diff options
81 files changed, 2269 insertions, 861 deletions
@@ -147,3 +147,5 @@ Qijiang Fan Rémy Léone Marco Ferragina reiv +Muratcan Simsek +Evan Lu diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index 09ce98ca2..f3fe0d432 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -1,4 +1,18 @@ -**Please include the full output of youtube-dl when run with `-v`**. +**Please include the full output of youtube-dl when run with `-v`**, i.e. add `-v` flag to your command line, copy the **whole** output and post it in the issue body wrapped in \`\`\` for better formatting. It should look similar to this: +``` +$ youtube-dl -v http://www.youtube.com/watch?v=BaW_jenozKcj +[debug] System config: [] +[debug] User config: [] +[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] +[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 +[debug] youtube-dl version 2015.12.06 +[debug] Git HEAD: 135392e +[debug] Python version 2.6.6 - Windows-2003Server-5.2.3790-SP2 +[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 +[debug] Proxy map: {} +... +``` +**Do not post screenshots of verbose log only plain text is acceptable.** The output (including the first lines) contains important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever. @@ -20,7 +34,7 @@ For bug reports, this means that your report should contain the *complete* outpu If your server has multiple IPs or you suspect censorship, adding `--call-home` may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/). -**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL. +**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like `http://www.youtube.com/watch?v=BaW_jenozKc`. There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. `http://www.youtube.com/`) is *not* an example URL. ### Are you using the latest version? @@ -28,7 +42,7 @@ Before reporting any issue, type `youtube-dl -U`. This should report that you're ### Is the issue already documented? -Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or at https://github.com/rg3/youtube-dl/search?type=Issues . If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity. +Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or browse the [GitHub Issues](https://github.com/rg3/youtube-dl/search?type=Issues) of this repository. If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity. ### Why are existing options not enough? @@ -35,7 +35,7 @@ You can also use pip: sudo pip install youtube-dl -Alternatively, refer to the [developer instructions](#developer-instructions) for how to check out and work with the git repository. For further options, including PGP signatures, see https://rg3.github.io/youtube-dl/download.html . +Alternatively, refer to the [developer instructions](#developer-instructions) for how to check out and work with the git repository. For further options, including PGP signatures, see the [youtube-dl Download Page](https://rg3.github.io/youtube-dl/download.html). # DESCRIPTION **youtube-dl** is a small command-line program to download videos from @@ -319,7 +319,7 @@ which means you can modify it, redistribute it or use it however you like. --all-formats Download all available video formats --prefer-free-formats Prefer free video formats unless a specific one is requested - -F, --list-formats List all available formats of specified + -F, --list-formats List all available formats of requested videos --youtube-skip-dash-manifest Do not download the DASH manifests and related data on YouTube videos @@ -414,7 +414,7 @@ You can configure youtube-dl by placing any supported command line option to a c You can use `--ignore-config` if you want to disable the configuration file for a particular youtube-dl run. -### Authentication with `.netrc` file ### +### Authentication with `.netrc` file You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every youtube-dl execution and prevent tracking plain text passwords in the shell command history. You can achieve this using a [`.netrc` file](http://stackoverflow.com/tags/.netrc/info) on per extractor basis. For that you will need to create a`.netrc` file in your `$HOME` and restrict permissions to read/write by you only: ``` @@ -559,11 +559,11 @@ If you want to play the video on a machine that is not running youtube-dl, you c YouTube has switched to a new video info format in July 2011 which is not supported by old versions of youtube-dl. See [above](#how-do-i-update-youtube-dl) for how to update youtube-dl. -### ERROR: unable to download video ### +### ERROR: unable to download video YouTube requires an additional signature since September 2012 which is not supported by old versions of youtube-dl. See [above](#how-do-i-update-youtube-dl) for how to update youtube-dl. -### Video URL contains an ampersand and I'm getting some strange output `[1] 2839` or `'v' is not recognized as an internal or external command` ### +### Video URL contains an ampersand and I'm getting some strange output `[1] 2839` or `'v' is not recognized as an internal or external command` That's actually the output from your shell. Since ampersand is one of the special shell characters it's interpreted by the shell preventing you from passing the whole URL to youtube-dl. To disable your shell from interpreting the ampersands (or any other special characters) you have to either put the whole URL in quotes or escape them with a backslash (which approach will work depends on your shell). @@ -587,7 +587,7 @@ In February 2015, the new YouTube player contained a character sequence in a str These two error codes indicate that the service is blocking your IP address because of overuse. Contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--source-address` options](#network-options) to select another IP address. -### SyntaxError: Non-ASCII character ### +### SyntaxError: Non-ASCII character The error @@ -616,7 +616,7 @@ From then on, after restarting your shell, you will be able to access both youtu Use the `-o` to specify an [output template](#output-template), for example `-o "/home/user/videos/%(title)s-%(id)s.%(ext)s"`. If you want this for all of your downloads, put the option into your [configuration file](#configuration). -### How do I download a video starting with a `-` ? +### How do I download a video starting with a `-`? Either prepend `http://www.youtube.com/watch?v=` or separate the ID from the options with `--`: @@ -757,7 +757,7 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl: ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc']) ``` -Most likely, you'll want to use various options. For a list of what can be done, have a look at [youtube_dl/YoutubeDL.py](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L117-L265). For a start, if you want to intercept youtube-dl's output, set a `logger` object. +Most likely, you'll want to use various options. For a list of what can be done, have a look at [`youtube_dl/YoutubeDL.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L121-L269). For a start, if you want to intercept youtube-dl's output, set a `logger` object. Here's a more complete example of a program that outputs only errors (and a short message after the download is finished), and downloads/converts the video to an mp3 file: @@ -798,9 +798,23 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl: # BUGS -Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues> . Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the irc channel #youtube-dl on freenode. +Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues>. Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the IRC channel [#youtube-dl](irc://chat.freenode.net/#youtube-dl) on freenode ([webchat](http://webchat.freenode.net/?randomnick=1&channels=youtube-dl)). -**Please include the full output of youtube-dl when run with `-v`**. +**Please include the full output of youtube-dl when run with `-v`**, i.e. add `-v` flag to your command line, copy the **whole** output and post it in the issue body wrapped in \`\`\` for better formatting. It should look similar to this: +``` +$ youtube-dl -v http://www.youtube.com/watch?v=BaW_jenozKcj +[debug] System config: [] +[debug] User config: [] +[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] +[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 +[debug] youtube-dl version 2015.12.06 +[debug] Git HEAD: 135392e +[debug] Python version 2.6.6 - Windows-2003Server-5.2.3790-SP2 +[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 +[debug] Proxy map: {} +... +``` +**Do not post screenshots of verbose log only plain text is acceptable.** The output (including the first lines) contains important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever. @@ -822,7 +836,7 @@ For bug reports, this means that your report should contain the *complete* outpu If your server has multiple IPs or you suspect censorship, adding `--call-home` may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/). -**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL. +**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like `http://www.youtube.com/watch?v=BaW_jenozKc`. There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. `http://www.youtube.com/`) is *not* an example URL. ### Are you using the latest version? @@ -830,7 +844,7 @@ Before reporting any issue, type `youtube-dl -U`. This should report that you're ### Is the issue already documented? -Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or at https://github.com/rg3/youtube-dl/search?type=Issues . If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity. +Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or browse the [GitHub Issues](https://github.com/rg3/youtube-dl/search?type=Issues) of this repository. If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity. ### Why are existing options not enough? @@ -860,4 +874,4 @@ It may sound strange, but some bug reports we receive are completely unrelated t youtube-dl is released into the public domain by the copyright holders. -This README file was originally written by Daniel Bolton (<https://github.com/dbbolton>) and is likewise released into the public domain. +This README file was originally written by [Daniel Bolton](https://github.com/dbbolton) and is likewise released into the public domain. diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 1df408610..8253335e3 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -15,8 +15,12 @@ - **abc.net.au** - **Abc7News** - **AcademicEarth:Course** + - **acast** + - **acast:channel** - **AddAnime** - **AdobeTV** + - **AdobeTVChannel** + - **AdobeTVShow** - **AdobeTVVideo** - **AdultSwim** - **Aftenposten** @@ -43,6 +47,7 @@ - **arte.tv:future** - **AtresPlayer** - **ATTTechChannel** + - **AudiMedia** - **audiomack** - **audiomack:album** - **Azubu** @@ -92,6 +97,7 @@ - **Clipfish** - **cliphunter** - **Clipsyndicate** + - **cloudtime**: CloudTime - **Cloudy** - **Clubic** - **Clyp** @@ -182,7 +188,9 @@ - **Freesound** - **freespeech.org** - **FreeVideo** + - **Funimation** - **FunnyOrDie** + - **GameInformer** - **Gamekings** - **GameOne** - **gameone:playlist** @@ -307,7 +315,6 @@ - **MovieClips** - **MovieFap** - **Moviezine** - - **movshare**: MovShare - **MPORA** - **MSNBC** - **MTV** @@ -394,7 +401,7 @@ - **orf:tvthek**: ORF TVthek - **parliamentlive.tv**: UK parliament videos - **Patreon** - - **PBS** + - **pbs**: Public Broadcasting Service (PBS) and member stations: PBS: Public Broadcasting Service, APT - Alabama Public Television (WBIQ), GPB/Georgia Public Broadcasting (WGTV), Mississippi Public Broadcasting (WMPN), Nashville Public Television (WNPT), WFSU-TV (WFSU), WSRE (WSRE), WTCI (WTCI), WPBA/Channel 30 (WPBA), Alaska Public Media (KAKM), Arizona PBS (KAET), KNME-TV/Channel 5 (KNME), Vegas PBS (KLVX), AETN/ARKANSAS ETV NETWORK (KETS), KET (WKLE), WKNO/Channel 10 (WKNO), LPB/LOUISIANA PUBLIC BROADCASTING (WLPB), OETA (KETA), Ozarks Public Television (KOZK), WSIU Public Broadcasting (WSIU), KEET TV (KEET), KIXE/Channel 9 (KIXE), KPBS San Diego (KPBS), KQED (KQED), KVIE Public Television (KVIE), PBS SoCal/KOCE (KOCE), ValleyPBS (KVPT), CONNECTICUT PUBLIC TELEVISION (WEDH), KNPB Channel 5 (KNPB), SOPTV (KSYS), Rocky Mountain PBS (KRMA), KENW-TV3 (KENW), KUED Channel 7 (KUED), Wyoming PBS (KCWC), Colorado Public Television / KBDI 12 (KBDI), KBYU-TV (KBYU), Thirteen/WNET New York (WNET), WGBH/Channel 2 (WGBH), WGBY (WGBY), NJTV Public Media NJ (WNJT), WLIW21 (WLIW), mpt/Maryland Public Television (WMPB), WETA Television and Radio (WETA), WHYY (WHYY), PBS 39 (WLVT), WVPT - Your Source for PBS and More! (WVPT), Howard University Television (WHUT), WEDU PBS (WEDU), WGCU Public Media (WGCU), WPBT2 (WPBT), WUCF TV (WUCF), WUFT/Channel 5 (WUFT), WXEL/Channel 42 (WXEL), WLRN/Channel 17 (WLRN), WUSF Public Broadcasting (WUSF), ETV (WRLK), UNC-TV (WUNC), PBS Hawaii - Oceanic Cable Channel 10 (KHET), Idaho Public Television (KAID), KSPS (KSPS), OPB (KOPB), KWSU/Channel 10 & KTNW/Channel 31 (KWSU), WILL-TV (WILL), Network Knowledge - WSEC/Springfield (WSEC), WTTW11 (WTTW), Iowa Public Television/IPTV (KDIN), Nine Network (KETC), PBS39 Fort Wayne (WFWA), WFYI Indianapolis (WFYI), Milwaukee Public Television (WMVS), WNIN (WNIN), WNIT Public Television (WNIT), WPT (WPNE), WVUT/Channel 22 (WVUT), WEIU/Channel 51 (WEIU), WQPT-TV (WQPT), WYCC PBS Chicago (WYCC), WIPB-TV (WIPB), WTIU (WTIU), CET (WCET), ThinkTVNetwork (WPTD), WBGU-TV (WBGU), WGVU TV (WGVU), NET1 (KUON), Pioneer Public Television (KWCM), SDPB Television (KUSD), TPT (KTCA), KSMQ (KSMQ), KPTS/Channel 8 (KPTS), KTWU/Channel 11 (KTWU), East Tennessee PBS (WSJK), WCTE-TV (WCTE), WLJT, Channel 11 (WLJT), WOSU TV (WOSU), WOUB/WOUC (WOUB), WVPB (WVPB), WKYU-PBS (WKYU), KERA 13 (KERA), MPBN (WCBB), Mountain Lake PBS (WCFE), NHPTV (WENH), Vermont PBS (WETK), witf (WITF), WQED Multimedia (WQED), WMHT Educational Telecommunications (WMHT), Q-TV (WDCQ), WTVS Detroit Public TV (WTVS), CMU Public Television (WCMU), WKAR-TV (WKAR), WNMU-TV Public TV 13 (WNMU), WDSE - WRPT (WDSE), WGTE TV (WGTE), Lakeland Public Television (KAWE), KMOS-TV - Channels 6.1, 6.2 and 6.3 (KMOS), MontanaPBS (KUSM), KRWG/Channel 22 (KRWG), KACV (KACV), KCOS/Channel 13 (KCOS), WCNY/Channel 24 (WCNY), WNED (WNED), WPBS (WPBS), WSKG Public TV (WSKG), WXXI (WXXI), WPSU (WPSU), WVIA Public Media Studios (WVIA), WTVI (WTVI), Western Reserve PBS (WNEO), WVIZ/PBS ideastream (WVIZ), KCTS 9 (KCTS), Basin PBS (KPBT), KUHT / Channel 8 (KUHT), KLRN (KLRN), KLRU (KLRU), WTJX Channel 12 (WTJX), WCVE PBS (WCVE), KBTC Public Television (KBTC) - **Periscope**: Periscope - **PhilharmonieDeParis**: Philharmonie de Paris - **Phoenix** @@ -480,6 +487,8 @@ - **Shared**: shared.sx and vivo.sx - **ShareSix** - **Sina** + - **skynewsarabia:video** + - **skynewsarabia:video** - **Slideshare** - **Slutload** - **smotri**: Smotri.com @@ -665,6 +674,7 @@ - **WebOfStories** - **WebOfStoriesPlaylist** - **Weibo** + - **wholecloud**: WholeCloud - **Wimp** - **Wistia** - **WNL** diff --git a/test/test_all_urls.py b/test/test_all_urls.py index a9db42b30..a0c11e6c1 100644 --- a/test/test_all_urls.py +++ b/test/test_all_urls.py @@ -121,8 +121,8 @@ class TestAllURLsMatching(unittest.TestCase): def test_pbs(self): # https://github.com/rg3/youtube-dl/issues/2350 - self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['PBS']) - self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['PBS']) + self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['pbs']) + self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['pbs']) def test_yahoo_https(self): # https://github.com/rg3/youtube-dl/issues/2701 diff --git a/test/test_utils.py b/test/test_utils.py index 501355c74..1c3290d9b 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -22,6 +22,7 @@ from youtube_dl.utils import ( DateRange, detect_exe_version, determine_ext, + encode_compat_str, encodeFilename, escape_rfc3986, escape_url, @@ -43,6 +44,7 @@ from youtube_dl.utils import ( sanitize_path, prepend_extension, replace_extension, + remove_quotes, shell_quote, smuggle_url, str_to_int, @@ -200,6 +202,15 @@ class TestUtil(unittest.TestCase): self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp') self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp') + def test_remove_quotes(self): + self.assertEqual(remove_quotes(None), None) + self.assertEqual(remove_quotes('"'), '"') + self.assertEqual(remove_quotes("'"), "'") + self.assertEqual(remove_quotes(';'), ';') + self.assertEqual(remove_quotes('";'), '";') + self.assertEqual(remove_quotes('""'), '') + self.assertEqual(remove_quotes('";"'), ';') + def test_ordered_set(self): self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7]) self.assertEqual(orderedSet([]), []) @@ -439,6 +450,10 @@ class TestUtil(unittest.TestCase): data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'}) self.assertTrue(isinstance(data, bytes)) + def test_encode_compat_str(self): + self.assertEqual(encode_compat_str(b'\xd1\x82\xd0\xb5\xd1\x81\xd1\x82', 'utf-8'), 'тест') + self.assertEqual(encode_compat_str('тест', 'utf-8'), 'тест') + def test_parse_iso8601(self): self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266) self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266) @@ -651,12 +666,13 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4') {'like_count': 190, 'dislike_count': 10})) def test_parse_dfxp_time_expr(self): - self.assertEqual(parse_dfxp_time_expr(None), 0.0) - self.assertEqual(parse_dfxp_time_expr(''), 0.0) + self.assertEqual(parse_dfxp_time_expr(None), None) + self.assertEqual(parse_dfxp_time_expr(''), None) self.assertEqual(parse_dfxp_time_expr('0.1'), 0.1) self.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1) self.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0) self.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1) + self.assertEqual(parse_dfxp_time_expr('00:00:01:100'), 1.1) def test_dfxp2srt(self): dfxp_data = '''<?xml version="1.0" encoding="UTF-8"?> @@ -666,6 +682,9 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4') <p begin="0" end="1">The following line contains Chinese characters and special symbols</p> <p begin="1" end="2">第二行<br/>♪♪</p> <p begin="2" dur="1"><span>Third<br/>Line</span></p> + <p begin="3" end="-1">Lines with invalid timestamps are ignored</p> + <p begin="-1" end="-1">Ignore, two</p> + <p begin="3" dur="-1">Ignored, three</p> </div> </body> </tt>''' diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 9a8c7da05..50425b8d7 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -47,7 +47,9 @@ from .utils import ( DEFAULT_OUTTMPL, determine_ext, DownloadError, + encode_compat_str, encodeFilename, + error_to_compat_str, ExtractorError, format_bytes, formatSeconds, @@ -495,7 +497,7 @@ class YoutubeDL(object): tb = '' if hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]: tb += ''.join(traceback.format_exception(*sys.exc_info()[1].exc_info)) - tb += compat_str(traceback.format_exc()) + tb += encode_compat_str(traceback.format_exc()) else: tb_data = traceback.format_list(traceback.extract_stack()) tb = ''.join(tb_data) @@ -674,14 +676,14 @@ class YoutubeDL(object): return self.process_ie_result(ie_result, download, extra_info) else: return ie_result - except ExtractorError as de: # An error we somewhat expected - self.report_error(compat_str(de), de.format_traceback()) + except ExtractorError as e: # An error we somewhat expected + self.report_error(compat_str(e), e.format_traceback()) break except MaxDownloadsReached: raise except Exception as e: if self.params.get('ignoreerrors', False): - self.report_error(compat_str(e), tb=compat_str(traceback.format_exc())) + self.report_error(error_to_compat_str(e), tb=encode_compat_str(traceback.format_exc())) break else: raise @@ -1110,6 +1112,12 @@ class YoutubeDL(object): 'contain the video, try using ' '"-f %s+%s"' % (format_2, format_1)) return + # Formats must be opposite (video+audio) + if formats_info[0].get('acodec') == 'none' and formats_info[1].get('acodec') == 'none': + self.report_error( + 'Both formats %s and %s are video-only, you must specify "-f video+audio"' + % (format_1, format_2)) + return output_ext = ( formats_info[0]['ext'] if self.params.get('merge_output_format') is None @@ -1453,7 +1461,7 @@ class YoutubeDL(object): if dn and not os.path.exists(dn): os.makedirs(dn) except (OSError, IOError) as err: - self.report_error('unable to create directory ' + compat_str(err)) + self.report_error('unable to create directory ' + error_to_compat_str(err)) return if self.params.get('writedescription', False): @@ -1504,7 +1512,7 @@ class YoutubeDL(object): sub_info['url'], info_dict['id'], note=False) except ExtractorError as err: self.report_warning('Unable to download subtitle for "%s": %s' % - (sub_lang, compat_str(err.cause))) + (sub_lang, error_to_compat_str(err.cause))) continue try: sub_filename = subtitles_filename(filename, sub_lang, sub_format) @@ -2033,4 +2041,4 @@ class YoutubeDL(object): (info_dict['extractor'], info_dict['id'], thumb_display_id, thumb_filename)) except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: self.report_warning('Unable to download thumbnail "%s": %s' % - (t['url'], compat_str(err))) + (t['url'], error_to_compat_str(err))) diff --git a/youtube_dl/downloader/common.py b/youtube_dl/downloader/common.py index b8bf8daf8..beae8c4d0 100644 --- a/youtube_dl/downloader/common.py +++ b/youtube_dl/downloader/common.py @@ -5,9 +5,9 @@ import re import sys import time -from ..compat import compat_str from ..utils import ( encodeFilename, + error_to_compat_str, decodeArgument, format_bytes, timeconvert, @@ -186,7 +186,7 @@ class FileDownloader(object): return os.rename(encodeFilename(old_filename), encodeFilename(new_filename)) except (IOError, OSError) as err: - self.report_error('unable to rename file: %s' % compat_str(err)) + self.report_error('unable to rename file: %s' % error_to_compat_str(err)) def try_utime(self, filename, last_modified_hdr): """Try to set the last-modified time of the given file.""" diff --git a/youtube_dl/downloader/f4m.py b/youtube_dl/downloader/f4m.py index 6170cc155..aaf0c49c8 100644 --- a/youtube_dl/downloader/f4m.py +++ b/youtube_dl/downloader/f4m.py @@ -15,6 +15,7 @@ from ..compat import ( ) from ..utils import ( encodeFilename, + fix_xml_ampersands, sanitize_open, struct_pack, struct_unpack, @@ -288,7 +289,10 @@ class F4mFD(FragmentFD): self.to_screen('[%s] Downloading f4m manifest' % self.FD_NAME) urlh = self.ydl.urlopen(man_url) man_url = urlh.geturl() - manifest = urlh.read() + # Some manifests may be malformed, e.g. prosiebensat1 generated manifests + # (see https://github.com/rg3/youtube-dl/issues/6215#issuecomment-121704244 + # and https://github.com/rg3/youtube-dl/issues/7823) + manifest = fix_xml_ampersands(urlh.read().decode('utf-8', 'ignore')).strip() doc = compat_etree_fromstring(manifest) formats = [(int(f.attrib.get('bitrate', -1)), f) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 5b842204f..add1df023 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -3,9 +3,15 @@ from __future__ import unicode_literals from .abc import ABCIE from .abc7news import Abc7NewsIE from .academicearth import AcademicEarthCourseIE +from .acast import ( + ACastIE, + ACastChannelIE, +) from .addanime import AddAnimeIE from .adobetv import ( AdobeTVIE, + AdobeTVShowIE, + AdobeTVChannelIE, AdobeTVVideoIE, ) from .adultswim import AdultSwimIE @@ -71,7 +77,6 @@ from .camdemy import ( CamdemyIE, CamdemyFolderIE ) -from .canal13cl import Canal13clIE from .canalplus import CanalplusIE from .canalc2 import Canalc2IE from .cbs import CBSIE @@ -199,7 +204,9 @@ from .francetv import ( from .freesound import FreesoundIE from .freespeech import FreespeechIE from .freevideo import FreeVideoIE +from .funimation import FunimationIE from .funnyordie import FunnyOrDieIE +from .gameinformer import GameInformerIE from .gamekings import GamekingsIE from .gameone import ( GameOneIE, @@ -223,9 +230,11 @@ from .globo import ( from .godtube import GodTubeIE from .goldenmoustache import GoldenMoustacheIE from .golem import GolemIE +from .googledrive import GoogleDriveIE from .googleplus import GooglePlusIE from .googlesearch import GoogleSearchIE from .goshgay import GoshgayIE +from .gputechconf import GPUTechConfIE from .groupon import GrouponIE from .hark import HarkIE from .hearthisat import HearThisAtIE @@ -351,7 +360,6 @@ from .motherless import MotherlessIE from .motorsport import MotorsportIE from .movieclips import MovieClipsIE from .moviezine import MoviezineIE -from .movshare import MovShareIE from .mtv import ( MTVIE, MTVServicesEmbeddedIE, @@ -417,7 +425,13 @@ from .noco import NocoIE from .normalboots import NormalbootsIE from .nosvideo import NosVideoIE from .nova import NovaIE -from .novamov import NovaMovIE +from .novamov import ( + NovaMovIE, + WholeCloudIE, + NowVideoIE, + VideoWeedIE, + CloudTimeIE, +) from .nowness import ( NownessIE, NownessPlaylistIE, @@ -427,7 +441,6 @@ from .nowtv import ( NowTVIE, NowTVListIE, ) -from .nowvideo import NowVideoIE from .npo import ( NPOIE, NPOLiveIE, @@ -636,6 +649,7 @@ from .teachingchannel import TeachingChannelIE from .teamcoco import TeamcocoIE from .techtalks import TechTalksIE from .ted import TEDIE +from .tele13 import Tele13IE from .telebruxelles import TeleBruxellesIE from .telecinco import TelecincoIE from .telegraaf import TelegraafIE @@ -664,6 +678,7 @@ from .tnaflix import ( EMPFlixIE, MovieFapIE, ) +from .toggle import ToggleIE from .thvideo import ( THVideoIE, THVideoPlaylistIE @@ -738,7 +753,6 @@ from .videofyme import VideofyMeIE from .videomega import VideoMegaIE from .videopremium import VideoPremiumIE from .videott import VideoTtIE -from .videoweed import VideoWeedIE from .vidme import VidmeIE from .vidzi import VidziIE from .vier import VierIE, VierVideosIE @@ -840,7 +854,7 @@ from .youtube import ( YoutubeTruncatedIDIE, YoutubeTruncatedURLIE, YoutubeUserIE, - YoutubeUserPlaylistsIE, + YoutubePlaylistsIE, YoutubeWatchLaterIE, ) from .zapiks import ZapiksIE diff --git a/youtube_dl/extractor/acast.py b/youtube_dl/extractor/acast.py new file mode 100644 index 000000000..be7913bc7 --- /dev/null +++ b/youtube_dl/extractor/acast.py @@ -0,0 +1,70 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import int_or_none + + +class ACastBaseIE(InfoExtractor): + _API_BASE_URL = 'https://www.acast.com/api/' + + +class ACastIE(ACastBaseIE): + IE_NAME = 'acast' + _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<channel>[^/]+)/(?P<id>[^/#?]+)' + _TEST = { + 'url': 'https://www.acast.com/condenasttraveler/-where-are-you-taipei-101-taiwan', + 'md5': 'ada3de5a1e3a2a381327d749854788bb', + 'info_dict': { + 'id': '57de3baa-4bb0-487e-9418-2692c1277a34', + 'ext': 'mp3', + 'title': '"Where Are You?": Taipei 101, Taiwan', + 'timestamp': 1196172000000, + 'description': 'md5:0c5d8201dfea2b93218ea986c91eee6e', + 'duration': 211, + } + } + + def _real_extract(self, url): + channel, display_id = re.match(self._VALID_URL, url).groups() + cast_data = self._download_json(self._API_BASE_URL + 'channels/%s/acasts/%s/playback' % (channel, display_id), display_id) + + return { + 'id': compat_str(cast_data['id']), + 'display_id': display_id, + 'url': cast_data['blings'][0]['audio'], + 'title': cast_data['name'], + 'description': cast_data.get('description'), + 'thumbnail': cast_data.get('image'), + 'timestamp': int_or_none(cast_data.get('publishingDate')), + 'duration': int_or_none(cast_data.get('duration')), + } + + +class ACastChannelIE(ACastBaseIE): + IE_NAME = 'acast:channel' + _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<id>[^/#?]+)' + _TEST = { + 'url': 'https://www.acast.com/condenasttraveler', + 'info_dict': { + 'id': '50544219-29bb-499e-a083-6087f4cb7797', + 'title': 'Condé Nast Traveler Podcast', + 'description': 'md5:98646dee22a5b386626ae31866638fbd', + }, + 'playlist_mincount': 20, + } + + @classmethod + def suitable(cls, url): + return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url) + + def _real_extract(self, url): + display_id = self._match_id(url) + channel_data = self._download_json(self._API_BASE_URL + 'channels/%s' % display_id, display_id) + casts = self._download_json(self._API_BASE_URL + 'channels/%s/acasts' % display_id, display_id) + entries = [self.url_result('https://www.acast.com/%s/%s' % (display_id, cast['url']), 'ACast') for cast in casts] + + return self.playlist_result(entries, compat_str(channel_data['id']), channel_data['name'], channel_data.get('description')) diff --git a/youtube_dl/extractor/adobetv.py b/youtube_dl/extractor/adobetv.py index 5e43adc51..8753ee2cf 100644 --- a/youtube_dl/extractor/adobetv.py +++ b/youtube_dl/extractor/adobetv.py @@ -1,23 +1,32 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( parse_duration, unified_strdate, str_to_int, + int_or_none, float_or_none, ISO639Utils, + determine_ext, ) -class AdobeTVIE(InfoExtractor): - _VALID_URL = r'https?://tv\.adobe\.com/watch/[^/]+/(?P<id>[^/]+)' +class AdobeTVBaseIE(InfoExtractor): + _API_BASE_URL = 'http://tv.adobe.com/api/v4/' + + +class AdobeTVIE(AdobeTVBaseIE): + _VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?watch/(?P<show_urlname>[^/]+)/(?P<id>[^/]+)' _TEST = { 'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/', 'md5': '9bc5727bcdd55251f35ad311ca74fa1e', 'info_dict': { - 'id': 'quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop', + 'id': '10981', 'ext': 'mp4', 'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop', 'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311', @@ -29,50 +38,106 @@ class AdobeTVIE(InfoExtractor): } def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - player = self._parse_json( - self._search_regex(r'html5player:\s*({.+?})\s*\n', webpage, 'player'), - video_id) + language, show_urlname, urlname = re.match(self._VALID_URL, url).groups() + if not language: + language = 'en' - title = player.get('title') or self._search_regex( - r'data-title="([^"]+)"', webpage, 'title') - description = self._og_search_description(webpage) - thumbnail = self._og_search_thumbnail(webpage) - - upload_date = unified_strdate( - self._html_search_meta('datepublished', webpage, 'upload date')) - - duration = parse_duration( - self._html_search_meta('duration', webpage, 'duration') or - self._search_regex( - r'Runtime:\s*(\d{2}:\d{2}:\d{2})', - webpage, 'duration', fatal=False)) - - view_count = str_to_int(self._search_regex( - r'<div class="views">\s*Views?:\s*([\d,.]+)\s*</div>', - webpage, 'view count')) + video_data = self._download_json( + self._API_BASE_URL + 'episode/get/?language=%s&show_urlname=%s&urlname=%s&disclosure=standard' % (language, show_urlname, urlname), + urlname)['data'][0] formats = [{ - 'url': source['src'], - 'format_id': source.get('quality') or source['src'].split('-')[-1].split('.')[0] or None, - 'tbr': source.get('bitrate'), - } for source in player['sources']] + 'url': source['url'], + 'format_id': source.get('quality_level') or source['url'].split('-')[-1].split('.')[0] or None, + 'width': int_or_none(source.get('width')), + 'height': int_or_none(source.get('height')), + 'tbr': int_or_none(source.get('video_data_rate')), + } for source in video_data['videos']] self._sort_formats(formats) return { - 'id': video_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'upload_date': upload_date, - 'duration': duration, - 'view_count': view_count, + 'id': compat_str(video_data['id']), + 'title': video_data['title'], + 'description': video_data.get('description'), + 'thumbnail': video_data.get('thumbnail'), + 'upload_date': unified_strdate(video_data.get('start_date')), + 'duration': parse_duration(video_data.get('duration')), + 'view_count': str_to_int(video_data.get('playcount')), 'formats': formats, } +class AdobeTVPlaylistBaseIE(AdobeTVBaseIE): + def _parse_page_data(self, page_data): + return [self.url_result(self._get_element_url(element_data)) for element_data in page_data] + + def _extract_playlist_entries(self, url, display_id): + page = self._download_json(url, display_id) + entries = self._parse_page_data(page['data']) + for page_num in range(2, page['paging']['pages'] + 1): + entries.extend(self._parse_page_data( + self._download_json(url + '&page=%d' % page_num, display_id)['data'])) + return entries + + +class AdobeTVShowIE(AdobeTVPlaylistBaseIE): + _VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?show/(?P<id>[^/]+)' + + _TEST = { + 'url': 'http://tv.adobe.com/show/the-complete-picture-with-julieanne-kost', + 'info_dict': { + 'id': '36', + 'title': 'The Complete Picture with Julieanne Kost', + 'description': 'md5:fa50867102dcd1aa0ddf2ab039311b27', + }, + 'playlist_mincount': 136, + } + + def _get_element_url(self, element_data): + return element_data['urls'][0] + + def _real_extract(self, url): + language, show_urlname = re.match(self._VALID_URL, url).groups() + if not language: + language = 'en' + query = 'language=%s&show_urlname=%s' % (language, show_urlname) + + show_data = self._download_json(self._API_BASE_URL + 'show/get/?%s' % query, show_urlname)['data'][0] + + return self.playlist_result( + self._extract_playlist_entries(self._API_BASE_URL + 'episode/?%s' % query, show_urlname), + compat_str(show_data['id']), + show_data['show_name'], + show_data['show_description']) + + +class AdobeTVChannelIE(AdobeTVPlaylistBaseIE): + _VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?channel/(?P<id>[^/]+)(?:/(?P<category_urlname>[^/]+))?' + + _TEST = { + 'url': 'http://tv.adobe.com/channel/development', + 'info_dict': { + 'id': 'development', + }, + 'playlist_mincount': 96, + } + + def _get_element_url(self, element_data): + return element_data['url'] + + def _real_extract(self, url): + language, channel_urlname, category_urlname = re.match(self._VALID_URL, url).groups() + if not language: + language = 'en' + query = 'language=%s&channel_urlname=%s' % (language, channel_urlname) + if category_urlname: + query += '&category_urlname=%s' % category_urlname + + return self.playlist_result( + self._extract_playlist_entries(self._API_BASE_URL + 'show/?%s' % query, channel_urlname), + channel_urlname) + + class AdobeTVVideoIE(InfoExtractor): _VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)' @@ -91,28 +156,25 @@ class AdobeTVVideoIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - player_params = self._parse_json(self._search_regex( - r'var\s+bridge\s*=\s*([^;]+);', webpage, 'player parameters'), - video_id) + video_data = self._download_json(url + '?format=json', video_id) formats = [{ + 'format_id': '%s-%s' % (determine_ext(source['src']), source.get('height')), 'url': source['src'], - 'width': source.get('width'), - 'height': source.get('height'), - 'tbr': source.get('bitrate'), - } for source in player_params['sources']] + 'width': int_or_none(source.get('width')), + 'height': int_or_none(source.get('height')), + 'tbr': int_or_none(source.get('bitrate')), + } for source in video_data['sources']] + self._sort_formats(formats) # For both metadata and downloaded files the duration varies among # formats. I just pick the max one duration = max(filter(None, [ float_or_none(source.get('duration'), scale=1000) - for source in player_params['sources']])) + for source in video_data['sources']])) subtitles = {} - for translation in player_params.get('translations', []): + for translation in video_data.get('translations', []): lang_id = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium']) if lang_id not in subtitles: subtitles[lang_id] = [] @@ -124,8 +186,9 @@ class AdobeTVVideoIE(InfoExtractor): return { 'id': video_id, 'formats': formats, - 'title': player_params['title'], - 'description': self._og_search_description(webpage), + 'title': video_data['title'], + 'description': video_data.get('description'), + 'thumbnail': video_data['video'].get('poster'), 'duration': duration, 'subtitles': subtitles, } diff --git a/youtube_dl/extractor/audimedia.py b/youtube_dl/extractor/audimedia.py index cad503510..b0b089dee 100644 --- a/youtube_dl/extractor/audimedia.py +++ b/youtube_dl/extractor/audimedia.py @@ -31,8 +31,8 @@ class AudiMediaIE(InfoExtractor): def _real_extract(self, url): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) - - raw_payload = self._search_regex(r'<script[^>]+class="amtv-embed"[^>]+id="([^"]+)"', webpage, 'raw payload'); + + raw_payload = self._search_regex(r'<script[^>]+class="amtv-embed"[^>]+id="([^"]+)"', webpage, 'raw payload') _, stage_mode, video_id, lang = raw_payload.split('-') # TODO: handle s and e stage_mode (live streams and ended live streams) diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 7fb80aa38..691aecc0d 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -47,9 +47,8 @@ class BBCCoUkIE(InfoExtractor): 'info_dict': { 'id': 'b039d07m', 'ext': 'flv', - 'title': 'Kaleidoscope, Leonard Cohen', + 'title': 'Leonard Cohen, Kaleidoscope - BBC Radio 4', 'description': 'The Canadian poet and songwriter reflects on his musical career.', - 'duration': 1740, }, 'params': { # rtmp download @@ -112,7 +111,8 @@ class BBCCoUkIE(InfoExtractor): 'params': { # rtmp download 'skip_download': True, - } + }, + 'skip': 'Episode is no longer available on BBC iPlayer Radio', }, { 'url': 'http://www.bbc.co.uk/music/clips/p02frcc3', 'note': 'Audio', @@ -454,6 +454,7 @@ class BBCCoUkIE(InfoExtractor): webpage = self._download_webpage(url, group_id, 'Downloading video page') programme_id = None + duration = None tviplayer = self._search_regex( r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById', @@ -473,7 +474,9 @@ class BBCCoUkIE(InfoExtractor): title = self._og_search_title(webpage) description = self._search_regex( r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>', - webpage, 'description', fatal=False) + webpage, 'description', default=None) + if not description: + description = self._html_search_meta('description', webpage) else: programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id) @@ -587,6 +590,7 @@ class BBCIE(BBCCoUkIE): 'ext': 'mp4', 'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''', 'duration': 56, + 'description': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''', }, 'params': { 'skip_download': True, @@ -729,6 +733,7 @@ class BBCIE(BBCCoUkIE): # article with multiple videos embedded with playlist.sxml (e.g. # http://www.bbc.com/sport/0/football/34475836) playlists = re.findall(r'<param[^>]+name="playlist"[^>]+value="([^"]+)"', webpage) + playlists.extend(re.findall(r'data-media-id="([^"]+/playlist\.sxml)"', webpage)) if playlists: entries = [ self._extract_from_playlist_sxml(playlist_url, playlist_id, timestamp) diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py index e63c2ac00..c8d921daf 100644 --- a/youtube_dl/extractor/beeg.py +++ b/youtube_dl/extractor/beeg.py @@ -34,15 +34,29 @@ class BeegIE(InfoExtractor): video_id = self._match_id(url) video = self._download_json( - 'http://beeg.com/api/v3/video/%s' % video_id, video_id) + 'http://beeg.com/api/v5/video/%s' % video_id, video_id) + + def split(o, e): + def cut(s, x): + n.append(s[:x]) + return s[x:] + n = [] + r = len(o) % e + if r > 0: + o = cut(o, r) + while len(o) > e: + o = cut(o, e) + n.append(o) + return n def decrypt_key(key): - # Reverse engineered from http://static.beeg.com/cpl/1067.js - a = '8RPUUCS35ZWp3ADnKcSmpH71ZusrROo' + # Reverse engineered from http://static.beeg.com/cpl/1105.js + a = '5ShMcIQlssOd7zChAIOlmeTZDaUxULbJRnywYaiB' e = compat_urllib_parse_unquote(key) - return ''.join([ - compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 25) + o = ''.join([ + compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 21) for n in range(len(e))]) + return ''.join(split(o, 3)[::-1]) def decrypt_url(encrypted_url): encrypted_url = self._proto_relative_url( diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py index 1c3644587..59beb11bc 100644 --- a/youtube_dl/extractor/bilibili.py +++ b/youtube_dl/extractor/bilibili.py @@ -2,16 +2,14 @@ from __future__ import unicode_literals import re -import json from .common import InfoExtractor -from ..compat import ( - compat_etree_fromstring, -) +from ..compat import compat_str from ..utils import ( int_or_none, unescapeHTML, ExtractorError, + xpath_text, ) @@ -58,27 +56,22 @@ class BiliBiliIE(InfoExtractor): cid = view_data['cid'] title = unescapeHTML(view_data['title']) - page = self._download_webpage( + doc = self._download_xml( 'http://interface.bilibili.com/v_cdn_play?appkey=8e9fc618fbd41e28&cid=%s' % cid, cid, 'Downloading page %s/%s' % (page_num, view_data['pages']) ) - try: - err_info = json.loads(page) - raise ExtractorError( - 'BiliBili said: ' + err_info['error_text'], expected=True) - except ValueError: - pass - doc = compat_etree_fromstring(page) + if xpath_text(doc, './result') == 'error': + raise ExtractorError('%s said: %s' % (self.IE_NAME, xpath_text(doc, './message')), expected=True) entries = [] for durl in doc.findall('./durl'): - size = durl.find('./filesize|./size') + size = xpath_text(durl, ['./filesize', './size']) formats = [{ 'url': durl.find('./url').text, - 'filesize': int_or_none(size.text) if size else None, + 'filesize': int_or_none(size), 'ext': 'flv', }] backup_urls = durl.find('./backup_url') @@ -88,21 +81,21 @@ class BiliBiliIE(InfoExtractor): formats.reverse() entries.append({ - 'id': '%s_part%s' % (cid, durl.find('./order').text), + 'id': '%s_part%s' % (cid, xpath_text(durl, './order')), 'title': title, - 'duration': int_or_none(durl.find('./length').text) // 1000, + 'duration': int_or_none(xpath_text(durl, './length'), 1000), 'formats': formats, }) info = { - 'id': str(cid), + 'id': compat_str(cid), 'title': title, 'description': view_data.get('description'), 'thumbnail': view_data.get('pic'), 'uploader': view_data.get('author'), 'timestamp': int_or_none(view_data.get('created')), - 'view_count': view_data.get('play'), - 'duration': int_or_none(doc.find('./timelength').text), + 'view_count': int_or_none(view_data.get('play')), + 'duration': int_or_none(xpath_text(doc, './timelength')), } if len(entries) == 1: diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index f5ebae1e6..03a4f446e 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -355,7 +355,7 @@ class BrightcoveLegacyIE(InfoExtractor): class BrightcoveNewIE(InfoExtractor): IE_NAME = 'brightcove:new' - _VALID_URL = r'https?://players\.brightcove\.net/(?P<account_id>\d+)/(?P<player_id>[^/]+)_(?P<embed>[^/]+)/index\.html\?.*videoId=(?P<video_id>\d+)' + _VALID_URL = r'https?://players\.brightcove\.net/(?P<account_id>\d+)/(?P<player_id>[^/]+)_(?P<embed>[^/]+)/index\.html\?.*videoId=(?P<video_id>(?:ref:)?\d+)' _TESTS = [{ 'url': 'http://players.brightcove.net/929656772001/e41d32dc-ec74-459e-a845-6c69f7b724ea_default/index.html?videoId=4463358922001', 'md5': 'c8100925723840d4b0d243f7025703be', @@ -387,14 +387,24 @@ class BrightcoveNewIE(InfoExtractor): 'params': { 'skip_download': True, } + }, { + # ref: prefixed video id + 'url': 'http://players.brightcove.net/3910869709001/21519b5c-4b3b-4363-accb-bdc8f358f823_default/index.html?videoId=ref:7069442', + 'only_matching': True, }] @staticmethod + def _extract_url(webpage): + urls = BrightcoveNewIE._extract_urls(webpage) + return urls[0] if urls else None + + @staticmethod def _extract_urls(webpage): # Reference: # 1. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/publish-video.html#setvideoiniframe - # 2. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/publish-video.html#setvideousingjavascript) + # 2. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/publish-video.html#setvideousingjavascript # 3. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/embed-in-page.html + # 4. https://support.brightcove.com/en/video-cloud/docs/dynamically-assigning-videos-player entries = [] @@ -407,9 +417,10 @@ class BrightcoveNewIE(InfoExtractor): for video_id, account_id, player_id, embed in re.findall( # According to examples from [3] it's unclear whether video id # may be optional and what to do when it is + # According to [4] data-video-id may be prefixed with ref: r'''(?sx) <video[^>]+ - data-video-id=["\'](\d+)["\'][^>]*>.*? + data-video-id=["\']((?:ref:)?\d+)["\'][^>]*>.*? </video>.*? <script[^>]+ src=["\'](?:https?:)?//players\.brightcove\.net/ diff --git a/youtube_dl/extractor/byutv.py b/youtube_dl/extractor/byutv.py index 3b2de517e..dda98059e 100644 --- a/youtube_dl/extractor/byutv.py +++ b/youtube_dl/extractor/byutv.py @@ -14,9 +14,10 @@ class BYUtvIE(InfoExtractor): 'info_dict': { 'id': 'studio-c-season-5-episode-5', 'ext': 'mp4', - 'description': 'md5:5438d33774b6bdc662f9485a340401cc', + 'description': 'md5:e07269172baff037f8e8bf9956bc9747', 'title': 'Season 5 Episode 5', - 'thumbnail': 're:^https?://.*\.jpg$' + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 1486.486, }, 'params': { 'skip_download': True, diff --git a/youtube_dl/extractor/canal13cl.py b/youtube_dl/extractor/canal13cl.py deleted file mode 100644 index 93241fefe..000000000 --- a/youtube_dl/extractor/canal13cl.py +++ /dev/null @@ -1,48 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor - - -class Canal13clIE(InfoExtractor): - _VALID_URL = r'^http://(?:www\.)?13\.cl/(?:[^/?#]+/)*(?P<id>[^/?#]+)' - _TEST = { - 'url': 'http://www.13.cl/t13/nacional/el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda', - 'md5': '4cb1fa38adcad8fea88487a078831755', - 'info_dict': { - 'id': '1403022125', - 'display_id': 'el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda', - 'ext': 'mp4', - 'title': 'El "círculo de hierro" de Michelle Bachelet en su regreso a La Moneda', - 'description': '(Foto: Agencia Uno) En nueve días más, Michelle Bachelet va a asumir por segunda vez como presidenta de la República. Entre aquellos que la acompañarán hay caras que se repiten y otras que se consolidan en su entorno de colaboradores más cercanos.', - } - } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = mobj.group('id') - - webpage = self._download_webpage(url, display_id) - - title = self._html_search_meta( - 'twitter:title', webpage, 'title', fatal=True) - description = self._html_search_meta( - 'twitter:description', webpage, 'description') - url = self._html_search_regex( - r'articuloVideo = \"(.*?)\"', webpage, 'url') - real_id = self._search_regex( - r'[^0-9]([0-9]{7,})[^0-9]', url, 'id', default=display_id) - thumbnail = self._html_search_regex( - r'articuloImagen = \"(.*?)\"', webpage, 'thumbnail') - - return { - 'id': real_id, - 'display_id': display_id, - 'url': url, - 'title': title, - 'description': description, - 'ext': 'mp4', - 'thumbnail': thumbnail, - } diff --git a/youtube_dl/extractor/clipfish.py b/youtube_dl/extractor/clipfish.py index 7af903571..3a47f6fa4 100644 --- a/youtube_dl/extractor/clipfish.py +++ b/youtube_dl/extractor/clipfish.py @@ -1,14 +1,9 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( - determine_ext, int_or_none, - js_to_json, - parse_iso8601, - remove_end, + unified_strdate, ) @@ -21,48 +16,47 @@ class ClipfishIE(InfoExtractor): 'id': '3966754', 'ext': 'mp4', 'title': 'FIFA 14 - E3 2013 Trailer', - 'timestamp': 1370938118, + 'description': 'Video zu FIFA 14: E3 2013 Trailer', 'upload_date': '20130611', 'duration': 82, + 'view_count': int, } } def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - video_info = self._parse_json( - js_to_json(self._html_search_regex( - '(?s)videoObject\s*=\s*({.+?});', webpage, 'video object')), - video_id) + video_info = self._download_json( + 'http://www.clipfish.de/devapi/id/%s?format=json&apikey=hbbtv' % video_id, + video_id)['items'][0] formats = [] - for video_url in re.findall(r'var\s+videourl\s*=\s*"([^"]+)"', webpage): - ext = determine_ext(video_url) - if ext == 'm3u8': - formats.append({ - 'url': video_url.replace('de.hls.fra.clipfish.de', 'hls.fra.clipfish.de'), - 'ext': 'mp4', - 'format_id': 'hls', - }) - else: - formats.append({ - 'url': video_url, - 'format_id': ext, - }) - self._sort_formats(formats) - title = remove_end(self._og_search_title(webpage), ' - Video') - thumbnail = self._og_search_thumbnail(webpage) - duration = int_or_none(video_info.get('length')) - timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage, 'upload date')) + m3u8_url = video_info.get('media_videourl_hls') + if m3u8_url: + formats.append({ + 'url': m3u8_url.replace('de.hls.fra.clipfish.de', 'hls.fra.clipfish.de'), + 'ext': 'mp4', + 'format_id': 'hls', + }) + + mp4_url = video_info.get('media_videourl') + if mp4_url: + formats.append({ + 'url': mp4_url, + 'format_id': 'mp4', + 'width': int_or_none(video_info.get('width')), + 'height': int_or_none(video_info.get('height')), + 'tbr': int_or_none(video_info.get('bitrate')), + }) return { 'id': video_id, - 'title': title, + 'title': video_info['title'], + 'description': video_info.get('descr'), 'formats': formats, - 'thumbnail': thumbnail, - 'duration': duration, - 'timestamp': timestamp, + 'thumbnail': video_info.get('media_content_thumbnail_large') or video_info.get('media_thumbnail'), + 'duration': int_or_none(video_info.get('media_length')), + 'upload_date': unified_strdate(video_info.get('pubDate')), + 'view_count': int_or_none(video_info.get('media_views')) } diff --git a/youtube_dl/extractor/cliphunter.py b/youtube_dl/extractor/cliphunter.py index d46592cc5..2996b6b09 100644 --- a/youtube_dl/extractor/cliphunter.py +++ b/youtube_dl/extractor/cliphunter.py @@ -1,7 +1,7 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import determine_ext +from ..utils import int_or_none _translation_table = { @@ -42,31 +42,26 @@ class CliphunterIE(InfoExtractor): video_title = self._search_regex( r'mediaTitle = "([^"]+)"', webpage, 'title') - fmts = {} - for fmt in ('mp4', 'flv'): - fmt_list = self._parse_json(self._search_regex( - r'var %sjson\s*=\s*(\[.*?\]);' % fmt, webpage, '%s formats' % fmt), video_id) - for f in fmt_list: - fmts[f['fname']] = _decode(f['sUrl']) - - qualities = self._parse_json(self._search_regex( - r'var player_btns\s*=\s*(.*?);\n', webpage, 'quality info'), video_id) + gexo_files = self._parse_json( + self._search_regex( + r'var\s+gexoFiles\s*=\s*({.+?});', webpage, 'gexo files'), + video_id) formats = [] - for fname, url in fmts.items(): - f = { - 'url': url, - } - if fname in qualities: - qual = qualities[fname] - f.update({ - 'format_id': '%s_%sp' % (determine_ext(url), qual['h']), - 'width': qual['w'], - 'height': qual['h'], - 'tbr': qual['br'], - }) - formats.append(f) - + for format_id, f in gexo_files.items(): + video_url = f.get('url') + if not video_url: + continue + fmt = f.get('fmt') + height = f.get('h') + format_id = '%s_%sp' % (fmt, height) if fmt and height else format_id + formats.append({ + 'url': _decode(video_url), + 'format_id': format_id, + 'width': int_or_none(f.get('w')), + 'height': int_or_none(height), + 'tbr': int_or_none(f.get('br')), + }) self._sort_formats(formats) thumbnail = self._search_regex( diff --git a/youtube_dl/extractor/cnet.py b/youtube_dl/extractor/cnet.py index 5dd69bff7..5c3908f72 100644 --- a/youtube_dl/extractor/cnet.py +++ b/youtube_dl/extractor/cnet.py @@ -1,15 +1,11 @@ # coding: utf-8 from __future__ import unicode_literals -import json +from .theplatform import ThePlatformIE +from ..utils import int_or_none -from .common import InfoExtractor -from ..utils import ( - ExtractorError, -) - -class CNETIE(InfoExtractor): +class CNETIE(ThePlatformIE): _VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/' _TESTS = [{ 'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/', @@ -18,25 +14,20 @@ class CNETIE(InfoExtractor): 'ext': 'flv', 'title': 'Hands-on with Microsoft Windows 8.1 Update', 'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.', - 'thumbnail': 're:^http://.*/flmswindows8.jpg$', 'uploader_id': '6085384d-619e-11e3-b231-14feb5ca9861', 'uploader': 'Sarah Mitroff', + 'duration': 70, }, - 'params': { - 'skip_download': 'requires rtmpdump', - } }, { 'url': 'http://www.cnet.com/videos/whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187/', 'info_dict': { 'id': '56527b93-d25d-44e3-b738-f989ce2e49ba', 'ext': 'flv', + 'title': 'Whiny potholes tweet at local government when hit by cars (Tomorrow Daily 187)', 'description': 'Khail and Ashley wonder what other civic woes can be solved by self-tweeting objects, investigate a new kind of VR camera and watch an origami robot self-assemble, walk, climb, dig and dissolve. #TDPothole', 'uploader_id': 'b163284d-6b73-44fc-b3e6-3da66c392d40', 'uploader': 'Ashley Esqueda', - 'title': 'Whiny potholes tweet at local government when hit by cars (Tomorrow Daily 187)', - }, - 'params': { - 'skip_download': True, # requires rtmpdump + 'duration': 1482, }, }] @@ -45,26 +36,13 @@ class CNETIE(InfoExtractor): webpage = self._download_webpage(url, display_id) data_json = self._html_search_regex( - r"<div class=\"cnetVideoPlayer\"\s+.*?data-cnet-video-options='([^']+)'", + r"data-cnet-video(?:-uvp)?-options='([^']+)'", webpage, 'data json') - data = json.loads(data_json) - vdata = data['video'] - if not vdata: - vdata = data['videos'][0] - if not vdata: - raise ExtractorError('Cannot find video data') - - mpx_account = data['config']['players']['default']['mpx_account'] - vid = vdata['files'].get('rtmp', vdata['files']['hds']) - tp_link = 'http://link.theplatform.com/s/%s/%s' % (mpx_account, vid) + data = self._parse_json(data_json, display_id) + vdata = data.get('video') or data['videos'][0] video_id = vdata['id'] - title = vdata.get('headline') - if title is None: - title = vdata.get('title') - if title is None: - raise ExtractorError('Cannot find title!') - thumbnail = vdata.get('image', {}).get('path') + title = vdata['title'] author = vdata.get('author') if author: uploader = '%s %s' % (author['firstName'], author['lastName']) @@ -73,13 +51,34 @@ class CNETIE(InfoExtractor): uploader = None uploader_id = None + mpx_account = data['config']['uvpConfig']['default']['mpx_account'] + + metadata = self.get_metadata('%s/%s' % (mpx_account, list(vdata['files'].values())[0]), video_id) + description = vdata.get('description') or metadata.get('description') + duration = int_or_none(vdata.get('duration')) or metadata.get('duration') + + formats = [] + subtitles = {} + for (fkey, vid) in vdata['files'].items(): + if fkey == 'hls_phone' and 'hls_tablet' in vdata['files']: + continue + release_url = 'http://link.theplatform.com/s/%s/%s?format=SMIL&mbr=true' % (mpx_account, vid) + if fkey == 'hds': + release_url += '&manifest=f4m' + tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % fkey) + formats.extend(tp_formats) + subtitles = self._merge_subtitles(subtitles, tp_subtitles) + self._sort_formats(formats) + return { - '_type': 'url_transparent', - 'url': tp_link, 'id': video_id, 'display_id': display_id, 'title': title, + 'description': description, + 'thumbnail': metadata.get('thumbnail'), + 'duration': duration, 'uploader': uploader, 'uploader_id': uploader_id, - 'thumbnail': thumbnail, + 'subtitles': subtitles, + 'formats': formats, } diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 6ab2d68d6..828f58f12 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -30,6 +30,7 @@ from ..utils import ( clean_html, compiled_regex_type, determine_ext, + error_to_compat_str, ExtractorError, fix_xml_ampersands, float_or_none, @@ -332,7 +333,8 @@ class InfoExtractor(object): return False if errnote is None: errnote = 'Unable to download webpage' - errmsg = '%s: %s' % (errnote, compat_str(err)) + + errmsg = '%s: %s' % (errnote, error_to_compat_str(err)) if fatal: raise ExtractorError(errmsg, sys.exc_info()[2], cause=err) else: @@ -622,7 +624,7 @@ class InfoExtractor(object): else: raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) except (IOError, netrc.NetrcParseError) as err: - self._downloader.report_warning('parsing .netrc: %s' % compat_str(err)) + self._downloader.report_warning('parsing .netrc: %s' % error_to_compat_str(err)) return (username, password) diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index ab7f3aec4..0c5b6617f 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -7,10 +7,10 @@ import itertools from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( - ExtractorError, determine_ext, + error_to_compat_str, + ExtractorError, int_or_none, parse_iso8601, sanitized_Request, @@ -99,6 +99,11 @@ class DailymotionIE(DailymotionBaseInfoExtractor): { 'url': 'http://www.dailymotion.com/video/xhza0o', 'only_matching': True, + }, + # with subtitles + { + 'url': 'http://www.dailymotion.com/video/x20su5f_the-power-of-nightmares-1-the-rise-of-the-politics-of-fear-bbc-2004_news', + 'only_matching': True, } ] @@ -122,7 +127,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor): webpage, 'comment count', fatal=False)) player_v5 = self._search_regex( - [r'buildPlayer\(({.+?})\);', r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);'], + [r'buildPlayer\(({.+?})\);\n', # See https://github.com/rg3/youtube-dl/issues/7826 + r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);', + r'buildPlayer\(({.+?})\);'], webpage, 'player v5', default=None) if player_v5: player = self._parse_json(player_v5, video_id) @@ -172,11 +179,13 @@ class DailymotionIE(DailymotionBaseInfoExtractor): uploader_id = metadata.get('owner', {}).get('id') subtitles = {} - for subtitle_lang, subtitle in metadata.get('subtitles', {}).get('data', {}).items(): - subtitles[subtitle_lang] = [{ - 'ext': determine_ext(subtitle_url), - 'url': subtitle_url, - } for subtitle_url in subtitle.get('urls', [])] + subtitles_data = metadata.get('subtitles', {}).get('data', {}) + if subtitles_data and isinstance(subtitles_data, dict): + for subtitle_lang, subtitle in subtitles_data.items(): + subtitles[subtitle_lang] = [{ + 'ext': determine_ext(subtitle_url), + 'url': subtitle_url, + } for subtitle_url in subtitle.get('urls', [])] return { 'id': video_id, @@ -269,7 +278,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor): 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id, video_id, note=False) except ExtractorError as err: - self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err)) + self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err)) return {} info = json.loads(sub_list) if (info['total'] > 0): diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index 321eec59e..39c481068 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -7,11 +7,11 @@ import socket from .common import InfoExtractor from ..compat import ( compat_http_client, - compat_str, compat_urllib_error, compat_urllib_parse_unquote, ) from ..utils import ( + error_to_compat_str, ExtractorError, limit_length, sanitized_Request, @@ -116,7 +116,7 @@ class FacebookIE(InfoExtractor): if re.search(r'id="checkpointSubmitButton"', check_response) is not None: self._downloader.report_warning('Unable to confirm login, you have to login in your brower and authorize the login.') except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.report_warning('unable to log in: %s' % compat_str(err)) + self._downloader.report_warning('unable to log in: %s' % error_to_compat_str(err)) return def _real_initialize(self): diff --git a/youtube_dl/extractor/faz.py b/youtube_dl/extractor/faz.py index cebdd0193..6f9b003c2 100644 --- a/youtube_dl/extractor/faz.py +++ b/youtube_dl/extractor/faz.py @@ -2,6 +2,11 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..utils import ( + xpath_element, + xpath_text, + int_or_none, +) class FazIE(InfoExtractor): @@ -37,31 +42,32 @@ class FazIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) + description = self._og_search_description(webpage) config_xml_url = self._search_regex( - r'writeFLV\(\'(.+?)\',', webpage, 'config xml url') + r'videoXMLURL\s*=\s*"([^"]+)', webpage, 'config xml url') config = self._download_xml( config_xml_url, video_id, 'Downloading config xml') - encodings = config.find('ENCODINGS') + encodings = xpath_element(config, 'ENCODINGS', 'encodings', True) formats = [] for pref, code in enumerate(['LOW', 'HIGH', 'HQ']): - encoding = encodings.find(code) - if encoding is None: - continue - encoding_url = encoding.find('FILENAME').text - formats.append({ - 'url': encoding_url, - 'format_id': code.lower(), - 'quality': pref, - }) + encoding = xpath_element(encodings, code) + if encoding: + encoding_url = xpath_text(encoding, 'FILENAME') + if encoding_url: + formats.append({ + 'url': encoding_url, + 'format_id': code.lower(), + 'quality': pref, + 'tbr': int_or_none(xpath_text(encoding, 'AVERAGEBITRATE')), + }) self._sort_formats(formats) - descr = self._html_search_regex( - r'<p class="Content Copy">(.*?)</p>', webpage, 'description', fatal=False) return { 'id': video_id, 'title': self._og_search_title(webpage), 'formats': formats, - 'description': descr, - 'thumbnail': config.find('STILL/STILL_BIG').text, + 'description': description.strip() if description else None, + 'thumbnail': xpath_text(config, 'STILL/STILL_BIG'), + 'duration': int_or_none(xpath_text(config, 'DURATION')), } diff --git a/youtube_dl/extractor/fc2.py b/youtube_dl/extractor/fc2.py index 92e8c571f..4c81271d3 100644 --- a/youtube_dl/extractor/fc2.py +++ b/youtube_dl/extractor/fc2.py @@ -37,8 +37,8 @@ class FC2IE(InfoExtractor): 'params': { 'username': 'ytdl@yt-dl.org', 'password': '(snip)', - 'skip': 'requires actual password' - } + }, + 'skip': 'requires actual password', }, { 'url': 'http://video.fc2.com/en/a/content/20130926eZpARwsF', 'only_matching': True, diff --git a/youtube_dl/extractor/fktv.py b/youtube_dl/extractor/fktv.py index 40ea27895..5f6e65dae 100644 --- a/youtube_dl/extractor/fktv.py +++ b/youtube_dl/extractor/fktv.py @@ -1,12 +1,10 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( clean_html, determine_ext, - ExtractorError, + js_to_json, ) @@ -32,24 +30,22 @@ class FKTVIE(InfoExtractor): 'http://fernsehkritik.tv/folge-%s/play' % episode, episode) title = clean_html(self._html_search_regex( '<h3>([^<]+)</h3>', webpage, 'title')) - matches = re.search( - r'(?s)<video(?:(?!poster)[^>])+(?:poster="([^"]+)")?[^>]*>(.*)</video>', - webpage) - if matches is None: - raise ExtractorError('Unable to extract the video') - - poster, sources = matches.groups() - if poster is None: - self.report_warning('unable to extract thumbnail') - - urls = re.findall(r'<source[^>]+src="([^"]+)"', sources) - formats = [{ - 'url': furl, - 'format_id': determine_ext(furl), - } for furl in urls] + thumbnail = self._search_regex(r'POSTER\s*=\s*"([^"]+)', webpage, 'thumbnail', fatal=False) + sources = self._parse_json(self._search_regex(r'(?s)MEDIA\s*=\s*(\[.+?\]);', webpage, 'media'), episode, js_to_json) + + formats = [] + for source in sources: + furl = source.get('src') + if furl: + formats.append({ + 'url': furl, + 'format_id': determine_ext(furl), + }) + self._sort_formats(formats) + return { 'id': episode, 'title': title, 'formats': formats, - 'thumbnail': poster, + 'thumbnail': thumbnail, } diff --git a/youtube_dl/extractor/flickr.py b/youtube_dl/extractor/flickr.py index 91cd46e76..452b27b26 100644 --- a/youtube_dl/extractor/flickr.py +++ b/youtube_dl/extractor/flickr.py @@ -1,67 +1,87 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor +from ..compat import compat_urllib_parse from ..utils import ( ExtractorError, - find_xpath_attr, - sanitized_Request, + int_or_none, + qualities, ) class FlickrIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.|secure\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*' + _VALID_URL = r'https?://(?:www\.|secure\.)?flickr\.com/photos/[\w\-_@]+/(?P<id>\d+)' _TEST = { 'url': 'http://www.flickr.com/photos/forestwander-nature-pictures/5645318632/in/photostream/', - 'md5': '6fdc01adbc89d72fc9c4f15b4a4ba87b', + 'md5': '164fe3fa6c22e18d448d4d5af2330f31', 'info_dict': { 'id': '5645318632', - 'ext': 'mp4', - "description": "Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up.", - "uploader_id": "forestwander-nature-pictures", - "title": "Dark Hollow Waterfalls" + 'ext': 'mpg', + '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.', + 'title': 'Dark Hollow Waterfalls', + 'duration': 19, + 'timestamp': 1303528740, + 'upload_date': '20110423', + 'uploader_id': '10922353@N03', + 'uploader': 'Forest Wander', + 'comment_count': int, + 'view_count': int, + 'tags': list, } } - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) + _API_BASE_URL = 'https://api.flickr.com/services/rest?' - video_id = mobj.group('id') - video_uploader_id = mobj.group('uploader_id') - webpage_url = 'http://www.flickr.com/photos/' + video_uploader_id + '/' + video_id - req = sanitized_Request(webpage_url) - req.add_header( - 'User-Agent', - # it needs a more recent version - 'Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20150101 Firefox/38.0 (Chrome)') - webpage = self._download_webpage(req, video_id) + def _call_api(self, method, video_id, api_key, note, secret=None): + query = { + 'photo_id': video_id, + 'method': 'flickr.%s' % method, + 'api_key': api_key, + 'format': 'json', + 'nojsoncallback': 1, + } + if secret: + query['secret'] = secret + data = self._download_json(self._API_BASE_URL + compat_urllib_parse.urlencode(query), video_id, note) + if data['stat'] != 'ok': + raise ExtractorError(data['message']) + return data - secret = self._search_regex(r'secret"\s*:\s*"(\w+)"', webpage, 'secret') + def _real_extract(self, url): + video_id = self._match_id(url) - first_url = 'https://secure.flickr.com/apps/video/video_mtl_xml.gne?v=x&photo_id=' + video_id + '&secret=' + secret + '&bitrate=700&target=_self' - first_xml = self._download_xml(first_url, video_id, 'Downloading first data webpage') + api_key = self._download_json('https://www.flickr.com/hermes_error_beacon.gne', video_id, 'Downloading api key',)['site_key'] - node_id = find_xpath_attr( - first_xml, './/{http://video.yahoo.com/YEP/1.0/}Item', 'id', - 'id').text + video_info = self._call_api('photos.getInfo', video_id, api_key, 'Downloading video info')['photo'] + if video_info['media'] == 'video': + streams = self._call_api('video.getStreamInfo', video_id, api_key, 'Downloading streams info', video_info['secret'])['streams'] - second_url = 'https://secure.flickr.com/video_playlist.gne?node_id=' + node_id + '&tech=flash&mode=playlist&bitrate=700&secret=' + secret + '&rd=video.yahoo.com&noad=1' - second_xml = self._download_xml(second_url, video_id, 'Downloading second data webpage') + preference = qualities(['iphone_wifi', '700', 'appletv', 'orig']) - self.report_extraction(video_id) + formats = [] + for stream in streams['stream']: + stream_type = str(stream.get('type')) + formats.append({ + 'format_id': stream_type, + 'url': stream['_content'], + 'preference': preference(stream_type), + }) + self._sort_formats(formats) - stream = second_xml.find('.//STREAM') - if stream is None: - raise ExtractorError('Unable to extract video url') - video_url = stream.attrib['APP'] + stream.attrib['FULLPATH'] + owner = video_info.get('owner', {}) - return { - 'id': video_id, - 'url': video_url, - 'ext': 'mp4', - 'title': self._og_search_title(webpage), - 'description': self._og_search_description(webpage), - 'thumbnail': self._og_search_thumbnail(webpage), - 'uploader_id': video_uploader_id, - } + return { + 'id': video_id, + 'title': video_info['title']['_content'], + 'description': video_info.get('description', {}).get('_content'), + 'formats': formats, + 'timestamp': int_or_none(video_info.get('dateuploaded')), + 'duration': int_or_none(video_info.get('video', {}).get('duration')), + 'uploader_id': owner.get('nsid'), + 'uploader': owner.get('realname'), + 'comment_count': int_or_none(video_info.get('comments', {}).get('_content')), + 'view_count': int_or_none(video_info.get('views')), + 'tags': [tag.get('_content') for tag in video_info.get('tags', {}).get('tag', [])] + } + else: + raise ExtractorError('not a video', expected=True) diff --git a/youtube_dl/extractor/footyroom.py b/youtube_dl/extractor/footyroom.py index 4c7dbca40..370fd006f 100644 --- a/youtube_dl/extractor/footyroom.py +++ b/youtube_dl/extractor/footyroom.py @@ -13,6 +13,7 @@ class FootyRoomIE(InfoExtractor): 'title': 'Schalke 04 0 – 2 Real Madrid', }, 'playlist_count': 3, + 'skip': 'Video for this match is not available', }, { 'url': 'http://footyroom.com/georgia-0-2-germany-2015-03/', 'info_dict': { diff --git a/youtube_dl/extractor/funimation.py b/youtube_dl/extractor/funimation.py new file mode 100644 index 000000000..d1a95d87f --- /dev/null +++ b/youtube_dl/extractor/funimation.py @@ -0,0 +1,193 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + clean_html, + determine_ext, + encode_dict, + int_or_none, + sanitized_Request, + ExtractorError, + urlencode_postdata +) + + +class FunimationIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?funimation\.com/shows/[^/]+/videos/(?:official|promotional)/(?P<id>[^/?#&]+)' + + _NETRC_MACHINE = 'funimation' + + _TESTS = [{ + 'url': 'http://www.funimation.com/shows/air/videos/official/breeze', + 'info_dict': { + 'id': '658', + 'display_id': 'breeze', + 'ext': 'mp4', + 'title': 'Air - 1 - Breeze', + 'description': 'md5:1769f43cd5fc130ace8fd87232207892', + 'thumbnail': 're:https?://.*\.jpg', + }, + }, { + 'url': 'http://www.funimation.com/shows/hacksign/videos/official/role-play', + 'info_dict': { + 'id': '31128', + 'display_id': 'role-play', + 'ext': 'mp4', + 'title': '.hack//SIGN - 1 - Role Play', + 'description': 'md5:b602bdc15eef4c9bbb201bb6e6a4a2dd', + 'thumbnail': 're:https?://.*\.jpg', + }, + }, { + 'url': 'http://www.funimation.com/shows/attack-on-titan-junior-high/videos/promotional/broadcast-dub-preview', + 'info_dict': { + 'id': '9635', + 'display_id': 'broadcast-dub-preview', + 'ext': 'mp4', + 'title': 'Attack on Titan: Junior High - Broadcast Dub Preview', + 'description': 'md5:f8ec49c0aff702a7832cd81b8a44f803', + 'thumbnail': 're:https?://.*\.(?:jpg|png)', + }, + }] + + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + data = urlencode_postdata(encode_dict({ + 'email_field': username, + 'password_field': password, + })) + login_request = sanitized_Request('http://www.funimation.com/login', data, headers={ + 'User-Agent': 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0', + 'Content-Type': 'application/x-www-form-urlencoded' + }) + login_page = self._download_webpage( + login_request, None, 'Logging in as %s' % username) + if any(p in login_page for p in ('funimation.com/logout', '>Log Out<')): + return + error = self._html_search_regex( + r'(?s)<div[^>]+id=["\']errorMessages["\'][^>]*>(.+?)</div>', + login_page, 'error messages', default=None) + if error: + raise ExtractorError('Unable to login: %s' % error, expected=True) + raise ExtractorError('Unable to log in') + + def _real_initialize(self): + self._login() + + def _real_extract(self, url): + display_id = self._match_id(url) + + errors = [] + formats = [] + + ERRORS_MAP = { + 'ERROR_MATURE_CONTENT_LOGGED_IN': 'matureContentLoggedIn', + 'ERROR_MATURE_CONTENT_LOGGED_OUT': 'matureContentLoggedOut', + 'ERROR_SUBSCRIPTION_LOGGED_OUT': 'subscriptionLoggedOut', + 'ERROR_VIDEO_EXPIRED': 'videoExpired', + 'ERROR_TERRITORY_UNAVAILABLE': 'territoryUnavailable', + 'SVODBASIC_SUBSCRIPTION_IN_PLAYER': 'basicSubscription', + 'SVODNON_SUBSCRIPTION_IN_PLAYER': 'nonSubscription', + 'ERROR_PLAYER_NOT_RESPONDING': 'playerNotResponding', + 'ERROR_UNABLE_TO_CONNECT_TO_CDN': 'unableToConnectToCDN', + 'ERROR_STREAM_NOT_FOUND': 'streamNotFound', + } + + USER_AGENTS = ( + # PC UA is served with m3u8 that provides some bonus lower quality formats + ('pc', 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0'), + # Mobile UA allows to extract direct links and also does not fail when + # PC UA fails with hulu error (e.g. + # http://www.funimation.com/shows/hacksign/videos/official/role-play) + ('mobile', 'Mozilla/5.0 (Linux; Android 4.4.2; Nexus 4 Build/KOT49H) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.114 Mobile Safari/537.36'), + ) + + for kind, user_agent in USER_AGENTS: + request = sanitized_Request(url) + request.add_header('User-Agent', user_agent) + webpage = self._download_webpage( + request, display_id, 'Downloading %s webpage' % kind) + + playlist = self._parse_json( + self._search_regex( + r'var\s+playersData\s*=\s*(\[.+?\]);\n', + webpage, 'players data'), + display_id)[0]['playlist'] + + items = next(item['items'] for item in playlist if item.get('items')) + item = next(item for item in items if item.get('itemAK') == display_id) + + error_messages = {} + video_error_messages = self._search_regex( + r'var\s+videoErrorMessages\s*=\s*({.+?});\n', + webpage, 'error messages', default=None) + if video_error_messages: + error_messages_json = self._parse_json(video_error_messages, display_id, fatal=False) + if error_messages_json: + for _, error in error_messages_json.items(): + type_ = error.get('type') + description = error.get('description') + content = error.get('content') + if type_ == 'text' and description and content: + error_message = ERRORS_MAP.get(description) + if error_message: + error_messages[error_message] = content + + for video in item.get('videoSet', []): + auth_token = video.get('authToken') + if not auth_token: + continue + funimation_id = video.get('FUNImationID') or video.get('videoId') + preference = 1 if video.get('languageMode') == 'dub' else 0 + if not auth_token.startswith('?'): + auth_token = '?%s' % auth_token + for quality, height in (('sd', 480), ('hd', 720), ('hd1080', 1080)): + format_url = video.get('%sUrl' % quality) + if not format_url: + continue + if not format_url.startswith(('http', '//')): + errors.append(format_url) + continue + if determine_ext(format_url) == 'm3u8': + m3u8_formats = self._extract_m3u8_formats( + format_url + auth_token, display_id, 'mp4', entry_protocol='m3u8_native', + preference=preference, m3u8_id='%s-hls' % funimation_id, fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + else: + tbr = int_or_none(self._search_regex( + r'-(\d+)[Kk]', format_url, 'tbr', default=None)) + formats.append({ + 'url': format_url + auth_token, + 'format_id': '%s-http-%dp' % (funimation_id, height), + 'height': height, + 'tbr': tbr, + 'preference': preference, + }) + + if not formats and errors: + raise ExtractorError( + '%s returned error: %s' + % (self.IE_NAME, clean_html(error_messages.get(errors[0], errors[0]))), + expected=True) + + self._sort_formats(formats) + + title = item['title'] + artist = item.get('artist') + if artist: + title = '%s - %s' % (artist, title) + description = self._og_search_description(webpage) or item.get('description') + thumbnail = self._og_search_thumbnail(webpage) or item.get('posterUrl') + video_id = item.get('itemId') or display_id + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/gameinformer.py b/youtube_dl/extractor/gameinformer.py new file mode 100644 index 000000000..25870c131 --- /dev/null +++ b/youtube_dl/extractor/gameinformer.py @@ -0,0 +1,43 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import int_or_none + + +class GameInformerIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?gameinformer\.com/(?:[^/]+/)*(?P<id>.+)\.aspx' + _TEST = { + 'url': 'http://www.gameinformer.com/b/features/archive/2015/09/26/replay-animal-crossing.aspx', + 'info_dict': { + 'id': '4515472681001', + 'ext': 'm3u8', + 'title': 'Replay - Animal Crossing', + 'description': 'md5:2e211891b215c85d061adc7a4dd2d930', + 'timestamp': 1443457610706, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + bc_api_url = self._search_regex(r"getVideo\('([^']+)'", webpage, 'brightcove api url') + json_data = self._download_json( + bc_api_url + '&video_fields=id,name,shortDescription,publishedDate,videoStillURL,length,IOSRenditions', + display_id) + + return { + 'id': compat_str(json_data['id']), + 'display_id': display_id, + 'url': json_data['IOSRenditions'][0]['url'], + 'title': json_data['name'], + 'description': json_data.get('shortDescription'), + 'timestamp': int_or_none(json_data.get('publishedDate')), + 'duration': int_or_none(json_data.get('length')), + } diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index f5dd88f54..3c3066e38 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -53,6 +53,8 @@ from .onionstudios import OnionStudiosIE from .snagfilms import SnagFilmsEmbedIE from .screenwavemedia import ScreenwaveMediaIE from .mtv import MTVServicesEmbeddedIE +from .pladform import PladformIE +from .googledrive import GoogleDriveIE from .jwplatform import JWPlatformIE @@ -339,6 +341,7 @@ class GenericIE(InfoExtractor): 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ', 'ext': 'mp4', 'title': '2cc213299525360.mov', # that's what we get + 'duration': 238.231, }, 'add_ie': ['Ooyala'], }, @@ -350,6 +353,7 @@ class GenericIE(InfoExtractor): 'ext': 'mp4', 'title': '"Steve Jobs: Man in the Machine" trailer', 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."', + 'duration': 135.427, }, 'params': { 'skip_download': True, @@ -960,8 +964,9 @@ class GenericIE(InfoExtractor): 'info_dict': { 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs', 'ext': 'mp4', - 'description': 'VIDEO: Index/Match versus VLOOKUP.', + 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.', 'title': 'This is what separates the Excel masters from the wannabes', + 'duration': 191.933, }, 'params': { # m3u8 downloads @@ -1496,7 +1501,7 @@ class GenericIE(InfoExtractor): re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage)) if mobj is not None: - return OoyalaIE._build_url_result(mobj.group('ec')) + return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url})) # Look for multiple Ooyala embeds on SBN network websites mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage) @@ -1504,7 +1509,7 @@ class GenericIE(InfoExtractor): embeds = self._parse_json(mobj.group(1), video_id, fatal=False) if embeds: return _playlist_from_matches( - embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala') + embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala') # Look for Aparat videos mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage) @@ -1733,10 +1738,9 @@ class GenericIE(InfoExtractor): return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform') # Look for Pladform embeds - mobj = re.search( - r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage) - if mobj is not None: - return self.url_result(mobj.group('url'), 'Pladform') + pladform_url = PladformIE._extract_url(webpage) + if pladform_url: + return self.url_result(pladform_url) # Look for Playwire embeds mobj = re.search( @@ -1761,6 +1765,11 @@ class GenericIE(InfoExtractor): if nbc_sports_url: return self.url_result(nbc_sports_url, 'NBCSportsVPlayer') + # Look for Google Drive embeds + google_drive_url = GoogleDriveIE._extract_url(webpage) + if google_drive_url: + return self.url_result(google_drive_url, 'GoogleDrive') + # Look for UDN embeds mobj = re.search( r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage) diff --git a/youtube_dl/extractor/googledrive.py b/youtube_dl/extractor/googledrive.py new file mode 100644 index 000000000..f354c9c7a --- /dev/null +++ b/youtube_dl/extractor/googledrive.py @@ -0,0 +1,88 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + int_or_none, +) + + +class GoogleDriveIE(InfoExtractor): + _VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28})' + _TEST = { + 'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1', + 'md5': '881f7700aec4f538571fa1e0eed4a7b6', + 'info_dict': { + 'id': '0ByeS4oOUV-49Zzh4R1J6R09zazQ', + 'ext': 'mp4', + 'title': 'Big Buck Bunny.mp4', + 'duration': 46, + } + } + _FORMATS_EXT = { + '5': 'flv', + '6': 'flv', + '13': '3gp', + '17': '3gp', + '18': 'mp4', + '22': 'mp4', + '34': 'flv', + '35': 'flv', + '36': '3gp', + '37': 'mp4', + '38': 'mp4', + '43': 'webm', + '44': 'webm', + '45': 'webm', + '46': 'webm', + '59': 'mp4', + } + + @staticmethod + def _extract_url(webpage): + mobj = re.search( + r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28})', + webpage) + if mobj: + return 'https://drive.google.com/file/d/%s' % mobj.group('id') + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage( + 'http://docs.google.com/file/d/%s' % video_id, video_id, encoding='unicode_escape') + + reason = self._search_regex(r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None) + if reason: + raise ExtractorError(reason) + + title = self._search_regex(r'"title"\s*,\s*"([^"]+)', webpage, 'title') + duration = int_or_none(self._search_regex( + r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds', default=None)) + fmt_stream_map = self._search_regex( + r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage, 'fmt stream map').split(',') + fmt_list = self._search_regex(r'"fmt_list"\s*,\s*"([^"]+)', webpage, 'fmt_list').split(',') + + formats = [] + for fmt, fmt_stream in zip(fmt_list, fmt_stream_map): + fmt_id, fmt_url = fmt_stream.split('|') + resolution = fmt.split('/')[1] + width, height = resolution.split('x') + formats.append({ + 'url': fmt_url, + 'format_id': fmt_id, + 'resolution': resolution, + 'width': int_or_none(width), + 'height': int_or_none(height), + 'ext': self._FORMATS_EXT[fmt_id], + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'thumbnail': self._og_search_thumbnail(webpage), + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/gputechconf.py b/youtube_dl/extractor/gputechconf.py new file mode 100644 index 000000000..145b55bf3 --- /dev/null +++ b/youtube_dl/extractor/gputechconf.py @@ -0,0 +1,55 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + xpath_element, + xpath_text, + int_or_none, + parse_duration, +) + + +class GPUTechConfIE(InfoExtractor): + _VALID_URL = r'https?://on-demand\.gputechconf\.com/gtc/2015/video/S(?P<id>\d+)\.html' + _TEST = { + 'url': 'http://on-demand.gputechconf.com/gtc/2015/video/S5156.html', + 'md5': 'a8862a00a0fd65b8b43acc5b8e33f798', + 'info_dict': { + 'id': '5156', + 'ext': 'mp4', + 'title': 'Coordinating More Than 3 Million CUDA Threads for Social Network Analysis', + 'duration': 1219, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + root_path = self._search_regex(r'var\s+rootPath\s*=\s*"([^"]+)', webpage, 'root path', 'http://evt.dispeak.com/nvidia/events/gtc15/') + xml_file_id = self._search_regex(r'var\s+xmlFileId\s*=\s*"([^"]+)', webpage, 'xml file id') + + doc = self._download_xml('%sxml/%s.xml' % (root_path, xml_file_id), video_id) + + metadata = xpath_element(doc, 'metadata') + http_host = xpath_text(metadata, 'httpHost', 'http host', True) + mbr_videos = xpath_element(metadata, 'MBRVideos') + + formats = [] + for mbr_video in mbr_videos.findall('MBRVideo'): + stream_name = xpath_text(mbr_video, 'streamName') + if stream_name: + formats.append({ + 'url': 'http://%s/%s' % (http_host, stream_name.replace('mp4:', '')), + 'tbr': int_or_none(xpath_text(mbr_video, 'bitrate')), + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': xpath_text(metadata, 'title'), + 'duration': parse_duration(xpath_text(metadata, 'endTime')), + 'creator': xpath_text(metadata, 'speaker'), + 'formats': formats, + } diff --git a/youtube_dl/extractor/groupon.py b/youtube_dl/extractor/groupon.py index 8b9e0e2f8..63c05b6a6 100644 --- a/youtube_dl/extractor/groupon.py +++ b/youtube_dl/extractor/groupon.py @@ -18,6 +18,8 @@ class GrouponIE(InfoExtractor): 'id': 'tubGNycTo_9Uxg82uESj4i61EYX8nyuf', 'ext': 'mp4', 'title': 'Bikram Yoga Huntington Beach | Orange County', + 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', + 'duration': 44.961, }, }], 'params': { diff --git a/youtube_dl/extractor/howcast.py b/youtube_dl/extractor/howcast.py index 16677f179..e8f51e545 100644 --- a/youtube_dl/extractor/howcast.py +++ b/youtube_dl/extractor/howcast.py @@ -16,6 +16,7 @@ class HowcastIE(InfoExtractor): 'description': 'md5:dbe792e5f6f1489027027bf2eba188a3', 'timestamp': 1276081287, 'upload_date': '20100609', + 'duration': 56.823, }, 'params': { # m3u8 download diff --git a/youtube_dl/extractor/hypem.py b/youtube_dl/extractor/hypem.py index cca3dd498..b3706fe6d 100644 --- a/youtube_dl/extractor/hypem.py +++ b/youtube_dl/extractor/hypem.py @@ -28,15 +28,12 @@ class HypemIE(InfoExtractor): track_id = self._match_id(url) data = {'ax': 1, 'ts': time.time()} - data_encoded = compat_urllib_parse.urlencode(data) - complete_url = url + "?" + data_encoded - request = sanitized_Request(complete_url) + request = sanitized_Request(url + '?' + compat_urllib_parse.urlencode(data)) response, urlh = self._download_webpage_handle( request, track_id, 'Downloading webpage with the url') - cookie = urlh.headers.get('Set-Cookie', '') html_tracks = self._html_search_regex( - r'(?ms)<script type="application/json" id="displayList-data">\s*(.*?)\s*</script>', + r'(?ms)<script type="application/json" id="displayList-data">(.+?)</script>', response, 'tracks') try: track_list = json.loads(html_tracks) @@ -46,15 +43,14 @@ class HypemIE(InfoExtractor): key = track['key'] track_id = track['id'] - artist = track['artist'] title = track['song'] - serve_url = "http://hypem.com/serve/source/%s/%s" % (track_id, key) request = sanitized_Request( - serve_url, '', {'Content-Type': 'application/json'}) - request.add_header('cookie', cookie) + 'http://hypem.com/serve/source/%s/%s' % (track_id, key), + '', {'Content-Type': 'application/json'}) song_data = self._download_json(request, track_id, 'Downloading metadata') - final_url = song_data["url"] + final_url = song_data['url'] + artist = track.get('artist') return { 'id': track_id, diff --git a/youtube_dl/extractor/infoq.py b/youtube_dl/extractor/infoq.py index 71cfd12c5..016af2084 100644 --- a/youtube_dl/extractor/infoq.py +++ b/youtube_dl/extractor/infoq.py @@ -1,3 +1,5 @@ +# coding: utf-8 + from __future__ import unicode_literals import base64 @@ -5,8 +7,9 @@ import base64 from .common import InfoExtractor from ..compat import ( compat_urllib_parse_unquote, - compat_urlparse, + compat_parse_qs, ) +from ..utils import determine_ext class InfoQIE(InfoExtractor): @@ -16,7 +19,7 @@ class InfoQIE(InfoExtractor): 'url': 'http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things', 'md5': 'b5ca0e0a8c1fed93b0e65e48e462f9a2', 'info_dict': { - 'id': '12-jan-pythonthings', + 'id': 'A-Few-of-My-Favorite-Python-Things', 'ext': 'mp4', 'description': 'Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.', 'title': 'A Few of My Favorite [Python] Things', @@ -24,40 +27,84 @@ class InfoQIE(InfoExtractor): }, { 'url': 'http://www.infoq.com/fr/presentations/changez-avis-sur-javascript', 'only_matching': True, + }, { + 'url': 'http://www.infoq.com/cn/presentations/openstack-continued-delivery', + 'md5': '4918d0cca1497f2244572caf626687ef', + 'info_dict': { + 'id': 'openstack-continued-delivery', + 'title': 'OpenStack持续交付之路', + 'ext': 'flv', + 'description': 'md5:308d981fb28fa42f49f9568322c683ff', + }, }] - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + def _extract_bokecc_videos(self, webpage, video_id): + # TODO: bokecc.com is a Chinese video cloud platform + # It should have an independent extractor but I don't have other + # examples using bokecc + player_params_str = self._html_search_regex( + r'<script[^>]+src="http://p\.bokecc\.com/player\?([^"]+)', + webpage, 'player params', default=None) - video_title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title') - video_description = self._html_search_meta('description', webpage, 'description') + player_params = compat_parse_qs(player_params_str) + + info_xml = self._download_xml( + 'http://p.bokecc.com/servlet/playinfo?uid=%s&vid=%s&m=1' % ( + player_params['siteid'][0], player_params['vid'][0]), video_id) + + return [{ + 'format_id': 'bokecc', + 'url': quality.find('./copy').attrib['playurl'], + 'preference': int(quality.attrib['value']), + } for quality in info_xml.findall('./video/quality')] + def _extract_rtmp_videos(self, webpage): # The server URL is hardcoded video_url = 'rtmpe://video.infoq.com/cfx/st/' # Extract video URL encoded_id = self._search_regex( - r"jsclassref\s*=\s*'([^']*)'", webpage, 'encoded id') + r"jsclassref\s*=\s*'([^']*)'", webpage, 'encoded id', default=None) + real_id = compat_urllib_parse_unquote(base64.b64decode(encoded_id.encode('ascii')).decode('utf-8')) playpath = 'mp4:' + real_id - video_filename = playpath.split('/')[-1] - video_id, extension = video_filename.split('.') - - http_base = self._search_regex( - r'EXPRESSINSTALL_SWF\s*=\s*[^"]*"((?:https?:)?//[^/"]+/)', webpage, - 'HTTP base URL') - - formats = [{ + return [{ 'format_id': 'rtmp', 'url': video_url, - 'ext': extension, + 'ext': determine_ext(playpath), 'play_path': playpath, - }, { + }] + + def _extract_http_videos(self, webpage): + http_video_url = self._search_regex(r'P\.s\s*=\s*\'([^\']+)\'', webpage, 'video URL') + + policy = self._search_regex(r'InfoQConstants.scp\s*=\s*\'([^\']+)\'', webpage, 'policy') + signature = self._search_regex(r'InfoQConstants.scs\s*=\s*\'([^\']+)\'', webpage, 'signature') + key_pair_id = self._search_regex(r'InfoQConstants.sck\s*=\s*\'([^\']+)\'', webpage, 'key-pair-id') + + return [{ 'format_id': 'http', - 'url': compat_urlparse.urljoin(url, http_base) + real_id, + 'url': http_video_url, + 'http_headers': { + 'Cookie': 'CloudFront-Policy=%s; CloudFront-Signature=%s; CloudFront-Key-Pair-Id=%s' % ( + policy, signature, key_pair_id), + }, }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + video_title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title') + video_description = self._html_search_meta('description', webpage, 'description') + + if '/cn/' in url: + # for China videos, HTTP video URL exists but always fails with 403 + formats = self._extract_bokecc_videos(webpage, video_id) + else: + formats = self._extract_rtmp_videos(webpage) + self._extract_http_videos(webpage) + self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/iqiyi.py b/youtube_dl/extractor/iqiyi.py index 2df1da3f0..c3731a110 100644 --- a/youtube_dl/extractor/iqiyi.py +++ b/youtube_dl/extractor/iqiyi.py @@ -205,9 +205,8 @@ class IqiyiIE(InfoExtractor): def get_enc_key(self, swf_url, video_id): # TODO: automatic key extraction - # last update at 2015-10-22 for Zombie::bite - # '7223c67061dbea1259d0ceb44f44b6d62288f4f80c972170de5201d2321060270e05'[2:66][0::2] - enc_key = '2c76de15dcb44bd28ff0927d50d31620' + # last update at 2015-12-18 for Zombie::bite + enc_key = '8b6b683780897eb8d9a48a02ccc4817d'[::-1] return enc_key def _real_extract(self, url): diff --git a/youtube_dl/extractor/keezmovies.py b/youtube_dl/extractor/keezmovies.py index d79261bb5..126ca13df 100644 --- a/youtube_dl/extractor/keezmovies.py +++ b/youtube_dl/extractor/keezmovies.py @@ -1,23 +1,25 @@ from __future__ import unicode_literals -import os import re from .common import InfoExtractor -from ..compat import compat_urllib_parse_urlparse -from ..utils import sanitized_Request +from ..utils import ( + sanitized_Request, + url_basename, +) class KeezMoviesIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/.+?(?P<id>[0-9]+)(?:[/?&]|$)' _TEST = { 'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711', - 'md5': '6e297b7e789329923fcf83abb67c9289', + 'md5': '1c1e75d22ffa53320f45eeb07bc4cdc0', 'info_dict': { 'id': '1214711', 'ext': 'mp4', 'title': 'Petite Asian Lady Mai Playing In Bathtub', 'age_limit': 18, + 'thumbnail': 're:^https?://.*\.jpg$', } } @@ -36,21 +38,29 @@ class KeezMoviesIE(InfoExtractor): video_title = self._html_search_regex( r'<h1 [^>]*>([^<]+)', webpage, 'title') - video_url = self._html_search_regex( - r'(?s)html5VideoPlayer = .*?src="([^"]+)"', webpage, 'video URL') - path = compat_urllib_parse_urlparse(video_url).path - extension = os.path.splitext(path)[1][1:] - format = path.split('/')[4].split('_')[:2] - format = "-".join(format) + flashvars = self._parse_json(self._search_regex( + r'var\s+flashvars\s*=\s*([^;]+);', webpage, 'flashvars'), video_id) + + formats = [] + for height in (180, 240, 480): + if flashvars.get('quality_%dp' % height): + video_url = flashvars['quality_%dp' % height] + a_format = { + 'url': video_url, + 'height': height, + 'format_id': '%dp' % height, + } + filename_parts = url_basename(video_url).split('_') + if len(filename_parts) >= 2 and re.match(r'\d+[Kk]', filename_parts[1]): + a_format['tbr'] = int(filename_parts[1][:-1]) + formats.append(a_format) age_limit = self._rta_search(webpage) return { 'id': video_id, 'title': video_title, - 'url': video_url, - 'ext': extension, - 'format': format, - 'format_id': format, + 'formats': formats, 'age_limit': age_limit, + 'thumbnail': flashvars.get('image_url') } diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py index 3c786a36d..67d6271e1 100644 --- a/youtube_dl/extractor/metacafe.py +++ b/youtube_dl/extractor/metacafe.py @@ -154,10 +154,10 @@ class MetacafeIE(InfoExtractor): # Extract URL, uploader and title from webpage self.report_extraction(video_id) video_url = None - mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) + mobj = re.search(r'(?m)&(?:media|video)URL=([^&]+)', webpage) if mobj is not None: mediaURL = compat_urllib_parse_unquote(mobj.group(1)) - video_ext = mediaURL[-3:] + video_ext = determine_ext(mediaURL) # Extract gdaKey if available mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) @@ -229,7 +229,7 @@ class MetacafeIE(InfoExtractor): age_limit = ( 18 - if re.search(r'"contentRating":"restricted"', webpage) + if re.search(r'(?:"contentRating":|"rating",)"restricted"', webpage) else 0) if isinstance(video_url, list): diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index d47aeceda..c2b7ed9ab 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -64,7 +64,8 @@ class MixcloudIE(InfoExtractor): preview_url = self._search_regex( r'\s(?:data-preview-url|m-preview)="([^"]+)"', webpage, 'preview url') - song_url = preview_url.replace('/previews/', '/c/originals/') + song_url = re.sub(r'audiocdn(\d+)', r'stream\1', preview_url) + song_url = song_url.replace('/previews/', '/c/originals/') if not self._check_url(song_url, track_id, 'mp3'): song_url = song_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/') if not self._check_url(song_url, track_id, 'm4a'): diff --git a/youtube_dl/extractor/movshare.py b/youtube_dl/extractor/movshare.py deleted file mode 100644 index 6101063f2..000000000 --- a/youtube_dl/extractor/movshare.py +++ /dev/null @@ -1,27 +0,0 @@ -from __future__ import unicode_literals - -from .novamov import NovaMovIE - - -class MovShareIE(NovaMovIE): - IE_NAME = 'movshare' - IE_DESC = 'MovShare' - - _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'movshare\.(?:net|sx|ag)'} - - _HOST = 'www.movshare.net' - - _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' - _TITLE_REGEX = r'<strong>Title:</strong> ([^<]+)</p>' - _DESCRIPTION_REGEX = r'<strong>Description:</strong> ([^<]+)</p>' - - _TEST = { - 'url': 'http://www.movshare.net/video/559e28be54d96', - 'md5': 'abd31a2132947262c50429e1d16c1bfd', - 'info_dict': { - 'id': '559e28be54d96', - 'ext': 'flv', - 'title': 'dissapeared image', - 'description': 'optical illusion dissapeared image magic illusion', - } - } diff --git a/youtube_dl/extractor/nba.py b/youtube_dl/extractor/nba.py index 944096e1c..7c6b7841d 100644 --- a/youtube_dl/extractor/nba.py +++ b/youtube_dl/extractor/nba.py @@ -1,63 +1,102 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( - remove_end, parse_duration, + int_or_none, + xpath_text, + xpath_attr, ) class NBAIE(InfoExtractor): - _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?:nba/)?video(?P<id>/[^?]*?)/?(?:/index\.html)?(?:\?.*)?$' + _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?P<path>(?:[^/]+/)?video/(?P<id>[^?]*?))/?(?:/index\.html)?(?:\?.*)?$' _TESTS = [{ 'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html', - 'md5': 'c0edcfc37607344e2ff8f13c378c88a4', + 'md5': '9e7729d3010a9c71506fd1248f74e4f4', 'info_dict': { - 'id': '0021200253-okc-bkn-recap.nba', - 'ext': 'mp4', + 'id': '0021200253-okc-bkn-recap', + 'ext': 'flv', 'title': 'Thunder vs. Nets', 'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.', 'duration': 181, + 'timestamp': 1354638466, + 'upload_date': '20121204', }, }, { 'url': 'http://www.nba.com/video/games/hornets/2014/12/05/0021400276-nyk-cha-play5.nba/', 'only_matching': True, }, { - 'url': 'http://watch.nba.com/nba/video/channels/playoffs/2015/05/20/0041400301-cle-atl-recap.nba', + 'url': 'http://watch.nba.com/video/channels/playoffs/2015/05/20/0041400301-cle-atl-recap.nba', + 'md5': 'b2b39b81cf28615ae0c3360a3f9668c4', 'info_dict': { - 'id': '0041400301-cle-atl-recap.nba', + 'id': '0041400301-cle-atl-recap', 'ext': 'mp4', - 'title': 'NBA GAME TIME | Video: Hawks vs. Cavaliers Game 1', + 'title': 'Hawks vs. Cavaliers Game 1', 'description': 'md5:8094c3498d35a9bd6b1a8c396a071b4d', 'duration': 228, - }, - 'params': { - 'skip_download': True, + 'timestamp': 1432134543, + 'upload_date': '20150520', } }] def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - video_url = 'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4' + path, video_id = re.match(self._VALID_URL, url).groups() + if path.startswith('nba/'): + path = path[3:] + video_info = self._download_xml('http://www.nba.com/%s.xml' % path, video_id) + video_id = xpath_text(video_info, 'slug') + title = xpath_text(video_info, 'headline') + description = xpath_text(video_info, 'description') + duration = parse_duration(xpath_text(video_info, 'length')) + timestamp = int_or_none(xpath_attr(video_info, 'dateCreated', 'uts')) - shortened_video_id = video_id.rpartition('/')[2] - title = remove_end( - self._og_search_title(webpage, default=shortened_video_id), ' : NBA.com') + thumbnails = [] + for image in video_info.find('images'): + thumbnails.append({ + 'id': image.attrib.get('cut'), + 'url': image.text, + 'width': int_or_none(image.attrib.get('width')), + 'height': int_or_none(image.attrib.get('height')), + }) - description = self._og_search_description(webpage) - duration_str = self._html_search_meta( - 'duration', webpage, 'duration', default=None) - if not duration_str: - duration_str = self._html_search_regex( - r'Duration:</b>\s*(\d+:\d+)', webpage, 'duration', fatal=False) - duration = parse_duration(duration_str) + formats = [] + for video_file in video_info.findall('.//file'): + video_url = video_file.text + if video_url.startswith('/'): + continue + if video_url.endswith('.m3u8'): + m3u8_formats = self._extract_m3u8_formats(video_url, video_id, m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + elif video_url.endswith('.f4m'): + f4m_formats = self._extract_f4m_formats(video_url + '?hdcore=3.4.1.1', video_id, f4m_id='hds', fatal=False) + if f4m_formats: + formats.extend(f4m_formats) + else: + key = video_file.attrib.get('bitrate') + format_info = { + 'format_id': key, + 'url': video_url, + } + mobj = re.search(r'(\d+)x(\d+)(?:_(\d+))?', key) + if mobj: + format_info.update({ + 'width': int(mobj.group(1)), + 'height': int(mobj.group(2)), + 'tbr': int_or_none(mobj.group(3)), + }) + formats.append(format_info) + self._sort_formats(formats) return { - 'id': shortened_video_id, - 'url': video_url, + 'id': video_id, 'title': title, 'description': description, 'duration': duration, + 'timestamp': timestamp, + 'thumbnails': thumbnails, + 'formats': formats, } diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index e683d24c4..340c922bd 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -3,14 +3,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_str, - compat_HTTPError, -) +from ..compat import compat_HTTPError from ..utils import ( ExtractorError, find_xpath_attr, lowercase_escape, + smuggle_url, unescapeHTML, ) @@ -62,12 +60,13 @@ class NBCIE(InfoExtractor): theplatform_url = unescapeHTML(lowercase_escape(self._html_search_regex( [ r'(?:class="video-player video-player-full" data-mpx-url|class="player" src)="(.*?)"', + r'<iframe[^>]+src="((?:https?:)?//player\.theplatform\.com/[^"]+)"', r'"embedURL"\s*:\s*"([^"]+)"' ], webpage, 'theplatform url').replace('_no_endcard', '').replace('\\/', '/'))) if theplatform_url.startswith('//'): theplatform_url = 'http:' + theplatform_url - return self.url_result(theplatform_url) + return self.url_result(smuggle_url(theplatform_url, {'source_url': url})) class NBCSportsVPlayerIE(InfoExtractor): @@ -187,7 +186,7 @@ class NBCNewsIE(InfoExtractor): 'title': info.find('headline').text, 'ext': 'flv', 'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text, - 'description': compat_str(info.find('caption').text), + 'description': info.find('caption').text, 'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text, } else: diff --git a/youtube_dl/extractor/ndr.py b/youtube_dl/extractor/ndr.py index 16213eed9..894c51399 100644 --- a/youtube_dl/extractor/ndr.py +++ b/youtube_dl/extractor/ndr.py @@ -88,10 +88,10 @@ class NDRIE(NDRBaseIE): 'embedURL', webpage, 'embed URL', fatal=True) description = self._search_regex( r'<p[^>]+itemprop="description">([^<]+)</p>', - webpage, 'description', fatal=False) + webpage, 'description', default=None) or self._og_search_description(webpage) timestamp = parse_iso8601( self._search_regex( - r'<span itemprop="datePublished" content="([^"]+)">', + r'<span[^>]+itemprop="(?:datePublished|uploadDate)"[^>]+content="([^"]+)"', webpage, 'upload date', fatal=False)) return { '_type': 'url_transparent', diff --git a/youtube_dl/extractor/noco.py b/youtube_dl/extractor/noco.py index 76bd21e6d..d440313d5 100644 --- a/youtube_dl/extractor/noco.py +++ b/youtube_dl/extractor/noco.py @@ -9,6 +9,7 @@ from .common import InfoExtractor from ..compat import ( compat_str, compat_urllib_parse, + compat_urlparse, ) from ..utils import ( clean_html, @@ -82,14 +83,21 @@ class NocoIE(InfoExtractor): if 'erreur' in login: raise ExtractorError('Unable to login: %s' % clean_html(login['erreur']), expected=True) + @staticmethod + def _ts(): + return int(time.time() * 1000) + def _call_api(self, path, video_id, note, sub_lang=None): - ts = compat_str(int(time.time() * 1000)) + ts = compat_str(self._ts() + self._ts_offset) tk = hashlib.md5((hashlib.md5(ts.encode('ascii')).hexdigest() + '#8S?uCraTedap6a').encode('ascii')).hexdigest() url = self._API_URL_TEMPLATE % (path, ts, tk) if sub_lang: url += self._SUB_LANG_TEMPLATE % sub_lang - resp = self._download_json(url, video_id, note) + request = sanitized_Request(url) + request.add_header('Referer', self._referer) + + resp = self._download_json(request, video_id, note) if isinstance(resp, dict) and resp.get('error'): self._raise_error(resp['error'], resp['description']) @@ -102,8 +110,22 @@ class NocoIE(InfoExtractor): expected=True) def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) + + # Timestamp adjustment offset between server time and local time + # must be calculated in order to use timestamps closest to server's + # in all API requests (see https://github.com/rg3/youtube-dl/issues/7864) + webpage = self._download_webpage(url, video_id) + + player_url = self._search_regex( + r'(["\'])(?P<player>https?://noco\.tv/(?:[^/]+/)+NocoPlayer.+?\.swf.*?)\1', + webpage, 'noco player', group='player', + default='http://noco.tv/cdata/js/player/NocoPlayer-v1.2.40.swf') + + qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(player_url).query) + ts = int_or_none(qs.get('ts', [None])[0]) + self._ts_offset = ts - self._ts() if ts else 0 + self._referer = player_url medias = self._call_api( 'shows/%s/medias' % video_id, @@ -155,8 +177,8 @@ class NocoIE(InfoExtractor): 'format_id': format_id_extended, 'width': int_or_none(fmt.get('res_width')), 'height': int_or_none(fmt.get('res_lines')), - 'abr': int_or_none(fmt.get('audiobitrate')), - 'vbr': int_or_none(fmt.get('videobitrate')), + 'abr': int_or_none(fmt.get('audiobitrate'), 1000), + 'vbr': int_or_none(fmt.get('videobitrate'), 1000), 'filesize': int_or_none(fmt.get('filesize')), 'format_note': qualities[format_id].get('quality_name'), 'quality': qualities[format_id].get('priority'), diff --git a/youtube_dl/extractor/novamov.py b/youtube_dl/extractor/novamov.py index 6163e8855..d68c1ad79 100644 --- a/youtube_dl/extractor/novamov.py +++ b/youtube_dl/extractor/novamov.py @@ -17,15 +17,16 @@ class NovaMovIE(InfoExtractor): IE_NAME = 'novamov' IE_DESC = 'NovaMov' - _VALID_URL_TEMPLATE = r'http://(?:(?:www\.)?%(host)s/(?:file|video)/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<id>[a-z\d]{13})' + _VALID_URL_TEMPLATE = r'http://(?:(?:www\.)?%(host)s/(?:file|video|mobile/#/videos)/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<id>[a-z\d]{13})' _VALID_URL = _VALID_URL_TEMPLATE % {'host': 'novamov\.com'} _HOST = 'www.novamov.com' _FILE_DELETED_REGEX = r'This file no longer exists on our servers!</h2>' - _FILEKEY_REGEX = r'flashvars\.filekey="(?P<filekey>[^"]+)";' + _FILEKEY_REGEX = r'flashvars\.filekey=(?P<filekey>"?[^"]+"?);' _TITLE_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>' _DESCRIPTION_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>' + _URL_TEMPLATE = 'http://%s/video/%s' _TEST = { 'url': 'http://www.novamov.com/video/4rurhn9x446jj', @@ -39,20 +40,28 @@ class NovaMovIE(InfoExtractor): 'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)' } + def _check_existence(self, webpage, video_id): + if re.search(self._FILE_DELETED_REGEX, webpage) is not None: + raise ExtractorError('Video %s does not exist' % video_id, expected=True) + def _real_extract(self, url): video_id = self._match_id(url) - url = 'http://%s/video/%s' % (self._HOST, video_id) + url = self._URL_TEMPLATE % (self._HOST, video_id) webpage = self._download_webpage( url, video_id, 'Downloading video page') - if re.search(self._FILE_DELETED_REGEX, webpage) is not None: - raise ExtractorError('Video %s does not exist' % video_id, expected=True) + self._check_existence(webpage, video_id) def extract_filekey(default=NO_DEFAULT): - return self._search_regex( + filekey = self._search_regex( self._FILEKEY_REGEX, webpage, 'filekey', default=default) + if filekey is not default and (filekey[0] != '"' or filekey[-1] != '"'): + return self._search_regex( + r'var\s+%s\s*=\s*"([^"]+)"' % re.escape(filekey), webpage, 'filekey', default=default) + else: + return filekey filekey = extract_filekey(default=None) @@ -69,6 +78,7 @@ class NovaMovIE(InfoExtractor): request.add_header('Referer', post_url) webpage = self._download_webpage( request, video_id, 'Downloading continue to the video page') + self._check_existence(webpage, video_id) filekey = extract_filekey() @@ -92,3 +102,89 @@ class NovaMovIE(InfoExtractor): 'title': title, 'description': description } + + +class WholeCloudIE(NovaMovIE): + IE_NAME = 'wholecloud' + IE_DESC = 'WholeCloud' + + _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': '(?:wholecloud\.net|movshare\.(?:net|sx|ag))'} + + _HOST = 'www.wholecloud.net' + + _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' + _TITLE_REGEX = r'<strong>Title:</strong> ([^<]+)</p>' + _DESCRIPTION_REGEX = r'<strong>Description:</strong> ([^<]+)</p>' + + _TEST = { + 'url': 'http://www.wholecloud.net/video/559e28be54d96', + 'md5': 'abd31a2132947262c50429e1d16c1bfd', + 'info_dict': { + 'id': '559e28be54d96', + 'ext': 'flv', + 'title': 'dissapeared image', + 'description': 'optical illusion dissapeared image magic illusion', + } + } + + +class NowVideoIE(NovaMovIE): + IE_NAME = 'nowvideo' + IE_DESC = 'NowVideo' + + _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:to|ch|ec|sx|eu|at|ag|co|li)'} + + _HOST = 'www.nowvideo.to' + + _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' + _TITLE_REGEX = r'<h4>([^<]+)</h4>' + _DESCRIPTION_REGEX = r'</h4>\s*<p>([^<]+)</p>' + + _TEST = { + 'url': 'http://www.nowvideo.sx/video/f1d6fce9a968b', + 'md5': '12c82cad4f2084881d8bc60ee29df092', + 'info_dict': { + 'id': 'f1d6fce9a968b', + 'ext': 'flv', + 'title': 'youtubedl test video BaWjenozKc', + 'description': 'Description', + }, + } + + +class VideoWeedIE(NovaMovIE): + IE_NAME = 'videoweed' + IE_DESC = 'VideoWeed' + + _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'videoweed\.(?:es|com)'} + + _HOST = 'www.videoweed.es' + + _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' + _TITLE_REGEX = r'<h1 class="text_shadow">([^<]+)</h1>' + _URL_TEMPLATE = 'http://%s/file/%s' + + _TEST = { + 'url': 'http://www.videoweed.es/file/b42178afbea14', + 'md5': 'abd31a2132947262c50429e1d16c1bfd', + 'info_dict': { + 'id': 'b42178afbea14', + 'ext': 'flv', + 'title': 'optical illusion dissapeared image magic illusion', + 'description': '' + }, + } + + +class CloudTimeIE(NovaMovIE): + IE_NAME = 'cloudtime' + IE_DESC = 'CloudTime' + + _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'cloudtime\.to'} + + _HOST = 'www.cloudtime.to' + + _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' + _TITLE_REGEX = r'<div[^>]+class=["\']video_det["\'][^>]*>\s*<strong>([^<]+)</strong>' + + _TEST = None diff --git a/youtube_dl/extractor/nowness.py b/youtube_dl/extractor/nowness.py index d480fb58c..446f5901c 100644 --- a/youtube_dl/extractor/nowness.py +++ b/youtube_dl/extractor/nowness.py @@ -1,7 +1,10 @@ # encoding: utf-8 from __future__ import unicode_literals -from .brightcove import BrightcoveLegacyIE +from .brightcove import ( + BrightcoveLegacyIE, + BrightcoveNewIE, +) from .common import InfoExtractor from ..compat import compat_str from ..utils import ( @@ -23,9 +26,12 @@ class NownessBaseIE(InfoExtractor): note='Downloading player JavaScript', errnote='Unable to download player JavaScript') bc_url = BrightcoveLegacyIE._extract_brightcove_url(player_code) - if bc_url is None: - raise ExtractorError('Could not find player definition') - return self.url_result(bc_url, 'BrightcoveLegacy') + if bc_url: + return self.url_result(bc_url, BrightcoveLegacyIE.ie_key()) + bc_url = BrightcoveNewIE._extract_url(player_code) + if bc_url: + return self.url_result(bc_url, BrightcoveNewIE.ie_key()) + raise ExtractorError('Could not find player definition') elif source == 'vimeo': return self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo') elif source == 'youtube': diff --git a/youtube_dl/extractor/nowtv.py b/youtube_dl/extractor/nowtv.py index 67e34b294..fd107aca2 100644 --- a/youtube_dl/extractor/nowtv.py +++ b/youtube_dl/extractor/nowtv.py @@ -71,7 +71,7 @@ class NowTVBaseIE(InfoExtractor): class NowTVIE(NowTVBaseIE): - _VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<show_id>[^/]+)/(?:list/[^/]+/)?(?P<id>[^/]+)/(?:player|preview)' + _VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<show_id>[^/]+)/(?:(?:list/[^/]+|jahr/\d{4}/\d{1,2})/)?(?P<id>[^/]+)/(?:player|preview)' _TESTS = [{ # rtl @@ -190,6 +190,9 @@ class NowTVIE(NowTVBaseIE): }, { 'url': 'http://www.nowtv.de/rtl2/echtzeit/list/aktuell/schnelles-geld-am-ende-der-welt/player', 'only_matching': True, + }, { + 'url': 'http://www.nowtv.de/rtl2/zuhause-im-glueck/jahr/2015/11/eine-erschuetternde-diagnose/player', + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/nowvideo.py b/youtube_dl/extractor/nowvideo.py deleted file mode 100644 index 57ee3d366..000000000 --- a/youtube_dl/extractor/nowvideo.py +++ /dev/null @@ -1,28 +0,0 @@ -from __future__ import unicode_literals - -from .novamov import NovaMovIE - - -class NowVideoIE(NovaMovIE): - IE_NAME = 'nowvideo' - IE_DESC = 'NowVideo' - - _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:to|ch|ec|sx|eu|at|ag|co|li)'} - - _HOST = 'www.nowvideo.to' - - _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' - _FILEKEY_REGEX = r'var fkzd="([^"]+)";' - _TITLE_REGEX = r'<h4>([^<]+)</h4>' - _DESCRIPTION_REGEX = r'</h4>\s*<p>([^<]+)</p>' - - _TEST = { - 'url': 'http://www.nowvideo.ch/video/0mw0yow7b6dxa', - 'md5': 'f8fbbc8add72bd95b7850c6a02fc8817', - 'info_dict': { - 'id': '0mw0yow7b6dxa', - 'ext': 'flv', - 'title': 'youtubedl test video _BaW_jenozKc.mp4', - 'description': 'Description', - } - } diff --git a/youtube_dl/extractor/ooyala.py b/youtube_dl/extractor/ooyala.py index a262a9f6d..8603fd692 100644 --- a/youtube_dl/extractor/ooyala.py +++ b/youtube_dl/extractor/ooyala.py @@ -1,108 +1,78 @@ from __future__ import unicode_literals import re -import json import base64 from .common import InfoExtractor from ..utils import ( - unescapeHTML, - ExtractorError, - determine_ext, int_or_none, + float_or_none, + ExtractorError, + unsmuggle_url, ) +from ..compat import compat_urllib_parse class OoyalaBaseIE(InfoExtractor): - def _extract_result(self, info, more_info): - embedCode = info['embedCode'] - video_url = info.get('ipad_url') or info['url'] - - if determine_ext(video_url) == 'm3u8': - formats = self._extract_m3u8_formats(video_url, embedCode, ext='mp4') - else: - formats = [{ - 'url': video_url, - 'ext': 'mp4', - }] - - return { - 'id': embedCode, - 'title': unescapeHTML(info['title']), - 'formats': formats, - 'description': unescapeHTML(more_info['description']), - 'thumbnail': more_info['promo'], + def _extract(self, content_tree_url, video_id, domain='example.org'): + content_tree = self._download_json(content_tree_url, video_id)['content_tree'] + metadata = content_tree[list(content_tree)[0]] + embed_code = metadata['embed_code'] + pcode = metadata.get('asset_pcode') or embed_code + video_info = { + 'id': embed_code, + 'title': metadata['title'], + 'description': metadata.get('description'), + 'thumbnail': metadata.get('thumbnail_image') or metadata.get('promo_image'), + 'duration': float_or_none(metadata.get('duration'), 1000), } - def _extract(self, player_url, video_id): - player = self._download_webpage(player_url, video_id) - mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="', - player, 'mobile player url') - # Looks like some videos are only available for particular devices - # (e.g. http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0 - # is only available for ipad) - # Working around with fetching URLs for all the devices found starting with 'unknown' - # until we succeed or eventually fail for each device. - devices = re.findall(r'device\s*=\s*"([^"]+)";', player) - devices.remove('unknown') - devices.insert(0, 'unknown') - for device in devices: - mobile_player = self._download_webpage( - '%s&device=%s' % (mobile_url, device), video_id, - 'Downloading mobile player JS for %s device' % device) - videos_info = self._search_regex( - r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);', - mobile_player, 'info', fatal=False, default=None) - if videos_info: - break - - if not videos_info: - formats = [] + urls = [] + formats = [] + for supported_format in ('mp4', 'm3u8', 'hds', 'rtmp'): auth_data = self._download_json( - 'http://player.ooyala.com/sas/player_api/v1/authorization/embed_code/%s/%s?domain=www.example.org&supportedFormats=mp4,webm' % (video_id, video_id), - video_id) - - cur_auth_data = auth_data['authorization_data'][video_id] - - for stream in cur_auth_data['streams']: - formats.append({ - 'url': base64.b64decode(stream['url']['data'].encode('ascii')).decode('utf-8'), - 'ext': stream.get('delivery_type'), - 'format': stream.get('video_codec'), - 'format_id': stream.get('profile'), - 'width': int_or_none(stream.get('width')), - 'height': int_or_none(stream.get('height')), - 'abr': int_or_none(stream.get('audio_bitrate')), - 'vbr': int_or_none(stream.get('video_bitrate')), - }) - if formats: - return { - 'id': video_id, - 'formats': formats, - 'title': 'Ooyala video', - } - - if not cur_auth_data['authorized']: - raise ExtractorError(cur_auth_data['message'], expected=True) - - if not videos_info: - raise ExtractorError('Unable to extract info') - videos_info = videos_info.replace('\\"', '"') - videos_more_info = self._search_regex( - r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"', '"') - videos_info = json.loads(videos_info) - videos_more_info = json.loads(videos_more_info) - - if videos_more_info.get('lineup'): - videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])] - return { - '_type': 'playlist', - 'id': video_id, - 'title': unescapeHTML(videos_more_info['title']), - 'entries': videos, - } - else: - return self._extract_result(videos_info[0], videos_more_info) + 'http://player.ooyala.com/sas/player_api/v1/authorization/embed_code/%s/%s?' % (pcode, embed_code) + compat_urllib_parse.urlencode({'domain': domain, 'supportedFormats': supported_format}), + video_id, 'Downloading %s JSON' % supported_format) + + cur_auth_data = auth_data['authorization_data'][embed_code] + + if cur_auth_data['authorized']: + for stream in cur_auth_data['streams']: + url = base64.b64decode(stream['url']['data'].encode('ascii')).decode('utf-8') + if url in urls: + continue + urls.append(url) + delivery_type = stream['delivery_type'] + if delivery_type == 'hls' or '.m3u8' in url: + m3u8_formats = self._extract_m3u8_formats(url, embed_code, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + elif delivery_type == 'hds' or '.f4m' in url: + f4m_formats = self._extract_f4m_formats(url, embed_code, f4m_id='hds', fatal=False) + if f4m_formats: + formats.extend(f4m_formats) + elif '.smil' in url: + smil_formats = self._extract_smil_formats(url, embed_code, fatal=False) + if smil_formats: + formats.extend(smil_formats) + else: + formats.append({ + 'url': url, + 'ext': stream.get('delivery_type'), + 'vcodec': stream.get('video_codec'), + 'format_id': delivery_type, + 'width': int_or_none(stream.get('width')), + 'height': int_or_none(stream.get('height')), + 'abr': int_or_none(stream.get('audio_bitrate')), + 'vbr': int_or_none(stream.get('video_bitrate')), + 'fps': float_or_none(stream.get('framerate')), + }) + else: + raise ExtractorError('%s said: %s' % (self.IE_NAME, cur_auth_data['message']), expected=True) + self._sort_formats(formats) + + video_info['formats'] = formats + return video_info class OoyalaIE(OoyalaBaseIE): @@ -117,6 +87,7 @@ class OoyalaIE(OoyalaBaseIE): 'ext': 'mp4', 'title': 'Explaining Data Recovery from Hard Drives and SSDs', 'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.', + 'duration': 853.386, }, }, { # Only available for ipad @@ -125,7 +96,7 @@ class OoyalaIE(OoyalaBaseIE): 'id': 'x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0', 'ext': 'mp4', 'title': 'Simulation Overview - Levels of Simulation', - 'description': '', + 'duration': 194.948, }, }, { @@ -136,7 +107,8 @@ class OoyalaIE(OoyalaBaseIE): 'info_dict': { 'id': 'FiOG81ZTrvckcchQxmalf4aQj590qTEx', 'ext': 'mp4', - 'title': 'Ooyala video', + 'title': 'Divide Tool Path.mp4', + 'duration': 204.405, } } ] @@ -151,9 +123,11 @@ class OoyalaIE(OoyalaBaseIE): ie=cls.ie_key()) def _real_extract(self, url): + url, smuggled_data = unsmuggle_url(url, {}) embed_code = self._match_id(url) - player_url = 'http://player.ooyala.com/player.js?embedCode=%s' % embed_code - return self._extract(player_url, embed_code) + domain = smuggled_data.get('domain') + content_tree_url = 'http://player.ooyala.com/player_api/v1/content_tree/embed_code/%s/%s' % (embed_code, embed_code) + return self._extract(content_tree_url, embed_code, domain) class OoyalaExternalIE(OoyalaBaseIE): @@ -170,7 +144,7 @@ class OoyalaExternalIE(OoyalaBaseIE): .*?&pcode= ) (?P<pcode>.+?) - (&|$) + (?:&|$) ''' _TEST = { @@ -179,7 +153,7 @@ class OoyalaExternalIE(OoyalaBaseIE): 'id': 'FkYWtmazr6Ed8xmvILvKLWjd4QvYZpzG', 'ext': 'mp4', 'title': 'dm_140128_30for30Shorts___JudgingJewellv2', - 'description': '', + 'duration': 1302000, }, 'params': { # m3u8 download @@ -188,9 +162,6 @@ class OoyalaExternalIE(OoyalaBaseIE): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - partner_id = mobj.group('partner_id') - video_id = mobj.group('id') - pcode = mobj.group('pcode') - player_url = 'http://player.ooyala.com/player.js?externalId=%s:%s&pcode=%s' % (partner_id, video_id, pcode) - return self._extract(player_url, video_id) + partner_id, video_id, pcode = re.match(self._VALID_URL, url).groups() + content_tree_url = 'http://player.ooyala.com/player_api/v1/content_tree/external_id/%s/%s:%s' % (pcode, partner_id, video_id) + return self._extract(content_tree_url, video_id) diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index b787e2a73..744e4a09a 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -15,16 +15,181 @@ from ..utils import ( class PBSIE(InfoExtractor): + _STATIONS = ( + (r'(?:video|www)\.pbs\.org', 'PBS: Public Broadcasting Service'), # http://www.pbs.org/ + (r'video\.aptv\.org', 'APT - Alabama Public Television (WBIQ)'), # http://aptv.org/ + (r'video\.gpb\.org', 'GPB/Georgia Public Broadcasting (WGTV)'), # http://www.gpb.org/ + (r'video\.mpbonline\.org', 'Mississippi Public Broadcasting (WMPN)'), # http://www.mpbonline.org + (r'video\.wnpt\.org', 'Nashville Public Television (WNPT)'), # http://www.wnpt.org + (r'video\.wfsu\.org', 'WFSU-TV (WFSU)'), # http://wfsu.org/ + (r'video\.wsre\.org', 'WSRE (WSRE)'), # http://www.wsre.org + (r'video\.wtcitv\.org', 'WTCI (WTCI)'), # http://www.wtcitv.org + (r'video\.pba\.org', 'WPBA/Channel 30 (WPBA)'), # http://pba.org/ + (r'video\.alaskapublic\.org', 'Alaska Public Media (KAKM)'), # http://alaskapublic.org/kakm + # (r'kuac\.org', 'KUAC (KUAC)'), # http://kuac.org/kuac-tv/ + # (r'ktoo\.org', '360 North (KTOO)'), # http://www.ktoo.org/ + # (r'azpm\.org', 'KUAT 6 (KUAT)'), # http://www.azpm.org/ + (r'video\.azpbs\.org', 'Arizona PBS (KAET)'), # http://www.azpbs.org + (r'portal\.knme\.org', 'KNME-TV/Channel 5 (KNME)'), # http://www.newmexicopbs.org/ + (r'video\.vegaspbs\.org', 'Vegas PBS (KLVX)'), # http://vegaspbs.org/ + (r'watch\.aetn\.org', 'AETN/ARKANSAS ETV NETWORK (KETS)'), # http://www.aetn.org/ + (r'video\.ket\.org', 'KET (WKLE)'), # http://www.ket.org/ + (r'video\.wkno\.org', 'WKNO/Channel 10 (WKNO)'), # http://www.wkno.org/ + (r'video\.lpb\.org', 'LPB/LOUISIANA PUBLIC BROADCASTING (WLPB)'), # http://www.lpb.org/ + (r'videos\.oeta\.tv', 'OETA (KETA)'), # http://www.oeta.tv + (r'video\.optv\.org', 'Ozarks Public Television (KOZK)'), # http://www.optv.org/ + (r'watch\.wsiu\.org', 'WSIU Public Broadcasting (WSIU)'), # http://www.wsiu.org/ + (r'video\.keet\.org', 'KEET TV (KEET)'), # http://www.keet.org + (r'pbs\.kixe\.org', 'KIXE/Channel 9 (KIXE)'), # http://kixe.org/ + (r'video\.kpbs\.org', 'KPBS San Diego (KPBS)'), # http://www.kpbs.org/ + (r'video\.kqed\.org', 'KQED (KQED)'), # http://www.kqed.org + (r'vids\.kvie\.org', 'KVIE Public Television (KVIE)'), # http://www.kvie.org + (r'video\.pbssocal\.org', 'PBS SoCal/KOCE (KOCE)'), # http://www.pbssocal.org/ + (r'video\.valleypbs\.org', 'ValleyPBS (KVPT)'), # http://www.valleypbs.org/ + (r'video\.cptv\.org', 'CONNECTICUT PUBLIC TELEVISION (WEDH)'), # http://cptv.org + (r'watch\.knpb\.org', 'KNPB Channel 5 (KNPB)'), # http://www.knpb.org/ + (r'video\.soptv\.org', 'SOPTV (KSYS)'), # http://www.soptv.org + # (r'klcs\.org', 'KLCS/Channel 58 (KLCS)'), # http://www.klcs.org + # (r'krcb\.org', 'KRCB Television & Radio (KRCB)'), # http://www.krcb.org + # (r'kvcr\.org', 'KVCR TV/DT/FM :: Vision for the Future (KVCR)'), # http://kvcr.org + (r'video\.rmpbs\.org', 'Rocky Mountain PBS (KRMA)'), # http://www.rmpbs.org + (r'video\.kenw\.org', 'KENW-TV3 (KENW)'), # http://www.kenw.org + (r'video\.kued\.org', 'KUED Channel 7 (KUED)'), # http://www.kued.org + (r'video\.wyomingpbs\.org', 'Wyoming PBS (KCWC)'), # http://www.wyomingpbs.org + (r'video\.cpt12\.org', 'Colorado Public Television / KBDI 12 (KBDI)'), # http://www.cpt12.org/ + (r'video\.kbyueleven\.org', 'KBYU-TV (KBYU)'), # http://www.kbyutv.org/ + (r'video\.thirteen\.org', 'Thirteen/WNET New York (WNET)'), # http://www.thirteen.org + (r'video\.wgbh\.org', 'WGBH/Channel 2 (WGBH)'), # http://wgbh.org + (r'video\.wgby\.org', 'WGBY (WGBY)'), # http://www.wgby.org + (r'watch\.njtvonline\.org', 'NJTV Public Media NJ (WNJT)'), # http://www.njtvonline.org/ + # (r'ripbs\.org', 'Rhode Island PBS (WSBE)'), # http://www.ripbs.org/home/ + (r'watch\.wliw\.org', 'WLIW21 (WLIW)'), # http://www.wliw.org/ + (r'video\.mpt\.tv', 'mpt/Maryland Public Television (WMPB)'), # http://www.mpt.org + (r'watch\.weta\.org', 'WETA Television and Radio (WETA)'), # http://www.weta.org + (r'video\.whyy\.org', 'WHYY (WHYY)'), # http://www.whyy.org + (r'video\.wlvt\.org', 'PBS 39 (WLVT)'), # http://www.wlvt.org/ + (r'video\.wvpt\.net', 'WVPT - Your Source for PBS and More! (WVPT)'), # http://www.wvpt.net + (r'video\.whut\.org', 'Howard University Television (WHUT)'), # http://www.whut.org + (r'video\.wedu\.org', 'WEDU PBS (WEDU)'), # http://www.wedu.org + (r'video\.wgcu\.org', 'WGCU Public Media (WGCU)'), # http://www.wgcu.org/ + # (r'wjct\.org', 'WJCT Public Broadcasting (WJCT)'), # http://www.wjct.org + (r'video\.wpbt2\.org', 'WPBT2 (WPBT)'), # http://www.wpbt2.org + (r'video\.wucftv\.org', 'WUCF TV (WUCF)'), # http://wucftv.org + (r'video\.wuft\.org', 'WUFT/Channel 5 (WUFT)'), # http://www.wuft.org + (r'watch\.wxel\.org', 'WXEL/Channel 42 (WXEL)'), # http://www.wxel.org/home/ + (r'video\.wlrn\.org', 'WLRN/Channel 17 (WLRN)'), # http://www.wlrn.org/ + (r'video\.wusf\.usf\.edu', 'WUSF Public Broadcasting (WUSF)'), # http://wusf.org/ + (r'video\.scetv\.org', 'ETV (WRLK)'), # http://www.scetv.org + (r'video\.unctv\.org', 'UNC-TV (WUNC)'), # http://www.unctv.org/ + # (r'pbsguam\.org', 'PBS Guam (KGTF)'), # http://www.pbsguam.org/ + (r'video\.pbshawaii\.org', 'PBS Hawaii - Oceanic Cable Channel 10 (KHET)'), # http://www.pbshawaii.org/ + (r'video\.idahoptv\.org', 'Idaho Public Television (KAID)'), # http://idahoptv.org + (r'video\.ksps\.org', 'KSPS (KSPS)'), # http://www.ksps.org/home/ + (r'watch\.opb\.org', 'OPB (KOPB)'), # http://www.opb.org + (r'watch\.nwptv\.org', 'KWSU/Channel 10 & KTNW/Channel 31 (KWSU)'), # http://www.kwsu.org + (r'video\.will\.illinois\.edu', 'WILL-TV (WILL)'), # http://will.illinois.edu/ + (r'video\.networkknowledge\.tv', 'Network Knowledge - WSEC/Springfield (WSEC)'), # http://www.wsec.tv + (r'video\.wttw\.com', 'WTTW11 (WTTW)'), # http://www.wttw.com/ + # (r'wtvp\.org', 'WTVP & WTVP.org, Public Media for Central Illinois (WTVP)'), # http://www.wtvp.org/ + (r'video\.iptv\.org', 'Iowa Public Television/IPTV (KDIN)'), # http://www.iptv.org/ + (r'video\.ninenet\.org', 'Nine Network (KETC)'), # http://www.ninenet.org + (r'video\.wfwa\.org', 'PBS39 Fort Wayne (WFWA)'), # http://wfwa.org/ + (r'video\.wfyi\.org', 'WFYI Indianapolis (WFYI)'), # http://www.wfyi.org + (r'video\.mptv\.org', 'Milwaukee Public Television (WMVS)'), # http://www.mptv.org + (r'video\.wnin\.org', 'WNIN (WNIN)'), # http://www.wnin.org/ + (r'video\.wnit\.org', 'WNIT Public Television (WNIT)'), # http://www.wnit.org/ + (r'video\.wpt\.org', 'WPT (WPNE)'), # http://www.wpt.org/ + (r'video\.wvut\.org', 'WVUT/Channel 22 (WVUT)'), # http://wvut.org/ + (r'video\.weiu\.net', 'WEIU/Channel 51 (WEIU)'), # http://www.weiu.net + (r'video\.wqpt\.org', 'WQPT-TV (WQPT)'), # http://www.wqpt.org + (r'video\.wycc\.org', 'WYCC PBS Chicago (WYCC)'), # http://www.wycc.org + # (r'lakeshorepublicmedia\.org', 'Lakeshore Public Television (WYIN)'), # http://lakeshorepublicmedia.org/ + (r'video\.wipb\.org', 'WIPB-TV (WIPB)'), # http://wipb.org + (r'video\.indianapublicmedia\.org', 'WTIU (WTIU)'), # http://indianapublicmedia.org/tv/ + (r'watch\.cetconnect\.org', 'CET (WCET)'), # http://www.cetconnect.org + (r'video\.thinktv\.org', 'ThinkTVNetwork (WPTD)'), # http://www.thinktv.org + (r'video\.wbgu\.org', 'WBGU-TV (WBGU)'), # http://wbgu.org + (r'video\.wgvu\.org', 'WGVU TV (WGVU)'), # http://www.wgvu.org/ + (r'video\.netnebraska\.org', 'NET1 (KUON)'), # http://netnebraska.org + (r'video\.pioneer\.org', 'Pioneer Public Television (KWCM)'), # http://www.pioneer.org + (r'watch\.sdpb\.org', 'SDPB Television (KUSD)'), # http://www.sdpb.org + (r'video\.tpt\.org', 'TPT (KTCA)'), # http://www.tpt.org + (r'watch\.ksmq\.org', 'KSMQ (KSMQ)'), # http://www.ksmq.org/ + (r'watch\.kpts\.org', 'KPTS/Channel 8 (KPTS)'), # http://www.kpts.org/ + (r'watch\.ktwu\.org', 'KTWU/Channel 11 (KTWU)'), # http://ktwu.org + # (r'shptv\.org', 'Smoky Hills Public Television (KOOD)'), # http://www.shptv.org + # (r'kcpt\.org', 'KCPT Kansas City Public Television (KCPT)'), # http://kcpt.org/ + # (r'blueridgepbs\.org', 'Blue Ridge PBS (WBRA)'), # http://www.blueridgepbs.org/ + (r'watch\.easttennesseepbs\.org', 'East Tennessee PBS (WSJK)'), # http://easttennesseepbs.org + (r'video\.wcte\.tv', 'WCTE-TV (WCTE)'), # http://www.wcte.org + (r'video\.wljt\.org', 'WLJT, Channel 11 (WLJT)'), # http://wljt.org/ + (r'video\.wosu\.org', 'WOSU TV (WOSU)'), # http://wosu.org/ + (r'video\.woub\.org', 'WOUB/WOUC (WOUB)'), # http://woub.org/tv/index.php?section=5 + (r'video\.wvpublic\.org', 'WVPB (WVPB)'), # http://wvpublic.org/ + (r'video\.wkyupbs\.org', 'WKYU-PBS (WKYU)'), # http://www.wkyupbs.org + # (r'wyes\.org', 'WYES-TV/New Orleans (WYES)'), # http://www.wyes.org + (r'video\.kera\.org', 'KERA 13 (KERA)'), # http://www.kera.org/ + (r'video\.mpbn\.net', 'MPBN (WCBB)'), # http://www.mpbn.net/ + (r'video\.mountainlake\.org', 'Mountain Lake PBS (WCFE)'), # http://www.mountainlake.org/ + (r'video\.nhptv\.org', 'NHPTV (WENH)'), # http://nhptv.org/ + (r'video\.vpt\.org', 'Vermont PBS (WETK)'), # http://www.vpt.org + (r'video\.witf\.org', 'witf (WITF)'), # http://www.witf.org + (r'watch\.wqed\.org', 'WQED Multimedia (WQED)'), # http://www.wqed.org/ + (r'video\.wmht\.org', 'WMHT Educational Telecommunications (WMHT)'), # http://www.wmht.org/home/ + (r'video\.deltabroadcasting\.org', 'Q-TV (WDCQ)'), # http://www.deltabroadcasting.org + (r'video\.dptv\.org', 'WTVS Detroit Public TV (WTVS)'), # http://www.dptv.org/ + (r'video\.wcmu\.org', 'CMU Public Television (WCMU)'), # http://www.wcmu.org + (r'video\.wkar\.org', 'WKAR-TV (WKAR)'), # http://wkar.org/ + (r'wnmuvideo\.nmu\.edu', 'WNMU-TV Public TV 13 (WNMU)'), # http://wnmutv.nmu.edu + (r'video\.wdse\.org', 'WDSE - WRPT (WDSE)'), # http://www.wdse.org/ + (r'video\.wgte\.org', 'WGTE TV (WGTE)'), # http://www.wgte.org + (r'video\.lptv\.org', 'Lakeland Public Television (KAWE)'), # http://www.lakelandptv.org + # (r'prairiepublic\.org', 'PRAIRIE PUBLIC (KFME)'), # http://www.prairiepublic.org/ + (r'video\.kmos\.org', 'KMOS-TV - Channels 6.1, 6.2 and 6.3 (KMOS)'), # http://www.kmos.org/ + (r'watch\.montanapbs\.org', 'MontanaPBS (KUSM)'), # http://montanapbs.org + (r'video\.krwg\.org', 'KRWG/Channel 22 (KRWG)'), # http://www.krwg.org + (r'video\.kacvtv\.org', 'KACV (KACV)'), # http://www.panhandlepbs.org/home/ + (r'video\.kcostv\.org', 'KCOS/Channel 13 (KCOS)'), # www.kcostv.org + (r'video\.wcny\.org', 'WCNY/Channel 24 (WCNY)'), # http://www.wcny.org + (r'video\.wned\.org', 'WNED (WNED)'), # http://www.wned.org/ + (r'watch\.wpbstv\.org', 'WPBS (WPBS)'), # http://www.wpbstv.org + (r'video\.wskg\.org', 'WSKG Public TV (WSKG)'), # http://wskg.org + (r'video\.wxxi\.org', 'WXXI (WXXI)'), # http://wxxi.org + (r'video\.wpsu\.org', 'WPSU (WPSU)'), # http://www.wpsu.org + # (r'wqln\.org', 'WQLN/Channel 54 (WQLN)'), # http://www.wqln.org + (r'on-demand\.wvia\.org', 'WVIA Public Media Studios (WVIA)'), # http://www.wvia.org/ + (r'video\.wtvi\.org', 'WTVI (WTVI)'), # http://www.wtvi.org/ + # (r'whro\.org', 'WHRO (WHRO)'), # http://whro.org + (r'video\.westernreservepublicmedia\.org', 'Western Reserve PBS (WNEO)'), # http://www.WesternReservePublicMedia.org/ + (r'video\.ideastream\.org', 'WVIZ/PBS ideastream (WVIZ)'), # http://www.wviz.org/ + (r'video\.kcts9\.org', 'KCTS 9 (KCTS)'), # http://kcts9.org/ + (r'video\.basinpbs\.org', 'Basin PBS (KPBT)'), # http://www.basinpbs.org + (r'video\.houstonpbs\.org', 'KUHT / Channel 8 (KUHT)'), # http://www.houstonpublicmedia.org/ + # (r'tamu\.edu', 'KAMU - TV (KAMU)'), # http://KAMU.tamu.edu + # (r'kedt\.org', 'KEDT/Channel 16 (KEDT)'), # http://www.kedt.org + (r'video\.klrn\.org', 'KLRN (KLRN)'), # http://www.klrn.org + (r'video\.klru\.tv', 'KLRU (KLRU)'), # http://www.klru.org + # (r'kmbh\.org', 'KMBH-TV (KMBH)'), # http://www.kmbh.org + # (r'knct\.org', 'KNCT (KNCT)'), # http://www.knct.org + # (r'ktxt\.org', 'KTTZ-TV (KTXT)'), # http://www.ktxt.org + (r'video\.wtjx\.org', 'WTJX Channel 12 (WTJX)'), # http://www.wtjx.org/ + (r'video\.ideastations\.org', 'WCVE PBS (WCVE)'), # http://ideastations.org/ + (r'video\.kbtc\.org', 'KBTC Public Television (KBTC)'), # http://kbtc.org + ) + + IE_NAME = 'pbs' + IE_DESC = 'Public Broadcasting Service (PBS) and member stations: %s' % ', '.join(list(zip(*_STATIONS))[1]) + _VALID_URL = r'''(?x)https?:// (?: # Direct video URL - video\.pbs\.org/(?:viralplayer|video)/(?P<id>[0-9]+)/? | + (?:%s)/(?:viralplayer|video)/(?P<id>[0-9]+)/? | # Article with embedded player (or direct video) (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) | # Player (?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/ ) - ''' + ''' % '|'.join(list(zip(*_STATIONS))[0]) _TESTS = [ { @@ -174,6 +339,10 @@ class PBSIE(InfoExtractor): { 'url': 'http://player.pbs.org/widget/partnerplayer/2365297708/?start=0&end=0&chapterbar=false&endscreen=false&topbar=true', 'only_matching': True, + }, + { + 'url': 'http://watch.knpb.org/video/2365616055/', + 'only_matching': True, } ] _ERRORS = { @@ -204,6 +373,7 @@ class PBSIE(InfoExtractor): MEDIA_ID_REGEXES = [ r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed r'class="coveplayerid">([^<]+)<', # coveplayer + r'<section[^>]+data-coveid="(\d+)"', # coveplayer from http://www.pbs.org/wgbh/frontline/film/real-csi/ r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>', # jwplayer ] diff --git a/youtube_dl/extractor/pladform.py b/youtube_dl/extractor/pladform.py index 551c8c9f0..bc559d1df 100644 --- a/youtube_dl/extractor/pladform.py +++ b/youtube_dl/extractor/pladform.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( ExtractorError, @@ -44,6 +46,13 @@ class PladformIE(InfoExtractor): 'only_matching': True, }] + @staticmethod + def _extract_url(webpage): + mobj = re.search( + r'<iframe[^>]+src="(?P<url>(?:https?:)?//out\.pladform\.ru/player\?.+?)"', webpage) + if mobj: + return mobj.group('url') + def _real_extract(self, url): video_id = self._match_id(url) diff --git a/youtube_dl/extractor/pluralsight.py b/youtube_dl/extractor/pluralsight.py index aa7dbcb63..55c11b3bf 100644 --- a/youtube_dl/extractor/pluralsight.py +++ b/youtube_dl/extractor/pluralsight.py @@ -1,5 +1,6 @@ from __future__ import unicode_literals +import re import json import random import collections @@ -14,6 +15,7 @@ from ..utils import ( ExtractorError, int_or_none, parse_duration, + qualities, sanitized_Request, ) @@ -140,15 +142,28 @@ class PluralsightIE(PluralsightBaseIE): 'low': {'width': 640, 'height': 480}, 'medium': {'width': 848, 'height': 640}, 'high': {'width': 1024, 'height': 768}, + 'high-widescreen': {'width': 1280, 'height': 720}, } + QUALITIES_PREFERENCE = ('low', 'medium', 'high', 'high-widescreen',) + quality_key = qualities(QUALITIES_PREFERENCE) + AllowedQuality = collections.namedtuple('AllowedQuality', ['ext', 'qualities']) ALLOWED_QUALITIES = ( - AllowedQuality('webm', ('high',)), - AllowedQuality('mp4', ('low', 'medium', 'high',)), + AllowedQuality('webm', ['high', ]), + AllowedQuality('mp4', ['low', 'medium', 'high', ]), ) + # Some courses also offer widescreen resolution for high quality (see + # https://github.com/rg3/youtube-dl/issues/7766) + widescreen = True if re.search( + r'courseSupportsWidescreenVideoFormats\s*:\s*true', webpage) else False + best_quality = 'high-widescreen' if widescreen else 'high' + if widescreen: + for allowed_quality in ALLOWED_QUALITIES: + allowed_quality.qualities.append(best_quality) + # In order to minimize the number of calls to ViewClip API and reduce # the probability of being throttled or banned by Pluralsight we will request # only single format until formats listing was explicitly requested. @@ -157,19 +172,19 @@ class PluralsightIE(PluralsightBaseIE): else: def guess_allowed_qualities(): req_format = self._downloader.params.get('format') or 'best' - req_format_split = req_format.split('-') + req_format_split = req_format.split('-', 1) if len(req_format_split) > 1: req_ext, req_quality = req_format_split for allowed_quality in ALLOWED_QUALITIES: if req_ext == allowed_quality.ext and req_quality in allowed_quality.qualities: return (AllowedQuality(req_ext, (req_quality, )), ) req_ext = 'webm' if self._downloader.params.get('prefer_free_formats') else 'mp4' - return (AllowedQuality(req_ext, ('high', )), ) + return (AllowedQuality(req_ext, (best_quality, )), ) allowed_qualities = guess_allowed_qualities() formats = [] - for ext, qualities in allowed_qualities: - for quality in qualities: + for ext, qualities_ in allowed_qualities: + for quality in qualities_: f = QUALITIES[quality].copy() clip_post = { 'a': author, @@ -205,6 +220,7 @@ class PluralsightIE(PluralsightBaseIE): 'url': clip_url, 'ext': ext, 'format_id': format_id, + 'quality': quality_key(quality), }) formats.append(f) self._sort_formats(formats) diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py index 6b09550b0..9db62adb1 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -17,9 +17,9 @@ from ..utils import ( class RutubeIE(InfoExtractor): IE_NAME = 'rutube' IE_DESC = 'Rutube videos' - _VALID_URL = r'https?://rutube\.ru/video/(?P<id>[\da-z]{32})' + _VALID_URL = r'https?://rutube\.ru/(?:video|play/embed)/(?P<id>[\da-z]{32})' - _TEST = { + _TESTS = [{ 'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/', 'info_dict': { 'id': '3eac3b4561676c17df9132a9a1e62e3e', @@ -36,7 +36,10 @@ class RutubeIE(InfoExtractor): # It requires ffmpeg (m3u8 download) 'skip_download': True, }, - } + }, { + 'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py index 919704261..7de7b7273 100644 --- a/youtube_dl/extractor/safari.py +++ b/youtube_dl/extractor/safari.py @@ -6,12 +6,12 @@ import re from .common import InfoExtractor from .brightcove import BrightcoveLegacyIE -from ..compat import compat_urllib_parse from ..utils import ( ExtractorError, sanitized_Request, smuggle_url, std_headers, + urlencode_postdata, ) @@ -57,7 +57,7 @@ class SafariBaseIE(InfoExtractor): } request = sanitized_Request( - self._LOGIN_URL, compat_urllib_parse.urlencode(login_form), headers=headers) + self._LOGIN_URL, urlencode_postdata(login_form), headers=headers) login_page = self._download_webpage( request, None, 'Logging in as %s' % username) diff --git a/youtube_dl/extractor/skynewsarabia.py b/youtube_dl/extractor/skynewsarabia.py index f09fee102..05e1b02ad 100644 --- a/youtube_dl/extractor/skynewsarabia.py +++ b/youtube_dl/extractor/skynewsarabia.py @@ -9,7 +9,7 @@ from ..utils import ( ) -class SkyNewArabiaBaseIE(InfoExtractor): +class SkyNewsArabiaBaseIE(InfoExtractor): _IMAGE_BASE_URL = 'http://www.skynewsarabia.com/web/images' def _call_api(self, path, value): @@ -40,7 +40,7 @@ class SkyNewArabiaBaseIE(InfoExtractor): } -class SkyNewsArabiaIE(SkyNewArabiaBaseIE): +class SkyNewsArabiaIE(SkyNewsArabiaBaseIE): IE_NAME = 'skynewsarabia:video' _VALID_URL = r'https?://(?:www\.)?skynewsarabia\.com/web/video/(?P<id>[0-9]+)' _TEST = { @@ -66,7 +66,7 @@ class SkyNewsArabiaIE(SkyNewArabiaBaseIE): return self._extract_video_info(video_data) -class SkyNewsArabiaArticleIE(SkyNewArabiaBaseIE): +class SkyNewsArabiaArticleIE(SkyNewsArabiaBaseIE): IE_NAME = 'skynewsarabia:video' _VALID_URL = r'https?://(?:www\.)?skynewsarabia\.com/web/article/(?P<id>[0-9]+)' _TESTS = [{ diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py index daf6ad555..ea8fc258d 100644 --- a/youtube_dl/extractor/sohu.py +++ b/youtube_dl/extractor/sohu.py @@ -158,6 +158,7 @@ class SohuIE(InfoExtractor): 'file': clips_url[i], 'new': su[i], 'prod': 'flash', + 'rb': 1, } if cdnId is not None: diff --git a/youtube_dl/extractor/srf.py b/youtube_dl/extractor/srf.py index 77eec0bc7..16e1bf2d6 100644 --- a/youtube_dl/extractor/srf.py +++ b/youtube_dl/extractor/srf.py @@ -11,7 +11,7 @@ from ..utils import ( class SrfIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.srf\.ch/play(?:er)?/tv/[^/]+/video/(?P<display_id>[^?]+)\?id=|tp\.srgssr\.ch/p/flash\?urn=urn:srf:ais:video:)(?P<id>[0-9a-f\-]{36})' + _VALID_URL = r'https?://(?:www\.srf\.ch/play(?:er)?/(?:tv|radio)/[^/]+/(?P<media_type>video|audio)/(?P<display_id>[^?]+)\?id=|tp\.srgssr\.ch/p/flash\?urn=urn:srf:ais:video:)(?P<id>[0-9a-f\-]{36})' _TESTS = [{ 'url': 'http://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5', 'md5': '4cd93523723beff51bb4bee974ee238d', @@ -36,6 +36,20 @@ class SrfIE(InfoExtractor): 'timestamp': 1373493600, }, }, { + 'url': 'http://www.srf.ch/play/radio/hoerspielarchiv-srf-musikwelle/audio/saegel-ohni-wind-von-jakob-stebler?id=415bf3d3-6429-4de7-968d-95866e37cfbc', + 'md5': '', + 'info_dict': { + 'id': '415bf3d3-6429-4de7-968d-95866e37cfbc', + 'display_id': 'saegel-ohni-wind-von-jakob-stebler', + 'ext': 'mp3', + 'upload_date': '20080518', + 'title': '«Sägel ohni Wind» von Jakob Stebler', + 'timestamp': 1211112000, + }, + 'params': { + 'skip_download': True, # requires rtmpdump + }, + }, { 'url': 'http://www.srf.ch/player/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5', 'only_matching': True, }, { @@ -44,11 +58,13 @@ class SrfIE(InfoExtractor): }] def _real_extract(self, url): - video_id = self._match_id(url) - display_id = re.match(self._VALID_URL, url).group('display_id') or video_id + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + media_type = mobj.group('media_type') + display_id = mobj.group('display_id') or video_id video_data = self._download_xml( - 'http://il.srgssr.ch/integrationlayer/1.0/ue/srf/video/play/%s.xml' % video_id, + 'http://il.srgssr.ch/integrationlayer/1.0/ue/srf/%s/play/%s.xml' % (media_type, video_id), display_id) title = xpath_text( @@ -64,7 +80,7 @@ class SrfIE(InfoExtractor): for url_node in item.findall('url'): quality = url_node.attrib['quality'] full_url = url_node.text - original_ext = determine_ext(full_url) + original_ext = determine_ext(full_url).lower() format_id = '%s-%s' % (quality, item.attrib['protocol']) if original_ext == 'f4m': formats.extend(self._extract_f4m_formats( diff --git a/youtube_dl/extractor/teachingchannel.py b/youtube_dl/extractor/teachingchannel.py index 117afa9bf..e0477382c 100644 --- a/youtube_dl/extractor/teachingchannel.py +++ b/youtube_dl/extractor/teachingchannel.py @@ -16,6 +16,7 @@ class TeachingChannelIE(InfoExtractor): 'ext': 'mp4', 'title': 'A History of Teaming', 'description': 'md5:2a9033db8da81f2edffa4c99888140b3', + 'duration': 422.255, }, 'params': { # m3u8 download diff --git a/youtube_dl/extractor/tele13.py b/youtube_dl/extractor/tele13.py new file mode 100644 index 000000000..a363b4d40 --- /dev/null +++ b/youtube_dl/extractor/tele13.py @@ -0,0 +1,81 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from .youtube import YoutubeIE +from ..utils import ( + js_to_json, + qualities, + determine_ext, +) + + +class Tele13IE(InfoExtractor): + _VALID_URL = r'^http://(?:www\.)?t13\.cl/videos(?:/[^/]+)+/(?P<id>[\w-]+)' + _TESTS = [ + { + 'url': 'http://www.t13.cl/videos/actualidad/el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda', + 'md5': '4cb1fa38adcad8fea88487a078831755', + 'info_dict': { + 'id': 'el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda', + 'ext': 'mp4', + 'title': 'El círculo de hierro de Michelle Bachelet en su regreso a La Moneda', + }, + 'params': { + # HTTP Error 404: Not Found + 'skip_download': True, + }, + }, + { + 'url': 'http://www.t13.cl/videos/mundo/tendencias/video-captan-misteriosa-bola-fuego-cielos-bangkok', + 'md5': '867adf6a3b3fef932c68a71d70b70946', + 'info_dict': { + 'id': 'rOoKv2OMpOw', + 'ext': 'mp4', + 'title': 'Shooting star seen on 7-Sep-2015', + 'description': 'md5:7292ff2a34b2f673da77da222ae77e1e', + 'uploader': 'Porjai Jaturongkhakun', + 'upload_date': '20150906', + 'uploader_id': 'UCnLY_3ezwNcDSC_Wc6suZxw', + }, + 'add_ie': ['Youtube'], + } + ] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + setup_js = self._search_regex(r"(?s)jwplayer\('player-vivo'\).setup\((\{.*?\})\)", webpage, 'setup code') + sources = self._parse_json(self._search_regex(r'sources\s*:\s*(\[[^\]]+\])', setup_js, 'sources'), display_id, js_to_json) + + preference = qualities(['Móvil', 'SD', 'HD']) + formats = [] + urls = [] + for f in sources: + format_url = f['file'] + if format_url and format_url not in urls: + ext = determine_ext(format_url) + if ext == 'm3u8': + m3u8_formats = self._extract_m3u8_formats(format_url, display_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + elif YoutubeIE.suitable(format_url): + return self.url_result(format_url, 'Youtube') + else: + formats.append({ + 'url': format_url, + 'format_id': f.get('label'), + 'preference': preference(f.get('label')), + 'ext': ext, + }) + urls.append(format_url) + self._sort_formats(formats) + + return { + 'id': display_id, + 'title': self._search_regex(r'title\s*:\s*"([^"]+)"', setup_js, 'title'), + 'description': self._html_search_meta('description', webpage, 'description'), + 'thumbnail': self._search_regex(r'image\s*:\s*"([^"]+)"', setup_js, 'thumbnail', default=None), + 'formats': formats, + } diff --git a/youtube_dl/extractor/tf1.py b/youtube_dl/extractor/tf1.py index 3a68eaa80..6890021cf 100644 --- a/youtube_dl/extractor/tf1.py +++ b/youtube_dl/extractor/tf1.py @@ -6,7 +6,7 @@ from .common import InfoExtractor class TF1IE(InfoExtractor): """TF1 uses the wat.tv player.""" - _VALID_URL = r'http://(?:(?:videos|www|lci)\.tf1|www\.tfou)\.fr/.*?-(?P<id>\d+)(?:-\d+)?\.html' + _VALID_URL = r'http://(?:(?:videos|www|lci)\.tf1|www\.tfou)\.fr/(?:[^/]+/)*(?P<id>.+?)\.html' _TESTS = [{ 'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html', 'info_dict': { @@ -22,7 +22,7 @@ class TF1IE(InfoExtractor): }, { 'url': 'http://www.tfou.fr/chuggington/videos/le-grand-mysterioso-chuggington-7085291-739.html', 'info_dict': { - 'id': '12043945', + 'id': 'le-grand-mysterioso-chuggington-7085291-739', 'ext': 'mp4', 'title': 'Le grand Mystérioso - Chuggington', 'description': 'Le grand Mystérioso - Emery rêve qu\'un article lui soit consacré dans le journal.', @@ -32,22 +32,24 @@ class TF1IE(InfoExtractor): # Sometimes wat serves the whole file with the --test option 'skip_download': True, }, + 'skip': 'HTTP Error 410: Gone', }, { 'url': 'http://www.tf1.fr/tf1/koh-lanta/videos/replay-koh-lanta-22-mai-2015.html', 'only_matching': True, }, { 'url': 'http://lci.tf1.fr/sept-a-huit/videos/sept-a-huit-du-24-mai-2015-8611550.html', 'only_matching': True, + }, { + 'url': 'http://www.tf1.fr/hd1/documentaire/videos/mylene-farmer-d-une-icone.html', + 'only_matching': True, }] def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - embed_url = self._html_search_regex( - r'["\'](https?://www.wat.tv/embedframe/.*?)["\']', webpage, 'embed url') - embed_page = self._download_webpage(embed_url, video_id, - 'Downloading embed player page') - wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat id') + wat_id = self._html_search_regex( + r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})\1', + webpage, 'wat id', group='id') wat_info = self._download_json( 'http://www.wat.tv/interface/contentv3/%s' % wat_id, video_id) return self.url_result(wat_info['media']['url'], 'Wat') diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index 1555aa77c..0bf6726b5 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -16,11 +16,12 @@ from ..compat import ( from ..utils import ( determine_ext, ExtractorError, - xpath_with_ns, - unsmuggle_url, + float_or_none, int_or_none, + sanitized_Request, + unsmuggle_url, url_basename, - float_or_none, + xpath_with_ns, ) default_ns = 'http://www.w3.org/2005/SMIL21/Language' @@ -204,7 +205,12 @@ class ThePlatformIE(ThePlatformBaseIE): smil_url = url # Explicitly specified SMIL (see https://github.com/rg3/youtube-dl/issues/7385) elif '/guid/' in url: - webpage = self._download_webpage(url, video_id) + headers = {} + source_url = smuggled_data.get('source_url') + if source_url: + headers['Referer'] = source_url + request = sanitized_Request(url, headers=headers) + webpage = self._download_webpage(request, video_id) smil_url = self._search_regex( r'<link[^>]+href=(["\'])(?P<url>.+?)\1[^>]+type=["\']application/smil\+xml', webpage, 'smil url', group='url') diff --git a/youtube_dl/extractor/toggle.py b/youtube_dl/extractor/toggle.py new file mode 100644 index 000000000..a47239952 --- /dev/null +++ b/youtube_dl/extractor/toggle.py @@ -0,0 +1,194 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + determine_ext, + ExtractorError, + float_or_none, + int_or_none, + parse_iso8601, + sanitized_Request, +) + + +class ToggleIE(InfoExtractor): + IE_NAME = 'toggle' + _VALID_URL = r'https?://video\.toggle\.sg/(?:en|zh)/(?:series|clips|movies)/(?:[^/]+/)+(?P<id>[0-9]+)' + _TESTS = [{ + 'url': 'http://video.toggle.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115', + 'info_dict': { + 'id': '343115', + 'ext': 'mp4', + 'title': 'Lion Moms Premiere', + 'description': 'md5:aea1149404bff4d7f7b6da11fafd8e6b', + 'upload_date': '20150910', + 'timestamp': 1441858274, + }, + 'params': { + 'skip_download': 'm3u8 download', + } + }, { + 'note': 'DRM-protected video', + 'url': 'http://video.toggle.sg/en/movies/dug-s-special-mission/341413', + 'info_dict': { + 'id': '341413', + 'ext': 'wvm', + 'title': 'Dug\'s Special Mission', + 'description': 'md5:e86c6f4458214905c1772398fabc93e0', + 'upload_date': '20150827', + 'timestamp': 1440644006, + }, + 'params': { + 'skip_download': 'DRM-protected wvm download', + } + }, { + # this also tests correct video id extraction + 'note': 'm3u8 links are geo-restricted, but Android/mp4 is okay', + 'url': 'http://video.toggle.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861', + 'info_dict': { + 'id': '332861', + 'ext': 'mp4', + 'title': '28th SEA Games (5 Show) - Episode 11', + 'description': 'md5:3cd4f5f56c7c3b1340c50a863f896faa', + 'upload_date': '20150605', + 'timestamp': 1433480166, + }, + 'params': { + 'skip_download': 'DRM-protected wvm download', + }, + 'skip': 'm3u8 links are geo-restricted' + }, { + 'url': 'http://video.toggle.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331', + 'only_matching': True, + }, { + 'url': 'http://video.toggle.sg/zh/series/zero-calling-s2-hd/ep13/336367', + 'only_matching': True, + }, { + 'url': 'http://video.toggle.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302', + 'only_matching': True, + }, { + 'url': 'http://video.toggle.sg/en/movies/seven-days/321936', + 'only_matching': True, + }] + + _FORMAT_PREFERENCES = { + 'wvm-STBMain': -10, + 'wvm-iPadMain': -20, + 'wvm-iPhoneMain': -30, + 'wvm-Android': -40, + } + _API_USER = 'tvpapi_147' + _API_PASS = '11111' + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage( + url, video_id, note='Downloading video page') + + api_user = self._search_regex( + r'apiUser\s*:\s*(["\'])(?P<user>.+?)\1', webpage, 'apiUser', + default=self._API_USER, group='user') + api_pass = self._search_regex( + r'apiPass\s*:\s*(["\'])(?P<pass>.+?)\1', webpage, 'apiPass', + default=self._API_PASS, group='pass') + + params = { + 'initObj': { + 'Locale': { + 'LocaleLanguage': '', + 'LocaleCountry': '', + 'LocaleDevice': '', + 'LocaleUserState': 0 + }, + 'Platform': 0, + 'SiteGuid': 0, + 'DomainID': '0', + 'UDID': '', + 'ApiUser': api_user, + 'ApiPass': api_pass + }, + 'MediaID': video_id, + 'mediaType': 0, + } + + req = sanitized_Request( + 'http://tvpapi.as.tvinci.com/v2_9/gateways/jsonpostgw.aspx?m=GetMediaInfo', + json.dumps(params).encode('utf-8')) + info = self._download_json(req, video_id, 'Downloading video info json') + + title = info['MediaName'] + + formats = [] + for video_file in info.get('Files', []): + video_url, vid_format = video_file.get('URL'), video_file.get('Format') + if not video_url or not vid_format: + continue + ext = determine_ext(video_url) + vid_format = vid_format.replace(' ', '') + # if geo-restricted, m3u8 is inaccessible, but mp4 is okay + if ext == 'm3u8': + m3u8_formats = self._extract_m3u8_formats( + video_url, video_id, ext='mp4', m3u8_id=vid_format, + note='Downloading %s m3u8 information' % vid_format, + errnote='Failed to download %s m3u8 information' % vid_format, + fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + elif ext in ('mp4', 'wvm'): + # wvm are drm-protected files + formats.append({ + 'ext': ext, + 'url': video_url, + 'format_id': vid_format, + 'preference': self._FORMAT_PREFERENCES.get(ext + '-' + vid_format) or -1, + 'format_note': 'DRM-protected video' if ext == 'wvm' else None + }) + if not formats: + # Most likely because geo-blocked + raise ExtractorError('No downloadable videos found', expected=True) + self._sort_formats(formats) + + duration = int_or_none(info.get('Duration')) + description = info.get('Description') + created_at = parse_iso8601(info.get('CreationDate') or None) + + average_rating = float_or_none(info.get('Rating')) + view_count = int_or_none(info.get('ViewCounter') or info.get('view_counter')) + like_count = int_or_none(info.get('LikeCounter') or info.get('like_counter')) + + thumbnails = [] + for picture in info.get('Pictures', []): + if not isinstance(picture, dict): + continue + pic_url = picture.get('URL') + if not pic_url: + continue + thumbnail = { + 'url': pic_url, + } + pic_size = picture.get('PicSize', '') + m = re.search(r'(?P<width>\d+)[xX](?P<height>\d+)', pic_size) + if m: + thumbnail.update({ + 'width': int(m.group('width')), + 'height': int(m.group('height')), + }) + thumbnails.append(thumbnail) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'duration': duration, + 'timestamp': created_at, + 'average_rating': average_rating, + 'view_count': view_count, + 'like_count': like_count, + 'thumbnails': thumbnails, + 'formats': formats, + } diff --git a/youtube_dl/extractor/trilulilu.py b/youtube_dl/extractor/trilulilu.py index 185accc4b..a800449e9 100644 --- a/youtube_dl/extractor/trilulilu.py +++ b/youtube_dl/extractor/trilulilu.py @@ -1,80 +1,103 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ExtractorError +from ..utils import ( + ExtractorError, + int_or_none, + parse_iso8601, +) class TriluliluIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?trilulilu\.ro/(?:video-[^/]+/)?(?P<id>[^/#\?]+)' - _TEST = { - 'url': 'http://www.trilulilu.ro/video-animatie/big-buck-bunny-1', - 'md5': 'c1450a00da251e2769b74b9005601cac', + _VALID_URL = r'https?://(?:(?:www|m)\.)?trilulilu\.ro/(?:[^/]+/)?(?P<id>[^/#\?]+)' + _TESTS = [{ + 'url': 'http://www.trilulilu.ro/big-buck-bunny-1', + 'md5': '68da087b676a6196a413549212f60cc6', 'info_dict': { 'id': 'ae2899e124140b', 'ext': 'mp4', 'title': 'Big Buck Bunny', 'description': ':) pentru copilul din noi', + 'uploader_id': 'chipy', + 'upload_date': '20120304', + 'timestamp': 1330830647, + 'uploader': 'chipy', + 'view_count': int, + 'like_count': int, + 'comment_count': int, }, - } + }, { + 'url': 'http://www.trilulilu.ro/adena-ft-morreti-inocenta', + 'md5': '929dfb8729dc71750463af88bbbbf4a4', + 'info_dict': { + 'id': 'f299710e3c91c5', + 'ext': 'mp4', + 'title': 'Adena ft. Morreti - Inocenta', + 'description': 'pop music', + 'uploader_id': 'VEVOmixt', + 'upload_date': '20151204', + 'uploader': 'VEVOmixt', + 'timestamp': 1449187937, + 'view_count': int, + 'like_count': int, + 'comment_count': int, + }, + }] def _real_extract(self, url): display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) + media_info = self._download_json('http://m.trilulilu.ro/%s?format=json' % display_id, display_id) - if re.search(r'Fişierul nu este disponibil pentru vizionare în ţara dumneavoastră', webpage): - raise ExtractorError( - 'This video is not available in your country.', expected=True) - elif re.search('Fişierul poate fi accesat doar de către prietenii lui', webpage): + age_limit = 0 + errors = media_info.get('errors', {}) + if errors.get('friends'): raise ExtractorError('This video is private.', expected=True) + elif errors.get('geoblock'): + raise ExtractorError('This video is not available in your country.', expected=True) + elif errors.get('xxx_unlogged'): + age_limit = 18 - flashvars_str = self._search_regex( - r'block_flash_vars\s*=\s*(\{[^\}]+\})', webpage, 'flashvars', fatal=False, default=None) + media_class = media_info.get('class') + if media_class not in ('video', 'audio'): + raise ExtractorError('not a video or an audio') - if flashvars_str: - flashvars = self._parse_json(flashvars_str, display_id) - else: - raise ExtractorError( - 'This page does not contain videos', expected=True) + user = media_info.get('user', {}) - if flashvars['isMP3'] == 'true': - raise ExtractorError( - 'Audio downloads are currently not supported', expected=True) + thumbnail = media_info.get('cover_url') + if thumbnail: + thumbnail.format(width='1600', height='1200') - video_id = flashvars['hash'] - title = self._og_search_title(webpage) - thumbnail = self._og_search_thumbnail(webpage) - description = self._og_search_description(webpage, default=None) - - format_url = ('http://fs%(server)s.trilulilu.ro/%(hash)s/' - 'video-formats2' % flashvars) - format_doc = self._download_xml( - format_url, video_id, - note='Downloading formats', - errnote='Error while downloading formats') - - video_url_template = ( - 'http://fs%(server)s.trilulilu.ro/stream.php?type=video' - '&source=site&hash=%(hash)s&username=%(userid)s&' - 'key=ministhebest&format=%%s&sig=&exp=' % - flashvars) - formats = [ - { - 'format_id': fnode.text.partition('-')[2], - 'url': video_url_template % fnode.text, - 'ext': fnode.text.partition('-')[0] - } - - for fnode in format_doc.findall('./formats/format') - ] + # TODO: get correct ext for audio files + stream_type = media_info.get('stream_type') + formats = [{ + 'url': media_info['href'], + 'ext': stream_type, + }] + if media_info.get('is_hd'): + formats.append({ + 'format_id': 'hd', + 'url': media_info['hrefhd'], + 'ext': stream_type, + }) + if media_class == 'audio': + formats[0]['vcodec'] = 'none' + else: + formats[0]['format_id'] = 'sd' return { - 'id': video_id, + 'id': media_info['identifier'].split('|')[1], 'display_id': display_id, 'formats': formats, - 'title': title, - 'description': description, + 'title': media_info['title'], + 'description': media_info.get('description'), 'thumbnail': thumbnail, + 'uploader_id': user.get('username'), + 'uploader': user.get('fullname'), + 'timestamp': parse_iso8601(media_info.get('published'), ' '), + 'duration': int_or_none(media_info.get('duration')), + 'view_count': int_or_none(media_info.get('count_views')), + 'like_count': int_or_none(media_info.get('count_likes')), + 'comment_count': int_or_none(media_info.get('count_comments')), + 'age_limit': age_limit, } diff --git a/youtube_dl/extractor/vevo.py b/youtube_dl/extractor/vevo.py index 571289421..02dfd36f4 100644 --- a/youtube_dl/extractor/vevo.py +++ b/youtube_dl/extractor/vevo.py @@ -3,7 +3,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_etree_fromstring +from ..compat import ( + compat_etree_fromstring, + compat_urlparse, +) from ..utils import ( ExtractorError, int_or_none, @@ -67,6 +70,17 @@ class VevoIE(InfoExtractor): 'params': { 'skip_download': 'true', } + }, { + 'note': 'No video_info', + 'url': 'http://www.vevo.com/watch/k-camp-1/Till-I-Die/USUV71503000', + 'md5': '8b83cc492d72fc9cf74a02acee7dc1b0', + 'info_dict': { + 'id': 'USUV71503000', + 'ext': 'mp4', + 'title': 'Till I Die - K Camp ft. T.I.', + 'duration': 193, + }, + 'expected_warnings': ['Unable to download SMIL file'], }] _SMIL_BASE_URL = 'http://smil.lvl3.vevo.com/' @@ -81,11 +95,17 @@ class VevoIE(InfoExtractor): if webpage is False: self._oauth_token = None else: + if 'THIS PAGE IS CURRENTLY UNAVAILABLE IN YOUR REGION' in webpage: + raise ExtractorError('%s said: This page is currently unavailable in your region.' % self.IE_NAME, expected=True) + self._oauth_token = self._search_regex( r'access_token":\s*"([^"]+)"', webpage, 'access token', fatal=False) def _formats_from_json(self, video_info): + if not video_info: + return [] + last_version = {'version': -1} for version in video_info['videoVersions']: # These are the HTTP downloads, other types are for different manifests @@ -110,9 +130,8 @@ class VevoIE(InfoExtractor): }) return formats - def _formats_from_smil(self, smil_xml): + def _formats_from_smil(self, smil_doc): formats = [] - smil_doc = compat_etree_fromstring(smil_xml.encode('utf-8')) els = smil_doc.findall('.//{http://www.w3.org/2001/SMIL20/Language}video') for el in els: src = el.attrib['src'] @@ -145,14 +164,14 @@ class VevoIE(InfoExtractor): }) return formats - def _download_api_formats(self, video_id): + def _download_api_formats(self, video_id, video_url): if not self._oauth_token: self._downloader.report_warning( 'No oauth token available, skipping API HLS download') return [] - api_url = 'https://apiv2.vevo.com/video/%s/streams/hls?token=%s' % ( - video_id, self._oauth_token) + api_url = compat_urlparse.urljoin(video_url, '//apiv2.vevo.com/video/%s/streams/hls?token=%s' % ( + video_id, self._oauth_token)) api_data = self._download_json( api_url, video_id, note='Downloading HLS formats', @@ -166,18 +185,26 @@ class VevoIE(InfoExtractor): preference=0) def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) + + webpage = None json_url = 'http://videoplayer.vevo.com/VideoService/AuthenticateVideo?isrc=%s' % video_id response = self._download_json(json_url, video_id) - video_info = response['video'] + video_info = response['video'] or {} - if not video_info: + if not video_info and response.get('statusCode') != 909: if 'statusMessage' in response: raise ExtractorError('%s said: %s' % (self.IE_NAME, response['statusMessage']), expected=True) raise ExtractorError('Unable to extract videos') + if not video_info: + if url.startswith('vevo:'): + raise ExtractorError('Please specify full Vevo URL for downloading', expected=True) + webpage = self._download_webpage(url, video_id) + + title = video_info.get('title') or self._og_search_title(webpage) + formats = self._formats_from_json(video_info) is_explicit = video_info.get('isExplicit') @@ -189,11 +216,11 @@ class VevoIE(InfoExtractor): age_limit = None # Download via HLS API - formats.extend(self._download_api_formats(video_id)) + formats.extend(self._download_api_formats(video_id, url)) # Download SMIL smil_blocks = sorted(( - f for f in video_info['videoVersions'] + f for f in video_info.get('videoVersions', []) if f['sourceType'] == 13), key=lambda f: f['version']) smil_url = '%s/Video/V2/VFILE/%s/%sr.smil' % ( @@ -205,23 +232,26 @@ class VevoIE(InfoExtractor): if smil_url_m is not None: smil_url = smil_url_m if smil_url: - smil_xml = self._download_webpage( - smil_url, video_id, 'Downloading SMIL info', fatal=False) - if smil_xml: - formats.extend(self._formats_from_smil(smil_xml)) + smil_doc = self._download_smil(smil_url, video_id, fatal=False) + if smil_doc: + formats.extend(self._formats_from_smil(smil_doc)) self._sort_formats(formats) - timestamp_ms = int_or_none(self._search_regex( + timestamp = int_or_none(self._search_regex( r'/Date\((\d+)\)/', - video_info['launchDate'], 'launch date', fatal=False)) + video_info['launchDate'], 'launch date', fatal=False), + scale=1000) if video_info else None + + duration = video_info.get('duration') or int_or_none( + self._html_search_meta('video:duration', webpage)) return { 'id': video_id, - 'title': video_info['title'], + 'title': title, 'formats': formats, - 'thumbnail': video_info['imageUrl'], - 'timestamp': timestamp_ms // 1000, - 'uploader': video_info['mainArtists'][0]['artistName'], - 'duration': video_info['duration'], + 'thumbnail': video_info.get('imageUrl'), + 'timestamp': timestamp, + 'uploader': video_info['mainArtists'][0]['artistName'] if video_info else None, + 'duration': duration, 'age_limit': age_limit, } diff --git a/youtube_dl/extractor/vice.py b/youtube_dl/extractor/vice.py index 01af7a995..3db6286e4 100644 --- a/youtube_dl/extractor/vice.py +++ b/youtube_dl/extractor/vice.py @@ -15,6 +15,7 @@ class ViceIE(InfoExtractor): 'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp', 'ext': 'mp4', 'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov', + 'duration': 725.983, }, 'params': { # Requires ffmpeg (m3u8 manifest) diff --git a/youtube_dl/extractor/videoweed.py b/youtube_dl/extractor/videoweed.py deleted file mode 100644 index ca2e50935..000000000 --- a/youtube_dl/extractor/videoweed.py +++ /dev/null @@ -1,26 +0,0 @@ -from __future__ import unicode_literals - -from .novamov import NovaMovIE - - -class VideoWeedIE(NovaMovIE): - IE_NAME = 'videoweed' - IE_DESC = 'VideoWeed' - - _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'videoweed\.(?:es|com)'} - - _HOST = 'www.videoweed.es' - - _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' - _TITLE_REGEX = r'<h1 class="text_shadow">([^<]+)</h1>' - - _TEST = { - 'url': 'http://www.videoweed.es/file/b42178afbea14', - 'md5': 'abd31a2132947262c50429e1d16c1bfd', - 'info_dict': { - 'id': 'b42178afbea14', - 'ext': 'flv', - 'title': 'optical illusion dissapeared image magic illusion', - 'description': '' - }, - } diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index f392ccf1c..ce08e6955 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -23,6 +23,7 @@ from ..utils import ( unsmuggle_url, urlencode_postdata, unescapeHTML, + parse_filesize, ) @@ -185,6 +186,20 @@ class VimeoIE(VimeoBaseInfoExtractor): }, }, { + # contains original format + 'url': 'https://vimeo.com/33951933', + 'md5': '53c688fa95a55bf4b7293d37a89c5c53', + 'info_dict': { + 'id': '33951933', + 'ext': 'mp4', + 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute', + 'uploader': 'The DMCI', + 'uploader_id': 'dmci', + 'upload_date': '20111220', + 'description': 'md5:ae23671e82d05415868f7ad1aec21147', + }, + }, + { 'url': 'https://vimeo.com/109815029', 'note': 'Video not completely processed, "failed" seed status', 'only_matching': True, @@ -392,6 +407,21 @@ class VimeoIE(VimeoBaseInfoExtractor): comment_count = None formats = [] + download_request = sanitized_Request('https://vimeo.com/%s?action=load_download_config' % video_id, headers={ + 'X-Requested-With': 'XMLHttpRequest'}) + download_data = self._download_json(download_request, video_id, fatal=False) + if download_data: + source_file = download_data.get('source_file') + if source_file and not source_file.get('is_cold') and not source_file.get('is_defrosting'): + formats.append({ + 'url': source_file['download_url'], + 'ext': source_file['extension'].lower(), + 'width': int_or_none(source_file.get('width')), + 'height': int_or_none(source_file.get('height')), + 'filesize': parse_filesize(source_file.get('size')), + 'format_id': source_file.get('public_name', 'Original'), + 'preference': 1, + }) config_files = config['video'].get('files') or config['request'].get('files', {}) for f in config_files.get('progressive', []): video_url = f.get('url') @@ -408,12 +438,12 @@ class VimeoIE(VimeoBaseInfoExtractor): m3u8_url = config_files.get('hls', {}).get('url') if m3u8_url: m3u8_formats = self._extract_m3u8_formats( - m3u8_url, video_id, 'mp4', 'm3u8_native', 0, 'hls', fatal=False) + m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) if m3u8_formats: formats.extend(m3u8_formats) # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps # at the same time without actual units specified. This lead to wrong sorting. - self._sort_formats(formats, field_preference=('height', 'width', 'fps', 'format_id')) + self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'format_id')) subtitles = {} text_tracks = config['request'].get('text_tracks') diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index d99a42a9f..90557fa61 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -18,6 +18,7 @@ from ..utils import ( unified_strdate, ) from .vimeo import VimeoIE +from .pladform import PladformIE class VKIE(InfoExtractor): @@ -164,6 +165,11 @@ class VKIE(InfoExtractor): # vk wrapper 'url': 'http://www.biqle.ru/watch/847655_160197695', 'only_matching': True, + }, + { + # pladform embed + 'url': 'https://vk.com/video-76116461_171554880', + 'only_matching': True, } ] @@ -254,10 +260,13 @@ class VKIE(InfoExtractor): if vimeo_url is not None: return self.url_result(vimeo_url) + pladform_url = PladformIE._extract_url(info_page) + if pladform_url: + return self.url_result(pladform_url) + m_rutube = re.search( r'\ssrc="((?:https?:)?//rutube\.ru\\?/video\\?/embed(?:.*?))\\?"', info_page) if m_rutube is not None: - self.to_screen('rutube video detected') rutube_url = self._proto_relative_url( m_rutube.group(1).replace('\\', '')) return self.url_result(rutube_url) diff --git a/youtube_dl/extractor/wdr.py b/youtube_dl/extractor/wdr.py index b46802306..ef096cbd2 100644 --- a/youtube_dl/extractor/wdr.py +++ b/youtube_dl/extractor/wdr.py @@ -10,8 +10,8 @@ from ..compat import ( compat_urlparse, ) from ..utils import ( - determine_ext, unified_strdate, + qualities, ) @@ -33,6 +33,7 @@ class WDRIE(InfoExtractor): 'params': { 'skip_download': True, }, + 'skip': 'Page Not Found', }, { 'url': 'http://www1.wdr.de/themen/av/videomargaspiegelisttot101-videoplayer.html', @@ -47,6 +48,7 @@ class WDRIE(InfoExtractor): 'params': { 'skip_download': True, }, + 'skip': 'Page Not Found', }, { 'url': 'http://www1.wdr.de/themen/kultur/audioerlebtegeschichtenmargaspiegel100-audioplayer.html', @@ -71,6 +73,7 @@ class WDRIE(InfoExtractor): 'upload_date': '20140717', 'is_live': False }, + 'skip': 'Page Not Found', }, { 'url': 'http://www1.wdr.de/mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100.html', @@ -83,10 +86,10 @@ class WDRIE(InfoExtractor): 'url': 'http://www1.wdr.de/mediathek/video/livestream/index.html', 'info_dict': { 'id': 'mdb-103364', - 'title': 're:^WDR Fernsehen [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'title': 're:^WDR Fernsehen Live [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', 'description': 'md5:ae2ff888510623bf8d4b115f95a9b7c9', 'ext': 'flv', - 'upload_date': '20150212', + 'upload_date': '20150101', 'is_live': True }, 'params': { @@ -150,25 +153,52 @@ class WDRIE(InfoExtractor): if upload_date: upload_date = unified_strdate(upload_date) + formats = [] + preference = qualities(['S', 'M', 'L', 'XL']) + if video_url.endswith('.f4m'): - video_url += '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18' - ext = 'flv' + f4m_formats = self._extract_f4m_formats(video_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18', page_id, f4m_id='hds', fatal=False) + if f4m_formats: + formats.extend(f4m_formats) elif video_url.endswith('.smil'): - fmt = self._extract_smil_formats(video_url, page_id)[0] - video_url = fmt['url'] - sep = '&' if '?' in video_url else '?' - video_url += sep - video_url += 'hdcore=3.3.0&plugin=aasp-3.3.0.99.43' - ext = fmt['ext'] + smil_formats = self._extract_smil_formats(video_url, page_id, False, { + 'hdcore': '3.3.0', + 'plugin': 'aasp-3.3.0.99.43', + }) + if smil_formats: + formats.extend(smil_formats) else: - ext = determine_ext(video_url) + formats.append({ + 'url': video_url, + 'http_headers': { + 'User-Agent': 'mobile', + }, + }) + + m3u8_url = self._search_regex(r'rel="adaptiv"[^>]+href="([^"]+)"', webpage, 'm3u8 url', default=None) + if m3u8_url: + m3u8_formats = self._extract_m3u8_formats(m3u8_url, page_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + + direct_urls = re.findall(r'rel="web(S|M|L|XL)"[^>]+href="([^"]+)"', webpage) + if direct_urls: + for quality, video_url in direct_urls: + formats.append({ + 'url': video_url, + 'preference': preference(quality), + 'http_headers': { + 'User-Agent': 'mobile', + }, + }) + + self._sort_formats(formats) description = self._html_search_meta('Description', webpage, 'description') return { 'id': page_id, - 'url': video_url, - 'ext': ext, + 'formats': formats, 'title': title, 'description': description, 'thumbnail': thumbnail, diff --git a/youtube_dl/extractor/wimp.py b/youtube_dl/extractor/wimp.py index e4f50e64c..041ff6c55 100644 --- a/youtube_dl/extractor/wimp.py +++ b/youtube_dl/extractor/wimp.py @@ -5,7 +5,7 @@ from .youtube import YoutubeIE class WimpIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?wimp\.com/(?P<id>[^/]+)/' + _VALID_URL = r'http://(?:www\.)?wimp\.com/(?P<id>[^/]+)' _TESTS = [{ 'url': 'http://www.wimp.com/maruexhausted/', 'md5': 'ee21217ffd66d058e8b16be340b74883', @@ -28,18 +28,23 @@ class WimpIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) - video_url = self._search_regex( - [r"[\"']file[\"']\s*[:,]\s*[\"'](.+?)[\"']", r"videoId\s*:\s*[\"']([^\"']+)[\"']"], - webpage, 'video URL') - if YoutubeIE.suitable(video_url): - self.to_screen('Found YouTube video') + + youtube_id = self._search_regex( + r"videoId\s*:\s*[\"']([0-9A-Za-z_-]{11})[\"']", + webpage, 'video URL', default=None) + if youtube_id: return { '_type': 'url', - 'url': video_url, + 'url': youtube_id, 'ie_key': YoutubeIE.ie_key(), } + video_url = self._search_regex( + r'<video[^>]+>\s*<source[^>]+src=(["\'])(?P<url>.+?)\1', + webpage, 'video URL', group='url') + return { 'id': video_id, 'url': video_url, diff --git a/youtube_dl/extractor/youku.py b/youtube_dl/extractor/youku.py index 69ecc837a..3a3432be8 100644 --- a/youtube_dl/extractor/youku.py +++ b/youtube_dl/extractor/youku.py @@ -25,8 +25,8 @@ class YoukuIE(InfoExtractor): ''' _TESTS = [{ + # MD5 is unstable 'url': 'http://v.youku.com/v_show/id_XMTc1ODE5Njcy.html', - 'md5': '5f3af4192eabacc4501508d54a8cabd7', 'info_dict': { 'id': 'XMTc1ODE5Njcy_part1', 'title': '★Smile﹗♡ Git Fresh -Booty Music舞蹈.', @@ -42,6 +42,7 @@ class YoukuIE(InfoExtractor): 'title': '武媚娘传奇 85', }, 'playlist_count': 11, + 'skip': 'Available in China only', }, { 'url': 'http://v.youku.com/v_show/id_XMTI1OTczNDM5Mg==.html', 'info_dict': { @@ -49,7 +50,6 @@ class YoukuIE(InfoExtractor): 'title': '花千骨 04', }, 'playlist_count': 13, - 'skip': 'Available in China only', }, { 'url': 'http://v.youku.com/v_show/id_XNjA1NzA2Njgw.html', 'note': 'Video protected with password', @@ -63,7 +63,7 @@ class YoukuIE(InfoExtractor): }, }] - def construct_video_urls(self, data1, data2): + def construct_video_urls(self, data): # get sid, token def yk_t(s1, s2): ls = list(range(256)) @@ -81,34 +81,24 @@ class YoukuIE(InfoExtractor): return bytes(s) sid, token = yk_t( - b'becaf9be', base64.b64decode(data2['ep'].encode('ascii')) + b'becaf9be', base64.b64decode(data['security']['encrypt_string'].encode('ascii')) ).decode('ascii').split('_') # get oip - oip = data2['ip'] - - # get fileid - string_ls = list( - 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890') - shuffled_string_ls = [] - seed = data1['seed'] - N = len(string_ls) - for ii in range(N): - seed = (seed * 0xd3 + 0x754f) % 0x10000 - idx = seed * len(string_ls) // 0x10000 - shuffled_string_ls.append(string_ls[idx]) - del string_ls[idx] + oip = data['security']['ip'] fileid_dict = {} - for format in data1['streamtypes']: - streamfileid = [ - int(i) for i in data1['streamfileids'][format].strip('*').split('*')] - fileid = ''.join( - [shuffled_string_ls[i] for i in streamfileid]) - fileid_dict[format] = fileid[:8] + '%s' + fileid[10:] + for stream in data['stream']: + format = stream.get('stream_type') + fileid = stream['stream_fileid'] + fileid_dict[format] = fileid def get_fileid(format, n): - fileid = fileid_dict[format] % hex(int(n))[2:].upper().zfill(2) + number = hex(int(str(n), 10))[2:].upper() + if len(number) == 1: + number = '0' + number + streamfileids = fileid_dict[format] + fileid = streamfileids[0:8] + number + streamfileids[10:] return fileid # get ep @@ -123,15 +113,15 @@ class YoukuIE(InfoExtractor): # generate video_urls video_urls_dict = {} - for format in data1['streamtypes']: + for stream in data['stream']: + format = stream.get('stream_type') video_urls = [] - for dt in data1['segs'][format]: - n = str(int(dt['no'])) + for dt in stream['segs']: + n = str(stream['segs'].index(dt)) param = { - 'K': dt['k'], + 'K': dt['key'], 'hd': self.get_hd(format), 'myp': 0, - 'ts': dt['seconds'], 'ypp': 0, 'ctype': 12, 'ev': 1, @@ -142,7 +132,7 @@ class YoukuIE(InfoExtractor): video_url = \ 'http://k.youku.com/player/getFlvPath/' + \ 'sid/' + sid + \ - '_' + str(int(n) + 1).zfill(2) + \ + '_00' + \ '/st/' + self.parse_ext_l(format) + \ '/fileid/' + get_fileid(format, n) + '?' + \ compat_urllib_parse.urlencode(param) @@ -153,23 +143,31 @@ class YoukuIE(InfoExtractor): def get_hd(self, fm): hd_id_dict = { + '3gp': '0', + '3gphd': '1', 'flv': '0', + 'flvhd': '0', 'mp4': '1', + 'mp4hd': '1', + 'mp4hd2': '1', + 'mp4hd3': '1', 'hd2': '2', 'hd3': '3', - '3gp': '0', - '3gphd': '1' } return hd_id_dict[fm] def parse_ext_l(self, fm): ext_dict = { + '3gp': 'flv', + '3gphd': 'mp4', 'flv': 'flv', + 'flvhd': 'flv', 'mp4': 'mp4', + 'mp4hd': 'mp4', + 'mp4hd2': 'flv', + 'mp4hd3': 'flv', 'hd2': 'flv', 'hd3': 'flv', - '3gp': 'flv', - '3gphd': 'mp4' } return ext_dict[fm] @@ -178,9 +176,13 @@ class YoukuIE(InfoExtractor): '3gp': 'h6', '3gphd': 'h5', 'flv': 'h4', + 'flvhd': 'h4', 'mp4': 'h3', + 'mp4hd': 'h3', + 'mp4hd2': 'h4', + 'mp4hd3': 'h4', 'hd2': 'h2', - 'hd3': 'h1' + 'hd3': 'h1', } return _dict[fm] @@ -188,45 +190,46 @@ class YoukuIE(InfoExtractor): video_id = self._match_id(url) def retrieve_data(req_url, note): - req = sanitized_Request(req_url) + headers = { + 'Referer': req_url, + } + self._set_cookie('youku.com', 'xreferrer', 'http://www.youku.com') + req = sanitized_Request(req_url, headers=headers) cn_verification_proxy = self._downloader.params.get('cn_verification_proxy') if cn_verification_proxy: req.add_header('Ytdl-request-proxy', cn_verification_proxy) raw_data = self._download_json(req, video_id, note=note) - return raw_data['data'][0] + + return raw_data['data'] video_password = self._downloader.params.get('videopassword', None) # request basic data - basic_data_url = 'http://v.youku.com/player/getPlayList/VideoIDS/%s' % video_id + basic_data_url = "http://play.youku.com/play/get.json?vid=%s&ct=12" % video_id if video_password: - basic_data_url += '?password=%s' % video_password - - data1 = retrieve_data( - basic_data_url, - 'Downloading JSON metadata 1') - data2 = retrieve_data( - 'http://v.youku.com/player/getPlayList/VideoIDS/%s/Pf/4/ctype/12/ev/1' % video_id, - 'Downloading JSON metadata 2') - - error_code = data1.get('error_code') - if error_code: - error = data1.get('error') - if error is not None and '因版权原因无法观看此视频' in error: + basic_data_url += '&pwd=%s' % video_password + + data = retrieve_data(basic_data_url, 'Downloading JSON metadata') + + error = data.get('error') + if error: + error_note = error.get('note') + if error_note is not None and '因版权原因无法观看此视频' in error_note: raise ExtractorError( 'Youku said: Sorry, this video is available in China only', expected=True) else: - msg = 'Youku server reported error %i' % error_code - if error is not None: - msg += ': ' + error + msg = 'Youku server reported error %i' % error.get('code') + if error_note is not None: + msg += ': ' + error_note raise ExtractorError(msg) - title = data1['title'] + # get video title + title = data['video']['title'] # generate video_urls_dict - video_urls_dict = self.construct_video_urls(data1, data2) + video_urls_dict = self.construct_video_urls(data) # construct info entries = [{ @@ -235,10 +238,11 @@ class YoukuIE(InfoExtractor): 'formats': [], # some formats are not available for all parts, we have to detect # which one has all - } for i in range(max(len(v) for v in data1['segs'].values()))] - for fm in data1['streamtypes']: + } for i in range(max(len(v.get('segs')) for v in data['stream']))] + for stream in data['stream']: + fm = stream.get('stream_type') video_urls = video_urls_dict[fm] - for video_url, seg, entry in zip(video_urls, data1['segs'][fm], entries): + for video_url, seg, entry in zip(video_urls, stream['segs'], entries): entry['formats'].append({ 'url': video_url, 'format_id': self.get_format_name(fm), diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 9b39505ba..4aac2cc03 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -26,6 +26,7 @@ from ..compat import ( from ..utils import ( clean_html, encode_dict, + error_to_compat_str, ExtractorError, float_or_none, get_element_by_attribute, @@ -33,6 +34,7 @@ from ..utils import ( int_or_none, orderedSet, parse_duration, + remove_quotes, remove_start, sanitized_Request, smuggle_url, @@ -395,12 +397,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'ext': 'mp4', 'upload_date': '20120506', 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]', + 'alt_title': 'I Love It (feat. Charli XCX)', 'description': 'md5:782e8651347686cba06e58f71ab51773', 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli', 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop', 'iconic ep', 'iconic', 'love', 'it'], 'uploader': 'Icona Pop', 'uploader_id': 'IconaPop', + 'creator': 'Icona Pop', } }, { @@ -411,9 +415,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'ext': 'mp4', 'upload_date': '20130703', 'title': 'Justin Timberlake - Tunnel Vision (Explicit)', + 'alt_title': 'Tunnel Vision', 'description': 'md5:64249768eec3bc4276236606ea996373', 'uploader': 'justintimberlakeVEVO', 'uploader_id': 'justintimberlakeVEVO', + 'creator': 'Justin Timberlake', 'age_limit': 18, } }, @@ -492,10 +498,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'id': 'nfWlot6h_JM', 'ext': 'm4a', 'title': 'Taylor Swift - Shake It Off', + 'alt_title': 'Shake It Off', 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3', 'uploader': 'TaylorSwiftVEVO', 'uploader_id': 'TaylorSwiftVEVO', 'upload_date': '20140818', + 'creator': 'Taylor Swift', }, 'params': { 'youtube_include_dash_manifest': True, @@ -551,9 +559,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'ext': 'mp4', 'upload_date': '20100430', 'uploader_id': 'deadmau5', + 'creator': 'deadmau5', 'description': 'md5:12c56784b8032162bb936a5f76d55360', 'uploader': 'deadmau5', 'title': 'Deadmau5 - Some Chords (HD)', + 'alt_title': 'Some Chords', }, 'expected_warnings': [ 'DASH manifest missing', @@ -701,10 +711,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'id': 'lsguqyKfVQg', 'ext': 'mp4', 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21', + 'alt_title': 'Dark Walk', 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a', 'upload_date': '20151119', 'uploader_id': 'IronSoulElf', 'uploader': 'IronSoulElf', + 'creator': 'Todd Haberman, Daniel Law Heath & Aaron Kaplan', }, 'params': { 'skip_download': True, @@ -892,7 +904,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id, video_id, note=False) except ExtractorError as err: - self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err)) + self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err)) return {} sub_lang_list = {} @@ -1308,6 +1320,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor): upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) upload_date = unified_strdate(upload_date) + m_music = re.search( + r'<h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*<ul[^>]*>\s*<li>(?P<title>.+?) by (?P<creator>.+?)(?:\(.+?\))?</li', + video_webpage) + if m_music: + video_alt_title = remove_quotes(unescapeHTML(m_music.group('title'))) + video_creator = clean_html(m_music.group('creator')) + else: + video_alt_title = video_creator = None + m_cat_container = self._search_regex( r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>', video_webpage, 'categories', default=None) @@ -1537,7 +1558,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader': video_uploader, 'uploader_id': video_uploader_id, 'upload_date': upload_date, + 'creator': video_creator, 'title': video_title, + 'alt_title': video_alt_title, 'thumbnail': video_thumbnail, 'description': video_description, 'categories': video_categories, @@ -1752,6 +1775,10 @@ class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor): }, }] + @classmethod + def suitable(cls, url): + return False if YoutubePlaylistsIE.suitable(url) else super(YoutubeChannelIE, cls).suitable(url) + def _real_extract(self, url): channel_id = self._match_id(url) @@ -1825,10 +1852,10 @@ class YoutubeUserIE(YoutubeChannelIE): return super(YoutubeUserIE, cls).suitable(url) -class YoutubeUserPlaylistsIE(YoutubePlaylistsBaseInfoExtractor): - IE_DESC = 'YouTube.com user playlists' - _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/user/(?P<id>[^/]+)/playlists' - IE_NAME = 'youtube:user:playlists' +class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor): + IE_DESC = 'YouTube.com user/channel playlists' + _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists' + IE_NAME = 'youtube:playlists' _TESTS = [{ 'url': 'http://www.youtube.com/user/ThirstForScience/playlists', @@ -1845,6 +1872,13 @@ class YoutubeUserPlaylistsIE(YoutubePlaylistsBaseInfoExtractor): 'id': 'igorkle1', 'title': 'Игорь Клейнер', }, + }, { + 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists', + 'playlist_mincount': 17, + 'info_dict': { + 'id': 'UCiU1dHvZObB2iP6xkJ__Icw', + 'title': 'Chem Player', + }, }] diff --git a/youtube_dl/jsinterp.py b/youtube_dl/jsinterp.py index 2191e8b89..a7440c582 100644 --- a/youtube_dl/jsinterp.py +++ b/youtube_dl/jsinterp.py @@ -232,7 +232,7 @@ class JSInterpreter(object): def extract_function(self, funcname): func_m = re.search( r'''(?x) - (?:function\s+%s|[{;]%s\s*=\s*function|var\s+%s\s*=\s*function)\s* + (?:function\s+%s|[{;,]%s\s*=\s*function|var\s+%s\s*=\s*function)\s* \((?P<args>[^)]*)\)\s* \{(?P<code>[^}]+)\}''' % ( re.escape(funcname), re.escape(funcname), re.escape(funcname)), diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 5ed723bc6..daca5d814 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -52,7 +52,7 @@ class FFmpegPostProcessor(PostProcessor): def _determine_executables(self): programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe'] - prefer_ffmpeg = self._downloader.params.get('prefer_ffmpeg', False) + prefer_ffmpeg = False self.basename = None self.probe_basename = None @@ -60,6 +60,7 @@ class FFmpegPostProcessor(PostProcessor): self._paths = None self._versions = None if self._downloader: + prefer_ffmpeg = self._downloader.params.get('prefer_ffmpeg', False) location = self._downloader.params.get('ffmpeg_location') if location is not None: if not os.path.exists(location): diff --git a/youtube_dl/update.py b/youtube_dl/update.py index 074eb64a7..995b8ed96 100644 --- a/youtube_dl/update.py +++ b/youtube_dl/update.py @@ -9,7 +9,7 @@ import subprocess import sys from zipimport import zipimporter -from .compat import compat_str +from .utils import encode_compat_str from .version import __version__ @@ -61,7 +61,7 @@ def update_self(to_screen, verbose, opener): newversion = opener.open(VERSION_URL).read().decode('utf-8').strip() except Exception: if verbose: - to_screen(compat_str(traceback.format_exc())) + to_screen(encode_compat_str(traceback.format_exc())) to_screen('ERROR: can\'t find the current version. Please try again later.') return if newversion == __version__: @@ -74,7 +74,7 @@ def update_self(to_screen, verbose, opener): versions_info = json.loads(versions_info) except Exception: if verbose: - to_screen(compat_str(traceback.format_exc())) + to_screen(encode_compat_str(traceback.format_exc())) to_screen('ERROR: can\'t obtain versions info. Please try again later.') return if 'signature' not in versions_info: @@ -123,7 +123,7 @@ def update_self(to_screen, verbose, opener): urlh.close() except (IOError, OSError): if verbose: - to_screen(compat_str(traceback.format_exc())) + to_screen(encode_compat_str(traceback.format_exc())) to_screen('ERROR: unable to download latest version') return @@ -137,7 +137,7 @@ def update_self(to_screen, verbose, opener): outf.write(newcontent) except (IOError, OSError): if verbose: - to_screen(compat_str(traceback.format_exc())) + to_screen(encode_compat_str(traceback.format_exc())) to_screen('ERROR: unable to write the new version') return @@ -157,7 +157,7 @@ start /b "" cmd /c del "%%~f0"&exit /b" return # Do not show premature success messages except (IOError, OSError): if verbose: - to_screen(compat_str(traceback.format_exc())) + to_screen(encode_compat_str(traceback.format_exc())) to_screen('ERROR: unable to overwrite current version') return @@ -169,7 +169,7 @@ start /b "" cmd /c del "%%~f0"&exit /b" urlh.close() except (IOError, OSError): if verbose: - to_screen(compat_str(traceback.format_exc())) + to_screen(encode_compat_str(traceback.format_exc())) to_screen('ERROR: unable to download latest version') return @@ -183,7 +183,7 @@ start /b "" cmd /c del "%%~f0"&exit /b" outf.write(newcontent) except (IOError, OSError): if verbose: - to_screen(compat_str(traceback.format_exc())) + to_screen(encode_compat_str(traceback.format_exc())) to_screen('ERROR: unable to overwrite current version') return diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index d0606b4bc..1737ac5f6 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -1406,6 +1406,15 @@ def remove_end(s, end): return s +def remove_quotes(s): + if s is None or len(s) < 2: + return s + for quote in ('"', "'", ): + if s[0] == quote and s[-1] == quote: + return s[1:-1] + return s + + def url_basename(url): path = compat_urlparse.urlparse(url).path return path.strip('/').split('/')[-1] @@ -1703,6 +1712,10 @@ def encode_dict(d, encoding='utf-8'): return dict((encode(k), encode(v)) for k, v in d.items()) +def encode_compat_str(string, encoding=preferredencoding(), errors='strict'): + return string if isinstance(string, compat_str) else compat_str(string, encoding, errors) + + US_RATINGS = { 'G': 0, 'PG': 10, @@ -1797,6 +1810,15 @@ def args_to_str(args): return ' '.join(shlex_quote(a) for a in args) +def error_to_compat_str(err): + err_str = str(err) + # On python 2 error byte string must be decoded with proper + # encoding rather than ascii + if sys.version_info[0] < 3: + err_str = err_str.decode(preferredencoding()) + return err_str + + def mimetype2ext(mt): _, _, res = mt.rpartition('/') @@ -1967,15 +1989,15 @@ def match_filter_func(filter_str): def parse_dfxp_time_expr(time_expr): if not time_expr: - return 0.0 + return mobj = re.match(r'^(?P<time_offset>\d+(?:\.\d+)?)s?$', time_expr) if mobj: return float(mobj.group('time_offset')) - mobj = re.match(r'^(\d+):(\d\d):(\d\d(?:\.\d+)?)$', time_expr) + mobj = re.match(r'^(\d+):(\d\d):(\d\d(?:(?:\.|:)\d+)?)$', time_expr) if mobj: - return 3600 * int(mobj.group(1)) + 60 * int(mobj.group(2)) + float(mobj.group(3)) + return 3600 * int(mobj.group(1)) + 60 * int(mobj.group(2)) + float(mobj.group(3).replace(':', '.')) def srt_subtitles_timecode(seconds): @@ -2011,10 +2033,15 @@ def dfxp2srt(dfxp_data): raise ValueError('Invalid dfxp/TTML subtitle') for para, index in zip(paras, itertools.count(1)): - begin_time = parse_dfxp_time_expr(para.attrib['begin']) + begin_time = parse_dfxp_time_expr(para.attrib.get('begin')) end_time = parse_dfxp_time_expr(para.attrib.get('end')) + dur = parse_dfxp_time_expr(para.attrib.get('dur')) + if begin_time is None: + continue if not end_time: - end_time = begin_time + parse_dfxp_time_expr(para.attrib['dur']) + if not dur: + continue + end_time = begin_time + dur out.append('%d\n%s --> %s\n%s\n\n' % ( index, srt_subtitles_timecode(begin_time), diff --git a/youtube_dl/version.py b/youtube_dl/version.py index bd0de9f53..01607693e 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2015.11.27.1' +__version__ = '2015.12.18' |