opts) + _enc = preferredencoding() + all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls] extractors = gen_extractors() @@ -499,7 +547,6 @@ def _real_main(argv=None): for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()): compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '')) matchedUrls = [url for url in all_urls if ie.suitable(url)] - all_urls = [url for url in all_urls if url not in matchedUrls] for mu in matchedUrls: compat_print(u' ' + mu) sys.exit(0) @@ -522,7 +569,7 @@ def _real_main(argv=None): if opts.usenetrc and (opts.username is not None or opts.password is not None): parser.error(u'using .netrc conflicts with giving username/password') if opts.password is not None and opts.username is None: - parser.error(u' account username missing\n') + parser.error(u'account username missing\n') if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid): parser.error(u'using output template conflicts with using title, video ID or auto number') if opts.usetitle and opts.useid: @@ -547,25 +594,17 @@ def _real_main(argv=None): if opts.retries is not None: try: opts.retries = int(opts.retries) - except (TypeError, ValueError) as err: + except (TypeError, ValueError): parser.error(u'invalid retry count specified') if opts.buffersize is not None: numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize) if numeric_buffersize is None: parser.error(u'invalid buffer size specified') opts.buffersize = numeric_buffersize - try: - opts.playliststart = int(opts.playliststart) - if opts.playliststart <= 0: - raise ValueError(u'Playlist start must be positive') - except (TypeError, ValueError) as err: - parser.error(u'invalid playlist start number specified') - try: - opts.playlistend = int(opts.playlistend) - if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart): - raise ValueError(u'Playlist end must be greater than playlist start') - except (TypeError, ValueError) as err: - parser.error(u'invalid playlist end number specified') + if opts.playliststart <= 0: + raise ValueError(u'Playlist start must be positive') + if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart: + raise ValueError(u'Playlist end must be greater than playlist start') if opts.extractaudio: if opts.audioformat not in ['best', 'aac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']: parser.error(u'invalid audio format specified') @@ -598,26 +637,31 @@ def _real_main(argv=None): or (opts.useid and u'%(id)s.%(ext)s') or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s') or u'%(title)s-%(id)s.%(ext)s') - if '%(ext)s' not in outtmpl and opts.extractaudio: + if not os.path.splitext(outtmpl)[1] and opts.extractaudio: parser.error(u'Cannot download a video and extract audio into the same' - u' file! Use "%%(ext)s" instead of %r' % - determine_ext(outtmpl, u'')) + u' file! Use "{0}.%(ext)s" instead of "{0}" as the output' + u' template'.format(outtmpl)) + + any_printing = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson + download_archive_fn = os.path.expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive ydl_opts = { 'usenetrc': opts.usenetrc, 'username': opts.username, 'password': opts.password, 'videopassword': opts.videopassword, - 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat), + 'quiet': (opts.quiet or any_printing), 'forceurl': opts.geturl, 'forcetitle': opts.gettitle, 'forceid': opts.getid, 'forcethumbnail': opts.getthumbnail, 'forcedescription': opts.getdescription, + 'forceduration': opts.getduration, 'forcefilename': opts.getfilename, 'forceformat': opts.getformat, + 'forcejson': opts.dumpjson, 'simulate': opts.simulate, - 'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat), + 'skip_download': (opts.skip_download or opts.simulate or any_printing), 'format': opts.format, 'format_limit': opts.format_limit, 'listformats': opts.listformats, @@ -661,39 +705,25 @@ def _real_main(argv=None): 'keepvideo': opts.keepvideo, 'min_filesize': opts.min_filesize, 'max_filesize': opts.max_filesize, + 'min_views': opts.min_views, + 'max_views': opts.max_views, 'daterange': date, 'cachedir': opts.cachedir, 'youtube_print_sig_code': opts.youtube_print_sig_code, 'age_limit': opts.age_limit, - 'download_archive': opts.download_archive, + 'download_archive': download_archive_fn, + 'cookiefile': opts.cookiefile, + 'nocheckcertificate': opts.no_check_certificate, + 'proxy': opts.proxy, + 'socket_timeout': opts.socket_timeout, + 'bidi_workaround': opts.bidi_workaround, + 'debug_printtraffic': opts.debug_printtraffic, + 'prefer_ffmpeg': opts.prefer_ffmpeg, + 'include_ads': opts.include_ads, } with YoutubeDL(ydl_opts) as ydl: - if opts.verbose: - write_string(u'[debug] youtube-dl version ' + __version__ + u'\n') - try: - sp = subprocess.Popen( - ['git', 'rev-parse', '--short', 'HEAD'], - stdout=subprocess.PIPE, stderr=subprocess.PIPE, - cwd=os.path.dirname(os.path.abspath(__file__))) - out, err = sp.communicate() - out = out.decode().strip() - if re.match('[0-9a-f]+', out): - write_string(u'[debug] Git HEAD: ' + out + u'\n') - except: - try: - sys.exc_clear() - except: - pass - write_string(u'[debug] Python version %s - %s' % - (platform.python_version(), platform_name()) + u'\n') - - proxy_map = {} - for handler in opener.handlers: - if hasattr(handler, 'proxies'): - proxy_map.update(handler.proxies) - write_string(u'[debug] Proxy map: ' + compat_str(proxy_map) + u'\n') - + ydl.print_debug_header() ydl.add_default_info_extractors() # PostProcessors @@ -706,64 +736,32 @@ def _real_main(argv=None): ydl.add_post_processor(FFmpegVideoConvertor(preferedformat=opts.recodevideo)) if opts.embedsubtitles: ydl.add_post_processor(FFmpegEmbedSubtitlePP(subtitlesformat=opts.subtitlesformat)) + if opts.xattrs: + ydl.add_post_processor(XAttrMetadataPP()) # Update version if opts.update_self: update_self(ydl.to_screen, opts.verbose) # Maybe do nothing - if len(all_urls) < 1: + if (len(all_urls) < 1) and (opts.load_info_filename is None): if not opts.update_self: parser.error(u'you must provide at least one URL') else: sys.exit() try: - retcode = ydl.download(all_urls) + if opts.load_info_filename is not None: + retcode = ydl.download_with_info_file(opts.load_info_filename) + else: + retcode = ydl.download(all_urls) except MaxDownloadsReached: ydl.to_screen(u'--max-download limit reached, aborting.') retcode = 101 - # Dump cookie jar if requested - if opts.cookiefile is not None: - try: - jar.save() - except (IOError, OSError): - sys.exit(u'ERROR: unable to save cookie jar') - sys.exit(retcode) -def _setup_opener(jar=None, opts=None, timeout=300): - if opts is None: - FakeOptions = collections.namedtuple( - 'FakeOptions', ['proxy', 'no_check_certificate']) - opts = FakeOptions(proxy=None, no_check_certificate=False) - - cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar) - if opts.proxy is not None: - if opts.proxy == '': - proxies = {} - else: - proxies = {'http': opts.proxy, 'https': opts.proxy} - else: - proxies = compat_urllib_request.getproxies() - # Set HTTPS proxy to HTTP one if given (https://github.com/rg3/youtube-dl/issues/805) - if 'http' in proxies and 'https' not in proxies: - proxies['https'] = proxies['http'] - proxy_handler = compat_urllib_request.ProxyHandler(proxies) - https_handler = make_HTTPS_handler(opts) - opener = compat_urllib_request.build_opener( - https_handler, proxy_handler, cookie_processor, YoutubeDLHandler()) - # Delete the default user-agent header, which would otherwise apply in - # cases where our custom HTTP handler doesn't come into play - # (See https://github.com/rg3/youtube-dl/issues/1309 for details) - opener.addheaders = [] - compat_urllib_request.install_opener(opener) - socket.setdefaulttimeout(timeout) - return opener - - def main(argv=None): try: _real_main(argv) diff --git a/youtube_dl/aes.py b/youtube_dl/aes.py index 9a0c93fa6..e9c5e2152 100644 --- a/youtube_dl/aes.py +++ b/youtube_dl/aes.py @@ -1,4 +1,4 @@ -__all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_decrypt_text'] +__all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_cbc_decrypt', 'aes_decrypt_text'] import base64 from math import ceil @@ -32,6 +32,31 @@ def aes_ctr_decrypt(data, key, counter): return decrypted_data +def aes_cbc_decrypt(data, key, iv): + """ + Decrypt with aes in CBC mode + + @param {int[]} data cipher + @param {int[]} key 16/24/32-Byte cipher key + @param {int[]} iv 16-Byte IV + @returns {int[]} decrypted data + """ + expanded_key = key_expansion(key) + block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES)) + + decrypted_data=[] + previous_cipher_block = iv + for i in range(block_count): + block = data[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES] + block += [0]*(BLOCK_SIZE_BYTES - len(block)) + + decrypted_block = aes_decrypt(block, expanded_key) + decrypted_data += xor(decrypted_block, previous_cipher_block) + previous_cipher_block = block + decrypted_data = decrypted_data[:len(data)] + + return decrypted_data + def key_expansion(data): """ Generate key schedule @@ -75,7 +100,7 @@ def aes_encrypt(data, expanded_key): @returns {int[]} 16-Byte cipher """ rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1 - + data = xor(data, expanded_key[:BLOCK_SIZE_BYTES]) for i in range(1, rounds+1): data = sub_bytes(data) @@ -83,6 +108,26 @@ def aes_encrypt(data, expanded_key): if i != rounds: data = mix_columns(data) data = xor(data, expanded_key[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES]) + + return data + +def aes_decrypt(data, expanded_key): + """ + Decrypt one block with aes + + @param {int[]} data 16-Byte cipher + @param {int[]} expanded_key 176/208/240-Byte expanded key + @returns {int[]} 16-Byte state + """ + rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1 + + for i in range(rounds, 0, -1): + data = xor(data, expanded_key[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES]) + if i != rounds: + data = mix_columns_inv(data) + data = shift_rows_inv(data) + data = sub_bytes_inv(data) + data = xor(data, expanded_key[:BLOCK_SIZE_BYTES]) return data @@ -139,14 +184,69 @@ SBOX = (0x63, 0x7C, 0x77, 0x7B, 0xF2, 0x6B, 0x6F, 0xC5, 0x30, 0x01, 0x67, 0x2B, 0x70, 0x3E, 0xB5, 0x66, 0x48, 0x03, 0xF6, 0x0E, 0x61, 0x35, 0x57, 0xB9, 0x86, 0xC1, 0x1D, 0x9E, 0xE1, 0xF8, 0x98, 0x11, 0x69, 0xD9, 0x8E, 0x94, 0x9B, 0x1E, 0x87, 0xE9, 0xCE, 0x55, 0x28, 0xDF, 0x8C, 0xA1, 0x89, 0x0D, 0xBF, 0xE6, 0x42, 0x68, 0x41, 0x99, 0x2D, 0x0F, 0xB0, 0x54, 0xBB, 0x16) -MIX_COLUMN_MATRIX = ((2,3,1,1), - (1,2,3,1), - (1,1,2,3), - (3,1,1,2)) +SBOX_INV = (0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38, 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb, + 0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87, 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb, + 0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d, 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e, + 0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2, 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25, + 0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16, 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92, + 0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda, 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84, + 0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a, 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06, + 0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02, 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b, + 0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea, 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73, + 0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85, 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e, + 0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89, 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b, + 0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20, 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4, + 0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31, 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f, + 0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d, 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef, + 0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0, 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61, + 0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26, 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d) +MIX_COLUMN_MATRIX = ((0x2,0x3,0x1,0x1), + (0x1,0x2,0x3,0x1), + (0x1,0x1,0x2,0x3), + (0x3,0x1,0x1,0x2)) +MIX_COLUMN_MATRIX_INV = ((0xE,0xB,0xD,0x9), + (0x9,0xE,0xB,0xD), + (0xD,0x9,0xE,0xB), + (0xB,0xD,0x9,0xE)) +RIJNDAEL_EXP_TABLE = (0x01, 0x03, 0x05, 0x0F, 0x11, 0x33, 0x55, 0xFF, 0x1A, 0x2E, 0x72, 0x96, 0xA1, 0xF8, 0x13, 0x35, + 0x5F, 0xE1, 0x38, 0x48, 0xD8, 0x73, 0x95, 0xA4, 0xF7, 0x02, 0x06, 0x0A, 0x1E, 0x22, 0x66, 0xAA, + 0xE5, 0x34, 0x5C, 0xE4, 0x37, 0x59, 0xEB, 0x26, 0x6A, 0xBE, 0xD9, 0x70, 0x90, 0xAB, 0xE6, 0x31, + 0x53, 0xF5, 0x04, 0x0C, 0x14, 0x3C, 0x44, 0xCC, 0x4F, 0xD1, 0x68, 0xB8, 0xD3, 0x6E, 0xB2, 0xCD, + 0x4C, 0xD4, 0x67, 0xA9, 0xE0, 0x3B, 0x4D, 0xD7, 0x62, 0xA6, 0xF1, 0x08, 0x18, 0x28, 0x78, 0x88, + 0x83, 0x9E, 0xB9, 0xD0, 0x6B, 0xBD, 0xDC, 0x7F, 0x81, 0x98, 0xB3, 0xCE, 0x49, 0xDB, 0x76, 0x9A, + 0xB5, 0xC4, 0x57, 0xF9, 0x10, 0x30, 0x50, 0xF0, 0x0B, 0x1D, 0x27, 0x69, 0xBB, 0xD6, 0x61, 0xA3, + 0xFE, 0x19, 0x2B, 0x7D, 0x87, 0x92, 0xAD, 0xEC, 0x2F, 0x71, 0x93, 0xAE, 0xE9, 0x20, 0x60, 0xA0, + 0xFB, 0x16, 0x3A, 0x4E, 0xD2, 0x6D, 0xB7, 0xC2, 0x5D, 0xE7, 0x32, 0x56, 0xFA, 0x15, 0x3F, 0x41, + 0xC3, 0x5E, 0xE2, 0x3D, 0x47, 0xC9, 0x40, 0xC0, 0x5B, 0xED, 0x2C, 0x74, 0x9C, 0xBF, 0xDA, 0x75, + 0x9F, 0xBA, 0xD5, 0x64, 0xAC, 0xEF, 0x2A, 0x7E, 0x82, 0x9D, 0xBC, 0xDF, 0x7A, 0x8E, 0x89, 0x80, + 0x9B, 0xB6, 0xC1, 0x58, 0xE8, 0x23, 0x65, 0xAF, 0xEA, 0x25, 0x6F, 0xB1, 0xC8, 0x43, 0xC5, 0x54, + 0xFC, 0x1F, 0x21, 0x63, 0xA5, 0xF4, 0x07, 0x09, 0x1B, 0x2D, 0x77, 0x99, 0xB0, 0xCB, 0x46, 0xCA, + 0x45, 0xCF, 0x4A, 0xDE, 0x79, 0x8B, 0x86, 0x91, 0xA8, 0xE3, 0x3E, 0x42, 0xC6, 0x51, 0xF3, 0x0E, + 0x12, 0x36, 0x5A, 0xEE, 0x29, 0x7B, 0x8D, 0x8C, 0x8F, 0x8A, 0x85, 0x94, 0xA7, 0xF2, 0x0D, 0x17, + 0x39, 0x4B, 0xDD, 0x7C, 0x84, 0x97, 0xA2, 0xFD, 0x1C, 0x24, 0x6C, 0xB4, 0xC7, 0x52, 0xF6, 0x01) +RIJNDAEL_LOG_TABLE = (0x00, 0x00, 0x19, 0x01, 0x32, 0x02, 0x1a, 0xc6, 0x4b, 0xc7, 0x1b, 0x68, 0x33, 0xee, 0xdf, 0x03, + 0x64, 0x04, 0xe0, 0x0e, 0x34, 0x8d, 0x81, 0xef, 0x4c, 0x71, 0x08, 0xc8, 0xf8, 0x69, 0x1c, 0xc1, + 0x7d, 0xc2, 0x1d, 0xb5, 0xf9, 0xb9, 0x27, 0x6a, 0x4d, 0xe4, 0xa6, 0x72, 0x9a, 0xc9, 0x09, 0x78, + 0x65, 0x2f, 0x8a, 0x05, 0x21, 0x0f, 0xe1, 0x24, 0x12, 0xf0, 0x82, 0x45, 0x35, 0x93, 0xda, 0x8e, + 0x96, 0x8f, 0xdb, 0xbd, 0x36, 0xd0, 0xce, 0x94, 0x13, 0x5c, 0xd2, 0xf1, 0x40, 0x46, 0x83, 0x38, + 0x66, 0xdd, 0xfd, 0x30, 0xbf, 0x06, 0x8b, 0x62, 0xb3, 0x25, 0xe2, 0x98, 0x22, 0x88, 0x91, 0x10, + 0x7e, 0x6e, 0x48, 0xc3, 0xa3, 0xb6, 0x1e, 0x42, 0x3a, 0x6b, 0x28, 0x54, 0xfa, 0x85, 0x3d, 0xba, + 0x2b, 0x79, 0x0a, 0x15, 0x9b, 0x9f, 0x5e, 0xca, 0x4e, 0xd4, 0xac, 0xe5, 0xf3, 0x73, 0xa7, 0x57, + 0xaf, 0x58, 0xa8, 0x50, 0xf4, 0xea, 0xd6, 0x74, 0x4f, 0xae, 0xe9, 0xd5, 0xe7, 0xe6, 0xad, 0xe8, + 0x2c, 0xd7, 0x75, 0x7a, 0xeb, 0x16, 0x0b, 0xf5, 0x59, 0xcb, 0x5f, 0xb0, 0x9c, 0xa9, 0x51, 0xa0, + 0x7f, 0x0c, 0xf6, 0x6f, 0x17, 0xc4, 0x49, 0xec, 0xd8, 0x43, 0x1f, 0x2d, 0xa4, 0x76, 0x7b, 0xb7, + 0xcc, 0xbb, 0x3e, 0x5a, 0xfb, 0x60, 0xb1, 0x86, 0x3b, 0x52, 0xa1, 0x6c, 0xaa, 0x55, 0x29, 0x9d, + 0x97, 0xb2, 0x87, 0x90, 0x61, 0xbe, 0xdc, 0xfc, 0xbc, 0x95, 0xcf, 0xcd, 0x37, 0x3f, 0x5b, 0xd1, + 0x53, 0x39, 0x84, 0x3c, 0x41, 0xa2, 0x6d, 0x47, 0x14, 0x2a, 0x9e, 0x5d, 0x56, 0xf2, 0xd3, 0xab, + 0x44, 0x11, 0x92, 0xd9, 0x23, 0x20, 0x2e, 0x89, 0xb4, 0x7c, 0xb8, 0x26, 0x77, 0x99, 0xe3, 0xa5, + 0x67, 0x4a, 0xed, 0xde, 0xc5, 0x31, 0xfe, 0x18, 0x0d, 0x63, 0x8c, 0x80, 0xc0, 0xf7, 0x70, 0x07) def sub_bytes(data): return [SBOX[x] for x in data] +def sub_bytes_inv(data): + return [SBOX_INV[x] for x in data] + def rotate(data): return data[1:] + [data[0]] @@ -160,30 +260,31 @@ def key_schedule_core(data, rcon_iteration): def xor(data1, data2): return [x^y for x, y in zip(data1, data2)] -def mix_column(data): +def rijndael_mul(a, b): + if(a==0 or b==0): + return 0 + return RIJNDAEL_EXP_TABLE[(RIJNDAEL_LOG_TABLE[a] + RIJNDAEL_LOG_TABLE[b]) % 0xFF] + +def mix_column(data, matrix): data_mixed = [] for row in range(4): mixed = 0 for column in range(4): - addend = data[column] - if MIX_COLUMN_MATRIX[row][column] in (2,3): - addend <<= 1 - if addend > 0xff: - addend &= 0xff - addend ^= 0x1b - if MIX_COLUMN_MATRIX[row][column] == 3: - addend ^= data[column] - mixed ^= addend & 0xff + # xor is (+) and (-) + mixed ^= rijndael_mul(data[column], matrix[row][column]) data_mixed.append(mixed) return data_mixed -def mix_columns(data): +def mix_columns(data, matrix=MIX_COLUMN_MATRIX): data_mixed = [] for i in range(4): column = data[i*4 : (i+1)*4] - data_mixed += mix_column(column) + data_mixed += mix_column(column, matrix) return data_mixed +def mix_columns_inv(data): + return mix_columns(data, MIX_COLUMN_MATRIX_INV) + def shift_rows(data): data_shifted = [] for column in range(4): @@ -191,6 +292,13 @@ def shift_rows(data): data_shifted.append( data[((column + row) & 0b11) * 4 + row] ) return data_shifted +def shift_rows_inv(data): + data_shifted = [] + for column in range(4): + for row in range(4): + data_shifted.append( data[((column - row) & 0b11) * 4 + row] ) + return data_shifted + def inc(data): data = data[:] # copy for i in range(len(data)-1,-1,-1): diff --git a/youtube_dl/downloader/__init__.py b/youtube_dl/downloader/__init__.py new file mode 100644 index 000000000..f19b490f1 --- /dev/null +++ b/youtube_dl/downloader/__init__.py @@ -0,0 +1,23 @@ +from .common import FileDownloader +from .hls import HlsFD +from .http import HttpFD +from .mplayer import MplayerFD +from .rtmp import RtmpFD + +from ..utils import ( + determine_ext, +) + +def get_suitable_downloader(info_dict): + """Get the downloader class that can handle the info dict.""" + url = info_dict['url'] + + if url.startswith('rtmp'): + return RtmpFD + if determine_ext(url) == u'm3u8': + return HlsFD + if url.startswith('mms') or url.startswith('rtsp'): + return MplayerFD + else: + return HttpFD + diff --git a/youtube_dl/downloader/common.py b/youtube_dl/downloader/common.py new file mode 100644 index 000000000..10143d56a --- /dev/null +++ b/youtube_dl/downloader/common.py @@ -0,0 +1,317 @@ +import os +import re +import sys +import time + +from ..utils import ( + encodeFilename, + timeconvert, + format_bytes, +) + + +class FileDownloader(object): + """File Downloader class. + + File downloader objects are the ones responsible of downloading the + actual video file and writing it to disk. + + File downloaders accept a lot of parameters. In order not to saturate + the object constructor with arguments, it receives a dictionary of + options instead. + + Available options: + + verbose: Print additional info to stdout. + quiet: Do not print messages to stdout. + ratelimit: Download speed limit, in bytes/sec. + retries: Number of times to retry for HTTP error 5xx + buffersize: Size of download buffer in bytes. + noresizebuffer: Do not automatically resize the download buffer. + continuedl: Try to continue downloads if possible. + noprogress: Do not print the progress bar. + logtostderr: Log messages to stderr instead of stdout. + consoletitle: Display progress in console window's titlebar. + nopart: Do not use temporary .part files. + updatetime: Use the Last-modified header to set output file timestamps. + test: Download only first bytes to test the downloader. + min_filesize: Skip files smaller than this size + max_filesize: Skip files larger than this size + + Subclasses of this one must re-define the real_download method. + """ + + params = None + + def __init__(self, ydl, params): + """Create a FileDownloader object with the given options.""" + self.ydl = ydl + self._progress_hooks = [] + self.params = params + + @staticmethod + def format_seconds(seconds): + (mins, secs) = divmod(seconds, 60) + (hours, mins) = divmod(mins, 60) + if hours > 99: + return '--:--:--' + if hours == 0: + return '%02d:%02d' % (mins, secs) + else: + return '%02d:%02d:%02d' % (hours, mins, secs) + + @staticmethod + def calc_percent(byte_counter, data_len): + if data_len is None: + return None + return float(byte_counter) / float(data_len) * 100.0 + + @staticmethod + def format_percent(percent): + if percent is None: + return '---.-%' + return '%6s' % ('%3.1f%%' % percent) + + @staticmethod + def calc_eta(start, now, total, current): + if total is None: + return None + dif = now - start + if current == 0 or dif < 0.001: # One millisecond + return None + rate = float(current) / dif + return int((float(total) - float(current)) / rate) + + @staticmethod + def format_eta(eta): + if eta is None: + return '--:--' + return FileDownloader.format_seconds(eta) + + @staticmethod + def calc_speed(start, now, bytes): + dif = now - start + if bytes == 0 or dif < 0.001: # One millisecond + return None + return float(bytes) / dif + + @staticmethod + def format_speed(speed): + if speed is None: + return '%10s' % '---b/s' + return '%10s' % ('%s/s' % format_bytes(speed)) + + @staticmethod + def best_block_size(elapsed_time, bytes): + new_min = max(bytes / 2.0, 1.0) + new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB + if elapsed_time < 0.001: + return int(new_max) + rate = bytes / elapsed_time + if rate > new_max: + return int(new_max) + if rate < new_min: + return int(new_min) + return int(rate) + + @staticmethod + def parse_bytes(bytestr): + """Parse a string indicating a byte quantity into an integer.""" + matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr) + if matchobj is None: + return None + number = float(matchobj.group(1)) + multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower()) + return int(round(number * multiplier)) + + def to_screen(self, *args, **kargs): + self.ydl.to_screen(*args, **kargs) + + def to_stderr(self, message): + self.ydl.to_screen(message) + + def to_console_title(self, message): + self.ydl.to_console_title(message) + + def trouble(self, *args, **kargs): + self.ydl.trouble(*args, **kargs) + + def report_warning(self, *args, **kargs): + self.ydl.report_warning(*args, **kargs) + + def report_error(self, *args, **kargs): + self.ydl.report_error(*args, **kargs) + + def slow_down(self, start_time, byte_counter): + """Sleep if the download speed is over the rate limit.""" + rate_limit = self.params.get('ratelimit', None) + if rate_limit is None or byte_counter == 0: + return + now = time.time() + elapsed = now - start_time + if elapsed <= 0.0: + return + speed = float(byte_counter) / elapsed + if speed > rate_limit: + time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) + + def temp_name(self, filename): + """Returns a temporary filename for the given filename.""" + if self.params.get('nopart', False) or filename == u'-' or \ + (os.path.exists(encodeFilename(filename)) and not os.path.isfile(encodeFilename(filename))): + return filename + return filename + u'.part' + + def undo_temp_name(self, filename): + if filename.endswith(u'.part'): + return filename[:-len(u'.part')] + return filename + + def try_rename(self, old_filename, new_filename): + try: + if old_filename == new_filename: + return + os.rename(encodeFilename(old_filename), encodeFilename(new_filename)) + except (IOError, OSError) as err: + self.report_error(u'unable to rename file: %s' % str(err)) + + def try_utime(self, filename, last_modified_hdr): + """Try to set the last-modified time of the given file.""" + if last_modified_hdr is None: + return + if not os.path.isfile(encodeFilename(filename)): + return + timestr = last_modified_hdr + if timestr is None: + return + filetime = timeconvert(timestr) + if filetime is None: + return filetime + # Ignore obviously invalid dates + if filetime == 0: + return + try: + os.utime(filename, (time.time(), filetime)) + except: + pass + return filetime + + def report_destination(self, filename): + """Report destination filename.""" + self.to_screen(u'[download] Destination: ' + filename) + + def _report_progress_status(self, msg, is_last_line=False): + fullmsg = u'[download] ' + msg + if self.params.get('progress_with_newline', False): + self.to_screen(fullmsg) + else: + if os.name == 'nt': + prev_len = getattr(self, '_report_progress_prev_line_length', + 0) + if prev_len > len(fullmsg): + fullmsg += u' ' * (prev_len - len(fullmsg)) + self._report_progress_prev_line_length = len(fullmsg) + clear_line = u'\r' + else: + clear_line = (u'\r\x1b[K' if sys.stderr.isatty() else u'\r') + self.to_screen(clear_line + fullmsg, skip_eol=not is_last_line) + self.to_console_title(u'youtube-dl ' + msg) + + def report_progress(self, percent, data_len_str, speed, eta): + """Report download progress.""" + if self.params.get('noprogress', False): + return + if eta is not None: + eta_str = self.format_eta(eta) + else: + eta_str = 'Unknown ETA' + if percent is not None: + percent_str = self.format_percent(percent) + else: + percent_str = 'Unknown %' + speed_str = self.format_speed(speed) + + msg = (u'%s of %s at %s ETA %s' % + (percent_str, data_len_str, speed_str, eta_str)) + self._report_progress_status(msg) + + def report_progress_live_stream(self, downloaded_data_len, speed, elapsed): + if self.params.get('noprogress', False): + return + downloaded_str = format_bytes(downloaded_data_len) + speed_str = self.format_speed(speed) + elapsed_str = FileDownloader.format_seconds(elapsed) + msg = u'%s at %s (%s)' % (downloaded_str, speed_str, elapsed_str) + self._report_progress_status(msg) + + def report_finish(self, data_len_str, tot_time): + """Report download finished.""" + if self.params.get('noprogress', False): + self.to_screen(u'[download] Download completed') + else: + self._report_progress_status( + (u'100%% of %s in %s' % + (data_len_str, self.format_seconds(tot_time))), + is_last_line=True) + + def report_resuming_byte(self, resume_len): + """Report attempt to resume at given byte.""" + self.to_screen(u'[download] Resuming download at byte %s' % resume_len) + + def report_retry(self, count, retries): + """Report retry in case of HTTP error 5xx""" + self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries)) + + def report_file_already_downloaded(self, file_name): + """Report file has already been fully downloaded.""" + try: + self.to_screen(u'[download] %s has already been downloaded' % file_name) + except UnicodeEncodeError: + self.to_screen(u'[download] The file has already been downloaded') + + def report_unable_to_resume(self): + """Report it was impossible to resume download.""" + self.to_screen(u'[download] Unable to resume') + + def download(self, filename, info_dict): + """Download to a filename using the info from info_dict + Return True on success and False otherwise + """ + # Check file already present + if self.params.get('continuedl', False) and os.path.isfile(encodeFilename(filename)) and not self.params.get('nopart', False): + self.report_file_already_downloaded(filename) + self._hook_progress({ + 'filename': filename, + 'status': 'finished', + 'total_bytes': os.path.getsize(encodeFilename(filename)), + }) + return True + + return self.real_download(filename, info_dict) + + def real_download(self, filename, info_dict): + """Real download process. Redefine in subclasses.""" + raise NotImplementedError(u'This method must be implemented by sublcasses') + + def _hook_progress(self, status): + for ph in self._progress_hooks: + ph(status) + + def add_progress_hook(self, ph): + """ ph gets called on download progress, with a dictionary with the entries + * filename: The final filename + * status: One of "downloading" and "finished" + + It can also have some of the following entries: + + * downloaded_bytes: Bytes on disks + * total_bytes: Total bytes, None if unknown + * tmpfilename: The filename we're currently writing to + * eta: The estimated time in seconds, None if unknown + * speed: The download speed in bytes/second, None if unknown + + Hooks are guaranteed to be called at least once (with status "finished") + if the download is successful. + """ + self._progress_hooks.append(ph) + diff --git a/youtube_dl/downloader/hls.py b/youtube_dl/downloader/hls.py new file mode 100644 index 000000000..fa983462b --- /dev/null +++ b/youtube_dl/downloader/hls.py @@ -0,0 +1,44 @@ +import os +import subprocess + +from .common import FileDownloader +from ..utils import ( + encodeFilename, +) + + +class HlsFD(FileDownloader): + def real_download(self, filename, info_dict): + url = info_dict['url'] + self.report_destination(filename) + tmpfilename = self.temp_name(filename) + + args = ['-y', '-i', url, '-f', 'mp4', '-c', 'copy', + '-bsf:a', 'aac_adtstoasc', tmpfilename] + + for program in ['avconv', 'ffmpeg']: + try: + subprocess.call([program, '-version'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT) + break + except (OSError, IOError): + pass + else: + self.report_error(u'm3u8 download detected but ffmpeg or avconv could not be found') + cmd = [program] + args + + retval = subprocess.call(cmd) + if retval == 0: + fsize = os.path.getsize(encodeFilename(tmpfilename)) + self.to_screen(u'\r[%s] %s bytes' % (cmd[0], fsize)) + self.try_rename(tmpfilename, filename) + self._hook_progress({ + 'downloaded_bytes': fsize, + 'total_bytes': fsize, + 'filename': filename, + 'status': 'finished', + }) + return True + else: + self.to_stderr(u"\n") + self.report_error(u'ffmpeg exited with code %d' % retval) + return False diff --git a/youtube_dl/downloader/http.py b/youtube_dl/downloader/http.py new file mode 100644 index 000000000..8407727ba --- /dev/null +++ b/youtube_dl/downloader/http.py @@ -0,0 +1,186 @@ +import os +import time + +from .common import FileDownloader +from ..utils import ( + compat_urllib_request, + compat_urllib_error, + ContentTooShortError, + + encodeFilename, + sanitize_open, + format_bytes, +) + + +class HttpFD(FileDownloader): + def real_download(self, filename, info_dict): + url = info_dict['url'] + tmpfilename = self.temp_name(filename) + stream = None + + # Do not include the Accept-Encoding header + headers = {'Youtubedl-no-compression': 'True'} + if 'user_agent' in info_dict: + headers['Youtubedl-user-agent'] = info_dict['user_agent'] + basic_request = compat_urllib_request.Request(url, None, headers) + request = compat_urllib_request.Request(url, None, headers) + + if self.params.get('test', False): + request.add_header('Range','bytes=0-10240') + + # Establish possible resume length + if os.path.isfile(encodeFilename(tmpfilename)): + resume_len = os.path.getsize(encodeFilename(tmpfilename)) + else: + resume_len = 0 + + open_mode = 'wb' + if resume_len != 0: + if self.params.get('continuedl', False): + self.report_resuming_byte(resume_len) + request.add_header('Range','bytes=%d-' % resume_len) + open_mode = 'ab' + else: + resume_len = 0 + + count = 0 + retries = self.params.get('retries', 0) + while count <= retries: + # Establish connection + try: + data = compat_urllib_request.urlopen(request) + break + except (compat_urllib_error.HTTPError, ) as err: + if (err.code < 500 or err.code >= 600) and err.code != 416: + # Unexpected HTTP error + raise + elif err.code == 416: + # Unable to resume (requested range not satisfiable) + try: + # Open the connection again without the range header + data = compat_urllib_request.urlopen(basic_request) + content_length = data.info()['Content-Length'] + except (compat_urllib_error.HTTPError, ) as err: + if err.code < 500 or err.code >= 600: + raise + else: + # Examine the reported length + if (content_length is not None and + (resume_len - 100 < int(content_length) < resume_len + 100)): + # The file had already been fully downloaded. + # Explanation to the above condition: in issue #175 it was revealed that + # YouTube sometimes adds or removes a few bytes from the end of the file, + # changing the file size slightly and causing problems for some users. So + # I decided to implement a suggested change and consider the file + # completely downloaded if the file size differs less than 100 bytes from + # the one in the hard drive. + self.report_file_already_downloaded(filename) + self.try_rename(tmpfilename, filename) + self._hook_progress({ + 'filename': filename, + 'status': 'finished', + }) + return True + else: + # The length does not match, we start the download over + self.report_unable_to_resume() + open_mode = 'wb' + break + # Retry + count += 1 + if count <= retries: + self.report_retry(count, retries) + + if count > retries: + self.report_error(u'giving up after %s retries' % retries) + return False + + data_len = data.info().get('Content-length', None) + if data_len is not None: + data_len = int(data_len) + resume_len + min_data_len = self.params.get("min_filesize", None) + max_data_len = self.params.get("max_filesize", None) + if min_data_len is not None and data_len < min_data_len: + self.to_screen(u'\r[download] File is smaller than min-filesize (%s bytes < %s bytes). Aborting.' % (data_len, min_data_len)) + return False + if max_data_len is not None and data_len > max_data_len: + self.to_screen(u'\r[download] File is larger than max-filesize (%s bytes > %s bytes). Aborting.' % (data_len, max_data_len)) + return False + + data_len_str = format_bytes(data_len) + byte_counter = 0 + resume_len + block_size = self.params.get('buffersize', 1024) + start = time.time() + while True: + # Download and write + before = time.time() + data_block = data.read(block_size) + after = time.time() + if len(data_block) == 0: + break + byte_counter += len(data_block) + + # Open file just in time + if stream is None: + try: + (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode) + assert stream is not None + filename = self.undo_temp_name(tmpfilename) + self.report_destination(filename) + except (OSError, IOError) as err: + self.report_error(u'unable to open for writing: %s' % str(err)) + return False + try: + stream.write(data_block) + except (IOError, OSError) as err: + self.to_stderr(u"\n") + self.report_error(u'unable to write data: %s' % str(err)) + return False + if not self.params.get('noresizebuffer', False): + block_size = self.best_block_size(after - before, len(data_block)) + + # Progress message + speed = self.calc_speed(start, time.time(), byte_counter - resume_len) + if data_len is None: + eta = percent = None + else: + percent = self.calc_percent(byte_counter, data_len) + eta = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len) + self.report_progress(percent, data_len_str, speed, eta) + + self._hook_progress({ + 'downloaded_bytes': byte_counter, + 'total_bytes': data_len, + 'tmpfilename': tmpfilename, + 'filename': filename, + 'status': 'downloading', + 'eta': eta, + 'speed': speed, + }) + + # Apply rate limit + self.slow_down(start, byte_counter - resume_len) + + if stream is None: + self.to_stderr(u"\n") + self.report_error(u'Did not get any data blocks') + return False + stream.close() + self.report_finish(data_len_str, (time.time() - start)) + if data_len is not None and byte_counter != data_len: + raise ContentTooShortError(byte_counter, int(data_len)) + self.try_rename(tmpfilename, filename) + + # Update file modification time + if self.params.get('updatetime', True): + info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None)) + + self._hook_progress({ + 'downloaded_bytes': byte_counter, + 'total_bytes': byte_counter, + 'filename': filename, + 'status': 'finished', + }) + + return True diff --git a/youtube_dl/downloader/mplayer.py b/youtube_dl/downloader/mplayer.py new file mode 100644 index 000000000..67e0e4189 --- /dev/null +++ b/youtube_dl/downloader/mplayer.py @@ -0,0 +1,40 @@ +import os +import subprocess + +from .common import FileDownloader +from ..utils import ( + encodeFilename, +) + + +class MplayerFD(FileDownloader): + def real_download(self, filename, info_dict): + url = info_dict['url'] + self.report_destination(filename) + tmpfilename = self.temp_name(filename) + + args = ['mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy', '-dumpstream', '-dumpfile', tmpfilename, url] + # Check for mplayer first + try: + subprocess.call(['mplayer', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT) + except (OSError, IOError): + self.report_error(u'MMS or RTSP download detected but "%s" could not be run' % args[0] ) + return False + + # Download using mplayer. + retval = subprocess.call(args) + if retval == 0: + fsize = os.path.getsize(encodeFilename(tmpfilename)) + self.to_screen(u'\r[%s] %s bytes' % (args[0], fsize)) + self.try_rename(tmpfilename, filename) + self._hook_progress({ + 'downloaded_bytes': fsize, + 'total_bytes': fsize, + 'filename': filename, + 'status': 'finished', + }) + return True + else: + self.to_stderr(u"\n") + self.report_error(u'mplayer exited with code %d' % retval) + return False diff --git a/youtube_dl/downloader/rtmp.py b/youtube_dl/downloader/rtmp.py new file mode 100644 index 000000000..b165e396f --- /dev/null +++ b/youtube_dl/downloader/rtmp.py @@ -0,0 +1,178 @@ +import os +import re +import subprocess +import sys +import time + +from .common import FileDownloader +from ..utils import ( + encodeFilename, + format_bytes, +) + + +class RtmpFD(FileDownloader): + def real_download(self, filename, info_dict): + def run_rtmpdump(args): + start = time.time() + resume_percent = None + resume_downloaded_data_len = None + proc = subprocess.Popen(args, stderr=subprocess.PIPE) + cursor_in_new_line = True + proc_stderr_closed = False + while not proc_stderr_closed: + # read line from stderr + line = u'' + while True: + char = proc.stderr.read(1) + if not char: + proc_stderr_closed = True + break + if char in [b'\r', b'\n']: + break + line += char.decode('ascii', 'replace') + if not line: + # proc_stderr_closed is True + continue + mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec \(([0-9]{1,2}\.[0-9])%\)', line) + if mobj: + downloaded_data_len = int(float(mobj.group(1))*1024) + percent = float(mobj.group(2)) + if not resume_percent: + resume_percent = percent + resume_downloaded_data_len = downloaded_data_len + eta = self.calc_eta(start, time.time(), 100-resume_percent, percent-resume_percent) + speed = self.calc_speed(start, time.time(), downloaded_data_len-resume_downloaded_data_len) + data_len = None + if percent > 0: + data_len = int(downloaded_data_len * 100 / percent) + data_len_str = u'~' + format_bytes(data_len) + self.report_progress(percent, data_len_str, speed, eta) + cursor_in_new_line = False + self._hook_progress({ + 'downloaded_bytes': downloaded_data_len, + 'total_bytes': data_len, + 'tmpfilename': tmpfilename, + 'filename': filename, + 'status': 'downloading', + 'eta': eta, + 'speed': speed, + }) + else: + # no percent for live streams + mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec', line) + if mobj: + downloaded_data_len = int(float(mobj.group(1))*1024) + time_now = time.time() + speed = self.calc_speed(start, time_now, downloaded_data_len) + self.report_progress_live_stream(downloaded_data_len, speed, time_now - start) + cursor_in_new_line = False + self._hook_progress({ + 'downloaded_bytes': downloaded_data_len, + 'tmpfilename': tmpfilename, + 'filename': filename, + 'status': 'downloading', + 'speed': speed, + }) + elif self.params.get('verbose', False): + if not cursor_in_new_line: + self.to_screen(u'') + cursor_in_new_line = True + self.to_screen(u'[rtmpdump] '+line) + proc.wait() + if not cursor_in_new_line: + self.to_screen(u'') + return proc.returncode + + url = info_dict['url'] + player_url = info_dict.get('player_url', None) + page_url = info_dict.get('page_url', None) + play_path = info_dict.get('play_path', None) + tc_url = info_dict.get('tc_url', None) + live = info_dict.get('rtmp_live', False) + conn = info_dict.get('rtmp_conn', None) + + self.report_destination(filename) + tmpfilename = self.temp_name(filename) + test = self.params.get('test', False) + + # Check for rtmpdump first + try: + subprocess.call(['rtmpdump', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT) + except (OSError, IOError): + self.report_error(u'RTMP download detected but "rtmpdump" could not be run') + return False + + # Download using rtmpdump. rtmpdump returns exit code 2 when + # the connection was interrumpted and resuming appears to be + # possible. This is part of rtmpdump's normal usage, AFAIK. + basic_args = ['rtmpdump', '--verbose', '-r', url, '-o', tmpfilename] + if player_url is not None: + basic_args += ['--swfVfy', player_url] + if page_url is not None: + basic_args += ['--pageUrl', page_url] + if play_path is not None: + basic_args += ['--playpath', play_path] + if tc_url is not None: + basic_args += ['--tcUrl', url] + if test: + basic_args += ['--stop', '1'] + if live: + basic_args += ['--live'] + if conn: + basic_args += ['--conn', conn] + args = basic_args + [[], ['--resume', '--skip', '1']][self.params.get('continuedl', False)] + + if sys.platform == 'win32' and sys.version_info < (3, 0): + # Windows subprocess module does not actually support Unicode + # on Python 2.x + # See http://stackoverflow.com/a/9951851/35070 + subprocess_encoding = sys.getfilesystemencoding() + args = [a.encode(subprocess_encoding, 'ignore') for a in args] + else: + subprocess_encoding = None + + if self.params.get('verbose', False): + if subprocess_encoding: + str_args = [ + a.decode(subprocess_encoding) if isinstance(a, bytes) else a + for a in args] + else: + str_args = args + try: + import pipes + shell_quote = lambda args: ' '.join(map(pipes.quote, str_args)) + except ImportError: + shell_quote = repr + self.to_screen(u'[debug] rtmpdump command line: ' + shell_quote(str_args)) + + retval = run_rtmpdump(args) + + while (retval == 2 or retval == 1) and not test: + prevsize = os.path.getsize(encodeFilename(tmpfilename)) + self.to_screen(u'[rtmpdump] %s bytes' % prevsize) + time.sleep(5.0) # This seems to be needed + retval = run_rtmpdump(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1]) + cursize = os.path.getsize(encodeFilename(tmpfilename)) + if prevsize == cursize and retval == 1: + break + # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those + if prevsize == cursize and retval == 2 and cursize > 1024: + self.to_screen(u'[rtmpdump] Could not download the whole video. This can happen for some advertisements.') + retval = 0 + break + if retval == 0 or (test and retval == 2): + fsize = os.path.getsize(encodeFilename(tmpfilename)) + self.to_screen(u'[rtmpdump] %s bytes' % fsize) + self.try_rename(tmpfilename, filename) + self._hook_progress({ + 'downloaded_bytes': fsize, + 'total_bytes': fsize, + 'filename': filename, + 'status': 'finished', + }) + return True + else: + self.to_stderr(u"\n") + self.report_error(u'rtmpdump exited with code %d' % retval) + return False diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 2d1e3cdfd..4d6aeabdf 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -1,5 +1,8 @@ -from .appletrailers import AppleTrailersIE +from .academicearth import AcademicEarthCourseIE from .addanime import AddAnimeIE +from .anitube import AnitubeIE +from .aparat import AparatIE +from .appletrailers import AppleTrailersIE from .archiveorg import ArchiveOrgIE from .ard import ARDIE from .arte import ( @@ -7,10 +10,12 @@ from .arte import ( ArteTVPlus7IE, ArteTVCreativeIE, ArteTVFutureIE, + ArteTVDDCIE, ) from .auengine import AUEngineIE from .bambuser import BambuserIE, BambuserChannelIE -from .bandcamp import BandcampIE +from .bandcamp import BandcampIE, BandcampAlbumIE +from .blinkx import BlinkxIE from .bliptv import BlipTVIE, BlipTVUserIE from .bloomberg import BloombergIE from .breakcom import BreakIE @@ -18,13 +23,20 @@ from .brightcove import BrightcoveIE from .c56 import C56IE from .canalplus import CanalplusIE from .canalc2 import Canalc2IE +from .cbs import CBSIE +from .channel9 import Channel9IE from .cinemassacre import CinemassacreIE +from .clipfish import ClipfishIE +from .clipsyndicate import ClipsyndicateIE +from .cmt import CMTIE from .cnn import CNNIE from .collegehumor import CollegeHumorIE -from .comedycentral import ComedyCentralIE +from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE from .condenast import CondeNastIE from .criterion import CriterionIE +from .crunchyroll import CrunchyrollIE from .cspan import CSpanIE +from .d8 import D8IE from .dailymotion import ( DailymotionIE, DailymotionPlaylistIE, @@ -35,11 +47,13 @@ from .depositfiles import DepositFilesIE from .dotsub import DotsubIE from .dreisat import DreiSatIE from .defense import DefenseGouvFrIE +from .dropbox import DropboxIE from .ebaumsworld import EbaumsWorldIE from .ehow import EHowIE from .eighttracks import EightTracksIE from .eitb import EitbIE from .escapist import EscapistIE +from .everyonesmixtape import EveryonesMixtapeIE from .exfm import ExfmIE from .extremetube import ExtremeTubeIE from .facebook import FacebookIE @@ -49,11 +63,13 @@ from .fktv import ( FKTVPosteckeIE, ) from .flickr import FlickrIE +from .franceinter import FranceInterIE from .francetv import ( PluzzIE, FranceTvInfoIE, - France2IE, - GenerationQuoiIE + FranceTVIE, + GenerationQuoiIE, + CultureboxIE, ) from .freesound import FreesoundIE from .funnyordie import FunnyOrDieIE @@ -68,25 +84,45 @@ from .hotnewhiphop import HotNewHipHopIE from .howcast import HowcastIE from .hypem import HypemIE from .ign import IGNIE, OneUPIE +from .imdb import ( + ImdbIE, + ImdbListIE +) from .ina import InaIE from .infoq import InfoQIE from .instagram import InstagramIE from .internetvideoarchive import InternetVideoArchiveIE +from .ivi import ( + IviIE, + IviCompilationIE +) from .jeuxvideo import JeuxVideoIE from .jukebox import JukeboxIE from .justintv import JustinTVIE +from .jpopsukitv import JpopsukiIE from .kankan import KankanIE from .keezmovies import KeezMoviesIE +from .khanacademy import KhanAcademyIE from .kickstarter import KickStarterIE from .keek import KeekIE from .liveleak import LiveLeakIE from .livestream import LivestreamIE, LivestreamOriginalIE +from .lynda import ( + LyndaIE, + LyndaCourseIE +) +from .macgamestore import MacGameStoreIE +from .mdr import MDRIE from .metacafe import MetacafeIE from .metacritic import MetacriticIE from .mit import TechTVMITIE, MITIE from .mixcloud import MixcloudIE +from .mpora import MporaIE from .mofosex import MofosexIE -from .mtv import MTVIE +from .mtv import ( + MTVIE, + MTVIggyIE, +) from .muzu import MuzuTVIE from .myspace import MySpaceIE from .myspass import MySpassIE @@ -94,15 +130,23 @@ from .myvideo import MyVideoIE from .naver import NaverIE from .nba import NBAIE from .nbc import NBCNewsIE +from .ndtv import NDTVIE from .newgrounds import NewgroundsIE from .nhl import NHLIE, NHLVideocenterIE +from .niconico import NiconicoIE +from .ninegag import NineGagIE +from .novamov import NovamovIE from .nowvideo import NowVideoIE from .ooyala import OoyalaIE from .orf import ORFIE from .pbs import PBSIE from .photobucket import PhotobucketIE +from .podomatic import PodomaticIE +from .pornhd import PornHdIE from .pornhub import PornHubIE from .pornotube import PornotubeIE +from .pyvideo import PyvideoIE +from .radiofrance import RadioFranceIE from .rbmaradio import RBMARadioIE from .redtube import RedTubeIE from .ringtv import RingTVIE @@ -111,9 +155,16 @@ from .rottentomatoes import RottenTomatoesIE from .roxwel import RoxwelIE from .rtlnow import RTLnowIE from .rutube import RutubeIE +from .servingsys import ServingSysIE from .sina import SinaIE from .slashdot import SlashdotIE from .slideshare import SlideshareIE +from .smotri import ( + SmotriIE, + SmotriCommunityIE, + SmotriUserIE, + SmotriBroadcastIE, +) from .sohu import SohuIE from .soundcloud import SoundcloudIE, SoundcloudSetIE, SoundcloudUserIE from .southparkstudios import ( @@ -123,15 +174,19 @@ from .southparkstudios import ( from .space import SpaceIE from .spankwire import SpankwireIE from .spiegel import SpiegelIE +from .spike import SpikeIE from .stanfordoc import StanfordOpenClassroomIE from .statigram import StatigramIE from .steam import SteamIE +from .streamcloud import StreamcloudIE from .sztvhu import SztvHuIE from .teamcoco import TeamcocoIE from .techtalks import TechTalksIE from .ted import TEDIE from .tf1 import TF1IE +from .theplatform import ThePlatformIE from .thisav import ThisAVIE +from .toutv import TouTvIE from .traileraddict import TrailerAddictIE from .trilulilu import TriluliluIE from .tube8 import Tube8IE @@ -150,19 +205,32 @@ from .viddler import ViddlerIE from .videodetective import VideoDetectiveIE from .videofyme import VideofyMeIE from .videopremium import VideoPremiumIE -from .vimeo import VimeoIE, VimeoChannelIE +from .vimeo import ( + VimeoIE, + VimeoChannelIE, + VimeoUserIE, + VimeoAlbumIE, + VimeoGroupsIE, + VimeoReviewIE, +) from .vine import VineIE +from .viki import VikiIE from .vk import VKIE from .wat import WatIE from .websurg import WeBSurgIE from .weibo import WeiboIE from .wimp import WimpIE +from .wistia import WistiaIE from .worldstarhiphop import WorldStarHipHopIE from .xhamster import XHamsterIE from .xnxx import XNXXIE from .xvideos import XVideosIE from .xtube import XTubeIE -from .yahoo import YahooIE, YahooSearchIE +from .yahoo import ( + YahooIE, + YahooNewsIE, + YahooSearchIE, +) from .youjizz import YouJizzIE from .youku import YoukuIE from .youporn import YouPornIE @@ -179,6 +247,8 @@ from .youtube import ( YoutubeTruncatedURLIE, YoutubeWatchLaterIE, YoutubeFavouritesIE, + YoutubeHistoryIE, + YoutubeTopListIE, ) from .zdf import ZDFIE diff --git a/youtube_dl/extractor/academicearth.py b/youtube_dl/extractor/academicearth.py new file mode 100644 index 000000000..72f81d01a --- /dev/null +++ b/youtube_dl/extractor/academicearth.py @@ -0,0 +1,32 @@ +from __future__ import unicode_literals +import re + +from .common import InfoExtractor + + +class AcademicEarthCourseIE(InfoExtractor): + _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/(?:courses|playlists)/(?P[^?#/]+)' + IE_NAME = 'AcademicEarth:Course' + + def _real_extract(self, url): + m = re.match(self._VALID_URL, url) + playlist_id = m.group('id') + + webpage = self._download_webpage(url, playlist_id) + title = self._html_search_regex( + r'

(.*?)

', webpage, u'title') + description = self._html_search_regex( + r'

(.*?)

', + webpage, u'description', fatal=False) + urls = re.findall( + r'

', + webpage) + entries = [self.url_result(u) for u in urls] + + return { + '_type': 'playlist', + 'id': playlist_id, + 'title': title, + 'description': description, + 'entries': entries, + } diff --git a/youtube_dl/extractor/addanime.py b/youtube_dl/extractor/addanime.py index b99d4b966..a3a1b999d 100644 --- a/youtube_dl/extractor/addanime.py +++ b/youtube_dl/extractor/addanime.py @@ -13,7 +13,7 @@ from ..utils import ( class AddAnimeIE(InfoExtractor): - _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video.php\?(?:.*?)v=(?P[\w_]+)(?:.*)' + _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video\.php\?(?:.*?)v=(?P[\w_]+)(?:.*)' IE_NAME = u'AddAnime' _TEST = { u'url': u'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9', diff --git a/youtube_dl/extractor/anitube.py b/youtube_dl/extractor/anitube.py new file mode 100644 index 000000000..2b019daa9 --- /dev/null +++ b/youtube_dl/extractor/anitube.py @@ -0,0 +1,53 @@ +import re + +from .common import InfoExtractor + + +class AnitubeIE(InfoExtractor): + IE_NAME = u'anitube.se' + _VALID_URL = r'https?://(?:www\.)?anitube\.se/video/(?P\d+)' + + _TEST = { + u'url': u'http://www.anitube.se/video/36621', + u'md5': u'59d0eeae28ea0bc8c05e7af429998d43', + u'file': u'36621.mp4', + u'info_dict': { + u'id': u'36621', + u'ext': u'mp4', + u'title': u'Recorder to Randoseru 01', + }, + u'skip': u'Blocked in the US', + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + key = self._html_search_regex(r'http://www\.anitube\.se/embed/([A-Za-z0-9_-]*)', + webpage, u'key') + + config_xml = self._download_xml('http://www.anitube.se/nuevo/econfig.php?key=%s' % key, + key) + + video_title = config_xml.find('title').text + + formats = [] + video_url = config_xml.find('file') + if video_url is not None: + formats.append({ + 'format_id': 'sd', + 'url': video_url.text, + }) + video_url = config_xml.find('filehd') + if video_url is not None: + formats.append({ + 'format_id': 'hd', + 'url': video_url.text, + }) + + return { + 'id': video_id, + 'title': video_title, + 'formats': formats + } diff --git a/youtube_dl/extractor/aparat.py b/youtube_dl/extractor/aparat.py new file mode 100644 index 000000000..7e93bc4df --- /dev/null +++ b/youtube_dl/extractor/aparat.py @@ -0,0 +1,56 @@ +#coding: utf-8 + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + HEADRequest, +) + + +class AparatIE(InfoExtractor): + _VALID_URL = r'^https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P[a-zA-Z0-9]+)' + + _TEST = { + u'url': u'http://www.aparat.com/v/wP8On', + u'file': u'wP8On.mp4', + u'md5': u'6714e0af7e0d875c5a39c4dc4ab46ad1', + u'info_dict': { + u"title": u"تیم گلکسی 11 - زومیت", + }, + #u'skip': u'Extremely unreliable', + } + + def _real_extract(self, url): + m = re.match(self._VALID_URL, url) + video_id = m.group('id') + + # Note: There is an easier-to-parse configuration at + # http://www.aparat.com/video/video/config/videohash/%video_id + # but the URL in there does not work + embed_url = (u'http://www.aparat.com/video/video/embed/videohash/' + + video_id + u'/vt/frame') + webpage = self._download_webpage(embed_url, video_id) + + video_urls = re.findall(r'fileList\[[0-9]+\]\s*=\s*"([^"]+)"', webpage) + for i, video_url in enumerate(video_urls): + req = HEADRequest(video_url) + res = self._request_webpage( + req, video_id, note=u'Testing video URL %d' % i, errnote=False) + if res: + break + else: + raise ExtractorError(u'No working video URLs found') + + title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, u'title') + thumbnail = self._search_regex( + r'\s+image:\s*"([^"]+)"', webpage, u'thumbnail', fatal=False) + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'ext': 'mp4', + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/appletrailers.py b/youtube_dl/extractor/appletrailers.py index 6d6237f8a..922cede05 100644 --- a/youtube_dl/extractor/appletrailers.py +++ b/youtube_dl/extractor/appletrailers.py @@ -1,5 +1,6 @@ +from __future__ import unicode_literals + import re -import xml.etree.ElementTree import json from .common import InfoExtractor @@ -10,48 +11,48 @@ from ..utils import ( class AppleTrailersIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?trailers.apple.com/trailers/(?P[^/]+)/(?P[^/]+)' + _VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/trailers/(?P[^/]+)/(?P[^/]+)' _TEST = { - u"url": u"http://trailers.apple.com/trailers/wb/manofsteel/", - u"playlist": [ + "url": "http://trailers.apple.com/trailers/wb/manofsteel/", + "playlist": [ { - u"file": u"manofsteel-trailer4.mov", - u"md5": u"d97a8e575432dbcb81b7c3acb741f8a8", - u"info_dict": { - u"duration": 111, - u"title": u"Trailer 4", - u"upload_date": u"20130523", - u"uploader_id": u"wb", + "file": "manofsteel-trailer4.mov", + "md5": "d97a8e575432dbcb81b7c3acb741f8a8", + "info_dict": { + "duration": 111, + "title": "Trailer 4", + "upload_date": "20130523", + "uploader_id": "wb", }, }, { - u"file": u"manofsteel-trailer3.mov", - u"md5": u"b8017b7131b721fb4e8d6f49e1df908c", - u"info_dict": { - u"duration": 182, - u"title": u"Trailer 3", - u"upload_date": u"20130417", - u"uploader_id": u"wb", + "file": "manofsteel-trailer3.mov", + "md5": "b8017b7131b721fb4e8d6f49e1df908c", + "info_dict": { + "duration": 182, + "title": "Trailer 3", + "upload_date": "20130417", + "uploader_id": "wb", }, }, { - u"file": u"manofsteel-trailer.mov", - u"md5": u"d0f1e1150989b9924679b441f3404d48", - u"info_dict": { - u"duration": 148, - u"title": u"Trailer", - u"upload_date": u"20121212", - u"uploader_id": u"wb", + "file": "manofsteel-trailer.mov", + "md5": "d0f1e1150989b9924679b441f3404d48", + "info_dict": { + "duration": 148, + "title": "Trailer", + "upload_date": "20121212", + "uploader_id": "wb", }, }, { - u"file": u"manofsteel-teaser.mov", - u"md5": u"5fe08795b943eb2e757fa95cb6def1cb", - u"info_dict": { - u"duration": 93, - u"title": u"Teaser", - u"upload_date": u"20120721", - u"uploader_id": u"wb", + "file": "manofsteel-teaser.mov", + "md5": "5fe08795b943eb2e757fa95cb6def1cb", + "info_dict": { + "duration": 93, + "title": "Teaser", + "upload_date": "20120721", + "uploader_id": "wb", }, } ] @@ -65,18 +66,18 @@ class AppleTrailersIE(InfoExtractor): uploader_id = mobj.group('company') playlist_url = compat_urlparse.urljoin(url, u'includes/playlists/itunes.inc') - playlist_snippet = self._download_webpage(playlist_url, movie) - playlist_cleaned = re.sub(r'(?s).*?', u'', playlist_snippet) - playlist_cleaned = re.sub(r'', r'', playlist_cleaned) - # The ' in the onClick attributes are not escaped, it couldn't be parsed - # with xml.etree.ElementTree.fromstring - # like: http://trailers.apple.com/trailers/wb/gravity/ - def _clean_json(m): - return u'iTunes.playURL(%s);' % m.group(1).replace('\'', ''') - playlist_cleaned = re.sub(self._JSON_RE, _clean_json, playlist_cleaned) - playlist_html = u'' + playlist_cleaned + u'' + def fix_html(s): + s = re.sub(r'(?s).*?', u'', s) + s = re.sub(r'', r'', s) + # The ' in the onClick attributes are not escaped, it couldn't be parsed + # like: http://trailers.apple.com/trailers/wb/gravity/ + def _clean_json(m): + return u'iTunes.playURL(%s);' % m.group(1).replace('\'', ''') + s = re.sub(self._JSON_RE, _clean_json, s) + s = u'' + s + u'' + return s + doc = self._download_xml(playlist_url, movie, transform_source=fix_html) - doc = xml.etree.ElementTree.fromstring(playlist_html) playlist = [] for li in doc.findall('./div/ul/li'): on_click = li.find('.//a').attrib['onClick'] @@ -111,9 +112,10 @@ class AppleTrailersIE(InfoExtractor): 'width': format['width'], 'height': int(format['height']), }) - formats = sorted(formats, key=lambda f: (f['height'], f['width'])) - info = { + self._sort_formats(formats) + + playlist.append({ '_type': 'video', 'id': video_id, 'title': title, @@ -124,12 +126,7 @@ class AppleTrailersIE(InfoExtractor): 'upload_date': upload_date, 'uploader_id': uploader_id, 'user_agent': 'QuickTime compatible (youtube-dl)', - } - # TODO: Remove when #980 has been merged - info['url'] = formats[-1]['url'] - info['ext'] = formats[-1]['ext'] - - playlist.append(info) + }) return { '_type': 'playlist', diff --git a/youtube_dl/extractor/archiveorg.py b/youtube_dl/extractor/archiveorg.py index 61ce4469a..34ce8429b 100644 --- a/youtube_dl/extractor/archiveorg.py +++ b/youtube_dl/extractor/archiveorg.py @@ -1,9 +1,10 @@ +from __future__ import unicode_literals + import json import re from .common import InfoExtractor from ..utils import ( - determine_ext, unified_strdate, ) @@ -11,25 +12,24 @@ from ..utils import ( class ArchiveOrgIE(InfoExtractor): IE_NAME = 'archive.org' IE_DESC = 'archive.org videos' - _VALID_URL = r'(?:https?://)?(?:www\.)?archive.org/details/(?P[^?/]+)(?:[?].*)?$' + _VALID_URL = r'(?:https?://)?(?:www\.)?archive\.org/details/(?P[^?/]+)(?:[?].*)?$' _TEST = { - u"url": u"http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect", - u'file': u'XD300-23_68HighlightsAResearchCntAugHumanIntellect.ogv', - u'md5': u'8af1d4cf447933ed3c7f4871162602db', - u'info_dict': { - u"title": u"1968 Demo - FJCC Conference Presentation Reel #1", - u"description": u"Reel 1 of 3: Also known as the \"Mother of All Demos\", Doug Engelbart's presentation at the Fall Joint Computer Conference in San Francisco, December 9, 1968 titled \"A Research Center for Augmenting Human Intellect.\" For this presentation, Doug and his team astonished the audience by not only relating their research, but demonstrating it live. This was the debut of the mouse, interactive computing, hypermedia, computer supported software engineering, video teleconferencing, etc. See also Doug's 1968 Demo page for more background, highlights, links, and the detailed paper published in this conference proceedings. Filmed on 3 reels: Reel 1 | Reel 2 | Reel 3", - u"upload_date": u"19681210", - u"uploader": u"SRI International" + "url": "http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect", + 'file': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect.ogv', + 'md5': '8af1d4cf447933ed3c7f4871162602db', + 'info_dict': { + "title": "1968 Demo - FJCC Conference Presentation Reel #1", + "description": "Reel 1 of 3: Also known as the \"Mother of All Demos\", Doug Engelbart's presentation at the Fall Joint Computer Conference in San Francisco, December 9, 1968 titled \"A Research Center for Augmenting Human Intellect.\" For this presentation, Doug and his team astonished the audience by not only relating their research, but demonstrating it live. This was the debut of the mouse, interactive computing, hypermedia, computer supported software engineering, video teleconferencing, etc. See also Doug's 1968 Demo page for more background, highlights, links, and the detailed paper published in this conference proceedings. Filmed on 3 reels: Reel 1 | Reel 2 | Reel 3", + "upload_date": "19681210", + "uploader": "SRI International" } } - def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - json_url = url + (u'?' if u'?' in url else '&') + u'output=json' + json_url = url + ('?' if '?' in url else '&') + 'output=json' json_data = self._download_webpage(json_url, video_id) data = json.loads(json_data) @@ -38,18 +38,18 @@ class ArchiveOrgIE(InfoExtractor): uploader = data['metadata']['creator'][0] upload_date = unified_strdate(data['metadata']['date'][0]) - formats = [{ + formats = [ + { 'format': fdata['format'], 'url': 'http://' + data['server'] + data['dir'] + fn, 'file_size': int(fdata['size']), } - for fn,fdata in data['files'].items() + for fn, fdata in data['files'].items() if 'Video' in fdata['format']] - formats.sort(key=lambda fdata: fdata['file_size']) - for f in formats: - f['ext'] = determine_ext(f['url']) - info = { + self._sort_formats(formats) + + return { '_type': 'video', 'id': video_id, 'title': title, @@ -57,12 +57,5 @@ class ArchiveOrgIE(InfoExtractor): 'description': description, 'uploader': uploader, 'upload_date': upload_date, + 'thumbnail': data.get('misc', {}).get('image'), } - thumbnail = data.get('misc', {}).get('image') - if thumbnail: - info['thumbnail'] = thumbnail - - # TODO: Remove when #980 has been merged - info.update(formats[-1]) - - return info diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index 44d0b5d70..7cf3785ac 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -1,7 +1,8 @@ # encoding: utf-8 +from __future__ import unicode_literals + import re import json -import xml.etree.ElementTree from .common import InfoExtractor from ..utils import ( @@ -11,6 +12,7 @@ from ..utils import ( determine_ext, get_element_by_id, compat_str, + get_element_by_attribute, ) # There are different sources of video in arte.tv, the extraction process @@ -18,11 +20,11 @@ from ..utils import ( # add tests. class ArteTvIE(InfoExtractor): - _VIDEOS_URL = r'(?:http://)?videos.arte.tv/(?Pfr|de)/.*-(?P.*?).html' - _LIVEWEB_URL = r'(?:http://)?liveweb.arte.tv/(?Pfr|de)/(?P.+?)/(?P.+)' + _VIDEOS_URL = r'(?:http://)?videos\.arte\.tv/(?Pfr|de)/.*-(?P.*?)\.html' + _LIVEWEB_URL = r'(?:http://)?liveweb\.arte\.tv/(?Pfr|de)/(?P.+?)/(?P.+)' _LIVE_URL = r'index-[0-9]+\.html$' - IE_NAME = u'arte.tv' + IE_NAME = 'arte.tv' @classmethod def suitable(cls, url): @@ -37,7 +39,7 @@ class ArteTvIE(InfoExtractor): # r'src="(.*?/videothek_js.*?\.js)', # 0, # [ - # (1, 'url', u'Invalid URL: %s' % url) + # (1, 'url', 'Invalid URL: %s' % url) # ] # ) # http_host = url.split('/')[2] @@ -49,12 +51,12 @@ class ArteTvIE(InfoExtractor): # '(rtmp://.*?)\'', # re.DOTALL, # [ - # (1, 'path', u'could not extract video path: %s' % url), - # (2, 'player', u'could not extract video player: %s' % url), - # (3, 'url', u'could not extract video url: %s' % url) + # (1, 'path', 'could not extract video path: %s' % url), + # (2, 'player', 'could not extract video player: %s' % url), + # (3, 'url', 'could not extract video url: %s' % url) # ] # ) - # video_url = u'%s/%s' % (info.get('url'), info.get('path')) + # video_url = '%s/%s' % (info.get('url'), info.get('path')) def _real_extract(self, url): mobj = re.match(self._VIDEOS_URL, url) @@ -78,8 +80,7 @@ class ArteTvIE(InfoExtractor): """Extract from videos.arte.tv""" ref_xml_url = url.replace('/videos/', '/do_delegate/videos/') ref_xml_url = ref_xml_url.replace('.html', ',view,asPlayerXml.xml') - ref_xml = self._download_webpage(ref_xml_url, video_id, note=u'Downloading metadata') - ref_xml_doc = xml.etree.ElementTree.fromstring(ref_xml) + ref_xml_doc = self._download_xml(ref_xml_url, video_id, note=u'Downloading metadata') config_node = find_xpath_attr(ref_xml_doc, './/video', 'lang', lang) config_xml_url = config_node.attrib['ref'] config_xml = self._download_webpage(config_xml_url, video_id, note=u'Downloading configuration') @@ -108,10 +109,9 @@ class ArteTvIE(InfoExtractor): def _extract_liveweb(self, url, name, lang): """Extract form http://liveweb.arte.tv/""" webpage = self._download_webpage(url, name) - video_id = self._search_regex(r'eventId=(\d+?)("|&)', webpage, u'event id') - config_xml = self._download_webpage('http://download.liveweb.arte.tv/o21/liveweb/events/event-%s.xml' % video_id, - video_id, u'Downloading information') - config_doc = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8')) + video_id = self._search_regex(r'eventId=(\d+?)("|&)', webpage, 'event id') + config_doc = self._download_xml('http://download.liveweb.arte.tv/o21/liveweb/events/event-%s.xml' % video_id, + video_id, 'Downloading information') event_doc = config_doc.find('event') url_node = event_doc.find('video').find('urlHd') if url_node is None: @@ -126,7 +126,7 @@ class ArteTvIE(InfoExtractor): class ArteTVPlus7IE(InfoExtractor): - IE_NAME = u'arte.tv:+7' + IE_NAME = 'arte.tv:+7' _VALID_URL = r'https?://www\.arte.tv/guide/(?Pfr|de)/(?:(?:sendungen|emissions)/)?(?P.*?)/(?P.*?)(\?.*)?' @classmethod @@ -145,7 +145,9 @@ class ArteTVPlus7IE(InfoExtractor): def _extract_from_webpage(self, webpage, video_id, lang): json_url = self._html_search_regex(r'arte_vp_url="(.*?)"', webpage, 'json url') + return self._extract_from_json_url(json_url, video_id, lang) + def _extract_from_json_url(self, json_url, video_id, lang): json_info = self._download_webpage(json_url, video_id, 'Downloading info json') self.report_extraction(video_id) info = json.loads(json_info) @@ -207,7 +209,7 @@ class ArteTVPlus7IE(InfoExtractor): if bitrate is not None: quality += '-%d' % bitrate if format_info.get('versionCode') is not None: - format_id = u'%s-%s' % (quality, format_info['versionCode']) + format_id = '%s-%s' % (quality, format_info['versionCode']) else: format_id = quality info = { @@ -216,7 +218,7 @@ class ArteTVPlus7IE(InfoExtractor): 'width': format_info.get('width'), 'height': height, } - if format_info['mediaType'] == u'rtmp': + if format_info['mediaType'] == 'rtmp': info['url'] = format_info['streamer'] info['play_path'] = 'mp4:' + format_info['url'] info['ext'] = 'flv' @@ -231,27 +233,27 @@ class ArteTVPlus7IE(InfoExtractor): # It also uses the arte_vp_url url from the webpage to extract the information class ArteTVCreativeIE(ArteTVPlus7IE): - IE_NAME = u'arte.tv:creative' + IE_NAME = 'arte.tv:creative' _VALID_URL = r'https?://creative\.arte\.tv/(?Pfr|de)/magazine?/(?P.+)' _TEST = { - u'url': u'http://creative.arte.tv/de/magazin/agentur-amateur-corporate-design', - u'file': u'050489-002.mp4', - u'info_dict': { - u'title': u'Agentur Amateur / Agence Amateur #2 : Corporate Design', + 'url': 'http://creative.arte.tv/de/magazin/agentur-amateur-corporate-design', + 'file': '050489-002.mp4', + 'info_dict': { + 'title': 'Agentur Amateur / Agence Amateur #2 : Corporate Design', }, } class ArteTVFutureIE(ArteTVPlus7IE): - IE_NAME = u'arte.tv:future' + IE_NAME = 'arte.tv:future' _VALID_URL = r'https?://future\.arte\.tv/(?Pfr|de)/(thema|sujet)/.*?#article-anchor-(?P\d+)' _TEST = { - u'url': u'http://future.arte.tv/fr/sujet/info-sciences#article-anchor-7081', - u'file': u'050940-003.mp4', - u'info_dict': { - u'title': u'Les champignons au secours de la planète', + 'url': 'http://future.arte.tv/fr/sujet/info-sciences#article-anchor-7081', + 'file': '050940-003.mp4', + 'info_dict': { + 'title': 'Les champignons au secours de la planète', }, } @@ -260,3 +262,21 @@ class ArteTVFutureIE(ArteTVPlus7IE): webpage = self._download_webpage(url, anchor_id) row = get_element_by_id(anchor_id, webpage) return self._extract_from_webpage(row, anchor_id, lang) + + +class ArteTVDDCIE(ArteTVPlus7IE): + IE_NAME = 'arte.tv:ddc' + _VALID_URL = r'http?://ddc\.arte\.tv/(?Pemission|folge)/(?P.+)' + + def _real_extract(self, url): + video_id, lang = self._extract_url_info(url) + if lang == 'folge': + lang = 'de' + elif lang == 'emission': + lang = 'fr' + webpage = self._download_webpage(url, video_id) + scriptElement = get_element_by_attribute('class', 'visu_video_block', webpage) + script_url = self._html_search_regex(r'src="(.*?)"', scriptElement, 'script url') + javascriptPlayerGenerator = self._download_webpage(script_url, video_id, 'Download javascript player generator') + json_url = self._search_regex(r"json_url=(.*)&rendering_place.*", javascriptPlayerGenerator, 'json url') + return self._extract_from_json_url(json_url, video_id, lang) diff --git a/youtube_dl/extractor/auengine.py b/youtube_dl/extractor/auengine.py index 0febbff4f..c6f30e626 100644 --- a/youtube_dl/extractor/auengine.py +++ b/youtube_dl/extractor/auengine.py @@ -1,46 +1,52 @@ -import os.path +from __future__ import unicode_literals + import re from .common import InfoExtractor from ..utils import ( compat_urllib_parse, - compat_urllib_parse_urlparse, + determine_ext, + ExtractorError, ) + class AUEngineIE(InfoExtractor): _TEST = { - u'url': u'http://auengine.com/embed.php?file=lfvlytY6&w=650&h=370', - u'file': u'lfvlytY6.mp4', - u'md5': u'48972bdbcf1a3a2f5533e62425b41d4f', - u'info_dict': { - u"title": u"[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]" + 'url': 'http://auengine.com/embed.php?file=lfvlytY6&w=650&h=370', + 'file': 'lfvlytY6.mp4', + 'md5': '48972bdbcf1a3a2f5533e62425b41d4f', + 'info_dict': { + 'title': '[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]' } } - _VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed.php\?.*?file=([^&]+).*?' + _VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed\.php\?.*?file=([^&]+).*?' def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group(1) webpage = self._download_webpage(url, video_id) title = self._html_search_regex(r'(?P<title>.+?)', - webpage, u'title') + webpage, 'title') title = title.strip() - links = re.findall(r'[^A-Za-z0-9]?(?:file|url):\s*["\'](http[^\'"&]*)', webpage) - links = [compat_urllib_parse.unquote(l) for l in links] + links = re.findall(r'\s(?:file|url):\s*["\']([^\'"]+)["\']', webpage) + links = map(compat_urllib_parse.unquote, links) + + thumbnail = None + video_url = None for link in links: - root, pathext = os.path.splitext(compat_urllib_parse_urlparse(link).path) - if pathext == '.png': + if link.endswith('.png'): thumbnail = link - elif pathext == '.mp4': - url = link - ext = pathext + elif '/videos/' in link: + video_url = link + if not video_url: + raise ExtractorError(u'Could not find video URL') + ext = '.' + determine_ext(video_url) if ext == title[-len(ext):]: title = title[:-len(ext)] - ext = ext[1:] - return [{ + + return { 'id': video_id, - 'url': url, - 'ext': ext, + 'url': video_url, 'title': title, 'thumbnail': thumbnail, - }] + } diff --git a/youtube_dl/extractor/bambuser.py b/youtube_dl/extractor/bambuser.py index 967568c4a..ccd31c4c7 100644 --- a/youtube_dl/extractor/bambuser.py +++ b/youtube_dl/extractor/bambuser.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re import json import itertools @@ -9,21 +11,26 @@ from ..utils import ( class BambuserIE(InfoExtractor): - IE_NAME = u'bambuser' + IE_NAME = 'bambuser' _VALID_URL = r'https?://bambuser\.com/v/(?P\d+)' _API_KEY = '005f64509e19a868399060af746a00aa' _TEST = { - u'url': u'http://bambuser.com/v/4050584', + 'url': 'http://bambuser.com/v/4050584', # MD5 seems to be flaky, see https://travis-ci.org/rg3/youtube-dl/jobs/14051016#L388 - #u'md5': u'fba8f7693e48fd4e8641b3fd5539a641', - u'info_dict': { - u'id': u'4050584', - u'ext': u'flv', - u'title': u'Education engineering days - lightning talks', - u'duration': 3741, - u'uploader': u'pixelversity', - u'uploader_id': u'344706', + #u'md5': 'fba8f7693e48fd4e8641b3fd5539a641', + 'info_dict': { + 'id': '4050584', + 'ext': 'flv', + 'title': 'Education engineering days - lightning talks', + 'duration': 3741, + 'uploader': 'pixelversity', + 'uploader_id': '344706', + }, + 'params': { + # It doesn't respect the 'Range' header, it would download the whole video + # caused the travis builds to fail: https://travis-ci.org/rg3/youtube-dl/jobs/14493845#L59 + 'skip_download': True, }, } @@ -48,8 +55,8 @@ class BambuserIE(InfoExtractor): class BambuserChannelIE(InfoExtractor): - IE_NAME = u'bambuser:channel' - _VALID_URL = r'http://bambuser.com/channel/(?P.*?)(?:/|#|\?|$)' + IE_NAME = 'bambuser:channel' + _VALID_URL = r'https?://bambuser\.com/channel/(?P.*?)(?:/|#|\?|$)' # The maximum number we can get with each request _STEP = 50 @@ -67,7 +74,7 @@ class BambuserChannelIE(InfoExtractor): # Without setting this header, we wouldn't get any result req.add_header('Referer', 'http://bambuser.com/channel/%s' % user) info_json = self._download_webpage(req, user, - u'Downloading page %d' % i) + 'Downloading page %d' % i) results = json.loads(info_json)['result'] if len(results) == 0: break diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py index 129a20f44..886b0dfab 100644 --- a/youtube_dl/extractor/bandcamp.py +++ b/youtube_dl/extractor/bandcamp.py @@ -1,23 +1,28 @@ +from __future__ import unicode_literals + import json import re from .common import InfoExtractor from ..utils import ( + compat_str, + compat_urlparse, ExtractorError, ) class BandcampIE(InfoExtractor): _VALID_URL = r'http://.*?\.bandcamp\.com/track/(?P.*)' - _TEST = { - u'url': u'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song', - u'file': u'1812978515.mp3', - u'md5': u'cdeb30cdae1921719a3cbcab696ef53c', - u'info_dict': { - u"title": u"youtube-dl test song \"'/\\\u00e4\u21ad" + _TESTS = [{ + 'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song', + 'file': '1812978515.mp3', + 'md5': 'c557841d5e50261777a6585648adf439', + 'info_dict': { + "title": "youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad", + "duration": 10, }, - u'skip': u'There is a limit of 200 free downloads / month for the test song' - } + '_skip': 'There is a limit of 200 free downloads / month for the test song' + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -26,38 +31,114 @@ class BandcampIE(InfoExtractor): # We get the link to the free download page m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage) if m_download is None: - raise ExtractorError(u'No free songs found') + m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage) + if m_trackinfo: + json_code = m_trackinfo.group(1) + data = json.loads(json_code) + d = data[0] + + duration = int(round(d['duration'])) + formats = [] + for format_id, format_url in d['file'].items(): + ext, _, abr_str = format_id.partition('-') + + formats.append({ + 'format_id': format_id, + 'url': format_url, + 'ext': format_id.partition('-')[0], + 'vcodec': 'none', + 'acodec': format_id.partition('-')[0], + 'abr': int(format_id.partition('-')[2]), + }) + + self._sort_formats(formats) + + return { + 'id': compat_str(d['id']), + 'title': d['title'], + 'formats': formats, + 'duration': duration, + } + else: + raise ExtractorError('No free songs found') download_link = m_download.group(1) - id = re.search(r'var TralbumData = {(.*?)id: (?P<id>\d*?)$', - webpage, re.MULTILINE|re.DOTALL).group('id') + video_id = re.search( + r'var TralbumData = {(.*?)id: (?P<id>\d*?)$', + webpage, re.MULTILINE | re.DOTALL).group('id') - download_webpage = self._download_webpage(download_link, id, + download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page') # We get the dictionary of the track from some javascrip code info = re.search(r'items: (.*?),$', download_webpage, re.MULTILINE).group(1) info = json.loads(info)[0] # We pick mp3-320 for now, until format selection can be easily implemented. - mp3_info = info[u'downloads'][u'mp3-320'] + mp3_info = info['downloads']['mp3-320'] # If we try to use this url it says the link has expired - initial_url = mp3_info[u'url'] + initial_url = mp3_info['url'] re_url = r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$' m_url = re.match(re_url, initial_url) #We build the url we will use to get the final track url # This url is build in Bandcamp in the script download_bunde_*.js - request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), id, m_url.group('ts')) - final_url_webpage = self._download_webpage(request_url, id, 'Requesting download url') + request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), video_id, m_url.group('ts')) + final_url_webpage = self._download_webpage(request_url, video_id, 'Requesting download url') # If we could correctly generate the .rand field the url would be #in the "download_url" key final_url = re.search(r'"retry_url":"(.*?)"', final_url_webpage).group(1) - track_info = {'id':id, - 'title' : info[u'title'], - 'ext' : 'mp3', - 'url' : final_url, - 'thumbnail' : info[u'thumb_url'], - 'uploader' : info[u'artist'] - } + return { + 'id': video_id, + 'title': info['title'], + 'ext': 'mp3', + 'vcodec': 'none', + 'url': final_url, + 'thumbnail': info.get('thumb_url'), + 'uploader': info.get('artist'), + } - return [track_info] + +class BandcampAlbumIE(InfoExtractor): + IE_NAME = 'Bandcamp:album' + _VALID_URL = r'http://.*?\.bandcamp\.com/album/(?P<title>.*)' + + _TEST = { + 'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1', + 'playlist': [ + { + 'file': '1353101989.mp3', + 'md5': '39bc1eded3476e927c724321ddf116cf', + 'info_dict': { + 'title': 'Intro', + } + }, + { + 'file': '38097443.mp3', + 'md5': '1a2c32e2691474643e912cc6cd4bffaa', + 'info_dict': { + 'title': 'Kero One - Keep It Alive (Blazo remix)', + } + }, + ], + 'params': { + 'playlistend': 2 + }, + 'skip': 'Bancamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test' + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + title = mobj.group('title') + webpage = self._download_webpage(url, title) + tracks_paths = re.findall(r'<a href="(.*?)" itemprop="url">', webpage) + if not tracks_paths: + raise ExtractorError('The page doesn\'t contain any tracks') + entries = [ + self.url_result(compat_urlparse.urljoin(url, t_path), ie=BandcampIE.ie_key()) + for t_path in tracks_paths] + title = self._search_regex(r'album_title : "(.*?)"', webpage, 'title') + return { + '_type': 'playlist', + 'title': title, + 'entries': entries, + } diff --git a/youtube_dl/extractor/blinkx.py b/youtube_dl/extractor/blinkx.py new file mode 100644 index 000000000..96408e4e0 --- /dev/null +++ b/youtube_dl/extractor/blinkx.py @@ -0,0 +1,95 @@ +from __future__ import unicode_literals + +import datetime +import json +import re + +from .common import InfoExtractor +from ..utils import ( + remove_start, +) + + +class BlinkxIE(InfoExtractor): + _VALID_URL = r'^(?:https?://(?:www\.)blinkx\.com/#?ce/|blinkx:)(?P<id>[^?]+)' + IE_NAME = 'blinkx' + + _TEST = { + 'url': 'http://www.blinkx.com/ce/8aQUy7GVFYgFzpKhT0oqsilwOGFRVXk3R1ZGWWdGenBLaFQwb3FzaWx3OGFRVXk3R1ZGWWdGenB', + 'file': '8aQUy7GV.mp4', + 'md5': '2e9a07364af40163a908edbf10bb2492', + 'info_dict': { + "title": "Police Car Rolls Away", + "uploader": "stupidvideos.com", + "upload_date": "20131215", + "description": "A police car gently rolls away from a fight. Maybe it felt weird being around a confrontation and just had to get out of there!", + "duration": 14.886, + "thumbnails": [{ + "width": 100, + "height": 76, + "url": "http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg", + }], + }, + } + + def _real_extract(self, rl): + m = re.match(self._VALID_URL, rl) + video_id = m.group('id') + display_id = video_id[:8] + + api_url = (u'https://apib4.blinkx.com/api.php?action=play_video&' + + 'video=%s' % video_id) + data_json = self._download_webpage(api_url, display_id) + data = json.loads(data_json)['api']['results'][0] + dt = datetime.datetime.fromtimestamp(data['pubdate_epoch']) + pload_date = dt.strftime('%Y%m%d') + + duration = None + thumbnails = [] + formats = [] + for m in data['media']: + if m['type'] == 'jpg': + thumbnails.append({ + 'url': m['link'], + 'width': int(m['w']), + 'height': int(m['h']), + }) + elif m['type'] == 'original': + duration = m['d'] + elif m['type'] == 'youtube': + yt_id = m['link'] + self.to_screen(u'Youtube video detected: %s' % yt_id) + return self.url_result(yt_id, 'Youtube', video_id=yt_id) + elif m['type'] in ('flv', 'mp4'): + vcodec = remove_start(m['vcodec'], 'ff') + acodec = remove_start(m['acodec'], 'ff') + tbr = (int(m['vbr']) + int(m['abr'])) // 1000 + format_id = (u'%s-%sk-%s' % + (vcodec, + tbr, + m['w'])) + formats.append({ + 'format_id': format_id, + 'url': m['link'], + 'vcodec': vcodec, + 'acodec': acodec, + 'abr': int(m['abr']) // 1000, + 'vbr': int(m['vbr']) // 1000, + 'tbr': tbr, + 'width': int(m['w']), + 'height': int(m['h']), + }) + + self._sort_formats(formats) + + return { + 'id': display_id, + 'fullid': video_id, + 'title': data['title'], + 'formats': formats, + 'uploader': data['channel_name'], + 'upload_date': pload_date, + 'description': data.get('description'), + 'thumbnails': thumbnails, + 'duration': duration, + } diff --git a/youtube_dl/extractor/bliptv.py b/youtube_dl/extractor/bliptv.py index 493504f75..3ce9b5324 100644 --- a/youtube_dl/extractor/bliptv.py +++ b/youtube_dl/extractor/bliptv.py @@ -1,16 +1,15 @@ +from __future__ import unicode_literals + import datetime import json -import os import re import socket from .common import InfoExtractor from ..utils import ( compat_http_client, - compat_parse_qs, compat_str, compat_urllib_error, - compat_urllib_parse_urlparse, compat_urllib_request, ExtractorError, @@ -22,43 +21,35 @@ class BlipTVIE(InfoExtractor): """Information extractor for blip.tv""" _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv/((.+/)|(play/)|(api\.swf#))(.+)$' - _URL_EXT = r'^.*\.([a-z0-9]+)$' - IE_NAME = u'blip.tv' + _TEST = { - u'url': u'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352', - u'file': u'5779306.m4v', - u'md5': u'80baf1ec5c3d2019037c1c707d676b9f', - u'info_dict': { - u"upload_date": u"20111205", - u"description": u"md5:9bc31f227219cde65e47eeec8d2dc596", - u"uploader": u"Comic Book Resources - CBR TV", - u"title": u"CBR EXCLUSIVE: \"Gotham City Imposters\" Bats VS Jokerz Short 3" + 'url': 'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352', + 'file': '5779306.mov', + 'md5': 'c6934ad0b6acf2bd920720ec888eb812', + 'info_dict': { + 'upload_date': '20111205', + 'description': 'md5:9bc31f227219cde65e47eeec8d2dc596', + 'uploader': 'Comic Book Resources - CBR TV', + 'title': 'CBR EXCLUSIVE: "Gotham City Imposters" Bats VS Jokerz Short 3', } } def report_direct_download(self, title): """Report information extraction.""" - self.to_screen(u'%s: Direct download detected' % title) + self.to_screen('%s: Direct download detected' % title) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) + raise ExtractorError('Invalid URL: %s' % url) # See https://github.com/rg3/youtube-dl/issues/857 - api_mobj = re.match(r'http://a\.blip\.tv/api\.swf#(?P<video_id>[\d\w]+)', url) - if api_mobj is not None: - url = 'http://blip.tv/play/g_%s' % api_mobj.group('video_id') - urlp = compat_urllib_parse_urlparse(url) - if urlp.path.startswith('/play/'): - request = compat_urllib_request.Request(url) - response = compat_urllib_request.urlopen(request) - redirecturl = response.geturl() - rurlp = compat_urllib_parse_urlparse(redirecturl) - file_id = compat_parse_qs(rurlp.fragment)['file'][0].rpartition('/')[2] - url = 'http://blip.tv/a/a-' + file_id - return self._real_extract(url) - + embed_mobj = re.search(r'^(?:https?://)?(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)([a-zA-Z0-9]+)', url) + if embed_mobj: + info_url = 'http://blip.tv/play/%s.x?p=1' % embed_mobj.group(1) + info_page = self._download_webpage(info_url, embed_mobj.group(1)) + video_id = self._search_regex(r'data-episode-id="(\d+)', info_page, 'video_id') + return self.url_result('http://blip.tv/a/a-' + video_id, 'BlipTV') if '?' in url: cchar = '&' @@ -68,69 +59,55 @@ class BlipTVIE(InfoExtractor): request = compat_urllib_request.Request(json_url) request.add_header('User-Agent', 'iTunes/10.6.1') self.report_extraction(mobj.group(1)) - info = None + urlh = self._request_webpage(request, None, False, + 'unable to download video info webpage') + try: - urlh = compat_urllib_request.urlopen(request) - if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download - basename = url.split('/')[-1] - title,ext = os.path.splitext(basename) - title = title.decode('UTF-8') - ext = ext.replace('.', '') - self.report_direct_download(title) - info = { - 'id': title, - 'url': url, - 'uploader': None, - 'upload_date': None, - 'title': title, - 'ext': ext, - 'urlhandle': urlh - } + json_code_bytes = urlh.read() + json_code = json_code_bytes.decode('utf-8') except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise ExtractorError(u'ERROR: unable to download video info webpage: %s' % compat_str(err)) - if info is None: # Regular URL - try: - json_code_bytes = urlh.read() - json_code = json_code_bytes.decode('utf-8') - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise ExtractorError(u'Unable to read video info webpage: %s' % compat_str(err)) + raise ExtractorError('Unable to read video info webpage: %s' % compat_str(err)) - try: - json_data = json.loads(json_code) - if 'Post' in json_data: - data = json_data['Post'] - else: - data = json_data + try: + json_data = json.loads(json_code) + if 'Post' in json_data: + data = json_data['Post'] + else: + data = json_data - upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d') - if 'additionalMedia' in data: - formats = sorted(data['additionalMedia'], key=lambda f: int(f['media_height'])) - best_format = formats[-1] - video_url = best_format['url'] - else: - video_url = data['media']['url'] - umobj = re.match(self._URL_EXT, video_url) - if umobj is None: - raise ValueError('Can not determine filename extension') - ext = umobj.group(1) + upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d') + formats = [] + if 'additionalMedia' in data: + for f in sorted(data['additionalMedia'], key=lambda f: int(f['media_height'])): + if not int(f['media_width']): # filter m3u8 + continue + formats.append({ + 'url': f['url'], + 'format_id': f['role'], + 'width': int(f['media_width']), + 'height': int(f['media_height']), + }) + else: + formats.append({ + 'url': data['media']['url'], + 'width': int(data['media']['width']), + 'height': int(data['media']['height']), + }) - info = { - 'id': compat_str(data['item_id']), - 'url': video_url, - 'uploader': data['display_name'], - 'upload_date': upload_date, - 'title': data['title'], - 'ext': ext, - 'format': data['media']['mimeType'], - 'thumbnail': data['thumbnailUrl'], - 'description': data['description'], - 'player_url': data['embedUrl'], - 'user_agent': 'iTunes/10.6.1', - } - except (ValueError,KeyError) as err: - raise ExtractorError(u'Unable to parse video information: %s' % repr(err)) + self._sort_formats(formats) - return [info] + return { + 'id': compat_str(data['item_id']), + 'uploader': data['display_name'], + 'upload_date': upload_date, + 'title': data['title'], + 'thumbnail': data['thumbnailUrl'], + 'description': data['description'], + 'user_agent': 'iTunes/10.6.1', + 'formats': formats, + } + except (ValueError, KeyError) as err: + raise ExtractorError('Unable to parse video information: %s' % repr(err)) class BlipTVUserIE(InfoExtractor): @@ -138,19 +115,19 @@ class BlipTVUserIE(InfoExtractor): _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$' _PAGE_SIZE = 12 - IE_NAME = u'blip.tv:user' + IE_NAME = 'blip.tv:user' def _real_extract(self, url): # Extract username mobj = re.match(self._VALID_URL, url) if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) + raise ExtractorError('Invalid URL: %s' % url) username = mobj.group(1) page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1' - page = self._download_webpage(url, username, u'Downloading user page') + page = self._download_webpage(url, username, 'Downloading user page') mobj = re.search(r'data-users-id="([^"]+)"', page) page_base = page_base % mobj.group(1) @@ -166,7 +143,7 @@ class BlipTVUserIE(InfoExtractor): while True: url = page_base + "&page=" + str(pagenum) page = self._download_webpage(url, username, - u'Downloading video ids from page %d' % pagenum) + 'Downloading video ids from page %d' % pagenum) # Extract video identifiers ids_in_page = [] @@ -188,6 +165,6 @@ class BlipTVUserIE(InfoExtractor): pagenum += 1 - urls = [u'http://blip.tv/%s' % video_id for video_id in video_ids] + urls = ['http://blip.tv/%s' % video_id for video_id in video_ids] url_entries = [self.url_result(vurl, 'BlipTV') for vurl in urls] return [self.playlist_result(url_entries, playlist_title = username)] diff --git a/youtube_dl/extractor/bloomberg.py b/youtube_dl/extractor/bloomberg.py index 3666a780b..d18bc7e0c 100644 --- a/youtube_dl/extractor/bloomberg.py +++ b/youtube_dl/extractor/bloomberg.py @@ -1,10 +1,11 @@ import re from .common import InfoExtractor +from .ooyala import OoyalaIE class BloombergIE(InfoExtractor): - _VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<name>.+?).html' + _VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<name>.+?)\.html' _TEST = { u'url': u'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html', @@ -23,5 +24,5 @@ class BloombergIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) name = mobj.group('name') webpage = self._download_webpage(url, name) - ooyala_url = self._og_search_video_url(webpage) - return self.url_result(ooyala_url, ie='Ooyala') + ooyala_code = self._search_regex(r'<source src="http://player.ooyala.com/player/[^/]+/([^".]+)', webpage, u'ooyala url') + return OoyalaIE._build_url_result(ooyala_code) diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index d8c35465a..e1c45d1f0 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -1,4 +1,5 @@ # encoding: utf-8 +from __future__ import unicode_literals import re import json @@ -8,11 +9,14 @@ from .common import InfoExtractor from ..utils import ( compat_urllib_parse, find_xpath_attr, + fix_xml_ampersands, compat_urlparse, compat_str, compat_urllib_request, + compat_parse_qs, ExtractorError, + unsmuggle_url, ) @@ -24,35 +28,47 @@ class BrightcoveIE(InfoExtractor): _TESTS = [ { # From http://www.8tv.cat/8aldia/videos/xavier-sala-i-martin-aquesta-tarda-a-8-al-dia/ - u'url': u'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1654948606001&flashID=myExperience&%40videoPlayer=2371591881001', - u'file': u'2371591881001.mp4', - u'md5': u'8eccab865181d29ec2958f32a6a754f5', - u'note': u'Test Brightcove downloads and detection in GenericIE', - u'info_dict': { - u'title': u'Xavier Sala i Martín: “Un banc que no presta és un banc zombi que no serveix per a res”', - u'uploader': u'8TV', - u'description': u'md5:a950cc4285c43e44d763d036710cd9cd', + 'url': 'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1654948606001&flashID=myExperience&%40videoPlayer=2371591881001', + 'file': '2371591881001.mp4', + 'md5': '5423e113865d26e40624dce2e4b45d95', + 'note': 'Test Brightcove downloads and detection in GenericIE', + 'info_dict': { + 'title': 'Xavier Sala i Martín: “Un banc que no presta és un banc zombi que no serveix per a res”', + 'uploader': '8TV', + 'description': 'md5:a950cc4285c43e44d763d036710cd9cd', } }, { # From http://medianetwork.oracle.com/video/player/1785452137001 - u'url': u'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1217746023001&flashID=myPlayer&%40videoPlayer=1785452137001', - u'file': u'1785452137001.flv', - u'info_dict': { - u'title': u'JVMLS 2012: Arrays 2.0 - Opportunities and Challenges', - u'description': u'John Rose speaks at the JVM Language Summit, August 1, 2012.', - u'uploader': u'Oracle', + 'url': 'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1217746023001&flashID=myPlayer&%40videoPlayer=1785452137001', + 'file': '1785452137001.flv', + 'info_dict': { + 'title': 'JVMLS 2012: Arrays 2.0 - Opportunities and Challenges', + 'description': 'John Rose speaks at the JVM Language Summit, August 1, 2012.', + 'uploader': 'Oracle', }, }, { # From http://mashable.com/2013/10/26/thermoelectric-bracelet-lets-you-control-your-body-temperature/ - u'url': u'http://c.brightcove.com/services/viewer/federated_f9?&playerID=1265504713001&publisherID=AQ%7E%7E%2CAAABBzUwv1E%7E%2CxP-xFHVUstiMFlNYfvF4G9yFnNaqCw_9&videoID=2750934548001', - u'info_dict': { - u'id': u'2750934548001', - u'ext': u'mp4', - u'title': u'This Bracelet Acts as a Personal Thermostat', - u'description': u'md5:547b78c64f4112766ccf4e151c20b6a0', - u'uploader': u'Mashable', + 'url': 'http://c.brightcove.com/services/viewer/federated_f9?&playerID=1265504713001&publisherID=AQ%7E%7E%2CAAABBzUwv1E%7E%2CxP-xFHVUstiMFlNYfvF4G9yFnNaqCw_9&videoID=2750934548001', + 'info_dict': { + 'id': '2750934548001', + 'ext': 'mp4', + 'title': 'This Bracelet Acts as a Personal Thermostat', + 'description': 'md5:547b78c64f4112766ccf4e151c20b6a0', + 'uploader': 'Mashable', + }, + }, + { + # test that the default referer works + # from http://national.ballet.ca/interact/video/Lost_in_Motion_II/ + 'url': 'http://link.brightcove.com/services/player/bcpid756015033001?bckey=AQ~~,AAAApYJi_Ck~,GxhXCegT1Dp39ilhXuxMJxasUhVNZiil&bctid=2878862109001', + 'info_dict': { + 'id': '2878862109001', + 'ext': 'mp4', + 'title': 'Lost in Motion II', + 'description': 'md5:363109c02998fee92ec02211bd8000df', + 'uploader': 'National Ballet of Canada', }, }, ] @@ -68,23 +84,45 @@ class BrightcoveIE(InfoExtractor): object_str = re.sub(r'(<param name="[^"]+" value="[^"]+")>', lambda m: m.group(1) + '/>', object_str) # Fix up some stupid XML, see https://github.com/rg3/youtube-dl/issues/1608 - object_str = object_str.replace(u'<--', u'<!--') + object_str = object_str.replace('<--', '<!--') + object_str = fix_xml_ampersands(object_str) object_doc = xml.etree.ElementTree.fromstring(object_str) - assert u'BrightcoveExperience' in object_doc.attrib['class'] - params = {'flashID': object_doc.attrib['id'], - 'playerID': find_xpath_attr(object_doc, './param', 'name', 'playerID').attrib['value'], - } - playerKey = find_xpath_attr(object_doc, './param', 'name', 'playerKey') + + fv_el = find_xpath_attr(object_doc, './param', 'name', 'flashVars') + if fv_el is not None: + flashvars = dict( + (k, v[0]) + for k, v in compat_parse_qs(fv_el.attrib['value']).items()) + else: + flashvars = {} + + def find_param(name): + if name in flashvars: + return flashvars[name] + node = find_xpath_attr(object_doc, './param', 'name', name) + if node is not None: + return node.attrib['value'] + return None + + params = {} + + playerID = find_param('playerID') + if playerID is None: + raise ExtractorError('Cannot find player ID') + params['playerID'] = playerID + + playerKey = find_param('playerKey') # Not all pages define this value if playerKey is not None: - params['playerKey'] = playerKey.attrib['value'] - videoPlayer = find_xpath_attr(object_doc, './param', 'name', '@videoPlayer') + params['playerKey'] = playerKey + # The three fields hold the id of the video + videoPlayer = find_param('@videoPlayer') or find_param('videoId') or find_param('videoID') if videoPlayer is not None: - params['@videoPlayer'] = videoPlayer.attrib['value'] - linkBase = find_xpath_attr(object_doc, './param', 'name', 'linkBaseURL') + params['@videoPlayer'] = videoPlayer + linkBase = find_param('linkBaseURL') if linkBase is not None: - params['linkBaseURL'] = linkBase.attrib['value'] + params['linkBaseURL'] = linkBase data = compat_urllib_parse.urlencode(params) return cls._FEDERATED_URL_TEMPLATE % data @@ -94,14 +132,20 @@ class BrightcoveIE(InfoExtractor): if it can't be found """ m_brightcove = re.search( - r'<object[^>]+?class=([\'"])[^>]*?BrightcoveExperience.*?\1.+?</object>', - webpage, re.DOTALL) + r'''(?sx)<object + (?: + [^>]+?class=([\'"])[^>]*?BrightcoveExperience.*?\1 | + [^>]*?>\s*<param\s+name="movie"\s+value="https?://[^/]*brightcove\.com/ + ).+?</object>''', + webpage) if m_brightcove is not None: return cls._build_brighcove_url(m_brightcove.group()) else: return None def _real_extract(self, url): + url, smuggled_data = unsmuggle_url(url, {}) + # Change the 'videoId' and others field to '@videoPlayer' url = re.sub(r'(?<=[?&])(videoI(d|D)|bctid)', '%40videoPlayer', url) # Change bckey (used by bcove.me urls) to playerKey @@ -112,33 +156,39 @@ class BrightcoveIE(InfoExtractor): videoPlayer = query.get('@videoPlayer') if videoPlayer: - return self._get_video_info(videoPlayer[0], query_str, query) + # We set the original url as the default 'Referer' header + referer = smuggled_data.get('Referer', url) + return self._get_video_info( + videoPlayer[0], query_str, query, referer=referer) else: player_key = query['playerKey'] return self._get_playlist_info(player_key[0]) - def _get_video_info(self, video_id, query_str, query): + def _get_video_info(self, video_id, query_str, query, referer=None): request_url = self._FEDERATED_URL_TEMPLATE % query_str req = compat_urllib_request.Request(request_url) linkBase = query.get('linkBaseURL') if linkBase is not None: - req.add_header('Referer', linkBase[0]) + referer = linkBase[0] + if referer is not None: + req.add_header('Referer', referer) webpage = self._download_webpage(req, video_id) self.report_extraction(video_id) info = self._search_regex(r'var experienceJSON = ({.*?});', webpage, 'json') info = json.loads(info)['data'] video_info = info['programmedContent']['videoPlayer']['mediaDTO'] + video_info['_youtubedl_adServerURL'] = info.get('adServerURL') return self._extract_video_info(video_info) def _get_playlist_info(self, player_key): playlist_info = self._download_webpage(self._PLAYLIST_URL_TEMPLATE % player_key, - player_key, u'Downloading playlist information') + player_key, 'Downloading playlist information') json_data = json.loads(playlist_info) if 'videoList' not in json_data: - raise ExtractorError(u'Empty playlist') + raise ExtractorError('Empty playlist') playlist_info = json_data['videoList'] videos = [self._extract_video_info(video_info) for video_info in playlist_info['mediaCollectionDTO']['videoDTOs']] @@ -166,6 +216,23 @@ class BrightcoveIE(InfoExtractor): info.update({ 'url': video_info['FLVFullLengthURL'], }) - else: - raise ExtractorError(u'Unable to extract video url for %s' % info['id']) + + if self._downloader.params.get('include_ads', False): + adServerURL = video_info.get('_youtubedl_adServerURL') + if adServerURL: + ad_info = { + '_type': 'url', + 'url': adServerURL, + } + if 'url' in info: + return { + '_type': 'playlist', + 'title': info['title'], + 'entries': [ad_info, info], + } + else: + return ad_info + + if 'url' not in info and not info.get('formats'): + raise ExtractorError('Unable to extract video url for %s' % info['id']) return info diff --git a/youtube_dl/extractor/c56.py b/youtube_dl/extractor/c56.py index dc3a8d47d..690bc7c25 100644 --- a/youtube_dl/extractor/c56.py +++ b/youtube_dl/extractor/c56.py @@ -1,21 +1,21 @@ # coding: utf-8 +from __future__ import unicode_literals import re import json from .common import InfoExtractor -from ..utils import determine_ext + class C56IE(InfoExtractor): _VALID_URL = r'https?://((www|player)\.)?56\.com/(.+?/)?(v_|(play_album.+-))(?P<textid>.+?)\.(html|swf)' - IE_NAME = u'56.com' - - _TEST ={ - u'url': u'http://www.56.com/u39/v_OTM0NDA3MTY.html', - u'file': u'93440716.flv', - u'md5': u'e59995ac63d0457783ea05f93f12a866', - u'info_dict': { - u'title': u'网事知多少 第32期：车怒', + IE_NAME = '56.com' + _TEST = { + 'url': 'http://www.56.com/u39/v_OTM0NDA3MTY.html', + 'file': '93440716.flv', + 'md5': 'e59995ac63d0457783ea05f93f12a866', + 'info_dict': { + 'title': '网事知多少 第32期：车怒', }, } @@ -23,14 +23,18 @@ class C56IE(InfoExtractor): mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE) text_id = mobj.group('textid') info_page = self._download_webpage('http://vxml.56.com/json/%s/' % text_id, - text_id, u'Downloading video info') + text_id, 'Downloading video info') info = json.loads(info_page)['info'] - best_format = sorted(info['rfiles'], key=lambda f: int(f['filesize']))[-1] - video_url = best_format['url'] + formats = [{ + 'format_id': f['type'], + 'filesize': int(f['filesize']), + 'url': f['url'] + } for f in info['rfiles']] + self._sort_formats(formats) - return {'id': info['vid'], - 'title': info['Subject'], - 'url': video_url, - 'ext': determine_ext(video_url), - 'thumbnail': info.get('bimg') or info.get('img'), - } + return { + 'id': info['vid'], + 'title': info['Subject'], + 'formats': formats, + 'thumbnail': info.get('bimg') or info.get('img'), + } diff --git a/youtube_dl/extractor/canalplus.py b/youtube_dl/extractor/canalplus.py index 1db9b24cf..7cdcd8399 100644 --- a/youtube_dl/extractor/canalplus.py +++ b/youtube_dl/extractor/canalplus.py @@ -1,10 +1,10 @@ # encoding: utf-8 import re -import xml.etree.ElementTree from .common import InfoExtractor from ..utils import unified_strdate + class CanalplusIE(InfoExtractor): _VALID_URL = r'https?://(www\.canalplus\.fr/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>\d+))' _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s' @@ -25,16 +25,15 @@ class CanalplusIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = mobj.groupdict().get('id') if video_id is None: webpage = self._download_webpage(url, mobj.group('path')) video_id = self._search_regex(r'videoId = "(\d+)";', webpage, u'video id') info_url = self._VIDEO_INFO_TEMPLATE % video_id - info_page = self._download_webpage(info_url,video_id, + doc = self._download_xml(info_url,video_id, u'Downloading video info') self.report_extraction(video_id) - doc = xml.etree.ElementTree.fromstring(info_page.encode('utf-8')) video_info = [video for video in doc if video.find('ID').text == video_id][0] infos = video_info.find('INFOS') media = video_info.find('MEDIA') diff --git a/youtube_dl/extractor/cbs.py b/youtube_dl/extractor/cbs.py new file mode 100644 index 000000000..ac0315853 --- /dev/null +++ b/youtube_dl/extractor/cbs.py @@ -0,0 +1,30 @@ +import re + +from .common import InfoExtractor + + +class CBSIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?cbs\.com/shows/[^/]+/video/(?P<id>[^/]+)/.*' + + _TEST = { + u'url': u'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/', + u'file': u'4JUVEwq3wUT7.flv', + u'info_dict': { + u'title': u'Connect Chat feat. Garth Brooks', + u'description': u'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!', + u'duration': 1495, + }, + u'params': { + # rtmp download + u'skip_download': True, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + real_id = self._search_regex( + r"video\.settings\.pid\s*=\s*'([^']+)';", + webpage, u'real video ID') + return self.url_result(u'theplatform:%s' % real_id) diff --git a/youtube_dl/extractor/channel9.py b/youtube_dl/extractor/channel9.py new file mode 100644 index 000000000..574881b70 --- /dev/null +++ b/youtube_dl/extractor/channel9.py @@ -0,0 +1,271 @@ +# encoding: utf-8 + +import re + +from .common import InfoExtractor +from ..utils import ExtractorError + +class Channel9IE(InfoExtractor): + ''' + Common extractor for channel9.msdn.com. + + The type of provided URL (video or playlist) is determined according to + meta Search.PageType from web page HTML rather than URL itself, as it is + not always possible to do. + ''' + IE_DESC = u'Channel 9' + IE_NAME = u'channel9' + _VALID_URL = r'^https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+)/?' + + _TESTS = [ + { + u'url': u'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002', + u'file': u'Events_TechEd_Australia_2013_KOS002.mp4', + u'md5': u'bbd75296ba47916b754e73c3a4bbdf10', + u'info_dict': { + u'title': u'Developer Kick-Off Session: Stuff We Love', + u'description': u'md5:c08d72240b7c87fcecafe2692f80e35f', + u'duration': 4576, + u'thumbnail': u'http://media.ch9.ms/ch9/9d51/03902f2d-fc97-4d3c-b195-0bfe15a19d51/KOS002_220.jpg', + u'session_code': u'KOS002', + u'session_day': u'Day 1', + u'session_room': u'Arena 1A', + u'session_speakers': [ u'Ed Blankenship', u'Andrew Coates', u'Brady Gaster', u'Patrick Klug', u'Mads Kristensen' ], + }, + }, + { + u'url': u'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing', + u'file': u'posts_Self-service-BI-with-Power-BI-nuclear-testing.mp4', + u'md5': u'b43ee4529d111bc37ba7ee4f34813e68', + u'info_dict': { + u'title': u'Self-service BI with Power BI - nuclear testing', + u'description': u'md5:d1e6ecaafa7fb52a2cacdf9599829f5b', + u'duration': 1540, + u'thumbnail': u'http://media.ch9.ms/ch9/87e1/0300391f-a455-4c72-bec3-4422f19287e1/selfservicenuk_512.jpg', + u'authors': [ u'Mike Wilmot' ], + }, + } + ] + + _RSS_URL = 'http://channel9.msdn.com/%s/RSS' + + # Sorted by quality + _known_formats = ['MP3', 'MP4', 'Mid Quality WMV', 'Mid Quality MP4', 'High Quality WMV', 'High Quality MP4'] + + def _restore_bytes(self, formatted_size): + if not formatted_size: + return 0 + m = re.match(r'^(?P<size>\d+(?:\.\d+)?)\s+(?P<units>[a-zA-Z]+)', formatted_size) + if not m: + return 0 + units = m.group('units') + try: + exponent = [u'B', u'KB', u'MB', u'GB', u'TB', u'PB', u'EB', u'ZB', u'YB'].index(units.upper()) + except ValueError: + return 0 + size = float(m.group('size')) + return int(size * (1024 ** exponent)) + + def _formats_from_html(self, html): + FORMAT_REGEX = r''' + (?x) + <a\s+href="(?P<url>[^"]+)">(?P<quality>[^<]+)</a>\s* + <span\s+class="usage">\((?P<note>[^\)]+)\)</span>\s* + (?:<div\s+class="popup\s+rounded">\s* + <h3>File\s+size</h3>\s*(?P<filesize>.*?)\s* + </div>)? # File size part may be missing + ''' + # Extract known formats + formats = [{ + 'url': x.group('url'), + 'format_id': x.group('quality'), + 'format_note': x.group('note'), + 'format': u'%s (%s)' % (x.group('quality'), x.group('note')), + 'filesize': self._restore_bytes(x.group('filesize')), # File size is approximate + 'preference': self._known_formats.index(x.group('quality')), + 'vcodec': 'none' if x.group('note') == 'Audio only' else None, + } for x in list(re.finditer(FORMAT_REGEX, html)) if x.group('quality') in self._known_formats] + + self._sort_formats(formats) + + return formats + + def _extract_title(self, html): + title = self._html_search_meta(u'title', html, u'title') + if title is None: + title = self._og_search_title(html) + TITLE_SUFFIX = u' (Channel 9)' + if title is not None and title.endswith(TITLE_SUFFIX): + title = title[:-len(TITLE_SUFFIX)] + return title + + def _extract_description(self, html): + DESCRIPTION_REGEX = r'''(?sx) + <div\s+class="entry-content">\s* + <div\s+id="entry-body">\s* + (?P<description>.+?)\s* + </div>\s* + </div> + ''' + m = re.search(DESCRIPTION_REGEX, html) + if m is not None: + return m.group('description') + return self._html_search_meta(u'description', html, u'description') + + def _extract_duration(self, html): + m = re.search(r'data-video_duration="(?P<hours>\d{2}):(?P<minutes>\d{2}):(?P<seconds>\d{2})"', html) + return ((int(m.group('hours')) * 60 * 60) + (int(m.group('minutes')) * 60) + int(m.group('seconds'))) if m else None + + def _extract_slides(self, html): + m = re.search(r'<a href="(?P<slidesurl>[^"]+)" class="slides">Slides</a>', html) + return m.group('slidesurl') if m is not None else None + + def _extract_zip(self, html): + m = re.search(r'<a href="(?P<zipurl>[^"]+)" class="zip">Zip</a>', html) + return m.group('zipurl') if m is not None else None + + def _extract_avg_rating(self, html): + m = re.search(r'<p class="avg-rating">Avg Rating: <span>(?P<avgrating>[^<]+)</span></p>', html) + return float(m.group('avgrating')) if m is not None else 0 + + def _extract_rating_count(self, html): + m = re.search(r'<div class="rating-count">\((?P<ratingcount>[^<]+)\)</div>', html) + return int(self._fix_count(m.group('ratingcount'))) if m is not None else 0 + + def _extract_view_count(self, html): + m = re.search(r'<li class="views">\s*<span class="count">(?P<viewcount>[^<]+)</span> Views\s*</li>', html) + return int(self._fix_count(m.group('viewcount'))) if m is not None else 0 + + def _extract_comment_count(self, html): + m = re.search(r'<li class="comments">\s*<a href="#comments">\s*<span class="count">(?P<commentcount>[^<]+)</span> Comments\s*</a>\s*</li>', html) + return int(self._fix_count(m.group('commentcount'))) if m is not None else 0 + + def _fix_count(self, count): + return int(str(count).replace(',', '')) if count is not None else None + + def _extract_authors(self, html): + m = re.search(r'(?s)<li class="author">(.*?)</li>', html) + if m is None: + return None + return re.findall(r'<a href="/Niners/[^"]+">([^<]+)</a>', m.group(1)) + + def _extract_session_code(self, html): + m = re.search(r'<li class="code">\s*(?P<code>.+?)\s*</li>', html) + return m.group('code') if m is not None else None + + def _extract_session_day(self, html): + m = re.search(r'<li class="day">\s*<a href="/Events/[^"]+">(?P<day>[^<]+)</a>\s*</li>', html) + return m.group('day') if m is not None else None + + def _extract_session_room(self, html): + m = re.search(r'<li class="room">\s*(?P<room>.+?)\s*</li>', html) + return m.group('room') if m is not None else None + + def _extract_session_speakers(self, html): + return re.findall(r'<a href="/Events/Speakers/[^"]+">([^<]+)</a>', html) + + def _extract_content(self, html, content_path): + # Look for downloadable content + formats = self._formats_from_html(html) + slides = self._extract_slides(html) + zip_ = self._extract_zip(html) + + # Nothing to download + if len(formats) == 0 and slides is None and zip_ is None: + self._downloader.report_warning(u'None of recording, slides or zip are available for %s' % content_path) + return + + # Extract meta + title = self._extract_title(html) + description = self._extract_description(html) + thumbnail = self._og_search_thumbnail(html) + duration = self._extract_duration(html) + avg_rating = self._extract_avg_rating(html) + rating_count = self._extract_rating_count(html) + view_count = self._extract_view_count(html) + comment_count = self._extract_comment_count(html) + + common = {'_type': 'video', + 'id': content_path, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'avg_rating': avg_rating, + 'rating_count': rating_count, + 'view_count': view_count, + 'comment_count': comment_count, + } + + result = [] + + if slides is not None: + d = common.copy() + d.update({ 'title': title + '-Slides', 'url': slides }) + result.append(d) + + if zip_ is not None: + d = common.copy() + d.update({ 'title': title + '-Zip', 'url': zip_ }) + result.append(d) + + if len(formats) > 0: + d = common.copy() + d.update({ 'title': title, 'formats': formats }) + result.append(d) + + return result + + def _extract_entry_item(self, html, content_path): + contents = self._extract_content(html, content_path) + if contents is None: + return contents + + authors = self._extract_authors(html) + + for content in contents: + content['authors'] = authors + + return contents + + def _extract_session(self, html, content_path): + contents = self._extract_content(html, content_path) + if contents is None: + return contents + + session_meta = {'session_code': self._extract_session_code(html), + 'session_day': self._extract_session_day(html), + 'session_room': self._extract_session_room(html), + 'session_speakers': self._extract_session_speakers(html), + } + + for content in contents: + content.update(session_meta) + + return contents + + def _extract_list(self, content_path): + rss = self._download_xml(self._RSS_URL % content_path, content_path, u'Downloading RSS') + entries = [self.url_result(session_url.text, 'Channel9') + for session_url in rss.findall('./channel/item/link')] + title_text = rss.find('./channel/title').text + return self.playlist_result(entries, content_path, title_text) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + content_path = mobj.group('contentpath') + + webpage = self._download_webpage(url, content_path, u'Downloading web page') + + page_type_m = re.search(r'<meta name="Search.PageType" content="(?P<pagetype>[^"]+)"/>', webpage) + if page_type_m is None: + raise ExtractorError(u'Search.PageType not found, don\'t know how to process this page', expected=True) + + page_type = page_type_m.group('pagetype') + if page_type == 'List': # List page, may contain list of 'item'-like objects + return self._extract_list(content_path) + elif page_type == 'Entry.Item': # Any 'item'-like page, may contain downloadable content + return self._extract_entry_item(webpage, content_path) + elif page_type == 'Session': # Event session page, may contain downloadable content + return self._extract_session(webpage, content_path) + else: + raise ExtractorError(u'Unexpected Search.PageType %s' % page_type, expected=True) \ No newline at end of file diff --git a/youtube_dl/extractor/clipfish.py b/youtube_dl/extractor/clipfish.py new file mode 100644 index 000000000..43efb08bf --- /dev/null +++ b/youtube_dl/extractor/clipfish.py @@ -0,0 +1,58 @@ +import re +import time +import xml.etree.ElementTree + +from .common import InfoExtractor +from ..utils import ExtractorError + + +class ClipfishIE(InfoExtractor): + IE_NAME = u'clipfish' + + _VALID_URL = r'^https?://(?:www\.)?clipfish\.de/.*?/video/(?P<id>[0-9]+)/' + _TEST = { + u'url': u'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/', + u'file': u'3966754.mp4', + u'md5': u'2521cd644e862936cf2e698206e47385', + u'info_dict': { + u'title': u'FIFA 14 - E3 2013 Trailer', + u'duration': 82, + }, + u'skip': 'Blocked in the US' + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group(1) + + info_url = ('http://www.clipfish.de/devxml/videoinfo/%s?ts=%d' % + (video_id, int(time.time()))) + doc = self._download_xml( + info_url, video_id, note=u'Downloading info page') + title = doc.find('title').text + video_url = doc.find('filename').text + if video_url is None: + xml_bytes = xml.etree.ElementTree.tostring(doc) + raise ExtractorError(u'Cannot find video URL in document %r' % + xml_bytes) + thumbnail = doc.find('imageurl').text + duration_str = doc.find('duration').text + m = re.match( + r'^(?P<hours>[0-9]+):(?P<minutes>[0-9]{2}):(?P<seconds>[0-9]{2}):(?P<ms>[0-9]*)$', + duration_str) + if m: + duration = ( + (int(m.group('hours')) * 60 * 60) + + (int(m.group('minutes')) * 60) + + (int(m.group('seconds'))) + ) + else: + duration = None + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'thumbnail': thumbnail, + 'duration': duration, + } diff --git a/youtube_dl/extractor/clipsyndicate.py b/youtube_dl/extractor/clipsyndicate.py new file mode 100644 index 000000000..9ab6a4ab6 --- /dev/null +++ b/youtube_dl/extractor/clipsyndicate.py @@ -0,0 +1,50 @@ +import re + +from .common import InfoExtractor +from ..utils import ( + find_xpath_attr, + fix_xml_ampersands +) + + +class ClipsyndicateIE(InfoExtractor): + _VALID_URL = r'http://www\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)' + + _TEST = { + u'url': u'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe', + u'md5': u'4d7d549451bad625e0ff3d7bd56d776c', + u'info_dict': { + u'id': u'4629301', + u'ext': u'mp4', + u'title': u'Brick Briscoe', + u'duration': 612, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + js_player = self._download_webpage( + 'http://eplayer.clipsyndicate.com/embed/player.js?va_id=%s' % video_id, + video_id, u'Downlaoding player') + # it includes a required token + flvars = self._search_regex(r'flvars: "(.*?)"', js_player, u'flvars') + + pdoc = self._download_xml( + 'http://eplayer.clipsyndicate.com/osmf/playlist?%s' % flvars, + video_id, u'Downloading video info', + transform_source=fix_xml_ampersands) + + track_doc = pdoc.find('trackList/track') + def find_param(name): + node = find_xpath_attr(track_doc, './/param', 'name', name) + if node is not None: + return node.attrib['value'] + + return { + 'id': video_id, + 'title': find_param('title'), + 'url': track_doc.find('location').text, + 'thumbnail': find_param('thumbnail'), + 'duration': int(find_param('duration')), + } diff --git a/youtube_dl/extractor/cmt.py b/youtube_dl/extractor/cmt.py new file mode 100644 index 000000000..88e0e9aba --- /dev/null +++ b/youtube_dl/extractor/cmt.py @@ -0,0 +1,19 @@ +from .mtv import MTVIE + +class CMTIE(MTVIE): + IE_NAME = u'cmt.com' + _VALID_URL = r'https?://www\.cmt\.com/videos/.+?/(?P<videoid>[^/]+)\.jhtml' + _FEED_URL = 'http://www.cmt.com/sitewide/apps/player/embed/rss/' + + _TESTS = [ + { + u'url': u'http://www.cmt.com/videos/garth-brooks/989124/the-call-featuring-trisha-yearwood.jhtml#artist=30061', + u'md5': u'e6b7ef3c4c45bbfae88061799bbba6c2', + u'info_dict': { + u'id': u'989124', + u'ext': u'mp4', + u'title': u'Garth Brooks - "The Call (featuring Trisha Yearwood)"', + u'description': u'Blame It All On My Roots', + }, + }, + ] diff --git a/youtube_dl/extractor/cnn.py b/youtube_dl/extractor/cnn.py index 34adf6dda..80bf59ade 100644 --- a/youtube_dl/extractor/cnn.py +++ b/youtube_dl/extractor/cnn.py @@ -1,8 +1,12 @@ +from __future__ import unicode_literals + import re -import xml.etree.ElementTree from .common import InfoExtractor -from ..utils import determine_ext +from ..utils import ( + int_or_none, + parse_duration, +) class CNNIE(InfoExtractor): @@ -10,21 +14,24 @@ class CNNIE(InfoExtractor): (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn|(?=&)))''' _TESTS = [{ - u'url': u'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn', - u'file': u'sports_2013_06_09_nadal-1-on-1.cnn.mp4', - u'md5': u'3e6121ea48df7e2259fe73a0628605c4', - u'info_dict': { - u'title': u'Nadal wins 8th French Open title', - u'description': u'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.', + 'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn', + 'file': 'sports_2013_06_09_nadal-1-on-1.cnn.mp4', + 'md5': '3e6121ea48df7e2259fe73a0628605c4', + 'info_dict': { + 'title': 'Nadal wins 8th French Open title', + 'description': 'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.', + 'duration': 135, + 'upload_date': '20130609', }, }, { - u"url": u"http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29", - u"file": u"us_2013_08_21_sot-student-gives-epic-speech.georgia-institute-of-technology.mp4", - u"md5": u"b5cc60c60a3477d185af8f19a2a26f4e", - u"info_dict": { - u"title": "Student's epic speech stuns new freshmen", - u"description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"" + "url": "http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29", + "file": "us_2013_08_21_sot-student-gives-epic-speech.georgia-institute-of-technology.mp4", + "md5": "b5cc60c60a3477d185af8f19a2a26f4e", + "info_dict": { + "title": "Student's epic speech stuns new freshmen", + "description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"", + "upload_date": "20130821", } }] @@ -32,27 +39,62 @@ class CNNIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) path = mobj.group('path') page_title = mobj.group('title') - info_url = u'http://cnn.com/video/data/3.0/%s/index.xml' % path - info_xml = self._download_webpage(info_url, page_title) - info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8')) + info_url = 'http://cnn.com/video/data/3.0/%s/index.xml' % path + info = self._download_xml(info_url, page_title) formats = [] + rex = re.compile(r'''(?x) + (?P<width>[0-9]+)x(?P<height>[0-9]+) + (?:_(?P<bitrate>[0-9]+)k)? + ''') for f in info.findall('files/file'): - mf = re.match(r'(\d+)x(\d+)(?:_(.*)k)?',f.attrib['bitrate']) - if mf is not None: - formats.append((int(mf.group(1)), int(mf.group(2)), int(mf.group(3) or 0), f.text)) - formats = sorted(formats) - (_,_,_, video_path) = formats[-1] - video_url = 'http://ht.cdn.turner.com/cnn/big%s' % video_path + video_url = 'http://ht.cdn.turner.com/cnn/big%s' % (f.text.strip()) + fdct = { + 'format_id': f.attrib['bitrate'], + 'url': video_url, + } + + mf = rex.match(f.attrib['bitrate']) + if mf: + fdct['width'] = int(mf.group('width')) + fdct['height'] = int(mf.group('height')) + fdct['tbr'] = int_or_none(mf.group('bitrate')) + else: + mf = rex.search(f.text) + if mf: + fdct['width'] = int(mf.group('width')) + fdct['height'] = int(mf.group('height')) + fdct['tbr'] = int_or_none(mf.group('bitrate')) + else: + mi = re.match(r'ios_(audio|[0-9]+)$', f.attrib['bitrate']) + if mi: + if mi.group(1) == 'audio': + fdct['vcodec'] = 'none' + fdct['ext'] = 'm4a' + else: + fdct['tbr'] = int(mi.group(1)) + + formats.append(fdct) + + self._sort_formats(formats) thumbnails = sorted([((int(t.attrib['height']),int(t.attrib['width'])), t.text) for t in info.findall('images/image')]) thumbs_dict = [{'resolution': res, 'url': t_url} for (res, t_url) in thumbnails] - return {'id': info.attrib['id'], - 'title': info.find('headline').text, - 'url': video_url, - 'ext': determine_ext(video_url), - 'thumbnail': thumbnails[-1][1], - 'thumbnails': thumbs_dict, - 'description': info.find('description').text, - } + metas_el = info.find('metas') + upload_date = ( + metas_el.attrib.get('version') if metas_el is not None else None) + + duration_el = info.find('length') + duration = parse_duration(duration_el.text) + + return { + 'id': info.attrib['id'], + 'title': info.find('headline').text, + 'formats': formats, + 'thumbnail': thumbnails[-1][1], + 'thumbnails': thumbs_dict, + 'description': info.find('description').text, + 'duration': duration, + 'upload_date': upload_date, + } diff --git a/youtube_dl/extractor/collegehumor.py b/youtube_dl/extractor/collegehumor.py index 8d4c93d6d..d10b7bd0c 100644 --- a/youtube_dl/extractor/collegehumor.py +++ b/youtube_dl/extractor/collegehumor.py @@ -1,87 +1,68 @@ +from __future__ import unicode_literals + +import json import re -import xml.etree.ElementTree from .common import InfoExtractor -from ..utils import ( - compat_urllib_parse_urlparse, - determine_ext, - - ExtractorError, -) class CollegeHumorIE(InfoExtractor): _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/(video|embed|e)/(?P<videoid>[0-9]+)/?(?P<shorttitle>.*)$' _TESTS = [{ - u'url': u'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe', - u'file': u'6902724.mp4', - u'md5': u'1264c12ad95dca142a9f0bf7968105a0', - u'info_dict': { - u'title': u'Comic-Con Cosplay Catastrophe', - u'description': u'Fans get creative this year at San Diego. Too creative. And yes, that\'s really Joss Whedon.', + 'url': 'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe', + 'file': '6902724.mp4', + 'md5': 'dcc0f5c1c8be98dc33889a191f4c26bd', + 'info_dict': { + 'title': 'Comic-Con Cosplay Catastrophe', + 'description': 'Fans get creative this year at San Diego. Too', + 'age_limit': 13, }, }, { - u'url': u'http://www.collegehumor.com/video/3505939/font-conference', - u'file': u'3505939.mp4', - u'md5': u'c51ca16b82bb456a4397987791a835f5', - u'info_dict': { - u'title': u'Font Conference', - u'description': u'This video wasn\'t long enough, so we made it double-spaced.', + 'url': 'http://www.collegehumor.com/video/3505939/font-conference', + 'file': '3505939.mp4', + 'md5': '72fa701d8ef38664a4dbb9e2ab721816', + 'info_dict': { + 'title': 'Font Conference', + 'description': 'This video wasn\'t long enough, so we made it double-spaced.', + 'age_limit': 10, }, }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) video_id = mobj.group('videoid') - info = { - 'id': video_id, - 'uploader': None, - 'upload_date': None, - } + jsonUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id + '.json' + data = json.loads(self._download_webpage( + jsonUrl, video_id, 'Downloading info JSON')) + vdata = data['video'] - self.report_extraction(video_id) - xmlUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id - metaXml = self._download_webpage(xmlUrl, video_id, - u'Downloading info XML', - u'Unable to download video info XML') - - mdoc = xml.etree.ElementTree.fromstring(metaXml) - try: - videoNode = mdoc.findall('./video')[0] - youtubeIdNode = videoNode.find('./youtubeID') - if youtubeIdNode is not None: - return self.url_result(youtubeIdNode.text, 'Youtube') - info['description'] = videoNode.findall('./description')[0].text - info['title'] = videoNode.findall('./caption')[0].text - info['thumbnail'] = videoNode.findall('./thumbnail')[0].text - next_url = videoNode.findall('./file')[0].text - except IndexError: - raise ExtractorError(u'Invalid metadata XML file') - - if next_url.endswith(u'manifest.f4m'): - manifest_url = next_url + '?hdcore=2.10.3' - manifestXml = self._download_webpage(manifest_url, video_id, - u'Downloading XML manifest', - u'Unable to download video info XML') - - adoc = xml.etree.ElementTree.fromstring(manifestXml) - try: - media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0] - node_id = media_node.attrib['url'] - video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text - except IndexError as err: - raise ExtractorError(u'Invalid manifest file') - url_pr = compat_urllib_parse_urlparse(info['thumbnail']) - info['url'] = url_pr.scheme + '://' + url_pr.netloc + video_id[:-2].replace('.csmil','').replace(',','') - info['ext'] = 'mp4' + AGE_LIMITS = {'nc17': 18, 'r': 18, 'pg13': 13, 'pg': 10, 'g': 0} + rating = vdata.get('rating') + if rating: + age_limit = AGE_LIMITS.get(rating.lower()) else: - # Old-style direct links - info['url'] = next_url - info['ext'] = determine_ext(info['url']) + age_limit = None # None = No idea - return info + PREFS = {'high_quality': 2, 'low_quality': 0} + formats = [] + for format_key in ('mp4', 'webm'): + for qname, qurl in vdata[format_key].items(): + formats.append({ + 'format_id': format_key + '_' + qname, + 'url': qurl, + 'format': format_key, + 'preference': PREFS.get(qname), + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': vdata['title'], + 'description': vdata.get('description'), + 'thumbnail': vdata.get('thumbnail'), + 'formats': formats, + 'age_limit': age_limit, + } diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py index 69b2beece..f0ad5c9a3 100644 --- a/youtube_dl/extractor/comedycentral.py +++ b/youtube_dl/extractor/comedycentral.py @@ -1,7 +1,9 @@ +from __future__ import unicode_literals + import re -import xml.etree.ElementTree from .common import InfoExtractor +from .mtv import MTVServicesInfoExtractor from ..utils import ( compat_str, compat_urllib_parse, @@ -11,8 +13,34 @@ from ..utils import ( ) -class ComedyCentralIE(InfoExtractor): - IE_DESC = u'The Daily Show / Colbert Report' +class ComedyCentralIE(MTVServicesInfoExtractor): + _VALID_URL = r'''(?x)https?://(?:www.)?comedycentral.com/ + (video-clips|episodes|cc-studios|video-collections) + /(?P<title>.*)''' + _FEED_URL = 'http://comedycentral.com/feeds/mrss/' + + _TEST = { + 'url': 'http://www.comedycentral.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother', + 'md5': '4167875aae411f903b751a21f357f1ee', + 'info_dict': { + 'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354', + 'ext': 'mp4', + 'title': 'CC:Stand-Up|Greg Fitzsimmons: Life on Stage|Uncensored - Too Good of a Mother', + 'description': 'After a certain point, breastfeeding becomes c**kblocking.', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + title = mobj.group('title') + webpage = self._download_webpage(url, title) + mgid = self._search_regex(r'data-mgid="(?P<mgid>mgid:.*?)"', + webpage, 'mgid') + return self._get_videos_info(mgid) + + +class ComedyCentralShowsIE(InfoExtractor): + IE_DESC = 'The Daily Show / Colbert Report' # urls can be abbreviations like :thedailyshow or :colbert # urls for episodes like: # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day @@ -29,14 +57,14 @@ class ComedyCentralIE(InfoExtractor): extended-interviews/(?P<interID>[0-9]+)/playlist_tds_extended_(?P<interview_title>.*?)/.*?))) $""" _TEST = { - u'url': u'http://www.thedailyshow.com/watch/thu-december-13-2012/kristen-stewart', - u'file': u'422212.mp4', - u'md5': u'4e2f5cb088a83cd8cdb7756132f9739d', - u'info_dict': { - u"upload_date": u"20121214", - u"description": u"Kristen Stewart", - u"uploader": u"thedailyshow", - u"title": u"thedailyshow-kristen-stewart part 1" + 'url': 'http://www.thedailyshow.com/watch/thu-december-13-2012/kristen-stewart', + 'file': '422212.mp4', + 'md5': '4e2f5cb088a83cd8cdb7756132f9739d', + 'info_dict': { + "upload_date": "20121214", + "description": "Kristen Stewart", + "uploader": "thedailyshow", + "title": "thedailyshow-kristen-stewart part 1" } } @@ -68,20 +96,20 @@ class ComedyCentralIE(InfoExtractor): def _transform_rtmp_url(rtmp_video_url): m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp.comedystor/.*)$', rtmp_video_url) if not m: - raise ExtractorError(u'Cannot transform RTMP url') + raise ExtractorError('Cannot transform RTMP url') base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/' return base + m.group('finalid') def _real_extract(self, url): mobj = re.match(self._VALID_URL, url, re.VERBOSE) if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) + raise ExtractorError('Invalid URL: %s' % url) if mobj.group('shortname'): if mobj.group('shortname') in ('tds', 'thedailyshow'): - url = u'http://www.thedailyshow.com/full-episodes/' + url = 'http://www.thedailyshow.com/full-episodes/' else: - url = u'http://www.colbertnation.com/full-episodes/' + url = 'http://www.colbertnation.com/full-episodes/' mobj = re.match(self._VALID_URL, url, re.VERBOSE) assert mobj is not None @@ -107,9 +135,9 @@ class ComedyCentralIE(InfoExtractor): url = htmlHandle.geturl() mobj = re.match(self._VALID_URL, url, re.VERBOSE) if mobj is None: - raise ExtractorError(u'Invalid redirected URL: ' + url) + raise ExtractorError('Invalid redirected URL: ' + url) if mobj.group('episode') == '': - raise ExtractorError(u'Redirected URL is still not specific: ' + url) + raise ExtractorError('Redirected URL is still not specific: ' + url) epTitle = mobj.group('episode') mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage) @@ -121,19 +149,18 @@ class ComedyCentralIE(InfoExtractor): altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage) if len(altMovieParams) == 0: - raise ExtractorError(u'unable to find Flash URL in webpage ' + url) + raise ExtractorError('unable to find Flash URL in webpage ' + url) else: mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])] uri = mMovieParams[0][1] indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri}) - indexXml = self._download_webpage(indexUrl, epTitle, - u'Downloading show index', - u'unable to download episode index') + idoc = self._download_xml(indexUrl, epTitle, + 'Downloading show index', + 'unable to download episode index') results = [] - idoc = xml.etree.ElementTree.fromstring(indexXml) itemEls = idoc.findall('.//item') for partNum,itemEl in enumerate(itemEls): mediaId = itemEl.findall('./guid')[0].text @@ -144,17 +171,16 @@ class ComedyCentralIE(InfoExtractor): configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' + compat_urllib_parse.urlencode({'uri': mediaId})) - configXml = self._download_webpage(configUrl, epTitle, - u'Downloading configuration for %s' % shortMediaId) + cdoc = self._download_xml(configUrl, epTitle, + 'Downloading configuration for %s' % shortMediaId) - cdoc = xml.etree.ElementTree.fromstring(configXml) turls = [] for rendition in cdoc.findall('.//rendition'): finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text) turls.append(finfo) if len(turls) == 0: - self._downloader.report_error(u'unable to download ' + mediaId + ': No videos found') + self._downloader.report_error('unable to download ' + mediaId + ': No videos found') continue formats = [] @@ -168,8 +194,8 @@ class ComedyCentralIE(InfoExtractor): 'width': w, }) - effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1) - info = { + effTitle = showId + '-' + epTitle + ' part ' + compat_str(partNum+1) + results.append({ 'id': shortMediaId, 'formats': formats, 'uploader': showId, @@ -177,11 +203,6 @@ class ComedyCentralIE(InfoExtractor): 'title': effTitle, 'thumbnail': None, 'description': compat_str(officialTitle), - } - - # TODO: Remove when #980 has been merged - info.update(info['formats'][-1]) - - results.append(info) + }) return results diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index f787d0a3c..582eb4f5b 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1,14 +1,17 @@ import base64 +import hashlib +import json import os import re import socket import sys import netrc +import xml.etree.ElementTree from ..utils import ( compat_http_client, compat_urllib_error, - compat_urllib_request, + compat_urllib_parse_urlparse, compat_str, clean_html, @@ -18,6 +21,8 @@ from ..utils import ( sanitize_filename, unescapeHTML, ) +_NO_DEFAULT = object() + class InfoExtractor(object): """Information Extractor class. @@ -33,15 +38,54 @@ class InfoExtractor(object): The dictionaries must include the following fields: id: Video identifier. - url: Final video URL. title: Video title, unescaped. - ext: Video filename extension. - Instead of url and ext, formats can also specified. + Additionally, it must contain either a formats entry or a url one: + + formats: A list of dictionaries for each format available, ordered + from worst to best quality. + + Potential fields: + * url Mandatory. The URL of the video file + * ext Will be calculated from url if missing + * format A human-readable description of the format + ("mp4 container with h264/opus"). + Calculated from the format_id, width, height. + and format_note fields if missing. + * format_id A short description of the format + ("mp4_h264_opus" or "19"). + Technically optional, but strongly recommended. + * format_note Additional info about the format + ("3D" or "DASH video") + * width Width of the video, if known + * height Height of the video, if known + * resolution Textual description of width and height + * tbr Average bitrate of audio and video in KBit/s + * abr Average audio bitrate in KBit/s + * acodec Name of the audio codec in use + * vbr Average video bitrate in KBit/s + * vcodec Name of the video codec in use + * filesize The number of bytes, if known in advance + * player_url SWF Player URL (used for rtmpdump). + * protocol The protocol that will be used for the actual + download, lower-case. + "http", "https", "rtsp", "rtmp" or so. + * preference Order number of this format. If this field is + present and not None, the formats get sorted + by this field. + -1 for default (order by other properties), + -2 or smaller for less than default. + * quality Order number of the video quality of this + format, irrespective of the file format. + -1 for default (order by other properties), + -2 or smaller for less than default. + url: Final video URL. + ext: Video filename extension. + format: The video format, defaults to ext (used for --get-format) + player_url: SWF Player URL (used for rtmpdump). The following fields are optional: - format: The video format, defaults to ext (used for --get-format) thumbnails: A list of dictionaries (with the entries "resolution" and "url") for the varying thumbnails thumbnail: Full URL to a video thumbnail image. @@ -50,31 +94,14 @@ class InfoExtractor(object): upload_date: Video upload date (YYYYMMDD). uploader_id: Nickname or id of the video uploader. location: Physical location of the video. - player_url: SWF Player URL (used for rtmpdump). subtitles: The subtitle file contents as a dictionary in the format {language: subtitles}. + duration: Length of the video in seconds, as an integer. view_count: How many users have watched the video on the platform. - urlhandle: [internal] The urlHandle to be used to download the file, - like returned by urllib.request.urlopen + like_count: Number of positive ratings of the video + dislike_count: Number of negative ratings of the video + comment_count: Number of comments on the video age_limit: Age restriction for the video, as an integer (years) - formats: A list of dictionaries for each format available, it must - be ordered from worst to best quality. Potential fields: - * url Mandatory. The URL of the video file - * ext Will be calculated from url if missing - * format A human-readable description of the format - ("mp4 container with h264/opus"). - Calculated from the format_id, width, height. - and format_note fields if missing. - * format_id A short description of the format - ("mp4_h264_opus" or "19") - * format_note Additional info about the format - ("3D" or "DASH video") - * width Width of the video, if known - * height Height of the video, if known - * abr Average audio bitrate in KBit/s - * acodec Name of the audio codec in use - * vbr Average video bitrate in KBit/s - * vcodec Name of the video codec in use webpage_url: The url to the video webpage, if given to youtube-dl it should allow to get the same result again. (It will be set by YoutubeDL if it's missing) @@ -149,27 +176,40 @@ class InfoExtractor(object): def IE_NAME(self): return type(self).__name__[:-2] - def _request_webpage(self, url_or_request, video_id, note=None, errnote=None): + def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True): """ Returns the response handle """ if note is None: self.report_download_webpage(video_id) elif note is not False: - self.to_screen(u'%s: %s' % (video_id, note)) + if video_id is None: + self.to_screen(u'%s' % (note,)) + else: + self.to_screen(u'%s: %s' % (video_id, note)) try: - return compat_urllib_request.urlopen(url_or_request) + return self._downloader.urlopen(url_or_request) except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + if errnote is False: + return False if errnote is None: errnote = u'Unable to download webpage' - raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2], cause=err) + errmsg = u'%s: %s' % (errnote, compat_str(err)) + if fatal: + raise ExtractorError(errmsg, sys.exc_info()[2], cause=err) + else: + self._downloader.report_warning(errmsg) + return False - def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None): + def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True): """ Returns a tuple (page content as string, URL handle) """ # Strip hashes from the URL (#1038) if isinstance(url_or_request, (compat_str, str)): url_or_request = url_or_request.partition('#')[0] - urlh = self._request_webpage(url_or_request, video_id, note, errnote) + urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal) + if urlh is False: + assert not fatal + return False content_type = urlh.headers.get('Content-Type', '') webpage_bytes = urlh.read() m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type) @@ -180,6 +220,8 @@ class InfoExtractor(object): webpage_bytes[:1024]) if m: encoding = m.group(1).decode('ascii') + elif webpage_bytes.startswith(b'\xff\xfe'): + encoding = 'utf-16' else: encoding = 'utf-8' if self._downloader.params.get('dump_intermediate_pages', False): @@ -195,6 +237,9 @@ class InfoExtractor(object): url = url_or_request.get_full_url() except AttributeError: url = url_or_request + if len(url) > 200: + h = u'___' + hashlib.md5(url).hexdigest() + url = url[:200 - len(h)] + h raw_filename = ('%s_%s.dump' % (video_id, url)) filename = sanitize_filename(raw_filename, restricted=True) self.to_screen(u'Saving request to ' + filename) @@ -204,9 +249,37 @@ class InfoExtractor(object): content = webpage_bytes.decode(encoding, 'replace') return (content, urlh) - def _download_webpage(self, url_or_request, video_id, note=None, errnote=None): + def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True): """ Returns the data of the page as a string """ - return self._download_webpage_handle(url_or_request, video_id, note, errnote)[0] + res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal) + if res is False: + return res + else: + content, _ = res + return content + + def _download_xml(self, url_or_request, video_id, + note=u'Downloading XML', errnote=u'Unable to download XML', + transform_source=None): + """Return the xml as an xml.etree.ElementTree.Element""" + xml_string = self._download_webpage(url_or_request, video_id, note, errnote) + if transform_source: + xml_string = transform_source(xml_string) + return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8')) + + def _download_json(self, url_or_request, video_id, + note=u'Downloading JSON metadata', + errnote=u'Unable to download JSON metadata'): + json_string = self._download_webpage(url_or_request, video_id, note, errnote) + try: + return json.loads(json_string) + except ValueError as ve: + raise ExtractorError('Failed to download JSON', cause=ve) + + def report_warning(self, msg, video_id=None): + idstr = u'' if video_id is None else u'%s: ' % video_id + self._downloader.report_warning( + u'[%s] %s%s' % (self.IE_NAME, idstr, msg)) def to_screen(self, msg): """Print msg to screen, prefixing it with '[ie_name]'""" @@ -229,14 +302,18 @@ class InfoExtractor(object): self.to_screen(u'Logging in') #Methods for following #608 - def url_result(self, url, ie=None): + @staticmethod + def url_result(url, ie=None, video_id=None): """Returns a url that points to a page that should be processed""" #TODO: ie should be the class used for getting the info video_info = {'_type': 'url', 'url': url, 'ie_key': ie} + if video_id is not None: + video_info['id'] = video_id return video_info - def playlist_result(self, entries, playlist_id=None, playlist_title=None): + @staticmethod + def playlist_result(entries, playlist_id=None, playlist_title=None): """Returns a playlist""" video_info = {'_type': 'playlist', 'entries': entries} @@ -246,7 +323,7 @@ class InfoExtractor(object): video_info['title'] = playlist_title return video_info - def _search_regex(self, pattern, string, name, default=None, fatal=True, flags=0): + def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0): """ Perform a regex search on the given string, using a single or a list of patterns returning the first matching group. @@ -260,7 +337,7 @@ class InfoExtractor(object): mobj = re.search(p, string, flags) if mobj: break - if sys.stderr.isatty() and os.name != 'nt': + if os.name != 'nt' and sys.stderr.isatty(): _name = u'\033[0;34m%s\033[0m' % name else: _name = name @@ -268,7 +345,7 @@ class InfoExtractor(object): if mobj: # return the first matching group return next(g for g in mobj.groups() if g is not None) - elif default is not None: + elif default is not _NO_DEFAULT: return default elif fatal: raise RegexNotFoundError(u'Unable to extract %s' % _name) @@ -277,7 +354,7 @@ class InfoExtractor(object): u'please report this issue on http://yt-dl.org/bug' % _name) return None - def _html_search_regex(self, pattern, string, name, default=None, fatal=True, flags=0): + def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0): """ Like _search_regex, but strips HTML tags and unescapes entities. """ @@ -321,7 +398,7 @@ class InfoExtractor(object): @staticmethod def _og_regexes(prop): content_re = r'content=(?:"([^>]+?)"|\'(.+?)\')' - property_re = r'property=[\'"]og:%s[\'"]' % re.escape(prop) + property_re = r'(?:name|property)=[\'"]og:%s[\'"]' % re.escape(prop) template = r'<meta[^>]+?%s[^>]+?%s' return [ template % (property_re, content_re), @@ -350,6 +427,18 @@ class InfoExtractor(object): if secure: regexes = self._og_regexes('video:secure_url') + regexes return self._html_search_regex(regexes, html, name, **kargs) + def _html_search_meta(self, name, html, display_name=None): + if display_name is None: + display_name = name + return self._html_search_regex( + r'''(?ix)<meta + (?=[^>]+(?:itemprop|name|property)=["\']%s["\']) + [^>]+content=["\']([^"\']+)["\']''' % re.escape(name), + html, display_name, fatal=False) + + def _dc_search_uploader(self, html): + return self._html_search_meta('dc.creator', html, 'uploader') + def _rta_search(self, html): # See http://www.rtalabel.org/index.php?content=howtofaq#single if re.search(r'(?ix)<meta\s+name="rating"\s+' @@ -358,6 +447,75 @@ class InfoExtractor(object): return 18 return 0 + def _media_rating_search(self, html): + # See http://www.tjg-designs.com/WP/metadata-code-examples-adding-metadata-to-your-web-pages/ + rating = self._html_search_meta('rating', html) + + if not rating: + return None + + RATING_TABLE = { + 'safe for kids': 0, + 'general': 8, + '14 years': 14, + 'mature': 17, + 'restricted': 19, + } + return RATING_TABLE.get(rating.lower(), None) + + def _sort_formats(self, formats): + def _formats_key(f): + # TODO remove the following workaround + from ..utils import determine_ext + if not f.get('ext') and 'url' in f: + f['ext'] = determine_ext(f['url']) + + preference = f.get('preference') + if preference is None: + proto = f.get('protocol') + if proto is None: + proto = compat_urllib_parse_urlparse(f.get('url', '')).scheme + + preference = 0 if proto in ['http', 'https'] else -0.1 + if f.get('ext') in ['f4f', 'f4m']: # Not yet supported + preference -= 0.5 + + if f.get('vcodec') == 'none': # audio only + if self._downloader.params.get('prefer_free_formats'): + ORDER = [u'aac', u'mp3', u'm4a', u'webm', u'ogg', u'opus'] + else: + ORDER = [u'webm', u'opus', u'ogg', u'mp3', u'aac', u'm4a'] + ext_preference = 0 + try: + audio_ext_preference = ORDER.index(f['ext']) + except ValueError: + audio_ext_preference = -1 + else: + if self._downloader.params.get('prefer_free_formats'): + ORDER = [u'flv', u'mp4', u'webm'] + else: + ORDER = [u'webm', u'flv', u'mp4'] + try: + ext_preference = ORDER.index(f['ext']) + except ValueError: + ext_preference = -1 + audio_ext_preference = 0 + + return ( + preference, + f.get('quality') if f.get('quality') is not None else -1, + f.get('height') if f.get('height') is not None else -1, + f.get('width') if f.get('width') is not None else -1, + ext_preference, + f.get('tbr') if f.get('tbr') is not None else -1, + f.get('vbr') if f.get('vbr') is not None else -1, + f.get('abr') if f.get('abr') is not None else -1, + audio_ext_preference, + f.get('filesize') if f.get('filesize') is not None else -1, + f.get('format_id'), + ) + formats.sort(key=_formats_key) + class SearchInfoExtractor(InfoExtractor): """ diff --git a/youtube_dl/extractor/condenast.py b/youtube_dl/extractor/condenast.py index f336a3c62..03b75b80d 100644 --- a/youtube_dl/extractor/condenast.py +++ b/youtube_dl/extractor/condenast.py @@ -1,4 +1,5 @@ # coding: utf-8 +from __future__ import unicode_literals import re import json @@ -20,30 +21,31 @@ class CondeNastIE(InfoExtractor): # The keys are the supported sites and the values are the name to be shown # to the user and in the extractor description. - _SITES = {'wired': u'WIRED', - 'gq': u'GQ', - 'vogue': u'Vogue', - 'glamour': u'Glamour', - 'wmagazine': u'W Magazine', - 'vanityfair': u'Vanity Fair', - } + _SITES = { + 'wired': 'WIRED', + 'gq': 'GQ', + 'vogue': 'Vogue', + 'glamour': 'Glamour', + 'wmagazine': 'W Magazine', + 'vanityfair': 'Vanity Fair', + } _VALID_URL = r'http://(video|www).(?P<site>%s).com/(?P<type>watch|series|video)/(?P<id>.+)' % '|'.join(_SITES.keys()) - IE_DESC = u'Condé Nast media group: %s' % ', '.join(sorted(_SITES.values())) + IE_DESC = 'Condé Nast media group: %s' % ', '.join(sorted(_SITES.values())) _TEST = { - u'url': u'http://video.wired.com/watch/3d-printed-speakers-lit-with-led', - u'file': u'5171b343c2b4c00dd0c1ccb3.mp4', - u'md5': u'1921f713ed48aabd715691f774c451f7', - u'info_dict': { - u'title': u'3D Printed Speakers Lit With LED', - u'description': u'Check out these beautiful 3D printed LED speakers. You can\'t actually buy them, but LumiGeek is working on a board that will let you make you\'re own.', + 'url': 'http://video.wired.com/watch/3d-printed-speakers-lit-with-led', + 'file': '5171b343c2b4c00dd0c1ccb3.mp4', + 'md5': '1921f713ed48aabd715691f774c451f7', + 'info_dict': { + 'title': '3D Printed Speakers Lit With LED', + 'description': 'Check out these beautiful 3D printed LED speakers. You can\'t actually buy them, but LumiGeek is working on a board that will let you make you\'re own.', } } def _extract_series(self, url, webpage): title = self._html_search_regex(r'<div class="cne-series-info">.*?<h1>(.+?)</h1>', - webpage, u'series title', flags=re.DOTALL) + webpage, 'series title', flags=re.DOTALL) url_object = compat_urllib_parse_urlparse(url) base_url = '%s://%s' % (url_object.scheme, url_object.netloc) m_paths = re.finditer(r'<p class="cne-thumb-title">.*?<a href="(/watch/.+?)["\?]', @@ -57,39 +59,41 @@ class CondeNastIE(InfoExtractor): description = self._html_search_regex([r'<div class="cne-video-description">(.+?)</div>', r'<div class="video-post-content">(.+?)</div>', ], - webpage, u'description', + webpage, 'description', fatal=False, flags=re.DOTALL) params = self._search_regex(r'var params = {(.+?)}[;,]', webpage, - u'player params', flags=re.DOTALL) - video_id = self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, u'video id') - player_id = self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, u'player id') - target = self._search_regex(r'target: [\'"](.+?)[\'"]', params, u'target') + 'player params', flags=re.DOTALL) + video_id = self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, 'video id') + player_id = self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, 'player id') + target = self._search_regex(r'target: [\'"](.+?)[\'"]', params, 'target') data = compat_urllib_parse.urlencode({'videoId': video_id, 'playerId': player_id, 'target': target, }) base_info_url = self._search_regex(r'url = [\'"](.+?)[\'"][,;]', - webpage, u'base info url', + webpage, 'base info url', default='http://player.cnevids.com/player/loader.js?') info_url = base_info_url + data info_page = self._download_webpage(info_url, video_id, - u'Downloading video info') - video_info = self._search_regex(r'var video = ({.+?});', info_page, u'video info') + 'Downloading video info') + video_info = self._search_regex(r'var video = ({.+?});', info_page, 'video info') video_info = json.loads(video_info) - def _formats_sort_key(f): - type_ord = 1 if f['type'] == 'video/mp4' else 0 - quality_ord = 1 if f['quality'] == 'high' else 0 - return (quality_ord, type_ord) - best_format = sorted(video_info['sources'][0], key=_formats_sort_key)[-1] + formats = [{ + 'format_id': '%s-%s' % (fdata['type'].split('/')[-1], fdata['quality']), + 'url': fdata['src'], + 'ext': fdata['type'].split('/')[-1], + 'quality': 1 if fdata['quality'] == 'high' else 0, + } for fdata in video_info['sources'][0]] + self._sort_formats(formats) - return {'id': video_id, - 'url': best_format['src'], - 'ext': best_format['type'].split('/')[-1], - 'title': video_info['title'], - 'thumbnail': video_info['poster_frame'], - 'description': description, - } + return { + 'id': video_id, + 'formats': formats, + 'title': video_info['title'], + 'thumbnail': video_info['poster_frame'], + 'description': description, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py new file mode 100644 index 000000000..2b66bddbb --- /dev/null +++ b/youtube_dl/extractor/crunchyroll.py @@ -0,0 +1,171 @@ +# encoding: utf-8 +import re, base64, zlib +from hashlib import sha1 +from math import pow, sqrt, floor +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + compat_urllib_parse, + compat_urllib_request, + bytes_to_intlist, + intlist_to_bytes, + unified_strdate, + clean_html, +) +from ..aes import ( + aes_cbc_decrypt, + inc, +) + +class CrunchyrollIE(InfoExtractor): + _VALID_URL = r'(?:https?://)?(?:www\.)?(?P<url>crunchyroll\.com/[^/]*/[^/?&]*?(?P<video_id>[0-9]+))(?:[/?&]|$)' + _TESTS = [{ + u'url': u'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513', + u'file': u'645513.flv', + #u'md5': u'b1639fd6ddfaa43788c85f6d1dddd412', + u'info_dict': { + u'title': u'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!', + u'description': u'md5:2d17137920c64f2f49981a7797d275ef', + u'thumbnail': u'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg', + u'uploader': u'Yomiuri Telecasting Corporation (YTV)', + u'upload_date': u'20131013', + }, + u'params': { + # rtmp + u'skip_download': True, + }, + }] + + _FORMAT_IDS = { + u'360': (u'60', u'106'), + u'480': (u'61', u'106'), + u'720': (u'62', u'106'), + u'1080': (u'80', u'108'), + } + + def _decrypt_subtitles(self, data, iv, id): + data = bytes_to_intlist(data) + iv = bytes_to_intlist(iv) + id = int(id) + + def obfuscate_key_aux(count, modulo, start): + output = list(start) + for _ in range(count): + output.append(output[-1] + output[-2]) + # cut off start values + output = output[2:] + output = list(map(lambda x: x % modulo + 33, output)) + return output + + def obfuscate_key(key): + num1 = int(floor(pow(2, 25) * sqrt(6.9))) + num2 = (num1 ^ key) << 5 + num3 = key ^ num1 + num4 = num3 ^ (num3 >> 3) ^ num2 + prefix = intlist_to_bytes(obfuscate_key_aux(20, 97, (1, 2))) + shaHash = bytes_to_intlist(sha1(prefix + str(num4).encode(u'ascii')).digest()) + # Extend 160 Bit hash to 256 Bit + return shaHash + [0] * 12 + + key = obfuscate_key(id) + class Counter: + __value = iv + def next_value(self): + temp = self.__value + self.__value = inc(self.__value) + return temp + decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv)) + return zlib.decompress(decrypted_data) + + def _convert_subtitles_to_srt(self, subtitles): + i=1 + output = u'' + for start, end, text in re.findall(r'<event [^>]*?start="([^"]+)" [^>]*?end="([^"]+)" [^>]*?text="([^"]+)"[^>]*?>', subtitles): + start = start.replace(u'.', u',') + end = end.replace(u'.', u',') + text = clean_html(text) + text = text.replace(u'\\N', u'\n') + if not text: + continue + output += u'%d\n%s --> %s\n%s\n\n' % (i, start, end, text) + i+=1 + return output + + def _real_extract(self,url): + mobj = re.match(self._VALID_URL, url) + + webpage_url = u'http://www.' + mobj.group('url') + video_id = mobj.group(u'video_id') + webpage = self._download_webpage(webpage_url, video_id) + note_m = self._html_search_regex(r'<div class="showmedia-trailer-notice">(.+?)</div>', webpage, u'trailer-notice', default=u'') + if note_m: + raise ExtractorError(note_m) + + video_title = self._html_search_regex(r'<h1[^>]*>(.+?)</h1>', webpage, u'video_title', flags=re.DOTALL) + video_title = re.sub(r' {2,}', u' ', video_title) + video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, u'video_description', default=u'') + if not video_description: + video_description = None + video_upload_date = self._html_search_regex(r'<div>Availability for free users:(.+?)</div>', webpage, u'video_upload_date', fatal=False, flags=re.DOTALL) + if video_upload_date: + video_upload_date = unified_strdate(video_upload_date) + video_uploader = self._html_search_regex(r'<div>\s*Publisher:(.+?)</div>', webpage, u'video_uploader', fatal=False, flags=re.DOTALL) + + playerdata_url = compat_urllib_parse.unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, u'playerdata_url')) + playerdata_req = compat_urllib_request.Request(playerdata_url) + playerdata_req.data = compat_urllib_parse.urlencode({u'current_page': webpage_url}) + playerdata_req.add_header(u'Content-Type', u'application/x-www-form-urlencoded') + playerdata = self._download_webpage(playerdata_req, video_id, note=u'Downloading media info') + + stream_id = self._search_regex(r'<media_id>([^<]+)', playerdata, u'stream_id') + video_thumbnail = self._search_regex(r'<episode_image_url>([^<]+)', playerdata, u'thumbnail', fatal=False) + + formats = [] + for fmt in re.findall(r'\?p([0-9]{3,4})=1', webpage): + stream_quality, stream_format = self._FORMAT_IDS[fmt] + video_format = fmt+u'p' + streamdata_req = compat_urllib_request.Request(u'http://www.crunchyroll.com/xml/') + # urlencode doesn't work! + streamdata_req.data = u'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality='+stream_quality+u'&media%5Fid='+stream_id+u'&video%5Fformat='+stream_format + streamdata_req.add_header(u'Content-Type', u'application/x-www-form-urlencoded') + streamdata_req.add_header(u'Content-Length', str(len(streamdata_req.data))) + streamdata = self._download_webpage(streamdata_req, video_id, note=u'Downloading media info for '+video_format) + video_url = self._search_regex(r'<host>([^<]+)', streamdata, u'video_url') + video_play_path = self._search_regex(r'<file>([^<]+)', streamdata, u'video_play_path') + formats.append({ + u'url': video_url, + u'play_path': video_play_path, + u'ext': 'flv', + u'format': video_format, + u'format_id': video_format, + }) + + subtitles = {} + for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage): + sub_page = self._download_webpage(u'http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id='+sub_id,\ + video_id, note=u'Downloading subtitles for '+sub_name) + id = self._search_regex(r'id=\'([0-9]+)', sub_page, u'subtitle_id', fatal=False) + iv = self._search_regex(r'<iv>([^<]+)', sub_page, u'subtitle_iv', fatal=False) + data = self._search_regex(r'<data>([^<]+)', sub_page, u'subtitle_data', fatal=False) + if not id or not iv or not data: + continue + id = int(id) + iv = base64.b64decode(iv) + data = base64.b64decode(data) + + subtitle = self._decrypt_subtitles(data, iv, id).decode(u'utf-8') + lang_code = self._search_regex(r'lang_code=\'([^\']+)', subtitle, u'subtitle_lang_code', fatal=False) + if not lang_code: + continue + subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle) + + return { + u'id': video_id, + u'title': video_title, + u'description': video_description, + u'thumbnail': video_thumbnail, + u'uploader': video_uploader, + u'upload_date': video_upload_date, + u'subtitles': subtitles, + u'formats': formats, + } diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py index 7bf03c584..a2cbd4d8d 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -1,20 +1,25 @@ +from __future__ import unicode_literals + +import json import re from .common import InfoExtractor from ..utils import ( - compat_urllib_parse, + unescapeHTML, ) + class CSpanIE(InfoExtractor): - _VALID_URL = r'http://www.c-spanvideo.org/program/(.*)' + _VALID_URL = r'http://www\.c-spanvideo\.org/program/(.*)' + IE_DESC = 'C-SPAN' _TEST = { - u'url': u'http://www.c-spanvideo.org/program/HolderonV', - u'file': u'315139.flv', - u'md5': u'74a623266956f69e4df0068ab6c80fe4', - u'info_dict': { - u"title": u"Attorney General Eric Holder on Voting Rights Act Decision" + 'url': 'http://www.c-spanvideo.org/program/HolderonV', + 'file': '315139.mp4', + 'md5': '8e44ce11f0f725527daccc453f553eb0', + 'info_dict': { + 'title': 'Attorney General Eric Holder on Voting Rights Act Decision', + 'description': 'Attorney General Eric Holder spoke to reporters following the Supreme Court decision in [Shelby County v. Holder] in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced until Congress established new guidelines for review.', }, - u'skip': u'Requires rtmpdump' } def _real_extract(self, url): @@ -22,30 +27,22 @@ class CSpanIE(InfoExtractor): prog_name = mobj.group(1) webpage = self._download_webpage(url, prog_name) video_id = self._search_regex(r'programid=(.*?)&', webpage, 'video id') - data = compat_urllib_parse.urlencode({'programid': video_id, - 'dynamic':'1'}) - info_url = 'http://www.c-spanvideo.org/common/services/flashXml.php?' + data - video_info = self._download_webpage(info_url, video_id, u'Downloading video info') - self.report_extraction(video_id) + title = self._html_search_regex( + r'<!-- title -->\n\s*<h1[^>]*>(.*?)</h1>', webpage, 'title') + description = self._og_search_description(webpage) - title = self._html_search_regex(r'<string name="title">(.*?)</string>', - video_info, 'title') - description = self._html_search_regex(r'<meta (?:property="og:|name=")description" content="(.*?)"', - webpage, 'description', - flags=re.MULTILINE|re.DOTALL) + info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id + data_json = self._download_webpage( + info_url, video_id, 'Downloading video info') + data = json.loads(data_json) - url = self._search_regex(r'<string name="URL">(.*?)</string>', - video_info, 'video url') - url = url.replace('$(protocol)', 'rtmp').replace('$(port)', '443') - path = self._search_regex(r'<string name="path">(.*?)</string>', - video_info, 'rtmp play path') + url = unescapeHTML(data['video']['files'][0]['path']['#text']) - return {'id': video_id, - 'title': title, - 'ext': 'flv', - 'url': url, - 'play_path': path, - 'description': description, - 'thumbnail': self._og_search_thumbnail(webpage), - } + return { + 'id': video_id, + 'title': title, + 'url': url, + 'description': description, + 'thumbnail': self._og_search_thumbnail(webpage), + } diff --git a/youtube_dl/extractor/d8.py b/youtube_dl/extractor/d8.py new file mode 100644 index 000000000..6b26ff2e3 --- /dev/null +++ b/youtube_dl/extractor/d8.py @@ -0,0 +1,25 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +from .canalplus import CanalplusIE + + +class D8IE(CanalplusIE): + _VALID_URL = r'https?://www\.d8\.tv/.*?/(?P<path>.*)' + _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/d8/%s' + IE_NAME = 'd8.tv' + + _TEST = { + 'url': 'http://www.d8.tv/d8-docs-mags/pid6589-d8-campagne-intime.html', + 'file': '966289.flv', + 'info_dict': { + 'title': 'Campagne intime - Documentaire exceptionnel', + 'description': 'md5:d2643b799fb190846ae09c61e59a859f', + 'upload_date': '20131108', + }, + 'params': { + # rtmp + 'skip_download': True, + }, + 'skip': 'videos get deleted after a while', + } diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 71f5e03ee..6685c94a3 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -11,6 +11,7 @@ from ..utils import ( get_element_by_attribute, get_element_by_id, orderedSet, + str_to_int, ExtractorError, ) @@ -27,7 +28,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor): class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): """Information Extractor for Dailymotion""" - _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/(?:embed/)?video/([^/]+)' + _VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(embed|#)/)?video/(?P<id>[^/?_]+)' IE_NAME = u'dailymotion' _FORMATS = [ @@ -80,7 +81,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): # Extract id and simplified title from URL mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1).split('_')[0].split('?')[0] + video_id = mobj.group('id') url = 'http://www.dailymotion.com/video/%s' % video_id @@ -100,10 +101,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): self.to_screen(u'Vevo video detected: %s' % vevo_id) return self.url_result(u'vevo:%s' % vevo_id, ie='Vevo') - video_uploader = self._search_regex([r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', - # Looking for official user - r'<(?:span|a) .*?rel="author".*?>([^<]+?)</'], - webpage, 'video uploader', fatal=False) age_limit = self._rta_search(webpage) video_upload_date = None @@ -146,15 +143,21 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): self._list_available_subtitles(video_id, webpage) return + view_count = self._search_regex( + r'video_views_count[^>]+>\s+([\d\.,]+)', webpage, u'view count', fatal=False) + if view_count is not None: + view_count = str_to_int(view_count) + return { 'id': video_id, 'formats': formats, - 'uploader': video_uploader, + 'uploader': info['owner_screenname'], 'upload_date': video_upload_date, 'title': self._og_search_title(webpage), 'subtitles': video_subtitles, 'thumbnail': info['thumbnail_url'], 'age_limit': age_limit, + 'view_count': view_count, } def _get_available_subtitles(self, video_id, webpage): diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py index a804e83bd..4876ecb48 100644 --- a/youtube_dl/extractor/daum.py +++ b/youtube_dl/extractor/daum.py @@ -1,6 +1,5 @@ # encoding: utf-8 import re -import xml.etree.ElementTree from .common import InfoExtractor from ..utils import ( @@ -10,7 +9,7 @@ from ..utils import ( class DaumIE(InfoExtractor): - _VALID_URL = r'https?://tvpot\.daum\.net/.*?clipid=(?P<id>\d+)' + _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/.*?clipid=(?P<id>\d+)' IE_NAME = u'daum.net' _TEST = { @@ -29,17 +28,16 @@ class DaumIE(InfoExtractor): video_id = mobj.group(1) canonical_url = 'http://tvpot.daum.net/v/%s' % video_id webpage = self._download_webpage(canonical_url, video_id) - full_id = self._search_regex(r'<link rel="video_src" href=".+?vid=(.+?)"', + full_id = self._search_regex( + r'<iframe src="http://videofarm.daum.net/controller/video/viewer/Video.html\?.*?vid=(.+?)[&"]', webpage, u'full id') query = compat_urllib_parse.urlencode({'vid': full_id}) - info_xml = self._download_webpage( + info = self._download_xml( 'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id, u'Downloading video info') - urls_xml = self._download_webpage( + urls = self._download_xml( 'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query, video_id, u'Downloading video formats info') - info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8')) - urls = xml.etree.ElementTree.fromstring(urls_xml.encode('utf-8')) self.to_screen(u'%s: Getting video urls' % video_id) formats = [] @@ -49,10 +47,9 @@ class DaumIE(InfoExtractor): 'vid': full_id, 'profile': profile, }) - url_xml = self._download_webpage( + url_doc = self._download_xml( 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query, video_id, note=False) - url_doc = xml.etree.ElementTree.fromstring(url_xml.encode('utf-8')) format_url = url_doc.find('result/url').text formats.append({ 'url': format_url, @@ -60,7 +57,7 @@ class DaumIE(InfoExtractor): 'format_id': profile, }) - info = { + return { 'id': video_id, 'title': info.find('TITLE').text, 'formats': formats, @@ -69,6 +66,3 @@ class DaumIE(InfoExtractor): 'duration': int(info.find('DURATION').text), 'upload_date': info.find('REGDTTM').text[:8], } - # TODO: Remove when #980 has been merged - info.update(formats[-1]) - return info diff --git a/youtube_dl/extractor/defense.py b/youtube_dl/extractor/defense.py index 424d960da..c5529f8d4 100644 --- a/youtube_dl/extractor/defense.py +++ b/youtube_dl/extractor/defense.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re import json @@ -5,15 +7,14 @@ from .common import InfoExtractor class DefenseGouvFrIE(InfoExtractor): - _IE_NAME = 'defense.gouv.fr' + IE_NAME = 'defense.gouv.fr' _VALID_URL = (r'http://.*?\.defense\.gouv\.fr/layout/set/' r'ligthboxvideo/base-de-medias/webtv/(.*)') _TEST = { - u'url': (u'http://www.defense.gouv.fr/layout/set/ligthboxvideo/' - u'base-de-medias/webtv/attaque-chimique-syrienne-du-21-aout-2013-1'), - u'file': u'11213.mp4', - u'md5': u'75bba6124da7e63d2d60b5244ec9430c', + 'url': 'http://www.defense.gouv.fr/layout/set/ligthboxvideo/base-de-medias/webtv/attaque-chimique-syrienne-du-21-aout-2013-1', + 'file': '11213.mp4', + 'md5': '75bba6124da7e63d2d60b5244ec9430c', "info_dict": { "title": "attaque-chimique-syrienne-du-21-aout-2013-1" } diff --git a/youtube_dl/extractor/dreisat.py b/youtube_dl/extractor/dreisat.py index 765cb1f37..0b11d1f10 100644 --- a/youtube_dl/extractor/dreisat.py +++ b/youtube_dl/extractor/dreisat.py @@ -1,22 +1,20 @@ # coding: utf-8 import re -import xml.etree.ElementTree from .common import InfoExtractor from ..utils import ( - determine_ext, unified_strdate, ) class DreiSatIE(InfoExtractor): IE_NAME = '3sat' - _VALID_URL = r'(?:http://)?(?:www\.)?3sat.de/mediathek/index.php\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$' + _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$' _TEST = { u"url": u"http://www.3sat.de/mediathek/index.php?obj=36983", - u'file': u'36983.webm', - u'md5': u'57c97d0469d71cf874f6815aa2b7c944', + u'file': u'36983.mp4', + u'md5': u'9dcfe344732808dbfcc901537973c922', u'info_dict': { u"title": u"Kaffeeland Schweiz", u"description": u"Über 80 Kaffeeröstereien liefern in der Schweiz das Getränk, in das das Land so vernarrt ist: Mehr als 1000 Tassen trinkt ein Schweizer pro Jahr. SCHWEIZWEIT nimmt die Kaffeekultur unter die...", @@ -30,8 +28,7 @@ class DreiSatIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id - details_xml = self._download_webpage(details_url, video_id, note=u'Downloading video details') - details_doc = xml.etree.ElementTree.fromstring(details_xml.encode('utf-8')) + details_doc = self._download_xml(details_url, video_id, note=u'Downloading video details') thumbnail_els = details_doc.findall('.//teaserimage') thumbnails = [{ @@ -54,20 +51,14 @@ class DreiSatIE(InfoExtractor): 'width': int(fe.find('./width').text), 'height': int(fe.find('./height').text), 'url': fe.find('./url').text, - 'ext': determine_ext(fe.find('./url').text), 'filesize': int(fe.find('./filesize').text), 'video_bitrate': int(fe.find('./videoBitrate').text), - '3sat_qualityname': fe.find('./quality').text, } for fe in format_els if not fe.find('./url').text.startswith('http://www.metafilegenerator.de/')] - def _sortkey(format): - qidx = ['low', 'med', 'high', 'veryhigh'].index(format['3sat_qualityname']) - prefer_http = 1 if 'rtmp' in format['url'] else 0 - return (qidx, prefer_http, format['video_bitrate']) - formats.sort(key=_sortkey) + self._sort_formats(formats) - info = { + return { '_type': 'video', 'id': video_id, 'title': video_title, @@ -78,8 +69,3 @@ class DreiSatIE(InfoExtractor): 'uploader': video_uploader, 'upload_date': upload_date, } - - # TODO: Remove when #980 has been merged - info.update(formats[-1]) - - return info diff --git a/youtube_dl/extractor/dropbox.py b/youtube_dl/extractor/dropbox.py new file mode 100644 index 000000000..d74981eea --- /dev/null +++ b/youtube_dl/extractor/dropbox.py @@ -0,0 +1,31 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import os.path +import re + +from .common import InfoExtractor + + +class DropboxIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?dropbox[.]com/s/(?P<id>[a-zA-Z0-9]{15})/(?P<title>[^?#]*)' + _TEST = { + 'url': 'https://www.dropbox.com/s/mcnzehi9wo55th4/20131219_085616.mp4', + 'file': 'mcnzehi9wo55th4.mp4', + 'md5': 'f6d65b1b326e82fd7ab7720bea3dacae', + 'info_dict': { + 'title': '20131219_085616' + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + title = os.path.splitext(mobj.group('title'))[0] + video_url = url + '?dl=1' + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + } diff --git a/youtube_dl/extractor/ebaumsworld.py b/youtube_dl/extractor/ebaumsworld.py index f02c6998b..877113d63 100644 --- a/youtube_dl/extractor/ebaumsworld.py +++ b/youtube_dl/extractor/ebaumsworld.py @@ -1,5 +1,4 @@ import re -import xml.etree.ElementTree from .common import InfoExtractor from ..utils import determine_ext @@ -21,9 +20,8 @@ class EbaumsWorldIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - config_xml = self._download_webpage( + config = self._download_xml( 'http://www.ebaumsworld.com/video/player/%s' % video_id, video_id) - config = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8')) video_url = config.find('file').text return { diff --git a/youtube_dl/extractor/eighttracks.py b/youtube_dl/extractor/eighttracks.py index 2cfbcd363..88f5526b8 100644 --- a/youtube_dl/extractor/eighttracks.py +++ b/youtube_dl/extractor/eighttracks.py @@ -1,4 +1,3 @@ -import itertools import json import random import re @@ -11,7 +10,7 @@ from ..utils import ( class EightTracksIE(InfoExtractor): IE_NAME = '8tracks' - _VALID_URL = r'https?://8tracks.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$' + _VALID_URL = r'https?://8tracks\.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$' _TEST = { u"name": u"EightTracks", u"url": u"http://8tracks.com/ytdl/youtube-dl-test-tracks-a", diff --git a/youtube_dl/extractor/escapist.py b/youtube_dl/extractor/escapist.py index 3aa2da52c..b1242f6bc 100644 --- a/youtube_dl/extractor/escapist.py +++ b/youtube_dl/extractor/escapist.py @@ -11,11 +11,11 @@ from ..utils import ( class EscapistIE(InfoExtractor): - _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$' + _VALID_URL = r'^https?://?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$' _TEST = { u'url': u'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate', u'file': u'6618-Breaking-Down-Baldurs-Gate.mp4', - u'md5': u'c6793dbda81388f4264c1ba18684a74d', + u'md5': u'ab3a706c681efca53f0a35f1415cf0d1', u'info_dict': { u"description": u"Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.", u"uploader": u"the-escapist-presents", @@ -25,50 +25,60 @@ class EscapistIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) showName = mobj.group('showname') videoId = mobj.group('episode') self.report_extraction(videoId) webpage = self._download_webpage(url, videoId) - videoDesc = self._html_search_regex('<meta name="description" content="([^"]*)"', + videoDesc = self._html_search_regex( + r'<meta name="description" content="([^"]*)"', webpage, u'description', fatal=False) - playerUrl = self._og_search_video_url(webpage, name='player url') + playerUrl = self._og_search_video_url(webpage, name=u'player URL') - title = self._html_search_regex('<meta name="title" content="([^"]*)"', - webpage, u'player url').split(' : ')[-1] + title = self._html_search_regex( + r'<meta name="title" content="([^"]*)"', + webpage, u'title').split(' : ')[-1] - configUrl = self._search_regex('config=(.*)$', playerUrl, u'config url') + configUrl = self._search_regex('config=(.*)$', playerUrl, u'config URL') configUrl = compat_urllib_parse.unquote(configUrl) - configJSON = self._download_webpage(configUrl, videoId, - u'Downloading configuration', - u'unable to download configuration') + formats = [] - # Technically, it's JavaScript, not JSON - configJSON = configJSON.replace("'", '"') + def _add_format(name, cfgurl): + configJSON = self._download_webpage( + cfgurl, videoId, + u'Downloading ' + name + ' configuration', + u'Unable to download ' + name + ' configuration') + # Technically, it's JavaScript, not JSON + configJSON = configJSON.replace("'", '"') + + try: + config = json.loads(configJSON) + except (ValueError,) as err: + raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err)) + playlist = config['playlist'] + formats.append({ + 'url': playlist[1]['url'], + 'format_id': name, + }) + + _add_format(u'normal', configUrl) + hq_url = (configUrl + + ('&hq=1' if '?' in configUrl else configUrl + '?hq=1')) try: - config = json.loads(configJSON) - except (ValueError,) as err: - raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err)) + _add_format(u'hq', hq_url) + except ExtractorError: + pass # That's fine, we'll just use normal quality - playlist = config['playlist'] - videoUrl = playlist[1]['url'] - - info = { + return { 'id': videoId, - 'url': videoUrl, + 'formats': formats, 'uploader': showName, - 'upload_date': None, 'title': title, - 'ext': 'mp4', 'thumbnail': self._og_search_thumbnail(webpage), 'description': videoDesc, 'player_url': playerUrl, } - - return [info] diff --git a/youtube_dl/extractor/everyonesmixtape.py b/youtube_dl/extractor/everyonesmixtape.py new file mode 100644 index 000000000..12829cbcc --- /dev/null +++ b/youtube_dl/extractor/everyonesmixtape.py @@ -0,0 +1,69 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_request, + ExtractorError, +) + + +class EveryonesMixtapeIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?everyonesmixtape\.com/#/mix/(?P<id>[0-9a-zA-Z]+)(?:/(?P<songnr>[0-9]))?$' + + _TEST = { + 'url': 'http://everyonesmixtape.com/#/mix/m7m0jJAbMQi/5', + 'file': '5bfseWNmlds.mp4', + "info_dict": { + "title": "Passion Pit - \"Sleepyhead\" (Official Music Video)", + "uploader": "FKR.TV", + "uploader_id": "frenchkissrecords", + "description": "Music video for \"Sleepyhead\" from Passion Pit's debut EP Chunk Of Change.\nBuy on iTunes: https://itunes.apple.com/us/album/chunk-of-change-ep/id300087641\n\nDirected by The Wilderness.\n\nhttp://www.passionpitmusic.com\nhttp://www.frenchkissrecords.com", + "upload_date": "20081015" + }, + 'params': { + 'skip_download': True, # This is simply YouTube + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + playlist_id = mobj.group('id') + + pllist_url = 'http://everyonesmixtape.com/mixtape.php?a=getMixes&u=-1&linked=%s&explore=' % playlist_id + pllist_req = compat_urllib_request.Request(pllist_url) + pllist_req.add_header('X-Requested-With', 'XMLHttpRequest') + + playlist_list = self._download_json( + pllist_req, playlist_id, note='Downloading playlist metadata') + try: + playlist_no = next(playlist['id'] + for playlist in playlist_list + if playlist['code'] == playlist_id) + except StopIteration: + raise ExtractorError('Playlist id not found') + + pl_url = 'http://everyonesmixtape.com/mixtape.php?a=getMix&id=%s&userId=null&code=' % playlist_no + pl_req = compat_urllib_request.Request(pl_url) + pl_req.add_header('X-Requested-With', 'XMLHttpRequest') + playlist = self._download_json( + pl_req, playlist_id, note='Downloading playlist info') + + entries = [{ + '_type': 'url', + 'url': t['url'], + 'title': t['title'], + } for t in playlist['tracks']] + + if mobj.group('songnr'): + songnr = int(mobj.group('songnr')) - 1 + return entries[songnr] + + playlist_title = playlist['mixData']['name'] + return { + '_type': 'playlist', + 'id': playlist_id, + 'title': playlist_title, + 'entries': entries, + } diff --git a/youtube_dl/extractor/exfm.py b/youtube_dl/extractor/exfm.py index a51d79b08..682901d16 100644 --- a/youtube_dl/extractor/exfm.py +++ b/youtube_dl/extractor/exfm.py @@ -8,7 +8,7 @@ class ExfmIE(InfoExtractor): IE_NAME = u'exfm' IE_DESC = u'ex.fm' _VALID_URL = r'(?:http://)?(?:www\.)?ex\.fm/song/([^/]+)' - _SOUNDCLOUD_URL = r'(?:http://)?(?:www\.)?api\.soundcloud.com/tracks/([^/]+)/stream' + _SOUNDCLOUD_URL = r'(?:http://)?(?:www\.)?api\.soundcloud\.com/tracks/([^/]+)/stream' _TESTS = [ { u'url': u'http://ex.fm/song/eh359', diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index f8bdfc2d3..8f9154c0e 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -1,5 +1,4 @@ import json -import netrc import re import socket @@ -18,7 +17,12 @@ from ..utils import ( class FacebookIE(InfoExtractor): """Information Extractor for Facebook""" - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)' + _VALID_URL = r'''(?x) + (?:https?://)?(?:\w+\.)?facebook\.com/ + (?:[^#?]*\#!/)? + (?:video/video\.php|photo\.php|video/embed)\?(?:.*?) + (?:v|video_id)=(?P<id>[0-9]+) + (?:.*)''' _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1' _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1' _NETRC_MACHINE = 'facebook' @@ -28,7 +32,7 @@ class FacebookIE(InfoExtractor): u'file': u'120708114770723.mp4', u'md5': u'48975a41ccc4b7a581abd68651c1a5a8', u'info_dict': { - u"duration": 279, + u"duration": 279, u"title": u"PEOPLE ARE AWESOME 2013" } } @@ -91,7 +95,7 @@ class FacebookIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) if mobj is None: raise ExtractorError(u'Invalid URL: %s' % url) - video_id = mobj.group('ID') + video_id = mobj.group('id') url = 'https://www.facebook.com/video/video.php?v=%s' % video_id webpage = self._download_webpage(url, video_id) diff --git a/youtube_dl/extractor/faz.py b/youtube_dl/extractor/faz.py index 89ed08db4..c6ab6952e 100644 --- a/youtube_dl/extractor/faz.py +++ b/youtube_dl/extractor/faz.py @@ -1,6 +1,5 @@ # encoding: utf-8 import re -import xml.etree.ElementTree from .common import InfoExtractor from ..utils import ( @@ -10,7 +9,7 @@ from ..utils import ( class FazIE(InfoExtractor): IE_NAME = u'faz.net' - _VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P<id>\d+).html' + _VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P<id>\d+)\.html' _TEST = { u'url': u'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html', @@ -28,9 +27,8 @@ class FazIE(InfoExtractor): webpage = self._download_webpage(url, video_id) config_xml_url = self._search_regex(r'writeFLV\(\'(.+?)\',', webpage, u'config xml url') - config_xml = self._download_webpage(config_xml_url, video_id, + config = self._download_xml(config_xml_url, video_id, u'Downloading config xml') - config = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8')) encodings = config.find('ENCODINGS') formats = [] @@ -46,13 +44,10 @@ class FazIE(InfoExtractor): }) descr = self._html_search_regex(r'<p class="Content Copy">(.*?)</p>', webpage, u'description') - info = { + return { 'id': video_id, 'title': self._og_search_title(webpage), 'formats': formats, 'description': descr, 'thumbnail': config.find('STILL/STILL_BIG').text, } - # TODO: Remove when #980 has been merged - info.update(formats[-1]) - return info diff --git a/youtube_dl/extractor/fktv.py b/youtube_dl/extractor/fktv.py index 9c89362ef..d7048c8c1 100644 --- a/youtube_dl/extractor/fktv.py +++ b/youtube_dl/extractor/fktv.py @@ -12,7 +12,7 @@ from ..utils import ( class FKTVIE(InfoExtractor): IE_NAME = u'fernsehkritik.tv' - _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik.tv/folge-(?P<ep>[0-9]+)(?:/.*)?' + _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik\.tv/folge-(?P<ep>[0-9]+)(?:/.*)?' _TEST = { u'url': u'http://fernsehkritik.tv/folge-1', @@ -39,7 +39,6 @@ class FKTVIE(InfoExtractor): for i, _ in enumerate(files, 1): video_id = '%04d%d' % (episode, i) video_url = 'http://dl%d.fernsehkritik.tv/fernsehkritik%d%s.flv' % (server, episode, '' if i == 1 else '-%d' % i) - video_title = 'Fernsehkritik %d.%d' % (episode, i) videos.append({ 'id': video_id, 'url': video_url, @@ -53,7 +52,7 @@ class FKTVIE(InfoExtractor): class FKTVPosteckeIE(InfoExtractor): IE_NAME = u'fernsehkritik.tv:postecke' - _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik.tv/inline-video/postecke.php\?(.*&)?ep=(?P<ep>[0-9]+)(&|$)' + _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik\.tv/inline-video/postecke\.php\?(.*&)?ep=(?P<ep>[0-9]+)(&|$)' _TEST = { u'url': u'http://fernsehkritik.tv/inline-video/postecke.php?iframe=true&width=625&height=440&ep=120', u'file': u'0120.flv', diff --git a/youtube_dl/extractor/flickr.py b/youtube_dl/extractor/flickr.py index e1d2f0526..21ea5ec2b 100644 --- a/youtube_dl/extractor/flickr.py +++ b/youtube_dl/extractor/flickr.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -11,13 +13,13 @@ class FlickrIE(InfoExtractor): """Information Extractor for Flickr videos""" _VALID_URL = r'(?:https?://)?(?:www\.|secure\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*' _TEST = { - u'url': u'http://www.flickr.com/photos/forestwander-nature-pictures/5645318632/in/photostream/', - u'file': u'5645318632.mp4', - u'md5': u'6fdc01adbc89d72fc9c4f15b4a4ba87b', - u'info_dict': { - u"description": u"Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up.", - u"uploader_id": u"forestwander-nature-pictures", - u"title": u"Dark Hollow Waterfalls" + 'url': 'http://www.flickr.com/photos/forestwander-nature-pictures/5645318632/in/photostream/', + 'file': '5645318632.mp4', + 'md5': '6fdc01adbc89d72fc9c4f15b4a4ba87b', + 'info_dict': { + "description": "Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up.", + "uploader_id": "forestwander-nature-pictures", + "title": "Dark Hollow Waterfalls" } } @@ -29,13 +31,13 @@ class FlickrIE(InfoExtractor): webpage_url = 'http://www.flickr.com/photos/' + video_uploader_id + '/' + video_id webpage = self._download_webpage(webpage_url, video_id) - secret = self._search_regex(r"photo_secret: '(\w+)'", webpage, u'secret') + secret = self._search_regex(r"photo_secret: '(\w+)'", webpage, 'secret') first_url = 'https://secure.flickr.com/apps/video/video_mtl_xml.gne?v=x&photo_id=' + video_id + '&secret=' + secret + '&bitrate=700&target=_self' first_xml = self._download_webpage(first_url, video_id, 'Downloading first data webpage') node_id = self._html_search_regex(r'<Item id="id">(\d+-\d+)</Item>', - first_xml, u'node_id') + first_xml, 'node_id') second_url = 'https://secure.flickr.com/video_playlist.gne?node_id=' + node_id + '&tech=flash&mode=playlist&bitrate=700&secret=' + secret + '&rd=video.yahoo.com&noad=1' second_xml = self._download_webpage(second_url, video_id, 'Downloading second data webpage') @@ -44,7 +46,7 @@ class FlickrIE(InfoExtractor): mobj = re.search(r'<STREAM APP="(.+?)" FULLPATH="(.+?)"', second_xml) if mobj is None: - raise ExtractorError(u'Unable to extract video url') + raise ExtractorError('Unable to extract video url') video_url = mobj.group(1) + unescapeHTML(mobj.group(2)) return [{ diff --git a/youtube_dl/extractor/franceinter.py b/youtube_dl/extractor/franceinter.py new file mode 100644 index 000000000..deb1b0b9d --- /dev/null +++ b/youtube_dl/extractor/franceinter.py @@ -0,0 +1,38 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class FranceInterIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]{6})' + _TEST = { + 'url': 'http://www.franceinter.fr/player/reecouter?play=793962', + 'file': '793962.mp3', + 'md5': '4764932e466e6f6c79c317d2e74f6884', + "info_dict": { + "title": "L’Histoire dans les jeux vidéo", + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + title = self._html_search_regex( + r'<span class="roll_overflow">(.*?)</span></h1>', webpage, 'title') + path = self._search_regex( + r'&urlAOD=(.*?)&startTime', webpage, 'video url') + video_url = 'http://www.franceinter.fr/' + path + + return { + 'id': video_id, + 'formats': [{ + 'url': video_url, + 'vcodec': 'none', + }], + 'title': title, + } diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index 086cafca0..b32ff9f86 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -1,6 +1,5 @@ # encoding: utf-8 import re -import xml.etree.ElementTree import json from .common import InfoExtractor @@ -11,11 +10,10 @@ from ..utils import ( class FranceTVBaseInfoExtractor(InfoExtractor): def _extract_video(self, video_id): - xml_desc = self._download_webpage( + info = self._download_xml( 'http://www.francetvinfo.fr/appftv/webservices/video/' 'getInfosOeuvre.php?id-diffusion=' + video_id, video_id, 'Downloading XML config') - info = xml.etree.ElementTree.fromstring(xml_desc.encode('utf-8')) manifest_url = info.find('videos/video/url').text video_url = manifest_url.replace('manifest.f4m', 'index_2_av.m3u8') @@ -23,7 +21,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor): thumbnail_path = info.find('image').text return {'id': video_id, - 'ext': 'mp4', + 'ext': 'flv' if video_url.startswith('rtmp') else 'mp4', 'url': video_url, 'title': info.find('titre').text, 'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path), @@ -47,7 +45,7 @@ class PluzzIE(FranceTVBaseInfoExtractor): class FranceTvInfoIE(FranceTVBaseInfoExtractor): IE_NAME = u'francetvinfo.fr' - _VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P<title>.+).html' + _VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P<title>.+)\.html' _TEST = { u'url': u'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html', @@ -68,35 +66,101 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor): return self._extract_video(video_id) -class France2IE(FranceTVBaseInfoExtractor): - IE_NAME = u'france2.fr' - _VALID_URL = r'''(?x)https?://www\.france2\.fr/ +class FranceTVIE(FranceTVBaseInfoExtractor): + IE_NAME = u'francetv' + IE_DESC = u'France 2, 3, 4, 5 and Ô' + _VALID_URL = r'''(?x)https?://www\.france[2345o]\.fr/ (?: - emissions/.*?/videos/(?P<id>\d+) - | emission/(?P<key>[^/?]+) + emissions/.*?/(videos|emissions)/(?P<id>[^/?]+) + | (emissions?|jt)/(?P<key>[^/?]+) )''' - _TEST = { - u'url': u'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104', - u'file': u'75540104.mp4', - u'info_dict': { - u'title': u'13h15, le samedi...', - u'description': u'md5:2e5b58ba7a2d3692b35c792be081a03d', + _TESTS = [ + # france2 + { + u'url': u'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104', + u'file': u'75540104.mp4', + u'info_dict': { + u'title': u'13h15, le samedi...', + u'description': u'md5:2e5b58ba7a2d3692b35c792be081a03d', + }, + u'params': { + # m3u8 download + u'skip_download': True, + }, }, - u'params': { - u'skip_download': True, + # france3 + { + u'url': u'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575', + u'info_dict': { + u'id': u'000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au', + u'ext': u'flv', + u'title': u'Le scandale du prix des médicaments', + u'description': u'md5:1384089fbee2f04fc6c9de025ee2e9ce', + }, + u'params': { + # rtmp download + u'skip_download': True, + }, }, - } + # france4 + { + u'url': u'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4', + u'info_dict': { + u'id': u'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4', + u'ext': u'flv', + u'title': u'Hero Corp Making of - Extrait 1', + u'description': u'md5:c87d54871b1790679aec1197e73d650a', + }, + u'params': { + # rtmp download + u'skip_download': True, + }, + }, + # france5 + { + u'url': u'http://www.france5.fr/emissions/c-a-dire/videos/92837968', + u'info_dict': { + u'id': u'92837968', + u'ext': u'mp4', + u'title': u'C à dire ?!', + u'description': u'md5:fb1db1cbad784dcce7c7a7bd177c8e2f', + }, + u'params': { + # m3u8 download + u'skip_download': True, + }, + }, + # franceo + { + u'url': u'http://www.franceo.fr/jt/info-afrique/04-12-2013', + u'info_dict': { + u'id': u'92327925', + u'ext': u'mp4', + u'title': u'Infô-Afrique', + u'description': u'md5:ebf346da789428841bee0fd2a935ea55', + }, + u'params': { + # m3u8 download + u'skip_download': True, + }, + u'skip': u'The id changes frequently', + }, + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) if mobj.group('key'): webpage = self._download_webpage(url, mobj.group('key')) - video_id = self._html_search_regex( - r'''(?x)<div\s+class="video-player">\s* + id_res = [ + (r'''(?x)<div\s+class="video-player">\s* <a\s+href="http://videos.francetv.fr/video/([0-9]+)"\s+ - class="francetv-video-player">''', - webpage, u'video ID') + class="francetv-video-player">'''), + (r'<a id="player_direct" href="http://info\.francetelevisions' + '\.fr/\?id-video=([^"/&]+)'), + (r'<a class="video" id="ftv_player_(.+?)"'), + ] + video_id = self._html_search_regex(id_res, webpage, u'video ID') else: video_id = mobj.group('id') return self._extract_video(video_id) @@ -127,3 +191,29 @@ class GenerationQuoiIE(InfoExtractor): info = json.loads(info_json) return self.url_result('http://www.dailymotion.com/video/%s' % info['id'], ie='Dailymotion') + + +class CultureboxIE(FranceTVBaseInfoExtractor): + IE_NAME = u'culturebox.francetvinfo.fr' + _VALID_URL = r'https?://culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)' + + _TEST = { + u'url': u'http://culturebox.francetvinfo.fr/einstein-on-the-beach-au-theatre-du-chatelet-146813', + u'info_dict': { + u'id': u'EV_6785', + u'ext': u'mp4', + u'title': u'Einstein on the beach au Théâtre du Châtelet', + u'description': u'md5:9ce2888b1efefc617b5e58b3f6200eeb', + }, + u'params': { + # m3u8 download + u'skip_download': True, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + name = mobj.group('name') + webpage = self._download_webpage(url, name) + video_id = self._search_regex(r'"http://videos\.francetv\.fr/video/(.*?)"', webpage, u'video id') + return self._extract_video(video_id) diff --git a/youtube_dl/extractor/gamekings.py b/youtube_dl/extractor/gamekings.py index c91669b0e..a3a5251fe 100644 --- a/youtube_dl/extractor/gamekings.py +++ b/youtube_dl/extractor/gamekings.py @@ -4,7 +4,7 @@ from .common import InfoExtractor class GamekingsIE(InfoExtractor): - _VALID_URL = r'http?://www\.gamekings\.tv/videos/(?P<name>[0-9a-z\-]+)' + _VALID_URL = r'http://www\.gamekings\.tv/videos/(?P<name>[0-9a-z\-]+)' _TEST = { u"url": u"http://www.gamekings.tv/videos/phoenix-wright-ace-attorney-dual-destinies-review/", u'file': u'20130811.mp4', diff --git a/youtube_dl/extractor/gamespot.py b/youtube_dl/extractor/gamespot.py index 098768361..380ebbe55 100644 --- a/youtube_dl/extractor/gamespot.py +++ b/youtube_dl/extractor/gamespot.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re import json @@ -13,18 +15,18 @@ from ..utils import ( class GameSpotIE(InfoExtractor): _VALID_URL = r'(?:http://)?(?:www\.)?gamespot\.com/.*-(?P<page_id>\d+)/?' _TEST = { - u"url": u"http://www.gamespot.com/arma-iii/videos/arma-iii-community-guide-sitrep-i-6410818/", - u"file": u"gs-2300-6410818.mp4", - u"md5": u"b2a30deaa8654fcccd43713a6b6a4825", - u"info_dict": { - u"title": u"Arma 3 - Community Guide: SITREP I", - u'description': u'Check out this video where some of the basics of Arma 3 is explained.', + "url": "http://www.gamespot.com/arma-iii/videos/arma-iii-community-guide-sitrep-i-6410818/", + "file": "gs-2300-6410818.mp4", + "md5": "b2a30deaa8654fcccd43713a6b6a4825", + "info_dict": { + "title": "Arma 3 - Community Guide: SITREP I", + 'description': 'Check out this video where some of the basics of Arma 3 is explained.', } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - page_id = video_id = mobj.group('page_id') + page_id = mobj.group('page_id') webpage = self._download_webpage(url, page_id) data_video_json = self._search_regex(r'data-video=\'(.*?)\'', webpage, u'data video') data_video = json.loads(unescapeHTML(data_video_json)) @@ -47,13 +49,10 @@ class GameSpotIE(InfoExtractor): 'format_id': q, }) - info = { + return { 'id': data_video['guid'], 'title': compat_urllib_parse.unquote(data_video['title']), 'formats': formats, 'description': get_meta_content('description', webpage), 'thumbnail': self._og_search_thumbnail(webpage), } - # TODO: Remove when #980 has been merged - info.update(formats[-1]) - return info diff --git a/youtube_dl/extractor/gametrailers.py b/youtube_dl/extractor/gametrailers.py index 3cc02d97e..c1fdd770e 100644 --- a/youtube_dl/extractor/gametrailers.py +++ b/youtube_dl/extractor/gametrailers.py @@ -1,36 +1,29 @@ +from __future__ import unicode_literals + import re -from .mtv import MTVIE, _media_xml_tag +from .mtv import MTVServicesInfoExtractor -class GametrailersIE(MTVIE): - """ - Gametrailers use the same videos system as MTVIE, it just changes the feed - url, where the uri is and the method to get the thumbnails. - """ - _VALID_URL = r'http://www.gametrailers.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)' + +class GametrailersIE(MTVServicesInfoExtractor): + _VALID_URL = r'http://www\.gametrailers\.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)' _TEST = { - u'url': u'http://www.gametrailers.com/videos/zbvr8i/mirror-s-edge-2-e3-2013--debut-trailer', - u'file': u'70e9a5d7-cf25-4a10-9104-6f3e7342ae0d.mp4', - u'md5': u'4c8e67681a0ea7ec241e8c09b3ea8cf7', - u'info_dict': { - u'title': u'E3 2013: Debut Trailer', - u'description': u'Faith is back! Check out the World Premiere trailer for Mirror\'s Edge 2 straight from the EA Press Conference at E3 2013!', + 'url': 'http://www.gametrailers.com/videos/zbvr8i/mirror-s-edge-2-e3-2013--debut-trailer', + 'file': '70e9a5d7-cf25-4a10-9104-6f3e7342ae0d.mp4', + 'md5': '4c8e67681a0ea7ec241e8c09b3ea8cf7', + 'info_dict': { + 'title': 'Mirror\'s Edge 2|E3 2013: Debut Trailer', + 'description': 'Faith is back! Check out the World Premiere trailer for Mirror\'s Edge 2 straight from the EA Press Conference at E3 2013!', }, } - # Overwrite MTVIE properties we don't want - _TESTS = [] _FEED_URL = 'http://www.gametrailers.com/feeds/mrss' - def _get_thumbnail_url(self, uri, itemdoc): - search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail')) - return itemdoc.find(search_path).attrib['url'] - def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) mgid = self._search_regex([r'data-video="(?P<mgid>mgid:.*?)"', r'data-contentId=\'(?P<mgid>mgid:.*?)\''], - webpage, u'mgid') + webpage, 'mgid') return self._get_videos_info(mgid) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 02322649d..e446ed326 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -1,9 +1,12 @@ # encoding: utf-8 +from __future__ import unicode_literals + import os import re from .common import InfoExtractor +from .youtube import YoutubeIE from ..utils import ( compat_urllib_error, compat_urllib_parse, @@ -11,64 +14,90 @@ from ..utils import ( compat_urlparse, ExtractorError, + HEADRequest, smuggle_url, unescapeHTML, + unified_strdate, + url_basename, ) from .brightcove import BrightcoveIE +from .ooyala import OoyalaIE class GenericIE(InfoExtractor): - IE_DESC = u'Generic downloader that works on some sites' + IE_DESC = 'Generic downloader that works on some sites' _VALID_URL = r'.*' - IE_NAME = u'generic' + IE_NAME = 'generic' _TESTS = [ { - u'url': u'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html', - u'file': u'13601338388002.mp4', - u'md5': u'6e15c93721d7ec9e9ca3fdbf07982cfd', - u'info_dict': { - u"uploader": u"www.hodiho.fr", - u"title": u"R\u00e9gis plante sa Jeep" + 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html', + 'file': '13601338388002.mp4', + 'md5': '6e15c93721d7ec9e9ca3fdbf07982cfd', + 'info_dict': { + 'uploader': 'www.hodiho.fr', + 'title': 'R\u00e9gis plante sa Jeep', } }, # embedded vimeo video { - u'add_ie': ['Vimeo'], - u'url': u'http://skillsmatter.com/podcast/home/move-semanticsperfect-forwarding-and-rvalue-references', - u'file': u'22444065.mp4', - u'md5': u'2903896e23df39722c33f015af0666e2', - u'info_dict': { - u'title': u'ACCU 2011: Move Semantics,Perfect Forwarding, and Rvalue references- Scott Meyers- 13/04/2011', - u"uploader_id": u"skillsmatter", - u"uploader": u"Skills Matter", + 'add_ie': ['Vimeo'], + 'url': 'http://skillsmatter.com/podcast/home/move-semanticsperfect-forwarding-and-rvalue-references', + 'file': '22444065.mp4', + 'md5': '2903896e23df39722c33f015af0666e2', + 'info_dict': { + 'title': 'ACCU 2011: Move Semantics,Perfect Forwarding, and Rvalue references- Scott Meyers- 13/04/2011', + 'uploader_id': 'skillsmatter', + 'uploader': 'Skills Matter', } }, # bandcamp page with custom domain { - u'add_ie': ['Bandcamp'], - u'url': u'http://bronyrock.com/track/the-pony-mash', - u'file': u'3235767654.mp3', - u'info_dict': { - u'title': u'The Pony Mash', - u'uploader': u'M_Pallante', + 'add_ie': ['Bandcamp'], + 'url': 'http://bronyrock.com/track/the-pony-mash', + 'file': '3235767654.mp3', + 'info_dict': { + 'title': 'The Pony Mash', + 'uploader': 'M_Pallante', }, - u'skip': u'There is a limit of 200 free downloads / month for the test song', + 'skip': 'There is a limit of 200 free downloads / month for the test song', }, # embedded brightcove video # it also tests brightcove videos that need to set the 'Referer' in the # http requests { - u'add_ie': ['Brightcove'], - u'url': u'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/', - u'info_dict': { - u'id': u'2765128793001', - u'ext': u'mp4', - u'title': u'Le cours de bourse : l’analyse technique', - u'description': u'md5:7e9ad046e968cb2d1114004aba466fd9', - u'uploader': u'BFM BUSINESS', + 'add_ie': ['Brightcove'], + 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/', + 'info_dict': { + 'id': '2765128793001', + 'ext': 'mp4', + 'title': 'Le cours de bourse : l’analyse technique', + 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9', + 'uploader': 'BFM BUSINESS', }, - u'params': { - u'skip_download': True, + 'params': { + 'skip_download': True, + }, + }, + # Direct link to a video + { + 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4', + 'file': 'trailer.mp4', + 'md5': '67d406c2bcb6af27fa886f31aa934bbe', + 'info_dict': { + 'id': 'trailer', + 'title': 'trailer', + 'upload_date': '20100513', + } + }, + # ooyala video + { + 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219', + 'file': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ.mp4', + 'md5': '5644c6ca5d5782c1d0d350dad9bd840c', + 'info_dict': { + 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ', + 'ext': 'mp4', + 'title': '2cc213299525360.mov', # that's what we get }, }, ] @@ -76,30 +105,27 @@ class GenericIE(InfoExtractor): def report_download_webpage(self, video_id): """Report webpage download.""" if not self._downloader.params.get('test', False): - self._downloader.report_warning(u'Falling back on generic information extractor.') + self._downloader.report_warning('Falling back on generic information extractor.') super(GenericIE, self).report_download_webpage(video_id) def report_following_redirect(self, new_url): """Report information extraction.""" - self._downloader.to_screen(u'[redirect] Following redirect to %s' % new_url) + self._downloader.to_screen('[redirect] Following redirect to %s' % new_url) - def _test_redirect(self, url): + def _send_head(self, url): """Check if it is a redirect, like url shorteners, in case return the new url.""" - class HeadRequest(compat_urllib_request.Request): - def get_method(self): - return "HEAD" class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler): """ Subclass the HTTPRedirectHandler to make it use our - HeadRequest also on the redirected URL + HEADRequest also on the redirected URL """ def redirect_request(self, req, fp, code, msg, headers, newurl): if code in (301, 302, 303, 307): newurl = newurl.replace(' ', '%20') newheaders = dict((k,v) for k,v in req.headers.items() if k.lower() not in ("content-length", "content-type")) - return HeadRequest(newurl, + return HEADRequest(newurl, headers=newheaders, origin_req_host=req.get_origin_req_host(), unverifiable=True) @@ -128,77 +154,188 @@ class GenericIE(InfoExtractor): compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]: opener.add_handler(handler()) - response = opener.open(HeadRequest(url)) + response = opener.open(HEADRequest(url)) if response is None: - raise ExtractorError(u'Invalid URL protocol') - new_url = response.geturl() - - if url == new_url: - return False - - self.report_following_redirect(new_url) - return new_url + raise ExtractorError('Invalid URL protocol') + return response def _real_extract(self, url): parsed_url = compat_urlparse.urlparse(url) if not parsed_url.scheme: self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http') return self.url_result('http://' + url) + video_id = os.path.splitext(url.split('/')[-1])[0] + + self.to_screen('%s: Requesting header' % video_id) try: - new_url = self._test_redirect(url) - if new_url: - return [self.url_result(new_url)] + response = self._send_head(url) + + # Check for redirect + new_url = response.geturl() + if url != new_url: + self.report_following_redirect(new_url) + return self.url_result(new_url) + + # Check for direct link to a video + content_type = response.headers.get('Content-Type', '') + m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type) + if m: + upload_date = response.headers.get('Last-Modified') + if upload_date: + upload_date = unified_strdate(upload_date) + return { + 'id': video_id, + 'title': os.path.splitext(url_basename(url))[0], + 'formats': [{ + 'format_id': m.group('format_id'), + 'url': url, + 'vcodec': 'none' if m.group('type') == 'audio' else None + }], + 'upload_date': upload_date, + } + except compat_urllib_error.HTTPError: # This may be a stupid server that doesn't like HEAD, our UA, or so pass - video_id = url.split('/')[-1] try: webpage = self._download_webpage(url, video_id) except ValueError: # since this is the last-resort InfoExtractor, if # this error is thrown, it'll be thrown here - raise ExtractorError(u'Failed to download URL: %s' % url) + raise ExtractorError('Failed to download URL: %s' % url) self.report_extraction(video_id) + + # it's tempting to parse this further, but you would + # have to take into account all the variations like + # Video Title - Site Name + # Site Name | Video Title + # Video Title - Tagline | Site Name + # and so on and so forth; it's just not practical + video_title = self._html_search_regex( + r'(?s)<title>(.*?)', webpage, 'video title', + default='video') + + # video uploader is domain name + video_uploader = self._search_regex( + r'^(?:https?://)?([^/]*)/.*', url, 'video uploader') + # Look for BrightCove: bc_url = BrightcoveIE._extract_brightcove_url(webpage) if bc_url is not None: - self.to_screen(u'Brightcove video detected.') - return self.url_result(bc_url, 'Brightcove') + self.to_screen('Brightcove video detected.') + surl = smuggle_url(bc_url, {'Referer': url}) + return self.url_result(surl, 'Brightcove') - # Look for embedded Vimeo player + # Look for embedded (iframe) Vimeo player mobj = re.search( - r']+?src="(https?://player.vimeo.com/video/.+?)"', webpage) + r']+?src="((?:https?:)?//player.vimeo.com/video/.+?)"', webpage) if mobj: player_url = unescapeHTML(mobj.group(1)) surl = smuggle_url(player_url, {'Referer': url}) return self.url_result(surl, 'Vimeo') - # Look for embedded YouTube player - mobj = re.findall( - r']+?src=(["\'])(?P(https?:)?//(?:www\.)?youtube.com/embed/.+?)\1', webpage) + # Look for embedded (swf embed) Vimeo player + mobj = re.search( + r']+?src="(https?://(?:www\.)?vimeo.com/moogaloop.swf.+?)"', webpage) if mobj: - #surl = unescapeHTML(mobj.group(u'url')) - surl_list = [tuppl[1] for tuppl in mobj] - return [self.url_result(x, 'Youtube') for x in surl_list] + return self.url_result(mobj.group(1), 'Vimeo') + # Look for embedded YouTube player + matches = re.findall(r'''(?x) + (?:]+?src=|embedSWF\(\s*) + (["\'])(?P(?:https?:)?//(?:www\.)?youtube\.com/ + (?:embed|v)/.+?) + \1''', webpage) + if matches: + urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Youtube') + for tuppl in matches] + return self.playlist_result( + urlrs, playlist_id=video_id, playlist_title=video_title) + + # Look for embedded Dailymotion player + matches = re.findall( + r']+?src=(["\'])(?P(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage) + if matches: + urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Dailymotion') + for tuppl in matches] + return self.playlist_result( + urlrs, playlist_id=video_id, playlist_title=video_title) + + # Look for embedded Wistia player + match = re.search( + r']+?src=(["\'])(?P(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage) + if match: + return { + '_type': 'url_transparent', + 'url': unescapeHTML(match.group('url')), + 'ie_key': 'Wistia', + 'uploader': video_uploader, + 'title': video_title, + 'id': video_id, + } + + # Look for embedded blip.tv player + mobj = re.search(r']*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage) + if mobj: + return self.url_result('http://blip.tv/a/a-'+mobj.group(1), 'BlipTV') + mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9]+)', webpage) + if mobj: + return self.url_result(mobj.group(1), 'BlipTV') # Look for Bandcamp pages with custom domain mobj = re.search(r']*?content="(.*?bandcamp\.com.*?)"', webpage) if mobj is not None: burl = unescapeHTML(mobj.group(1)) - return self.url_result(burl, 'Bandcamp') + # Don't set the extractor because it can be a track url or an album + return self.url_result(burl) + + # Look for embedded Vevo player + mobj = re.search( + r']+?src=(["\'])(?P(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage) + if mobj is not None: + return self.url_result(mobj.group('url')) + + # Look for Ooyala videos + mobj = re.search(r'player.ooyala.com/[^"?]+\?[^"]*?(?:embedCode|ec)=([^"&]+)', webpage) + if mobj is not None: + return OoyalaIE._build_url_result(mobj.group(1)) + + # Look for Aparat videos + mobj = re.search(r'