diff --git a/.gitignore b/.gitignore index 77469b8a7..ca4e8f353 100644 --- a/.gitignore +++ b/.gitignore @@ -17,4 +17,4 @@ youtube-dl.tar.gz .coverage cover/ updates_key.pem -*.egg-info +*.egg-info \ No newline at end of file diff --git a/.travis.yml b/.travis.yml index 0687c8957..7f1fa8a3c 100644 --- a/.travis.yml +++ b/.travis.yml @@ -8,6 +8,7 @@ notifications: email: - filippo.valsorda@gmail.com - phihag@phihag.de + - jaime.marquinez.ferrandiz+travis@gmail.com # irc: # channels: # - "irc.freenode.org#youtube-dl" diff --git a/Makefile b/Makefile index 84ea70d2c..e00f5e650 100644 --- a/Makefile +++ b/Makefile @@ -9,9 +9,19 @@ cleanall: clean PREFIX=/usr/local BINDIR=$(PREFIX)/bin MANDIR=$(PREFIX)/man -SYSCONFDIR=/etc PYTHON=/usr/bin/env python +# set SYSCONFDIR to /etc if PREFIX=/usr or PREFIX=/usr/local +ifeq ($(PREFIX),/usr) + SYSCONFDIR=/etc +else + ifeq ($(PREFIX),/usr/local) + SYSCONFDIR=/etc + else + SYSCONFDIR=$(PREFIX)/etc + endif +endif + install: youtube-dl youtube-dl.1 youtube-dl.bash-completion install -d $(DESTDIR)$(BINDIR) install -m 755 youtube-dl $(DESTDIR)$(BINDIR) diff --git a/README.md b/README.md index eaad456ac..2f3c81a7c 100644 --- a/README.md +++ b/README.md @@ -14,113 +14,137 @@ your Unix box, on Windows or on Mac OS X. It is released to the public domain, which means you can modify it, redistribute it or use it however you like. # OPTIONS - -h, --help print this help text and exit - --version print program version and exit - -U, --update update this program to latest version - -i, --ignore-errors continue on download errors - -r, --rate-limit LIMIT maximum download rate (e.g. 50k or 44.6m) - -R, --retries RETRIES number of retries (default is 10) - --buffer-size SIZE size of download buffer (e.g. 1024 or 16k) (default - is 1024) - --no-resize-buffer do not automatically adjust the buffer size. By - default, the buffer size is automatically resized - from an initial value of SIZE. - --dump-user-agent display the current browser identification - --user-agent UA specify a custom user agent - --list-extractors List all supported extractors and the URLs they - would handle + -h, --help print this help text and exit + --version print program version and exit + -U, --update update this program to latest version + -i, --ignore-errors continue on download errors + -r, --rate-limit LIMIT maximum download rate (e.g. 50k or 44.6m) + -R, --retries RETRIES number of retries (default is 10) + --buffer-size SIZE size of download buffer (e.g. 1024 or 16k) + (default is 1024) + --no-resize-buffer do not automatically adjust the buffer size. By + default, the buffer size is automatically resized + from an initial value of SIZE. + --dump-user-agent display the current browser identification + --user-agent UA specify a custom user agent + --referer REF specify a custom referer, use if the video access + is restricted to one domain + --list-extractors List all supported extractors and the URLs they + would handle + --proxy URL Use the specified HTTP/HTTPS proxy + --no-check-certificate Suppress HTTPS certificate validation. ## Video Selection: - --playlist-start NUMBER playlist video to start at (default is 1) - --playlist-end NUMBER playlist video to end at (default is last) - --match-title REGEX download only matching titles (regex or caseless - sub-string) - --reject-title REGEX skip download for matching titles (regex or - caseless sub-string) - --max-downloads NUMBER Abort after downloading NUMBER files - --min-filesize SIZE Do not download any videos smaller than SIZE (e.g. - 50k or 44.6m) - --max-filesize SIZE Do not download any videos larger than SIZE (e.g. - 50k or 44.6m) + --playlist-start NUMBER playlist video to start at (default is 1) + --playlist-end NUMBER playlist video to end at (default is last) + --match-title REGEX download only matching titles (regex or caseless + sub-string) + --reject-title REGEX skip download for matching titles (regex or + caseless sub-string) + --max-downloads NUMBER Abort after downloading NUMBER files + --min-filesize SIZE Do not download any videos smaller than SIZE + (e.g. 50k or 44.6m) + --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 ## Filesystem Options: - -t, --title use title in file name - --id use video ID in file name - -l, --literal [deprecated] alias of --title - -A, --auto-number number downloaded files starting from 00000 - -o, --output TEMPLATE output filename template. Use %(title)s to get the - title, %(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, %(upload_date)s for the upload date - (YYYYMMDD), %(extractor)s for the provider - (youtube, metacafe, etc), %(id)s for the video id - 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/%(upl - oader)s/%(title)s-%(id)s.%(ext)s' . - --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) - -w, --no-overwrites do not overwrite files - -c, --continue resume partially downloaded files - --no-continue do not resume partially downloaded files (restart - from beginning) - --cookies FILE file to read cookies from and dump cookie jar in - --no-part do not use .part files - --no-mtime do not use the Last-modified header to set the file - modification time - --write-description write video description to a .description file - --write-info-json write video metadata to a .info.json file + -t, --title use title in file name (default) + --id use only video ID in file name + -l, --literal [deprecated] alias of --title + -A, --auto-number number downloaded files starting from 00000 + -o, --output TEMPLATE output filename template. Use %(title)s to get + the title, %(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, %(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 + ownloads/%(uploader)s/%(title)s-%(id)s.%(ext)s' . + --autonumber-size NUMBER Specifies the number of digits in %(autonumber)s + when it is present in output filename template or + --autonumber option is given + --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) + -w, --no-overwrites do not overwrite files + -c, --continue resume partially downloaded files + --no-continue do not resume partially downloaded files (restart + from beginning) + --cookies FILE file to read cookies from and dump cookie jar in + --no-part do not use .part files + --no-mtime do not use the Last-modified header to set the + file modification time + --write-description write video description to a .description file + --write-info-json write video metadata to a .info.json file + --write-thumbnail write thumbnail image to disk ## Verbosity / Simulation Options: - -q, --quiet activates quiet mode - -s, --simulate do not download the video and do not write anything - to disk - --skip-download do not download the video - -g, --get-url simulate, quiet but print URL - -e, --get-title simulate, quiet but print title - --get-thumbnail simulate, quiet but print thumbnail URL - --get-description simulate, quiet but print video description - --get-filename simulate, quiet but print output filename - --get-format simulate, quiet but print output format - --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 + -q, --quiet activates quiet mode + -s, --simulate do not download the video and do not write + anything to disk + --skip-download do not download the video + -g, --get-url simulate, quiet but print URL + -e, --get-title simulate, quiet but print title + --get-id simulate, quiet but print id + --get-thumbnail simulate, quiet but print thumbnail URL + --get-description simulate, quiet but print video description + --get-filename simulate, quiet but print output filename + --get-format simulate, quiet but print output format + --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 + verbose) ## Video Format Options: - -f, --format FORMAT video format code - --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) - --write-srt write video closed captions to a .srt file - (currently youtube only) - --srt-lang LANG language of the closed captions to download - (optional) use IETF language tags like 'en' + -f, --format FORMAT video format code, specifiy the order of + preference using slashes: "-f 22/17/18" + --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) + --write-sub write subtitle file (currently youtube only) + --only-sub [deprecated] alias of --skip-download + --all-subs downloads all the available subtitles of the + video (currently youtube only) + --list-subs lists all available subtitles for the video + (currently youtube only) + --sub-format LANG subtitle format [srt/sbv] (default=srt) + (currently youtube only) + --sub-lang LANG language of the subtitles to download (optional) + use IETF language tags like 'en' ## Authentication Options: - -u, --username USERNAME account username - -p, --password PASSWORD account password - -n, --netrc use .netrc authentication data + -u, --username USERNAME account username + -p, --password PASSWORD account password + -n, --netrc use .netrc authentication data ## Post-processing Options: - -x, --extract-audio convert video files to audio-only files (requires - ffmpeg or avconv and ffprobe or avprobe) - --audio-format FORMAT "best", "aac", "vorbis", "mp3", "m4a", "opus", or - "wav"; best by default - --audio-quality QUALITY ffmpeg/avconv audio quality specification, insert a - value between 0 (better) and 9 (worse) for VBR or a - specific bitrate like 128K (default 5) - --recode-video FORMAT Encode the video to another format if necessary - (currently supported: mp4|flv|ogg|webm) - -k, --keep-video keeps the video file on disk after the post- - processing; the video is erased by default - --no-post-overwrites do not overwrite post-processed files; the post- - processed files are overwritten by default + -x, --extract-audio convert video files to audio-only files (requires + ffmpeg or avconv and ffprobe or avprobe) + --audio-format FORMAT "best", "aac", "vorbis", "mp3", "m4a", "opus", or + "wav"; best by default + --audio-quality QUALITY ffmpeg/avconv audio quality specification, insert + a value between 0 (better) and 9 (worse) for VBR + or a specific bitrate like 128K (default 5) + --recode-video FORMAT Encode the video to another format if necessary + (currently supported: mp4|flv|ogg|webm) + -k, --keep-video keeps the video file on disk after the post- + processing; the video is erased by default + --no-post-overwrites do not overwrite post-processed files; the post- + processed files are overwritten by default # CONFIGURATION @@ -138,6 +162,8 @@ The `-o` option allows users to indicate a template for the output file names. T - `ext`: The sequence will be replaced by the appropriate extension (like flv or mp4). - `epoch`: The sequence will be replaced by the Unix epoch when creating the file. - `autonumber`: The sequence will be replaced by a five-digit number that will be increased with each download, starting at zero. + - `playlist`: The name or the id of the playlist that contains the video. + - `playlist_index`: The index of the video in the playlist, a five-digit number. The current default template is `%(id)s.%(ext)s`, but that will be switchted to `%(title)s-%(id)s.%(ext)s` (which can be requested with `-t` at the moment). @@ -148,6 +174,19 @@ In some cases, you don't want special characters such as 中, spaces, or &, such $ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc --restrict-filenames youtube-dl_test_video_.mp4 # A simple file name +# VIDEO SELECTION + +Videos can be filtered by their upload date using the options `--date`, `--datebefore` or `--dateafter`, they accept dates in two formats: + + - Absolute dates: Dates in the format `YYYYMMDD`. + - Relative dates: Dates in the format `(now|today)[+-][0-9](day|week|month|year)(s)?` + +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 + # FAQ ### Can you please put the -b option back? diff --git a/devscripts/gh-pages/update-feed.py b/devscripts/gh-pages/update-feed.py new file mode 100755 index 000000000..cfff05fc8 --- /dev/null +++ b/devscripts/gh-pages/update-feed.py @@ -0,0 +1,57 @@ +#!/usr/bin/env python3 + +import datetime + +import textwrap + +import json + +atom_template=textwrap.dedent("""\ + + + youtube-dl releases + youtube-dl-updates-feed + @TIMESTAMP@ + @ENTRIES@ + """) + +entry_template=textwrap.dedent(""" + + youtube-dl-@VERSION@ + New version @VERSION@ + + +
+ Downloads available at http://youtube-dl.org/downloads/@VERSION@/ +
+ + + The youtube-dl maintainers + + @TIMESTAMP@ + + """) + +now = datetime.datetime.now() +now_iso = now.isoformat() + +atom_template = atom_template.replace('@TIMESTAMP@',now_iso) + +entries=[] + +versions_info = json.load(open('update/versions.json')) +versions = list(versions_info['versions'].keys()) +versions.sort() + +for v in versions: + entry = entry_template.replace('@TIMESTAMP@',v.replace('.','-')) + 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) + + diff --git a/devscripts/release.sh b/devscripts/release.sh index ee650f221..b2a91f817 100755 --- a/devscripts/release.sh +++ b/devscripts/release.sh @@ -69,6 +69,7 @@ ROOT=$(pwd) ORIGIN_URL=$(git config --get remote.origin.url) cd build/gh-pages "$ROOT/devscripts/gh-pages/add-version.py" $version + "$ROOT/devscripts/gh-pages/update-feed.py" "$ROOT/devscripts/gh-pages/sign-versions.py" < "$ROOT/updates_key.pem" "$ROOT/devscripts/gh-pages/generate-download.py" "$ROOT/devscripts/gh-pages/update-copyright.py" diff --git a/devscripts/transition_helper_exe/youtube-dl.py b/devscripts/transition_helper_exe/youtube-dl.py index dbb4c99e1..6297dfd40 100644 --- a/devscripts/transition_helper_exe/youtube-dl.py +++ b/devscripts/transition_helper_exe/youtube-dl.py @@ -40,7 +40,7 @@ raw_input() filename = sys.argv[0] -UPDATE_URL = "http://rg3.github.com/youtube-dl/update/" +UPDATE_URL = "http://rg3.github.io/youtube-dl/update/" VERSION_URL = UPDATE_URL + 'LATEST_VERSION' JSON_URL = UPDATE_URL + 'versions.json' UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537) diff --git a/test/parameters.json b/test/parameters.json index 8215d25c5..96998b5c3 100644 --- a/test/parameters.json +++ b/test/parameters.json @@ -29,6 +29,7 @@ "simulate": false, "skip_download": false, "subtitleslang": null, + "subtitlesformat": "srt", "test": true, "updatetime": true, "usenetrc": false, @@ -36,5 +37,8 @@ "verbose": true, "writedescription": false, "writeinfojson": true, - "writesubtitles": false -} \ No newline at end of file + "writesubtitles": false, + "onlysubtitles": false, + "allsubtitles": false, + "listssubtitles": false +} diff --git a/test/test_all_urls.py b/test/test_all_urls.py index 69717b3fc..a40360122 100644 --- a/test/test_all_urls.py +++ b/test/test_all_urls.py @@ -7,7 +7,7 @@ import unittest import os sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) -from youtube_dl.InfoExtractors import YoutubeIE, YoutubePlaylistIE +from youtube_dl.InfoExtractors import YoutubeIE, YoutubePlaylistIE, YoutubeChannelIE class TestAllURLsMatching(unittest.TestCase): def test_youtube_playlist_matching(self): @@ -24,6 +24,11 @@ class TestAllURLsMatching(unittest.TestCase): self.assertTrue(YoutubeIE.suitable(u'PLtS2H6bU1M')) self.assertFalse(YoutubeIE.suitable(u'https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) #668 + def test_youtube_channel_matching(self): + self.assertTrue(YoutubeChannelIE.suitable('https://www.youtube.com/channel/HCtnHdj3df7iM')) + self.assertTrue(YoutubeChannelIE.suitable('https://www.youtube.com/channel/HCtnHdj3df7iM?feature=gb_ch_rec')) + self.assertTrue(YoutubeChannelIE.suitable('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')) + def test_youtube_extract(self): self.assertEqual(YoutubeIE()._extract_id('http://www.youtube.com/watch?&v=BaW_jenozKc'), 'BaW_jenozKc') self.assertEqual(YoutubeIE()._extract_id('https://www.youtube.com/watch?&v=BaW_jenozKc'), 'BaW_jenozKc') diff --git a/test/test_download.py b/test/test_download.py index f1bccf58c..3eca333f2 100644 --- a/test/test_download.py +++ b/test/test_download.py @@ -20,6 +20,8 @@ from youtube_dl.utils import * DEF_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'tests.json') PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json") +RETRIES = 3 + # General configuration (from __init__, not very elegant...) jar = compat_cookiejar.CookieJar() cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar) @@ -56,6 +58,7 @@ with io.open(PARAMETERS_FILE, encoding='utf-8') as pf: class TestDownload(unittest.TestCase): + maxDiff = None def setUp(self): self.parameters = parameters self.defs = defs @@ -64,7 +67,7 @@ class TestDownload(unittest.TestCase): def generator(test_case): def test_template(self): - ie = getattr(youtube_dl.InfoExtractors, test_case['name'] + 'IE') + ie = youtube_dl.InfoExtractors.get_info_extractor(test_case['name']) if not ie._WORKING: print('Skipping: IE marked as not _WORKING') return @@ -79,9 +82,8 @@ def generator(test_case): params.update(test_case.get('params', {})) fd = FileDownloader(params) - fd.add_info_extractor(ie()) - for ien in test_case.get('add_ie', []): - fd.add_info_extractor(getattr(youtube_dl.InfoExtractors, ien + 'IE')()) + for ie in youtube_dl.InfoExtractors.gen_extractors(): + fd.add_info_extractor(ie) finished_hook_called = set() def _hook(status): if status['status'] == 'finished': @@ -94,7 +96,19 @@ def generator(test_case): _try_rm(tc['file'] + '.part') _try_rm(tc['file'] + '.info.json') try: - fd.download([test_case['url']]) + for retry in range(1, RETRIES + 1): + try: + fd.download([test_case['url']]) + except (DownloadError, ExtractorError) as err: + if retry == RETRIES: raise + + # Check if the exception is not a network related one + if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError): + raise + + print('Retrying: {0} failed tries\n\n##########\n\n'.format(retry)) + else: + break for tc in test_cases: if not test_case.get('params', {}).get('skip_download', False): diff --git a/test/test_utils.py b/test/test_utils.py index eeaaa7fad..c4b71362e 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -14,6 +14,8 @@ from youtube_dl.utils import timeconvert from youtube_dl.utils import sanitize_filename from youtube_dl.utils import unescapeHTML from youtube_dl.utils import orderedSet +from youtube_dl.utils import DateRange +from youtube_dl.utils import unified_strdate if sys.version_info < (3, 0): _compat_str = lambda b: b.decode('unicode-escape') @@ -95,6 +97,20 @@ class TestUtil(unittest.TestCase): def test_unescape_html(self): self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;')) + + def test_daterange(self): + _20century = DateRange("19000101","20000101") + self.assertFalse("17890714" in _20century) + _ac = DateRange("00010101") + self.assertTrue("19690721" in _ac) + _firstmilenium = DateRange(end="10000101") + self.assertTrue("07110427" in _firstmilenium) + + def test_unified_dates(self): + self.assertEqual(unified_strdate('December 21, 2010'), '20101221') + self.assertEqual(unified_strdate('8/7/2009'), '20090708') + self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214') + self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011') if __name__ == '__main__': unittest.main() diff --git a/test/test_youtube_lists.py b/test/test_youtube_lists.py index f4705bc5b..78657b51c 100644 --- a/test/test_youtube_lists.py +++ b/test/test_youtube_lists.py @@ -8,8 +8,9 @@ import json import os sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) -from youtube_dl.InfoExtractors import YoutubeUserIE, YoutubePlaylistIE, YoutubeIE +from youtube_dl.InfoExtractors import YoutubeUserIE, YoutubePlaylistIE, YoutubeIE, YoutubeChannelIE from youtube_dl.utils import * +from youtube_dl.FileDownloader import FileDownloader PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json") with io.open(PARAMETERS_FILE, encoding='utf-8') as pf: @@ -22,64 +23,87 @@ proxy_handler = compat_urllib_request.ProxyHandler() opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler()) compat_urllib_request.install_opener(opener) -class FakeDownloader(object): +class FakeDownloader(FileDownloader): def __init__(self): self.result = [] self.params = parameters def to_screen(self, s): print(s) - def trouble(self, s): + def trouble(self, s, tb=None): raise Exception(s) - def download(self, x): - self.result.append(x) + def extract_info(self, url): + self.result.append(url) + return url class TestYoutubeLists(unittest.TestCase): + def assertIsPlaylist(self,info): + """Make sure the info has '_type' set to 'playlist'""" + self.assertEqual(info['_type'], 'playlist') + def test_youtube_playlist(self): dl = FakeDownloader() ie = YoutubePlaylistIE(dl) - ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re') - ytie_results = [YoutubeIE()._extract_id(r[0]) for r in dl.result] + result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')[0] + self.assertIsPlaylist(result) + self.assertEqual(result['title'], 'ytdl test PL') + ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']] self.assertEqual(ytie_results, [ 'bV9L5Ht9LgY', 'FXxLjLQi3Fg', 'tU3Bgo5qJZE']) def test_issue_673(self): dl = FakeDownloader() ie = YoutubePlaylistIE(dl) - ie.extract('PLBB231211A4F62143') - self.assertTrue(len(dl.result) > 40) + result = ie.extract('PLBB231211A4F62143')[0] + self.assertEqual(result['title'], 'Team Fortress 2') + self.assertTrue(len(result['entries']) > 40) def test_youtube_playlist_long(self): dl = FakeDownloader() ie = YoutubePlaylistIE(dl) - ie.extract('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q') - self.assertTrue(len(dl.result) >= 799) + result = ie.extract('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')[0] + self.assertIsPlaylist(result) + self.assertTrue(len(result['entries']) >= 799) def test_youtube_playlist_with_deleted(self): #651 dl = FakeDownloader() ie = YoutubePlaylistIE(dl) - ie.extract('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC') - ytie_results = [YoutubeIE()._extract_id(r[0]) for r in dl.result] + result = ie.extract('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')[0] + ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']] self.assertFalse('pElCt5oNDuI' in ytie_results) self.assertFalse('KdPEApIVdWM' in ytie_results) + + def test_youtube_playlist_empty(self): + dl = FakeDownloader() + ie = YoutubePlaylistIE(dl) + result = ie.extract('https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx')[0] + self.assertIsPlaylist(result) + self.assertEqual(len(result['entries']), 0) def test_youtube_course(self): dl = FakeDownloader() ie = YoutubePlaylistIE(dl) # TODO find a > 100 (paginating?) videos course - ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8') - self.assertEqual(YoutubeIE()._extract_id(dl.result[0][0]), 'j9WZyLZCBzs') - self.assertEqual(len(dl.result), 25) - self.assertEqual(YoutubeIE()._extract_id(dl.result[-1][0]), 'rYefUsYuEp0') + result = ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')[0] + entries = result['entries'] + self.assertEqual(YoutubeIE()._extract_id(entries[0]['url']), 'j9WZyLZCBzs') + self.assertEqual(len(entries), 25) + self.assertEqual(YoutubeIE()._extract_id(entries[-1]['url']), 'rYefUsYuEp0') def test_youtube_channel(self): - # I give up, please find a channel that does paginate and test this like test_youtube_playlist_long - pass # TODO + dl = FakeDownloader() + ie = YoutubeChannelIE(dl) + #test paginated channel + result = ie.extract('https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w')[0] + self.assertTrue(len(result['entries']) > 90) + #test autogenerated channel + result = ie.extract('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')[0] + self.assertTrue(len(result['entries']) >= 18) def test_youtube_user(self): dl = FakeDownloader() ie = YoutubeUserIE(dl) - ie.extract('https://www.youtube.com/user/TheLinuxFoundation') - self.assertTrue(len(dl.result) >= 320) + result = ie.extract('https://www.youtube.com/user/TheLinuxFoundation')[0] + self.assertTrue(len(result['entries']) >= 320) if __name__ == '__main__': unittest.main() diff --git a/test/test_youtube_subtitles.py b/test/test_youtube_subtitles.py index 5d3566a35..a123e6d72 100644 --- a/test/test_youtube_subtitles.py +++ b/test/test_youtube_subtitles.py @@ -12,6 +12,7 @@ sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) from youtube_dl.InfoExtractors import YoutubeIE from youtube_dl.utils import * +from youtube_dl import FileDownloader PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json") with io.open(PARAMETERS_FILE, encoding='utf-8') as pf: @@ -24,13 +25,13 @@ proxy_handler = compat_urllib_request.ProxyHandler() opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler()) compat_urllib_request.install_opener(opener) -class FakeDownloader(object): +class FakeDownloader(FileDownloader): def __init__(self): self.result = [] self.params = parameters def to_screen(self, s): print(s) - def trouble(self, s): + def trouble(self, s, tb=None): raise Exception(s) def download(self, x): self.result.append(x) @@ -38,20 +39,63 @@ class FakeDownloader(object): md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest() class TestYoutubeSubtitles(unittest.TestCase): + def setUp(self): + DL = FakeDownloader() + DL.params['allsubtitles'] = False + DL.params['writesubtitles'] = False + DL.params['subtitlesformat'] = 'srt' + DL.params['listsubtitles'] = False + def test_youtube_no_subtitles(self): + DL = FakeDownloader() + DL.params['writesubtitles'] = False + IE = YoutubeIE(DL) + info_dict = IE.extract('QRS8MkLhQmM') + subtitles = info_dict[0]['subtitles'] + self.assertEqual(subtitles, None) def test_youtube_subtitles(self): DL = FakeDownloader() DL.params['writesubtitles'] = True IE = YoutubeIE(DL) info_dict = IE.extract('QRS8MkLhQmM') - self.assertEqual(md5(info_dict[0]['subtitles']), 'c3228550d59116f3c29fba370b55d033') - + sub = info_dict[0]['subtitles'][0] + self.assertEqual(md5(sub[2]), '4cd9278a35ba2305f47354ee13472260') def test_youtube_subtitles_it(self): DL = FakeDownloader() DL.params['writesubtitles'] = True DL.params['subtitleslang'] = 'it' IE = YoutubeIE(DL) info_dict = IE.extract('QRS8MkLhQmM') - self.assertEqual(md5(info_dict[0]['subtitles']), '132a88a0daf8e1520f393eb58f1f646a') + sub = info_dict[0]['subtitles'][0] + self.assertEqual(md5(sub[2]), '164a51f16f260476a05b50fe4c2f161d') + def test_youtube_onlysubtitles(self): + DL = FakeDownloader() + DL.params['writesubtitles'] = True + DL.params['onlysubtitles'] = True + IE = YoutubeIE(DL) + info_dict = IE.extract('QRS8MkLhQmM') + sub = info_dict[0]['subtitles'][0] + self.assertEqual(md5(sub[2]), '4cd9278a35ba2305f47354ee13472260') + def test_youtube_allsubtitles(self): + DL = FakeDownloader() + DL.params['allsubtitles'] = True + IE = YoutubeIE(DL) + info_dict = IE.extract('QRS8MkLhQmM') + subtitles = info_dict[0]['subtitles'] + self.assertEqual(len(subtitles), 13) + def test_youtube_subtitles_format(self): + DL = FakeDownloader() + DL.params['writesubtitles'] = True + DL.params['subtitlesformat'] = 'sbv' + IE = YoutubeIE(DL) + info_dict = IE.extract('QRS8MkLhQmM') + sub = info_dict[0]['subtitles'][0] + self.assertEqual(md5(sub[2]), '13aeaa0c245a8bed9a451cb643e3ad8b') + def test_youtube_list_subtitles(self): + DL = FakeDownloader() + DL.params['listsubtitles'] = True + IE = YoutubeIE(DL) + info_dict = IE.extract('QRS8MkLhQmM') + self.assertEqual(info_dict, None) if __name__ == '__main__': unittest.main() diff --git a/test/tests.json b/test/tests.json index e4ea0b41e..f57ebf1c9 100644 --- a/test/tests.json +++ b/test/tests.json @@ -76,8 +76,7 @@ "name": "StanfordOpenClassroom", "md5": "544a9468546059d4e80d76265b0443b8", "url": "http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100", - "file": "PracticalUnix_intro-environment.mp4", - "skip": "Currently offline" + "file": "PracticalUnix_intro-environment.mp4" }, { "name": "XNXX", @@ -113,9 +112,8 @@ { "name": "Escapist", "url": "http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate", - "file": "6618-Breaking-Down-Baldurs-Gate.flv", - "md5": "c6793dbda81388f4264c1ba18684a74d", - "skip": "Fails with timeout on Travis" + "file": "6618-Breaking-Down-Baldurs-Gate.mp4", + "md5": "c6793dbda81388f4264c1ba18684a74d" }, { "name": "GooglePlus", @@ -154,7 +152,8 @@ "file": "20274954.flv", "md5": "088f151799e8f572f84eb62f17d73e5c", "info_dict": { - "title": "Young Americans for Liberty February 7, 2012 2:28 AM" + "title": "Young Americans for Liberty February 7, 2012 2:28 AM", + "uploader": "Young Americans for Liberty" } }, { @@ -299,5 +298,189 @@ "url": "http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html", "file": "13601338388002.mp4", "md5": "85b90ccc9d73b4acd9138d3af4c27f89" + }, + { + "name": "Spiegel", + "url": "http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html", + "file": "1259285.mp4", + "md5": "2c2754212136f35fb4b19767d242f66e", + "info_dict": { + "title": "Vulkanausbruch in Ecuador: Der \"Feuerschlund\" ist wieder aktiv" + } + }, + { + "name": "LiveLeak", + "md5": "0813c2430bea7a46bf13acf3406992f4", + "url": "http://www.liveleak.com/view?i=757_1364311680", + "file": "757_1364311680.mp4", + "info_dict": { + "title": "Most unlucky car accident", + "description": "extremely bad day for this guy..!", + "uploader": "ljfriel2" + } + }, + { + "name": "WorldStarHipHop", + "url": "http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO", + "file": "wshh6a7q1ny0G34ZwuIO.mp4", + "md5": "9d04de741161603bf7071bbf4e883186", + "info_dict": { + "title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick! " + } + }, + { + "name": "ARD", + "url": "http://www.ardmediathek.de/das-erste/tagesschau-in-100-sek?documentId=14077640", + "file": "14077640.mp4", + "md5": "6ca8824255460c787376353f9e20bbd8", + "info_dict": { + "title": "11.04.2013 09:23 Uhr - Tagesschau in 100 Sekunden" + }, + "skip": "Requires rtmpdump" + }, + { + "name": "Tumblr", + "url": "http://birthdayproject2012.tumblr.com/post/17258355236/a-sample-video-from-leeann-if-you-need-an-idea", + "file": "17258355236.mp4", + "md5": "7c6a514d691b034ccf8567999e9e88a3", + "info_dict": { + "title": "Calling all Pris! - A sample video from LeeAnn. (If you need an idea..." + } + }, + { + "name": "SoundcloudSet", + "url":"https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep", + "playlist":[ + { + "file":"30510138.mp3", + "md5":"f9136bf103901728f29e419d2c70f55d", + "info_dict": { + "title":"D-D-Dance" + } + }, + { + "file":"47127625.mp3", + "md5":"09b6758a018470570f8fd423c9453dd8", + "info_dict": { + "title":"The Royal Concept - Gimme Twice" + } + }, + { + "file":"47127627.mp3", + "md5":"154abd4e418cea19c3b901f1e1306d9c", + "info_dict": { + "title":"Goldrushed" + } + }, + { + "file":"47127629.mp3", + "md5":"2f5471edc79ad3f33a683153e96a79c1", + "info_dict": { + "title":"In the End" + } + }, + { + "file":"47127631.mp3", + "md5":"f9ba87aa940af7213f98949254f1c6e2", + "info_dict": { + "title":"Knocked Up" + } + }, + { + "file":"75206121.mp3", + "md5":"f9d1fe9406717e302980c30de4af9353", + "info_dict": { + "title":"World On Fire" + } + } + ] + }, + { + "name":"Bandcamp", + "url":"http://youtube-dl.bandcamp.com/track/youtube-dl-test-song", + "file":"1812978515.mp3", + "md5":"cdeb30cdae1921719a3cbcab696ef53c", + "info_dict": { + "title":"youtube-dl test song \"'/\\ä↭" + }, + "skip": "There is a limit of 200 free downloads / month for the test song" + }, + { + "name": "RedTube", + "url": "http://www.redtube.com/66418", + "file": "66418.mp4", + "md5": "7b8c22b5e7098a3e1c09709df1126d2d", + "info_dict":{ + "title":"Sucked on a toilet" + } + }, + { + "name": "Photobucket", + "url": "http://media.photobucket.com/user/rachaneronas/media/TiredofLinkBuildingTryBacklinkMyDomaincom_zpsc0c3b9fa.mp4.html?filters[term]=search&filters[primary]=videos&filters[secondary]=images&sort=1&o=0", + "file": "zpsc0c3b9fa.mp4", + "md5": "7dabfb92b0a31f6c16cebc0f8e60ff99", + "info_dict":{ + "title":"Tired of Link Building? Try BacklinkMyDomain.com!" + } + }, + { + "name": "Ina", + "url": "www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html", + "file": "I12055569.mp4", + "md5": "a667021bf2b41f8dc6049479d9bb38a3", + "info_dict":{ + "title":"François Hollande \"Je crois que c'est clair\"" + } + }, + { + "name": "Yahoo", + "url": "http://screen.yahoo.com/obama-celebrates-iraq-victory-27592561.html", + "file": "27592561.flv", + "md5": "c6179bed843512823fd284fa2e7f012d", + "info_dict": { + "title": "Obama Celebrates Iraq Victory" + }, + "skip": "Requires rtmpdump" + }, + { + "name": "Howcast", + "url": "http://www.howcast.com/videos/390161-How-to-Tie-a-Square-Knot-Properly", + "file": "390161.mp4", + "md5": "1d7ba54e2c9d7dc6935ef39e00529138", + "info_dict":{ + "title":"How to Tie a Square Knot Properly", + "description":"The square knot, also known as the reef knot, is one of the oldest, most basic knots to tie, and can be used in many different ways. Here's the proper way to tie a square knot." + } + }, + { + "name": "Vine", + "url": "https://vine.co/v/b9KOOWX7HUx", + "file": "b9KOOWX7HUx.mp4", + "md5": "2f36fed6235b16da96ce9b4dc890940d", + "info_dict":{ + "title": "Chicken.", + "uploader": "Jack Dorsey" + } + }, + { + "name": "Flickr", + "url": "http://www.flickr.com/photos/forestwander-nature-pictures/5645318632/in/photostream/", + "file": "5645318632.mp4", + "md5": "6fdc01adbc89d72fc9c4f15b4a4ba87b", + "info_dict":{ + "title": "Dark Hollow Waterfalls", + "uploader_id": "forestwander-nature-pictures", + "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." + } + }, + { + "name": "Teamcoco", + "url": "http://teamcoco.com/video/louis-ck-interview-george-w-bush", + "file": "19705.mp4", + "md5": "27b6f7527da5acf534b15f21b032656e", + "info_dict":{ + "title": "Louis C.K. Interview Pt. 1 11/3/11", + "description": "Louis C.K. got starstruck by George W. Bush, so what? Part one." + } } ] diff --git a/youtube-dl b/youtube-dl index 65999d311..e3eb8774c 100755 Binary files a/youtube-dl and b/youtube-dl differ diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 795c22cad..62b17d5c5 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -7,6 +7,7 @@ import math import io import os import re +import shutil import socket import subprocess import sys @@ -17,6 +18,7 @@ if os.name == 'nt': import ctypes from .utils import * +from .InfoExtractors import get_info_extractor class FileDownloader(object): @@ -52,6 +54,7 @@ class FileDownloader(object): quiet: Do not print messages to stdout. forceurl: Force printing final URL. forcetitle: Force printing title. + forceid: Force printing ID. forcethumbnail: Force printing thumbnail URL. forcedescription: Force printing description. forcefilename: Force printing final filename. @@ -78,12 +81,18 @@ class FileDownloader(object): updatetime: Use the Last-modified header to set output file timestamps. writedescription: Write the video description to a .description file writeinfojson: Write the video description to a .info.json file - writesubtitles: Write the video subtitles to a .srt file + writethumbnail: Write the thumbnail image to a file + writesubtitles: Write the video subtitles to a file + allsubtitles: Downloads all the subtitles of the video + listsubtitles: Lists all available subtitles for the video + subtitlesformat: Subtitle format [sbv/srt] (default=srt) subtitleslang: Language of the subtitles to download test: Download only first bytes to test the downloader. keepvideo: Keep the video file after post-processing min_filesize: Skip files smaller than this size max_filesize: Skip files larger than this size + daterange: A DateRange object, download only if the upload_date is in the range. + skip_download: Skip the actual download of the video file """ params = None @@ -116,7 +125,7 @@ class FileDownloader(object): exponent = 0 else: exponent = int(math.log(bytes, 1024.0)) - suffix = 'bkMGTPEZY'[exponent] + suffix = ['B','KiB','MiB','GiB','TiB','PiB','EiB','ZiB','YiB'][exponent] converted = float(bytes) / float(1024 ** exponent) return '%.2f%s' % (converted, suffix) @@ -227,11 +236,21 @@ class FileDownloader(object): self.to_stderr(message) if self.params.get('verbose'): if tb is None: - tb_data = traceback.format_list(traceback.extract_stack()) - tb = u''.join(tb_data) + if sys.exc_info()[0]: # if .trouble has been called from an except block + tb = u'' + 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 += compat_str(traceback.format_exc()) + else: + tb_data = traceback.format_list(traceback.extract_stack()) + tb = u''.join(tb_data) self.to_stderr(tb) if not self.params.get('ignoreerrors', False): - raise DownloadError(message) + if sys.exc_info()[0] and hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]: + exc_info = sys.exc_info()[1].exc_info + else: + exc_info = sys.exc_info() + raise DownloadError(message, exc_info) self._download_retcode = 1 def report_warning(self, message): @@ -239,13 +258,25 @@ class FileDownloader(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(): + if sys.stderr.isatty() and os.name != 'nt': _msg_header=u'\033[0;33mWARNING:\033[0m' else: _msg_header=u'WARNING:' warning_message=u'%s %s' % (_msg_header,message) self.to_stderr(warning_message) + def report_error(self, message, tb=None): + ''' + 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' + else: + _msg_header = u'ERROR:' + error_message = u'%s %s' % (_msg_header, message) + self.trouble(error_message, tb) + 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) @@ -277,7 +308,7 @@ class FileDownloader(object): return os.rename(encodeFilename(old_filename), encodeFilename(new_filename)) except (IOError, OSError) as err: - self.trouble(u'ERROR: unable to rename file') + 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.""" @@ -301,9 +332,9 @@ class FileDownloader(object): """ Report that the description file is being written """ self.to_screen(u'[info] Writing video description to: ' + descfn) - def report_writesubtitles(self, srtfn): + def report_writesubtitles(self, sub_filename): """ Report that the subtitles file is being written """ - self.to_screen(u'[info] Writing video subtitles to: ' + srtfn) + self.to_screen(u'[info] Writing video subtitles to: ' + sub_filename) def report_writeinfojson(self, infofn): """ Report that the metadata file has been written """ @@ -317,12 +348,13 @@ class FileDownloader(object): """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 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[download] %s of %s at %s ETA %s' % - (percent_str, data_len_str, speed_str, eta_str), skip_eol=True) + 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_cons_title(u'youtube-dl - %s of %s at %s ETA %s' % (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip())) @@ -362,7 +394,13 @@ class FileDownloader(object): template_dict = dict(info_dict) template_dict['epoch'] = int(time.time()) - template_dict['autonumber'] = u'%05d' % self._num_downloads + autonumber_size = self.params.get('autonumber_size') + if autonumber_size is None: + autonumber_size = 5 + autonumber_templ = u'%0' + str(autonumber_size) + u'd' + template_dict['autonumber'] = autonumber_templ % self._num_downloads + if template_dict['playlist_index'] is not None: + template_dict['playlist_index'] = u'%05d' % template_dict['playlist_index'] sanitize = lambda k,v: sanitize_filename( u'NA' if v is None else compat_str(v), @@ -373,10 +411,10 @@ class FileDownloader(object): filename = self.params['outtmpl'] % template_dict return filename except KeyError as err: - self.trouble(u'ERROR: Erroneous output template') + self.report_error(u'Erroneous output template') return None except ValueError as err: - self.trouble(u'ERROR: Insufficient system charset ' + repr(preferredencoding())) + self.report_error(u'Insufficient system charset ' + repr(preferredencoding())) return None def _match_entry(self, info_dict): @@ -391,10 +429,144 @@ class FileDownloader(object): if rejecttitle: if re.search(rejecttitle, title, re.IGNORECASE): return u'"' + 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 None + + def extract_info(self, url, download=True, ie_key=None, extra_info={}): + ''' + Returns a list with a dictionary for each video we find. + If 'download', also downloads the videos. + extra_info is a dict containing the extra values to add to each result + ''' + + if ie_key: + ie = get_info_extractor(ie_key)() + ie.set_downloader(self) + ies = [ie] + else: + ies = self._ies + + for ie in ies: + if not ie.suitable(url): + 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.') + + try: + ie_result = ie.extract(url) + if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here) + break + if isinstance(ie_result, list): + # Backwards compatibility: old IE result format + for result in ie_result: + result.update(extra_info) + ie_result = { + '_type': 'compat_list', + 'entries': ie_result, + } + else: + ie_result.update(extra_info) + if 'extractor' not in ie_result: + ie_result['extractor'] = ie.IE_NAME + return self.process_ie_result(ie_result, download=download) + except ExtractorError as de: # An error we somewhat expected + self.report_error(compat_str(de), de.format_traceback()) + break + except Exception as e: + if self.params.get('ignoreerrors', False): + self.report_error(compat_str(e), tb=compat_str(traceback.format_exc())) + break + else: + raise + else: + self.report_error(u'no suitable InfoExtractor: %s' % url) + + def process_ie_result(self, ie_result, download=True, extra_info={}): + """ + Take the result of the ie(may be modified) and resolve all unresolved + references (URLs, playlist items). + + It will also download the videos if 'download'. + Returns the resolved ie_result. + """ + + result_type = ie_result.get('_type', 'video') # If not given we suppose it's a video, support the default old system + if result_type == 'video': + if 'playlist' not in ie_result: + # It isn't part of a playlist + ie_result['playlist'] = None + ie_result['playlist_index'] = None + if download: + self.process_info(ie_result) + return ie_result + elif result_type == 'url': + # We have to add extra_info to the results because it may be + # contained in a playlist + return self.extract_info(ie_result['url'], + download, + ie_key=ie_result.get('ie_key'), + extra_info=extra_info) + elif result_type == 'playlist': + # 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) + + playlist_results = [] + + n_all_entries = len(ie_result['entries']) + playliststart = self.params.get('playliststart', 1) - 1 + playlistend = self.params.get('playlistend', -1) + + if playlistend == -1: + entries = ie_result['entries'][playliststart:] + else: + 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)" % + (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)) + extra = { + 'playlist': playlist, + 'playlist_index': i + playliststart, + } + entry_result = self.process_ie_result(entry, + download=download, + extra_info=extra) + playlist_results.append(entry_result) + ie_result['entries'] = playlist_results + return ie_result + elif result_type == 'compat_list': + def _fixup(r): + r.setdefault('extractor', ie_result['extractor']) + return r + ie_result['entries'] = [ + self.process_ie_result(_fixup(r), download=download) + for r in ie_result['entries'] + ] + return ie_result + else: + raise Exception('Invalid result type: %s' % result_type) def process_info(self, info_dict): - """Process a single dictionary returned by an InfoExtractor.""" + """Process a single resolved IE result.""" + + assert info_dict.get('_type', 'video') == 'video' + #We increment the download the download count here to match the previous behaviour. + self.increment_downloads() + + info_dict['fulltitle'] = info_dict['title'] + if len(info_dict['title']) > 200: + info_dict['title'] = info_dict['title'][:197] + u'...' # Keep for backwards compatibility info_dict['stitle'] = info_dict['title'] @@ -417,6 +589,8 @@ class FileDownloader(object): # Forced printings if self.params.get('forcetitle', False): compat_print(info_dict['title']) + if self.params.get('forceid', False): + compat_print(info_dict['id']) if self.params.get('forceurl', False): compat_print(info_dict['url']) if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict: @@ -437,10 +611,10 @@ class FileDownloader(object): try: dn = os.path.dirname(encodeFilename(filename)) - if dn != '' and not os.path.exists(dn): # dn is already encoded + if dn != '' and not os.path.exists(dn): os.makedirs(dn) except (OSError, IOError) as err: - self.trouble(u'ERROR: unable to create directory ' + compat_str(err)) + self.report_error(u'unable to create directory ' + compat_str(err)) return if self.params.get('writedescription', False): @@ -450,20 +624,43 @@ class FileDownloader(object): with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile: descfile.write(info_dict['description']) except (OSError, IOError): - self.trouble(u'ERROR: Cannot write description file ' + descfn) + self.report_error(u'Cannot write description file ' + descfn) return if self.params.get('writesubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']: # subtitles download errors are already managed as troubles in relevant IE # that way it will silently go on when used with unsupporting IE - try: - srtfn = filename.rsplit('.', 1)[0] + u'.srt' - self.report_writesubtitles(srtfn) - with io.open(encodeFilename(srtfn), 'w', encoding='utf-8') as srtfile: - srtfile.write(info_dict['subtitles']) - except (OSError, IOError): - self.trouble(u'ERROR: Cannot write subtitles file ' + descfn) - return + subtitle = info_dict['subtitles'][0] + (sub_error, sub_lang, sub) = subtitle + sub_format = self.params.get('subtitlesformat') + if sub_error: + self.report_warning("Some error while getting the subtitles") + else: + try: + sub_filename = filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format + self.report_writesubtitles(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) + return + + if self.params.get('allsubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']: + subtitles = info_dict['subtitles'] + sub_format = self.params.get('subtitlesformat') + for subtitle in subtitles: + (sub_error, sub_lang, sub) = subtitle + if sub_error: + self.report_warning("Some error while getting the subtitles") + else: + try: + sub_filename = filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format + self.report_writesubtitles(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) + return if self.params.get('writeinfojson', False): infofn = filename + u'.info.json' @@ -472,9 +669,23 @@ class FileDownloader(object): 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.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn) + self.report_error(u'Cannot write metadata to JSON file ' + infofn) return + if self.params.get('writethumbnail', False): + if 'thumbnail' in info_dict: + thumb_format = info_dict['thumbnail'].rpartition(u'/')[2].rpartition(u'.')[2] + if not thumb_format: + thumb_format = 'jpg' + thumb_filename = filename.rpartition('.')[0] + u'.' + thumb_format + self.to_screen(u'[%s] %s: Downloading thumbnail ...' % + (info_dict['extractor'], info_dict['id'])) + 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)) + if not self.params.get('skip_download', False): if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)): success = True @@ -484,17 +695,17 @@ class FileDownloader(object): except (OSError, IOError) as err: raise UnavailableVideoError() except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self.trouble(u'ERROR: unable to download video data: %s' % str(err)) + self.report_error(u'unable to download video data: %s' % str(err)) return except (ContentTooShortError, ) as err: - self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) + self.report_error(u'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.trouble(u'ERROR: postprocessing: %s' % str(err)) + self.report_error(u'postprocessing: %s' % str(err)) return def download(self, url_list): @@ -503,49 +714,14 @@ class FileDownloader(object): raise SameFileError(self.params['outtmpl']) for url in url_list: - suitable_found = False - for ie in self._ies: - # Go to next InfoExtractor if not suitable - if not ie.suitable(url): - continue - - # Warn if the _WORKING attribute is False - 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. If you want to go on, use the -i option.') - - # Suitable InfoExtractor found - suitable_found = True - - # Extract information from URL and process it - try: - videos = ie.extract(url) - except ExtractorError as de: # An error we somewhat expected - self.trouble(u'ERROR: ' + compat_str(de), de.format_traceback()) - break - except Exception as e: - if self.params.get('ignoreerrors', False): - self.trouble(u'ERROR: ' + compat_str(e), tb=compat_str(traceback.format_exc())) - break - else: - raise - - if len(videos or []) > 1 and self.fixed_template(): - raise SameFileError(self.params['outtmpl']) - - for video in videos or []: - video['extractor'] = ie.IE_NAME - try: - self.increment_downloads() - self.process_info(video) - except UnavailableVideoError: - self.trouble(u'\nERROR: unable to download video') - - # Suitable InfoExtractor had been found; go to next URL - break - - if not suitable_found: - self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url) + try: + #It also downloads the videos + videos = self.extract_info(url) + except UnavailableVideoError: + self.report_error(u'unable to download video') + except MaxDownloadsReached: + self.to_screen(u'[info] Maximum number of downloaded files reached.') + raise return self._download_retcode @@ -572,7 +748,7 @@ class FileDownloader(object): except (IOError, OSError): self.report_warning(u'Unable to remove downloaded video file') - def _download_with_rtmpdump(self, filename, url, player_url, page_url): + def _download_with_rtmpdump(self, filename, url, player_url, page_url, play_path, tc_url): self.report_destination(filename) tmpfilename = self.temp_name(filename) @@ -580,17 +756,22 @@ class FileDownloader(object): try: subprocess.call(['rtmpdump', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT) except (OSError, IOError): - self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run') + 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', '-q', '-r', url, '-o', tmpfilename] + if self.params.get('verbose', False): basic_args[1] = '-v' if player_url is not None: basic_args += ['-W', player_url] if page_url is not None: basic_args += ['--pageUrl', page_url] + if play_path is not None: + basic_args += ['-y', play_path] + if tc_url is not None: + basic_args += ['--tcUrl', url] args = basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)] if self.params.get('verbose', False): try: @@ -625,7 +806,8 @@ class FileDownloader(object): }) return True else: - self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval) + self.to_stderr(u"\n") + self.report_error(u'rtmpdump exited with code %d' % retval) return False # Keep a copy of the main cookiejar to pass to external downloaders @@ -701,7 +883,9 @@ class FileDownloader(object): 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('page_url', None), + info_dict.get('play_path', None), + info_dict.get('tc_url', None)) tmpfilename = self.temp_name(filename) stream = None @@ -784,7 +968,7 @@ class FileDownloader(object): self.report_retry(count, retries) if count > retries: - self.trouble(u'ERROR: giving up after %s retries' % retries) + self.report_error(u'giving up after %s retries' % retries) return False data_len = data.info().get('Content-length', None) @@ -820,12 +1004,13 @@ class FileDownloader(object): filename = self.undo_temp_name(tmpfilename) self.report_destination(filename) except (OSError, IOError) as err: - self.trouble(u'ERROR: unable to open for writing: %s' % str(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.trouble(u'\nERROR: unable to write data: %s' % str(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)) @@ -851,7 +1036,8 @@ class FileDownloader(object): self.slow_down(start, byte_counter - resume_len) if stream is None: - self.trouble(u'\nERROR: Did not get any data blocks') + self.to_stderr(u"\n") + self.report_error(u'Did not get any data blocks') return False stream.close() self.report_finish() diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index baba4a9a2..6b644e15f 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -16,6 +16,9 @@ import xml.etree.ElementTree import random import math import operator +import hashlib +import binascii +import urllib from .utils import * @@ -48,7 +51,7 @@ class InfoExtractor(object): 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 .srt file contents. + subtitles: The subtitle file contents. urlhandle: [internal] The urlHandle to be used to download the file, like returned by urllib.request.urlopen @@ -114,8 +117,9 @@ class InfoExtractor(object): def _request_webpage(self, url_or_request, video_id, note=None, errnote=None): """ Returns the response handle """ if note is None: - note = u'Downloading video webpage' - self._downloader.to_screen(u'[%s] %s: %s' % (self.IE_NAME, video_id, note)) + self.report_download_webpage(video_id) + elif note is not False: + self.to_screen(u'%s: %s' % (video_id, note)) try: return compat_urllib_request.urlopen(url_or_request) except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: @@ -123,11 +127,108 @@ class InfoExtractor(object): errnote = u'Unable to download webpage' raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2]) + def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None): + """ Returns a tuple (page content as string, URL handle) """ + urlh = self._request_webpage(url_or_request, video_id, note, errnote) + content_type = urlh.headers.get('Content-Type', '') + m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type) + if m: + encoding = m.group(1) + else: + encoding = 'utf-8' + webpage_bytes = urlh.read() + if self._downloader.params.get('dump_intermediate_pages', False): + try: + url = url_or_request.get_full_url() + except AttributeError: + url = url_or_request + self.to_screen(u'Dumping request to ' + url) + dump = base64.b64encode(webpage_bytes).decode('ascii') + self._downloader.to_screen(dump) + content = webpage_bytes.decode(encoding, 'replace') + return (content, urlh) + def _download_webpage(self, url_or_request, video_id, note=None, errnote=None): """ Returns the data of the page as a string """ - urlh = self._request_webpage(url_or_request, video_id, note, errnote) - webpage_bytes = urlh.read() - return webpage_bytes.decode('utf-8', 'replace') + return self._download_webpage_handle(url_or_request, video_id, note, errnote)[0] + + def to_screen(self, msg): + """Print msg to screen, prefixing it with '[ie_name]'""" + self._downloader.to_screen(u'[%s] %s' % (self.IE_NAME, msg)) + + def report_extraction(self, id_or_name): + """Report information extraction.""" + self.to_screen(u'%s: Extracting information' % id_or_name) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self.to_screen(u'%s: Downloading webpage' % video_id) + + def report_age_confirmation(self): + """Report attempt to confirm age.""" + self.to_screen(u'Confirming age') + + #Methods for following #608 + #They set the correct value of the '_type' key + def video_result(self, video_info): + """Returns a video""" + video_info['_type'] = 'video' + return video_info + def url_result(self, url, ie=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} + return video_info + def playlist_result(self, entries, playlist_id=None, playlist_title=None): + """Returns a playlist""" + video_info = {'_type': 'playlist', + 'entries': entries} + if playlist_id: + video_info['id'] = playlist_id + if playlist_title: + video_info['title'] = playlist_title + return video_info + +class SearchInfoExtractor(InfoExtractor): + """ + Base class for paged search queries extractors. + They accept urls in the format _SEARCH_KEY(|all|[0-9]):{query} + Instances should define _SEARCH_KEY and _MAX_RESULTS. + """ + + @classmethod + def _make_valid_url(cls): + return r'%s(?P|[1-9][0-9]*|all):(?P[\s\S]+)' % cls._SEARCH_KEY + + @classmethod + def suitable(cls, url): + return re.match(cls._make_valid_url(), url) is not None + + def _real_extract(self, query): + mobj = re.match(self._make_valid_url(), query) + if mobj is None: + raise ExtractorError(u'Invalid search query "%s"' % query) + + prefix = mobj.group('prefix') + query = mobj.group('query') + if prefix == '': + return self._get_n_results(query, 1) + elif prefix == 'all': + return self._get_n_results(query, self._MAX_RESULTS) + else: + n = int(prefix) + if n <= 0: + raise ExtractorError(u'invalid download number %s for query "%s"' % (n, query)) + elif n > self._MAX_RESULTS: + self._downloader.report_warning(u'%s returns max %i results (you requested %i)' % (self._SEARCH_KEY, self._MAX_RESULTS, n)) + n = self._MAX_RESULTS + return self._get_n_results(query, n) + + def _get_n_results(self, query, n): + """Get a specified number of results for a query""" + raise NotImplementedError("This method must be implemented by sublclasses") class YoutubeIE(InfoExtractor): @@ -152,7 +253,7 @@ class YoutubeIE(InfoExtractor): ([0-9A-Za-z_-]+) # here is it! the YouTube video ID (?(1).+)? # if we found the ID, everything can follow $""" - _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' + _LANG_URL = r'https://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' _LOGIN_URL = 'https://accounts.google.com/ServiceLogin' _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' _NEXT_URL_RE = r'[\?&]next_url=([^&]+)' @@ -198,89 +299,114 @@ class YoutubeIE(InfoExtractor): def report_lang(self): """Report attempt to set language.""" - self._downloader.to_screen(u'[youtube] Setting language') + self.to_screen(u'Setting language') def report_login(self): """Report attempt to log in.""" - self._downloader.to_screen(u'[youtube] Logging in') - - def report_age_confirmation(self): - """Report attempt to confirm age.""" - self._downloader.to_screen(u'[youtube] Confirming age') + self.to_screen(u'Logging in') def report_video_webpage_download(self, video_id): """Report attempt to download video webpage.""" - self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id) + self.to_screen(u'%s: Downloading video webpage' % video_id) def report_video_info_webpage_download(self, video_id): """Report attempt to download video info webpage.""" - self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id) + self.to_screen(u'%s: Downloading video info webpage' % video_id) def report_video_subtitles_download(self, video_id): """Report attempt to download video info webpage.""" - self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles' % video_id) + self.to_screen(u'%s: Checking available subtitles' % video_id) + + def report_video_subtitles_request(self, video_id, sub_lang, format): + """Report attempt to download video info webpage.""" + self.to_screen(u'%s: Downloading video subtitles for %s.%s' % (video_id, sub_lang, format)) + + def report_video_subtitles_available(self, video_id, sub_lang_list): + """Report available subtitles.""" + sub_lang = ",".join(list(sub_lang_list.keys())) + self.to_screen(u'%s: Available subtitles for video: %s' % (video_id, sub_lang)) def report_information_extraction(self, video_id): """Report attempt to extract video information.""" - self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id) + self.to_screen(u'%s: Extracting video information' % video_id) def report_unavailable_format(self, video_id, format): """Report extracted video URL.""" - self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format)) + self.to_screen(u'%s: Format %s not available' % (video_id, format)) def report_rtmp_download(self): """Indicate the download will use the RTMP protocol.""" - self._downloader.to_screen(u'[youtube] RTMP download detected') + self.to_screen(u'RTMP download detected') - def _closed_captions_xml_to_srt(self, xml_string): - srt = '' - texts = re.findall(r'([^<]+)', xml_string, re.MULTILINE) - # TODO parse xml instead of regex - for n, (start, dur_tag, dur, caption) in enumerate(texts): - if not dur: dur = '4' - start = float(start) - end = start + float(dur) - start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000) - end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000) - caption = unescapeHTML(caption) - caption = unescapeHTML(caption) # double cycle, intentional - srt += str(n+1) + '\n' - srt += start + ' --> ' + end + '\n' - srt += caption + '\n\n' - return srt - - def _extract_subtitles(self, video_id): + def _get_available_subtitles(self, video_id): self.report_video_subtitles_download(video_id) request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id) try: - srt_list = compat_urllib_request.urlopen(request).read().decode('utf-8') + sub_list = compat_urllib_request.urlopen(request).read().decode('utf-8') except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None) - srt_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list) - srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list) - if not srt_lang_list: - return (u'WARNING: video has no closed captions', None) - if self._downloader.params.get('subtitleslang', False): - srt_lang = self._downloader.params.get('subtitleslang') - elif 'en' in srt_lang_list: - srt_lang = 'en' - else: - srt_lang = list(srt_lang_list.keys())[0] - if not srt_lang in srt_lang_list: - return (u'WARNING: no closed captions found in the specified language', None) + return (u'unable to download video subtitles: %s' % compat_str(err), None) + sub_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list) + sub_lang_list = dict((l[1], l[0]) for l in sub_lang_list) + if not sub_lang_list: + return (u'video doesn\'t have subtitles', None) + return sub_lang_list + + def _list_available_subtitles(self, video_id): + sub_lang_list = self._get_available_subtitles(video_id) + self.report_video_subtitles_available(video_id, sub_lang_list) + + def _request_subtitle(self, sub_lang, sub_name, video_id, format): + """ + Return tuple: + (error_message, sub_lang, sub) + """ + self.report_video_subtitles_request(video_id, sub_lang, format) params = compat_urllib_parse.urlencode({ - 'lang': srt_lang, - 'name': srt_lang_list[srt_lang].encode('utf-8'), + 'lang': sub_lang, + 'name': sub_name, 'v': video_id, + 'fmt': format, }) url = 'http://www.youtube.com/api/timedtext?' + params try: - srt_xml = compat_urllib_request.urlopen(url).read().decode('utf-8') + sub = compat_urllib_request.urlopen(url).read().decode('utf-8') except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None) - if not srt_xml: - return (u'WARNING: Did not fetch video subtitles', None) - return (None, self._closed_captions_xml_to_srt(srt_xml)) + return (u'unable to download video subtitles: %s' % compat_str(err), None, None) + if not sub: + return (u'Did not fetch video subtitles', None, None) + return (None, sub_lang, sub) + + def _extract_subtitle(self, video_id): + """ + Return a list with a tuple: + [(error_message, sub_lang, sub)] + """ + sub_lang_list = self._get_available_subtitles(video_id) + sub_format = self._downloader.params.get('subtitlesformat') + if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles + return [(sub_lang_list[0], None, None)] + if self._downloader.params.get('subtitleslang', False): + sub_lang = self._downloader.params.get('subtitleslang') + elif 'en' in sub_lang_list: + sub_lang = 'en' + else: + sub_lang = list(sub_lang_list.keys())[0] + if not sub_lang in sub_lang_list: + return [(u'no closed captions found in the specified language "%s"' % sub_lang, None, None)] + + subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format) + return [subtitle] + + def _extract_all_subtitles(self, video_id): + sub_lang_list = self._get_available_subtitles(video_id) + sub_format = self._downloader.params.get('subtitlesformat') + if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles + return [(sub_lang_list[0], None, None)] + subtitles = [] + for sub_lang in sub_lang_list: + subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format) + subtitles.append(subtitle) + return subtitles def _print_formats(self, formats): print('Available formats:') @@ -343,7 +469,7 @@ class YoutubeIE(InfoExtractor): # Log in login_form_strs = { - u'continue': u'http://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1', + u'continue': u'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1', u'Email': username, u'GALX': galx, u'Passwd': password, @@ -388,14 +514,12 @@ class YoutubeIE(InfoExtractor): self.report_age_confirmation() age_results = compat_urllib_request.urlopen(request).read().decode('utf-8') except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err)) - return + raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err)) def _extract_id(self, url): mobj = re.match(self._VALID_URL, url, re.VERBOSE) if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return + raise ExtractorError(u'Invalid URL: %s' % url) video_id = mobj.group(2) return video_id @@ -403,18 +527,17 @@ class YoutubeIE(InfoExtractor): # Extract original video URL from URL with redirection, like age verification, using next_url parameter mobj = re.search(self._NEXT_URL_RE, url) if mobj: - url = 'http://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/') + url = 'https://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/') video_id = self._extract_id(url) # Get video webpage self.report_video_webpage_download(video_id) - url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id + url = 'https://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id request = compat_urllib_request.Request(url) try: video_webpage_bytes = compat_urllib_request.urlopen(request).read() except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) - return + raise ExtractorError(u'Unable to download video webpage: %s' % compat_str(err)) video_webpage = video_webpage_bytes.decode('utf-8', 'ignore') @@ -428,37 +551,30 @@ class YoutubeIE(InfoExtractor): # Get video info self.report_video_info_webpage_download(video_id) for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: - video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' + video_info_url = ('https://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' % (video_id, el_type)) - request = compat_urllib_request.Request(video_info_url) - try: - video_info_webpage_bytes = compat_urllib_request.urlopen(request).read() - video_info_webpage = video_info_webpage_bytes.decode('utf-8', 'ignore') - video_info = compat_parse_qs(video_info_webpage) - if 'token' in video_info: - break - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err)) - return + video_info_webpage = self._download_webpage(video_info_url, video_id, + note=False, + errnote='unable to download video info webpage') + video_info = compat_parse_qs(video_info_webpage) + if 'token' in video_info: + break if 'token' not in video_info: if 'reason' in video_info: - self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0]) + raise ExtractorError(u'YouTube said: %s' % video_info['reason'][0]) else: - self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason') - return + raise ExtractorError(u'"token" parameter not in video info for unknown reason') # Check for "rental" videos if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: - self._downloader.trouble(u'ERROR: "rental" videos not supported') - return + raise ExtractorError(u'"rental" videos not supported') # Start extracting information self.report_information_extraction(video_id) # uploader if 'author' not in video_info: - self._downloader.trouble(u'ERROR: unable to extract uploader name') - return + raise ExtractorError(u'Unable to extract uploader name') video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0]) # uploader_id @@ -467,17 +583,16 @@ class YoutubeIE(InfoExtractor): if mobj is not None: video_uploader_id = mobj.group(1) else: - self._downloader.trouble(u'WARNING: unable to extract uploader nickname') + self._downloader.report_warning(u'unable to extract uploader nickname') # title if 'title' not in video_info: - self._downloader.trouble(u'ERROR: unable to extract video title') - return + raise ExtractorError(u'Unable to extract video title') video_title = compat_urllib_parse.unquote_plus(video_info['title'][0]) # thumbnail image if 'thumbnail_url' not in video_info: - self._downloader.trouble(u'WARNING: unable to extract video thumbnail') + self._downloader.report_warning(u'unable to extract video thumbnail') video_thumbnail = '' else: # don't panic if we can't find it video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0]) @@ -487,29 +602,42 @@ class YoutubeIE(InfoExtractor): mobj = re.search(r'id="eow-date.*?>(.*?)', video_webpage, re.DOTALL) if mobj is not None: upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) - format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y'] - for expression in format_expressions: - try: - upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d') - except: - pass + upload_date = unified_strdate(upload_date) # description video_description = get_element_by_id("eow-description", video_webpage) if video_description: video_description = clean_html(video_description) else: - video_description = '' + fd_mobj = re.search(r'= 1: - url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',') - url_data = [compat_parse_qs(uds) for uds in url_data_strs] - url_data = [ud for ud in url_data if 'itag' in ud and 'url' in ud] - url_map = dict((ud['itag'][0], ud['url'][0] + '&signature=' + ud['sig'][0]) for ud in url_data) + url_map = {} + for url_data_str in video_info['url_encoded_fmt_stream_map'][0].split(','): + url_data = compat_parse_qs(url_data_str) + if 'itag' in url_data and 'url' in url_data: + url = url_data['url'][0] + '&signature=' + url_data['sig'][0] + if not 'ratebypass' in url: url += '&ratebypass=yes' + url_map[url_data['itag'][0]] = url format_limit = self._downloader.params.get('format_limit', None) available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats @@ -537,8 +668,7 @@ class YoutubeIE(InfoExtractor): format_list = available_formats existing_formats = [x for x in format_list if x in url_map] if len(existing_formats) == 0: - self._downloader.trouble(u'ERROR: no known formats available for video') - return + raise ExtractorError(u'no known formats available for video') if self._downloader.params.get('listformats', None): self._print_formats(existing_formats) return @@ -558,11 +688,9 @@ class YoutubeIE(InfoExtractor): video_url_list = [(rf, url_map[rf])] break if video_url_list is None: - self._downloader.trouble(u'ERROR: requested format not available') - return + raise ExtractorError(u'requested format not available') else: - self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info') - return + raise ExtractorError(u'no conn or url_encoded_fmt_stream_map information found in video info') results = [] for format_param, video_real_url in video_url_list: @@ -598,24 +726,9 @@ class MetacafeIE(InfoExtractor): _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user' IE_NAME = u'metacafe' - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - def report_disclaimer(self): """Report disclaimer retrieval.""" - self._downloader.to_screen(u'[metacafe] Retrieving disclaimer') - - def report_age_confirmation(self): - """Report attempt to confirm age.""" - self._downloader.to_screen(u'[metacafe] Confirming age') - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id) + self.to_screen(u'Retrieving disclaimer') def _real_initialize(self): # Retrieve disclaimer @@ -624,8 +737,7 @@ class MetacafeIE(InfoExtractor): self.report_disclaimer() disclaimer = compat_urllib_request.urlopen(request).read() except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % compat_str(err)) - return + raise ExtractorError(u'Unable to retrieve disclaimer: %s' % compat_str(err)) # Confirm age disclaimer_form = { @@ -637,32 +749,23 @@ class MetacafeIE(InfoExtractor): self.report_age_confirmation() disclaimer = compat_urllib_request.urlopen(request).read() except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err)) - return + raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err)) def _real_extract(self, url): # Extract id and simplified title from URL mobj = re.match(self._VALID_URL, url) if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return + raise ExtractorError(u'Invalid URL: %s' % url) video_id = mobj.group(1) # Check if video comes from YouTube mobj2 = re.match(r'^yt-(.*)$', video_id) if mobj2 is not None: - self._downloader.download(['http://www.youtube.com/watch?v=%s' % mobj2.group(1)]) - return + return [self.url_result('http://www.youtube.com/watch?v=%s' % mobj2.group(1), 'Youtube')] # Retrieve video webpage to extract further information - request = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id) - try: - self.report_download_webpage(video_id) - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err)) - return + webpage = self._download_webpage('http://www.metacafe.com/watch/%s/' % video_id, video_id) # Extract URL, uploader and title from webpage self.report_extraction(video_id) @@ -681,30 +784,25 @@ class MetacafeIE(InfoExtractor): else: mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract media URL') - return + raise ExtractorError(u'Unable to extract media URL') vardict = compat_parse_qs(mobj.group(1)) if 'mediaData' not in vardict: - self._downloader.trouble(u'ERROR: unable to extract media URL') - return - mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0]) + raise ExtractorError(u'Unable to extract media URL') + mobj = re.search(r'"mediaURL":"(?Phttp.*?)",(.*?)"key":"(?P.*?)"', vardict['mediaData'][0]) if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract media URL') - return - mediaURL = mobj.group(1).replace('\\/', '/') + raise ExtractorError(u'Unable to extract media URL') + mediaURL = mobj.group('mediaURL').replace('\\/', '/') video_extension = mediaURL[-3:] - video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2)) + video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key')) mobj = re.search(r'(?im)(.*) - Video', webpage) if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract title') - return + raise ExtractorError(u'Unable to extract title') video_title = mobj.group(1).decode('utf-8') mobj = re.search(r'submitter=(.*?);', webpage) if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract uploader nickname') - return + raise ExtractorError(u'Unable to extract uploader nickname') video_uploader = mobj.group(1) return [{ @@ -716,27 +814,17 @@ class MetacafeIE(InfoExtractor): 'ext': video_extension.decode('utf-8'), }] - class DailymotionIE(InfoExtractor): """Information Extractor for Dailymotion""" _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)' IE_NAME = u'dailymotion' - _WORKING = False - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id) def _real_extract(self, url): # Extract id and simplified title from URL mobj = re.match(self._VALID_URL, url) if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return + raise ExtractorError(u'Invalid URL: %s' % url) video_id = mobj.group(1).split('_')[0].split('?')[0] @@ -751,23 +839,20 @@ class DailymotionIE(InfoExtractor): self.report_extraction(video_id) mobj = re.search(r'\s*var flashvars = (.*)', webpage) if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract media URL') - return + raise ExtractorError(u'Unable to extract media URL') flashvars = compat_urllib_parse.unquote(mobj.group(1)) for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']: if key in flashvars: max_quality = key - self._downloader.to_screen(u'[dailymotion] Using %s' % key) + self.to_screen(u'Using %s' % key) break else: - self._downloader.trouble(u'ERROR: unable to extract video URL') - return + raise ExtractorError(u'Unable to extract video URL') mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars) if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video URL') - return + raise ExtractorError(u'Unable to extract video URL') video_url = compat_urllib_parse.unquote(mobj.group(1)).replace('\\/', '/') @@ -775,8 +860,7 @@ class DailymotionIE(InfoExtractor): mobj = re.search(r'', webpage) if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract title') - return + raise ExtractorError(u'Unable to extract title') video_title = unescapeHTML(mobj.group('title')) video_uploader = None @@ -785,7 +869,7 @@ class DailymotionIE(InfoExtractor): # lookin for official user mobj_official = re.search(r'', webpage) if mobj_official is None: - self._downloader.trouble(u'WARNING: unable to extract uploader nickname') + self._downloader.report_warning(u'unable to extract uploader nickname') else: video_uploader = mobj_official.group(1) else: @@ -809,54 +893,52 @@ class DailymotionIE(InfoExtractor): class PhotobucketIE(InfoExtractor): """Information extractor for photobucket.com.""" - _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)' + # TODO: the original _VALID_URL was: + # r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)' + # Check if it's necessary to keep the old extracion process + _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P.*)\.(?P(flv)|(mp4))' IE_NAME = u'photobucket' - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id) - def _real_extract(self, url): # Extract id from URL mobj = re.match(self._VALID_URL, url) if mobj is None: - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) - return + raise ExtractorError(u'Invalid URL: %s' % url) - video_id = mobj.group(1) + video_id = mobj.group('id') - video_extension = 'flv' + video_extension = mobj.group('ext') # Retrieve video webpage to extract further information - request = compat_urllib_request.Request(url) - try: - self.report_download_webpage(video_id) - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) - return + webpage = self._download_webpage(url, video_id) # Extract URL, uploader, and title from webpage self.report_extraction(video_id) + # We try first by looking the javascript code: + mobj = re.search(r'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (?P.*?)\);', webpage) + if mobj is not None: + info = json.loads(mobj.group('json')) + return [{ + 'id': video_id, + 'url': info[u'downloadUrl'], + 'uploader': info[u'username'], + 'upload_date': datetime.date.fromtimestamp(info[u'creationDate']).strftime('%Y%m%d'), + 'title': info[u'title'], + 'ext': video_extension, + 'thumbnail': info[u'thumbUrl'], + }] + + # We try looking in other parts of the webpage mobj = re.search(r'', webpage) if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract media URL') - return + raise ExtractorError(u'Unable to extract media URL') mediaURL = compat_urllib_parse.unquote(mobj.group(1)) video_url = mediaURL mobj = re.search(r'(.*) video by (.*) - Photobucket', webpage) if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract title') - return + raise ExtractorError(u'Unable to extract title') video_title = mobj.group(1).decode('utf-8') video_uploader = mobj.group(2).decode('utf-8') @@ -872,147 +954,72 @@ class PhotobucketIE(InfoExtractor): class YahooIE(InfoExtractor): - """Information extractor for video.yahoo.com.""" + """Information extractor for screen.yahoo.com.""" + _VALID_URL = r'http://screen\.yahoo\.com/.*?-(?P\d*?)\.html' - _WORKING = False - # _VALID_URL matches all Yahoo! Video URLs - # _VPAGE_URL matches only the extractable '/watch/' URLs - _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?' - _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?' - IE_NAME = u'video.yahoo' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id) - - def _real_extract(self, url, new_video=True): - # Extract ID from URL + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) if mobj is None: - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) - return + raise ExtractorError(u'Invalid URL: %s' % url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + m_id = re.search(r'YUI\.namespace\("Media"\)\.CONTENT_ID = "(?P.+?)";', webpage) - video_id = mobj.group(2) - video_extension = 'flv' + if m_id is None: + # TODO: Check which url parameters are required + info_url = 'http://cosmos.bcst.yahoo.com/rest/v2/pops;lmsoverride=1;outputformat=mrss;cb=974419660;id=%s;rd=news.yahoo.com;datacontext=mdb;lg=KCa2IihxG3qE60vQ7HtyUy' % video_id + webpage = self._download_webpage(info_url, video_id, u'Downloading info webpage') + info_re = r'''<!\[CDATA\[(?P<title>.*?)\]\]>.* + .*?)\]\]>.* + .*?)\ .*\]\]>.* + ', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video title') - return - video_title = mobj.group(1).decode('utf-8') - - mobj = re.search(r'

(.*)

', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video uploader') - return - video_uploader = mobj.group(1).decode('utf-8') - - # Extract video thumbnail - mobj = re.search(r'', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video thumbnail') - return - video_thumbnail = mobj.group(1).decode('utf-8') - - # Extract video description - mobj = re.search(r'', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video description') - return - video_description = mobj.group(1).decode('utf-8') - if not video_description: - video_description = 'No description available.' - - # Extract video height and width - mobj = re.search(r'', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video height') - return - yv_video_height = mobj.group(1) - - mobj = re.search(r'', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video width') - return - yv_video_width = mobj.group(1) - - # Retrieve video playlist to extract media URL - # I'm not completely sure what all these options are, but we - # seem to need most of them, otherwise the server sends a 401. - yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents - yv_bitrate = '700' # according to Wikipedia this is hard-coded - request = compat_urllib_request.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id + - '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height + - '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797') - try: - self.report_download_webpage(video_id) - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) - return - - # Extract media URL from playlist XML - mobj = re.search(r'https?://)?(?:(?:www|player)\.)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?Pplay_redirect_hls\?clip_id=)?(?:videos?/)?(?P[0-9]+)' IE_NAME = u'vimeo' - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id) - def _real_extract(self, url, new_video=True): # Extract ID from URL mobj = re.match(self._VALID_URL, url) if mobj is None: - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) - return + raise ExtractorError(u'Invalid URL: %s' % url) video_id = mobj.group('id') if not mobj.group('proto'): @@ -1047,13 +1042,7 @@ class VimeoIE(InfoExtractor): # Retrieve video webpage to extract further information request = compat_urllib_request.Request(url, None, std_headers) - try: - self.report_download_webpage(video_id) - webpage_bytes = compat_urllib_request.urlopen(request).read() - webpage = webpage_bytes.decode('utf-8') - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) - return + webpage = self._download_webpage(request, video_id) # Now we begin extracting as much information as we can from what we # retrieved. First we extract the information common to all extractors, @@ -1065,8 +1054,10 @@ class VimeoIE(InfoExtractor): config = webpage.split(' = {config:')[1].split(',assets:')[0] config = json.loads(config) except: - self._downloader.trouble(u'ERROR: unable to extract info section') - return + if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage): + raise ExtractorError(u'The author has restricted the access to this video, try with the "--referer" option') + else: + raise ExtractorError(u'Unable to extract info section') # Extract title video_title = config["video"]["title"] @@ -1081,7 +1072,7 @@ class VimeoIE(InfoExtractor): # Extract video description video_description = get_element_by_attribute("itemprop", "description", webpage) if video_description: video_description = clean_html(video_description) - else: video_description = '' + else: video_description = u'' # Extract upload date video_upload_date = None @@ -1112,11 +1103,10 @@ class VimeoIE(InfoExtractor): video_quality = files[quality][0][2] video_codec = files[quality][0][0] video_extension = files[quality][0][1] - self._downloader.to_screen(u'[vimeo] %s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality)) + self.to_screen(u'%s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality)) break else: - self._downloader.trouble(u'ERROR: no known codec found') - return + raise ExtractorError(u'No known codec found') video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \ %(video_id, sig, timestamp, video_quality, video_codec.upper()) @@ -1142,28 +1132,15 @@ class ArteTvIE(InfoExtractor): IE_NAME = u'arte.tv' - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self._downloader.to_screen(u'[arte.tv] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[arte.tv] %s: Extracting information' % video_id) - def fetch_webpage(self, url): request = compat_urllib_request.Request(url) try: self.report_download_webpage(url) webpage = compat_urllib_request.urlopen(request).read() except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) - return + raise ExtractorError(u'Unable to retrieve video webpage: %s' % compat_str(err)) except ValueError as err: - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) - return + raise ExtractorError(u'Invalid URL: %s' % url) return webpage def grep_webpage(self, url, regex, regexFlags, matchTuples): @@ -1172,13 +1149,11 @@ class ArteTvIE(InfoExtractor): info = {} if mobj is None: - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) - return + raise ExtractorError(u'Invalid URL: %s' % url) for (i, key, err) in matchTuples: if mobj.group(i) is None: - self._downloader.trouble(err) - return + raise ExtractorError(err) else: info[key] = mobj.group(i) @@ -1191,7 +1166,7 @@ class ArteTvIE(InfoExtractor): r'src="(.*?/videothek_js.*?\.js)', 0, [ - (1, 'url', u'ERROR: Invalid URL: %s' % url) + (1, 'url', u'Invalid URL: %s' % url) ] ) http_host = url.split('/')[2] @@ -1203,9 +1178,9 @@ class ArteTvIE(InfoExtractor): '(rtmp://.*?)\'', re.DOTALL, [ - (1, 'path', u'ERROR: could not extract video path: %s' % url), - (2, 'player', u'ERROR: could not extract video player: %s' % url), - (3, 'url', u'ERROR: could not extract video url: %s' % url) + (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) ] ) video_url = u'%s/%s' % (info.get('url'), info.get('path')) @@ -1217,7 +1192,7 @@ class ArteTvIE(InfoExtractor): r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)', 0, [ - (1, 'url', u'ERROR: Invalid URL: %s' % url) + (1, 'url', u'Invalid URL: %s' % url) ] ) next_url = compat_urllib_parse.unquote(info.get('url')) @@ -1226,7 +1201,7 @@ class ArteTvIE(InfoExtractor): r'