Merge pull request #8 from rg3/master

update

.github/ISSUE_TEMPLATE.md

@@ -6,8 +6,8 @@
 
 ---
 
-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.04.24*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.05.01*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
-- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.04.24**
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.05.01**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
 [debug] User config: []
 [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
-[debug] youtube-dl version 2016.04.24
+[debug] youtube-dl version 2016.05.01
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}

AUTHORS

@@ -168,3 +168,7 @@ José Joaquín Atria
 Viťas Strádal
 Kagami Hiiragi
 Philip Huppert
+blahgeek
+Kevin Deldycke
+inondle
+Tomáš Čech

Makefile

@@ -1,7 +1,7 @@
 all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites
 
 clean:
-	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part *.info.json *.mp4 *.flv *.mp3 *.avi CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
+	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part *.info.json *.mp4 *.flv *.mp3 *.avi *.mkv *.webm CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
 	find . -name "*.pyc" -delete
 	find . -name "*.class" -delete
 

README.md

@@ -465,7 +465,7 @@ The basic usage is not to set any template arguments when downloading a single f
  - `display_id`: An alternative identifier for the video
  - `uploader`: Full name of the video uploader
  - `license`: License name the video is licensed under
- - `creator`: The main artist who created the video
+ - `creator`: The creator of the video
  - `release_date`: The date (YYYYMMDD) when the video was released
  - `timestamp`: UNIX timestamp of the moment the video became available
  - `upload_date`: Video upload date (YYYYMMDD)

docs/supportedsites.md

@@ -338,7 +338,6 @@
  - **mailru**: Видео@Mail.Ru
  - **MakersChannel**
  - **MakerTV**
- - **Malemotion**
  - **MatchTV**
  - **MDR**: MDR.DE and KiKA
  - **media.ccc.de**
@@ -375,8 +374,8 @@
  - **mtvservices:embedded**
  - **MuenchenTV**: münchen.tv
  - **MusicPlayOn**
- - **muzu.tv**
  - **Mwave**
+ - **MwaveMeetGreet**
  - **MySpace**
  - **MySpace:album**
  - **MySpass**
@@ -554,7 +553,6 @@
  - **SenateISVP**
  - **ServingSys**
  - **Sexu**
- - **SexyKarma**: Sexy Karma and Watch Indian Porn
  - **Shahid**
  - **Shared**: shared.sx and vivo.sx
  - **ShareSix**
@@ -567,8 +565,6 @@
  - **smotri:broadcast**: Smotri.com broadcasts
  - **smotri:community**: Smotri.com community videos
  - **smotri:user**: Smotri.com user videos
- - **SnagFilms**
- - **SnagFilmsEmbed**
  - **Snotr**
  - **Sohu**
  - **soundcloud**
@@ -610,6 +606,7 @@
  - **Syfy**
  - **SztvHu**
  - **Tagesschau**
+ - **tagesschau:player**
  - **Tapely**
  - **Tass**
  - **TDSLifeway**
@@ -725,6 +722,8 @@
  - **Vidzi**
  - **vier**
  - **vier:videos**
+ - **ViewLift**
+ - **ViewLiftEmbed**
  - **Viewster**
  - **Viidea**
  - **viki**
@@ -756,6 +755,7 @@
  - **Walla**
  - **WashingtonPost**
  - **wat.tv**
+ - **WatchIndianPorn**: Watch Indian Porn
  - **WDR**
  - **wdr:mobile**
  - **WDRMaus**: Sendung mit der Maus
@@ -775,6 +775,10 @@
  - **XFileShare**: XFileShare based sites: GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net, filehoot.com and vidto.me
  - **XHamster**
  - **XHamsterEmbed**
+ - **xiami:album**: 虾米音乐 - 专辑
+ - **xiami:artist**: 虾米音乐 - 歌手
+ - **xiami:collection**: 虾米音乐 - 精选集
+ - **xiami:song**: 虾米音乐
  - **XMinus**
  - **XNXX**
  - **Xstream**

test/test_compat.py

@@ -10,9 +10,9 @@ import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 
-from youtube_dl.utils import get_filesystem_encoding
 from youtube_dl.compat import (
     compat_getenv,
+    compat_setenv,
     compat_etree_fromstring,
     compat_expanduser,
     compat_shlex_split,
@@ -26,19 +26,22 @@ from youtube_dl.compat import (
 class TestCompat(unittest.TestCase):
     def test_compat_getenv(self):
         test_str = 'тест'
-        os.environ['YOUTUBE-DL-TEST'] = (
+        compat_setenv('YOUTUBE-DL-TEST', test_str)
-            test_str if sys.version_info >= (3, 0)
-            else test_str.encode(get_filesystem_encoding()))
         self.assertEqual(compat_getenv('YOUTUBE-DL-TEST'), test_str)
 
+    def test_compat_setenv(self):
+        test_var = 'YOUTUBE-DL-TEST'
+        test_str = 'тест'
+        compat_setenv(test_var, test_str)
+        compat_getenv(test_var)
+        self.assertEqual(compat_getenv(test_var), test_str)
+
     def test_compat_expanduser(self):
         old_home = os.environ.get('HOME')
         test_str = 'C:\Documents and Settings\тест\Application Data'
-        os.environ['HOME'] = (
+        compat_setenv('HOME', test_str)
-            test_str if sys.version_info >= (3, 0)
-            else test_str.encode(get_filesystem_encoding()))
         self.assertEqual(compat_expanduser('~'), test_str)
-        os.environ['HOME'] = old_home
+        compat_setenv('HOME', old_home or '')
 
     def test_all_present(self):
         import youtube_dl.compat

test/test_utils.py

@@ -139,8 +139,8 @@ class TestUtil(unittest.TestCase):
         self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
         self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
 
-        tests = 'a\xe4b\u4e2d\u56fd\u7684c'
+        tests = 'aäb\u4e2d\u56fd\u7684c'
-        self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
+        self.assertEqual(sanitize_filename(tests, restricted=True), 'aab_c')
         self.assertTrue(sanitize_filename('\xf6', restricted=True) != '')  # No empty filename
 
         forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
@@ -155,6 +155,10 @@ class TestUtil(unittest.TestCase):
         self.assertTrue(sanitize_filename('-', restricted=True) != '')
         self.assertTrue(sanitize_filename(':', restricted=True) != '')
 
+        self.assertEqual(sanitize_filename(
+            'ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ', restricted=True),
+            'AAAAAAAECEEEEIIIIDNOOOOOOUUUUYPssaaaaaaaeceeeeiiiionoooooouuuuypy')
+
     def test_sanitize_ids(self):
         self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
         self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')

youtube_dl/YoutubeDL.py

@@ -580,7 +580,7 @@ class YoutubeDL(object):
                 is_id=(k == 'id'))
             template_dict = dict((k, sanitize(k, v))
                                  for k, v in template_dict.items()
-                                 if v is not None)
+                                 if v is not None and not isinstance(v, (list, tuple, dict)))
             template_dict = collections.defaultdict(lambda: 'NA', template_dict)
 
             outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
@@ -1639,7 +1639,7 @@ class YoutubeDL(object):
                     # Just a single file
                     success = dl(filename, info_dict)
             except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-                self.report_error('unable to download video data: %s' % str(err))
+                self.report_error('unable to download video data: %s' % error_to_compat_str(err))
                 return
             except (OSError, IOError) as err:
                 raise UnavailableVideoError(err)
@@ -2018,6 +2018,7 @@ class YoutubeDL(object):
         if opts_cookiefile is None:
             self.cookiejar = compat_cookiejar.CookieJar()
         else:
+            opts_cookiefile = compat_expanduser(opts_cookiefile)
             self.cookiejar = compat_cookiejar.MozillaCookieJar(
                 opts_cookiefile)
             if os.access(opts_cookiefile, os.R_OK):

youtube_dl/__init__.py

@@ -86,7 +86,9 @@ def _real_main(argv=None):
             if opts.batchfile == '-':
                 batchfd = sys.stdin
             else:
-                batchfd = io.open(opts.batchfile, 'r', encoding='utf-8', errors='ignore')
+                batchfd = io.open(
+                    compat_expanduser(opts.batchfile),
+                    'r', encoding='utf-8', errors='ignore')
             batch_urls = read_batch_urls(batchfd)
             if opts.verbose:
                 write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
@@ -404,7 +406,7 @@ def _real_main(argv=None):
 
         try:
             if opts.load_info_filename is not None:
-                retcode = ydl.download_with_info_file(opts.load_info_filename)
+                retcode = ydl.download_with_info_file(compat_expanduser(opts.load_info_filename))
             else:
                 retcode = ydl.download(all_urls)
         except MaxDownloadsReached:

youtube_dl/compat.py

@@ -373,6 +373,9 @@ compat_os_name = os._name if os.name == 'java' else os.name
 if sys.version_info >= (3, 0):
     compat_getenv = os.getenv
     compat_expanduser = os.path.expanduser
+
+    def compat_setenv(key, value, env=os.environ):
+        env[key] = value
 else:
     # Environment variables should be decoded with filesystem encoding.
     # Otherwise it will fail if any non-ASCII characters present (see #3854 #3217 #2918)
@@ -384,6 +387,12 @@ else:
             env = env.decode(get_filesystem_encoding())
         return env
 
+    def compat_setenv(key, value, env=os.environ):
+        def encode(v):
+            from .utils import get_filesystem_encoding
+            return v.encode(get_filesystem_encoding()) if isinstance(v, compat_str) else v
+        env[encode(key)] = encode(value)
+
     # HACK: The default implementations of os.path.expanduser from cpython do not decode
     # environment variables with filesystem encoding. We will work around this by
     # providing adjusted implementations.
@@ -604,6 +613,7 @@ __all__ = [
     'compat_os_name',
     'compat_parse_qs',
     'compat_print',
+    'compat_setenv',
     'compat_shlex_split',
     'compat_socket_create_connection',
     'compat_str',

youtube_dl/downloader/external.py

@@ -6,6 +6,7 @@ import sys
 import re
 
 from .common import FileDownloader
+from ..compat import compat_setenv
 from ..postprocessor.ffmpeg import FFmpegPostProcessor, EXT_TO_OUT_FORMATS
 from ..utils import (
     cli_option,
@@ -198,6 +199,18 @@ class FFmpegFD(ExternalFD):
                 '-headers',
                 ''.join('%s: %s\r\n' % (key, val) for key, val in headers.items())]
 
+        env = None
+        proxy = self.params.get('proxy')
+        if proxy:
+            if not re.match(r'^[\da-zA-Z]+://', proxy):
+                proxy = 'http://%s' % proxy
+            # Since December 2015 ffmpeg supports -http_proxy option (see
+            # http://git.videolan.org/?p=ffmpeg.git;a=commit;h=b4eb1f29ebddd60c41a2eb39f5af701e38e0d3fd)
+            # We could switch to the following code if we are able to detect version properly
+            # args += ['-http_proxy', proxy]
+            env = os.environ.copy()
+            compat_setenv('HTTP_PROXY', proxy, env=env)
+
         protocol = info_dict.get('protocol')
 
         if protocol == 'rtmp':
@@ -224,7 +237,7 @@ class FFmpegFD(ExternalFD):
                 args += ['-rtmp_live', 'live']
 
         args += ['-i', url, '-c', 'copy']
-        if protocol == 'm3u8':
+        if protocol in ('m3u8', 'm3u8_native'):
             if self.params.get('hls_use_mpegts', False) or tmpfilename == '-':
                 args += ['-f', 'mpegts']
             else:
@@ -239,7 +252,7 @@ class FFmpegFD(ExternalFD):
 
         self._debug_cmd(args)
 
-        proc = subprocess.Popen(args, stdin=subprocess.PIPE)
+        proc = subprocess.Popen(args, stdin=subprocess.PIPE, env=env)
         try:
             retval = proc.wait()
         except KeyboardInterrupt:

youtube_dl/downloader/hls.py

@@ -4,6 +4,7 @@ import os.path
 import re
 
 from .fragment import FragmentFD
+from .external import FFmpegFD
 
 from ..compat import compat_urlparse
 from ..utils import (
@@ -17,12 +18,39 @@ class HlsFD(FragmentFD):
 
     FD_NAME = 'hlsnative'
 
+    @staticmethod
+    def can_download(manifest):
+        UNSUPPORTED_FEATURES = (
+            r'#EXT-X-KEY:METHOD=(?!NONE)',  # encrypted streams [1]
+            r'#EXT-X-BYTERANGE',  # playlists composed of byte ranges of media files [2]
+            # Live streams heuristic does not always work (e.g. geo restricted to Germany
+            # http://hls-geo.daserste.de/i/videoportal/Film/c_620000/622873/format,716451,716457,716450,716458,716459,.mp4.csmil/index_4_av.m3u8?null=0)
+            # r'#EXT-X-MEDIA-SEQUENCE:(?!0$)',  # live streams [3]
+            r'#EXT-X-PLAYLIST-TYPE:EVENT',  # media segments may be appended to the end of
+                                            # event media playlists [4]
+            # 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.2.4
+            # 2. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.2.2
+            # 3. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.2
+            # 4. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.5
+        )
+        return all(not re.search(feature, manifest) for feature in UNSUPPORTED_FEATURES)
+
     def real_download(self, filename, info_dict):
         man_url = info_dict['url']
         self.to_screen('[%s] Downloading m3u8 manifest' % self.FD_NAME)
         manifest = self.ydl.urlopen(man_url).read()
 
         s = manifest.decode('utf-8', 'ignore')
+
+        if not self.can_download(s):
+            self.report_warning(
+                'hlsnative has detected features it does not support, '
+                'extraction will be delegated to ffmpeg')
+            fd = FFmpegFD(self.ydl, self.params)
+            for ph in self._progress_hooks:
+                fd.add_progress_hook(ph)
+            return fd.real_download(filename, info_dict)
+
         fragment_urls = []
         for line in s.splitlines():
             line = line.strip()

youtube_dl/extractor/aol.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 class AolIE(InfoExtractor):
     IE_NAME = 'on.aol.com'
-    _VALID_URL = r'(?:aol-video:|https?://on\.aol\.com/.*-)(?P<id>[^/?-]+)'
+    _VALID_URL = r'(?:aol-video:|https?://on\.aol\.com/(?:[^/]+/)*(?:[^/?#&]+-)?)(?P<id>[^/?#&]+)'
 
     _TESTS = [{
         # video with 5min ID
@@ -53,6 +53,12 @@ class AolIE(InfoExtractor):
     }, {
         'url': 'http://on.aol.com/shows/park-bench-shw518173474-559a1b9be4b0c3bfad3357a7?context=SH:SHW518173474:PL4327:1460619712763',
         'only_matching': True,
+    }, {
+        'url': 'http://on.aol.com/video/519442220',
+        'only_matching': True,
+    }, {
+        'url': 'aol-video:5707d6b8e4b090497b04f706',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/arte.py

@@ -161,24 +161,53 @@ class ArteTVPlus7IE(InfoExtractor):
             'es': 'E[ESP]',
         }
 
+        langcode = LANGS.get(lang, lang)
+
         formats = []
         for format_id, format_dict in player_info['VSR'].items():
             f = dict(format_dict)
             versionCode = f.get('versionCode')
-            langcode = LANGS.get(lang, lang)
+            l = re.escape(langcode)
-            lang_rexs = [r'VO?%s-' % re.escape(langcode), r'VO?.-ST%s$' % re.escape(langcode)]
+
-            lang_pref = None
+            # Language preference from most to least priority
-            if versionCode:
+            # Reference: section 5.6.3 of
-                matched_lang_rexs = [r for r in lang_rexs if re.match(r, versionCode)]
+            # http://www.arte.tv/sites/en/corporate/files/complete-technical-guidelines-arte-geie-v1-05.pdf
-                lang_pref = -10 if not matched_lang_rexs else 10 * len(matched_lang_rexs)
+            PREFERENCES = (
-            source_pref = 0
+                # original version in requested language, without subtitles
-            if versionCode is not None:
+                r'VO{0}$'.format(l),
-                # The original version with subtitles has lower relevance
+                # original version in requested language, with partial subtitles in requested language
-                if re.match(r'VO-ST(F|A|E)', versionCode):
+                r'VO{0}-ST{0}$'.format(l),
-                    source_pref -= 10
+                # original version in requested language, with subtitles for the deaf and hard-of-hearing in requested language
-                # The version with sourds/mal subtitles has also lower relevance
+                r'VO{0}-STM{0}$'.format(l),
-                elif re.match(r'VO?(F|A|E)-STM\1', versionCode):
+                # non-original (dubbed) version in requested language, without subtitles
-                    source_pref -= 9
+                r'V{0}$'.format(l),
+                # non-original (dubbed) version in requested language, with subtitles partial subtitles in requested language
+                r'V{0}-ST{0}$'.format(l),
+                # non-original (dubbed) version in requested language, with subtitles for the deaf and hard-of-hearing in requested language
+                r'V{0}-STM{0}$'.format(l),
+                # original version in requested language, with partial subtitles in different language
+                r'VO{0}-ST(?!{0}).+?$'.format(l),
+                # original version in requested language, with subtitles for the deaf and hard-of-hearing in different language
+                r'VO{0}-STM(?!{0}).+?$'.format(l),
+                # original version in different language, with partial subtitles in requested language
+                r'VO(?:(?!{0}).+?)?-ST{0}$'.format(l),
+                # original version in different language, with subtitles for the deaf and hard-of-hearing in requested language
+                r'VO(?:(?!{0}).+?)?-STM{0}$'.format(l),
+                # original version in different language, without subtitles
+                r'VO(?:(?!{0}))?$'.format(l),
+                # original version in different language, with partial subtitles in different language
+                r'VO(?:(?!{0}).+?)?-ST(?!{0}).+?$'.format(l),
+                # original version in different language, with subtitles for the deaf and hard-of-hearing in different language
+                r'VO(?:(?!{0}).+?)?-STM(?!{0}).+?$'.format(l),
+            )
+
+            for pref, p in enumerate(PREFERENCES):
+                if re.match(p, versionCode):
+                    lang_pref = len(PREFERENCES) - pref
+                    break
+            else:
+                lang_pref = -1
+
             format = {
                 'format_id': format_id,
                 'preference': -10 if f.get('videoFormat') == 'M3U8' else None,
@@ -188,7 +217,6 @@ class ArteTVPlus7IE(InfoExtractor):
                 'height': int_or_none(f.get('height')),
                 'tbr': int_or_none(f.get('bitrate')),
                 'quality': qfunc(f.get('quality')),
-                'source_preference': source_pref,
             }
 
             if f.get('mediaType') == 'rtmp':

youtube_dl/extractor/biqle.py

@@ -0,0 +1,39 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class BIQLEIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?biqle\.(?:com|org|ru)/watch/(?P<id>-?\d+_\d+)'
+    _TESTS = [{
+        'url': 'http://www.biqle.ru/watch/847655_160197695',
+        'md5': 'ad5f746a874ccded7b8f211aeea96637',
+        'info_dict': {
+            'id': '160197695',
+            'ext': 'mp4',
+            'title': 'Foo Fighters - The Pretender (Live at Wembley Stadium)',
+            'uploader': 'Andrey Rogozin',
+            'upload_date': '20110605',
+        }
+    }, {
+        'url': 'https://biqle.org/watch/-44781847_168547604',
+        'md5': '7f24e72af1db0edf7c1aaba513174f97',
+        'info_dict': {
+            'id': '168547604',
+            'ext': 'mp4',
+            'title': 'Ребенок в шоке от автоматической мойки',
+            'uploader': 'Dmitry Kotov',
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        embed_url = self._proto_relative_url(self._search_regex(
+            r'<iframe.+?src="((?:http:)?//daxab\.com/[^"]+)".*?></iframe>', webpage, 'embed url'))
+
+        return {
+            '_type': 'url_transparent',
+            'url': embed_url,
+        }

youtube_dl/extractor/ccc.py

@@ -1,13 +1,9 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
-    parse_duration,
+    parse_iso8601,
-    qualities,
-    unified_strdate,
 )
 
 
@@ -19,14 +15,14 @@ class CCCIE(InfoExtractor):
         'url': 'https://media.ccc.de/v/30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor#video',
         'md5': '3a1eda8f3a29515d27f5adb967d7e740',
         'info_dict': {
-            'id': '30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor',
+            'id': '1839',
             'ext': 'mp4',
             'title': 'Introduction to Processor Design',
-            'description': 'md5:80be298773966f66d56cb11260b879af',
+            'description': 'md5:df55f6d073d4ceae55aae6f2fd98a0ac',
             'thumbnail': 're:^https?://.*\.jpg$',
-            'view_count': int,
             'upload_date': '20131228',
-            'duration': 3660,
+            'timestamp': 1388188800,
+            'duration': 3710,
         }
     }, {
         'url': 'https://media.ccc.de/v/32c3-7368-shopshifting#download',
@@ -34,79 +30,48 @@ class CCCIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(url, display_id)
+        event_id = self._search_regex("data-id='(\d+)'", webpage, 'event id')
+        event_data = self._download_json('https://media.ccc.de/public/events/%s' % event_id, event_id)
 
-        if self._downloader.params.get('prefer_free_formats'):
-            preference = qualities(['mp3', 'opus', 'mp4-lq', 'webm-lq', 'h264-sd', 'mp4-sd', 'webm-sd', 'mp4', 'webm', 'mp4-hd', 'h264-hd', 'webm-hd'])
-        else:
-            preference = qualities(['opus', 'mp3', 'webm-lq', 'mp4-lq', 'webm-sd', 'h264-sd', 'mp4-sd', 'webm', 'mp4', 'webm-hd', 'mp4-hd', 'h264-hd'])
-
-        title = self._html_search_regex(
-            r'(?s)<h1>(.*?)</h1>', webpage, 'title')
-        description = self._html_search_regex(
-            r'(?s)<h3>About</h3>(.+?)<h3>',
-            webpage, 'description', fatal=False)
-        upload_date = unified_strdate(self._html_search_regex(
-            r"(?s)<span[^>]+class='[^']*fa-calendar-o'[^>]*>(.+?)</span>",
-            webpage, 'upload date', fatal=False))
-        view_count = int_or_none(self._html_search_regex(
-            r"(?s)<span class='[^']*fa-eye'></span>(.*?)</li>",
-            webpage, 'view count', fatal=False))
-        duration = parse_duration(self._html_search_regex(
-            r'(?s)<span[^>]+class=(["\']).*?fa-clock-o.*?\1[^>]*></span>(?P<duration>.+?)</li',
-            webpage, 'duration', fatal=False, group='duration'))
-
-        matches = re.finditer(r'''(?xs)
-            <(?:span|div)\s+class='label\s+filetype'>(?P<format>[^<]*)</(?:span|div)>\s*
-            <(?:span|div)\s+class='label\s+filetype'>(?P<lang>[^<]*)</(?:span|div)>\s*
-            <a\s+download\s+href='(?P<http_url>[^']+)'>\s*
-            (?:
-                .*?
-                <a\s+(?:download\s+)?href='(?P<torrent_url>[^']+\.torrent)'
-            )?''', webpage)
         formats = []
-        for m in matches:
+        for recording in event_data.get('recordings', []):
-            format = m.group('format')
+            recording_url = recording.get('recording_url')
-            format_id = self._search_regex(
+            if not recording_url:
-                r'.*/([a-z0-9_-]+)/[^/]*$',
+                continue
-                m.group('http_url'), 'format id', default=None)
+            language = recording.get('language')
-            if format_id:
+            folder = recording.get('folder')
-                format_id = m.group('lang') + '-' + format_id
+            format_id = None
-            vcodec = 'h264' if 'h264' in format_id else (
+            if language:
-                'none' if format_id in ('mp3', 'opus') else None
+                format_id = language
+            if folder:
+                if language:
+                    format_id += '-' + folder
+                else:
+                    format_id = folder
+            vcodec = 'h264' if 'h264' in folder else (
+                'none' if folder in ('mp3', 'opus') else None
             )
             formats.append({
                 'format_id': format_id,
-                'format': format,
+                'url': recording_url,
-                'language': m.group('lang'),
+                'width': int_or_none(recording.get('width')),
-                'url': m.group('http_url'),
+                'height': int_or_none(recording.get('height')),
+                'filesize': int_or_none(recording.get('size'), invscale=1024 * 1024),
+                'language': language,
                 'vcodec': vcodec,
-                'preference': preference(format_id),
             })
-
-            if m.group('torrent_url'):
-                formats.append({
-                    'format_id': 'torrent-%s' % (format if format_id is None else format_id),
-                    'format': '%s (torrent)' % format,
-                    'proto': 'torrent',
-                    'format_note': '(unsupported; will just download the .torrent file)',
-                    'vcodec': vcodec,
-                    'preference': -100 + preference(format_id),
-                    'url': m.group('torrent_url'),
-                })
         self._sort_formats(formats)
 
-        thumbnail = self._html_search_regex(
-            r"<video.*?poster='([^']+)'", webpage, 'thumbnail', fatal=False)
-
         return {
-            'id': video_id,
+            'id': event_id,
-            'title': title,
+            'display_id': display_id,
-            'description': description,
+            'title': event_data['title'],
-            'thumbnail': thumbnail,
+            'description': event_data.get('description'),
-            'view_count': view_count,
+            'thumbnail': event_data.get('thumb_url'),
-            'upload_date': upload_date,
+            'timestamp': parse_iso8601(event_data.get('date')),
-            'duration': duration,
+            'duration': int_or_none(event_data.get('length')),
+            'tags': event_data.get('tags'),
             'formats': formats,
         }

youtube_dl/extractor/ceskatelevize.py

@@ -33,19 +33,33 @@ class CeskaTelevizeIE(InfoExtractor):
             'skip_download': True,
         },
     }, {
-        'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina',
+        'url': 'http://www.ceskatelevize.cz/ivysilani/10441294653-hyde-park-civilizace/215411058090502/bonus/20641-bonus-01-en',
         'info_dict': {
-            'id': '61924494876844374',
+            'id': '61924494877028507',
             'ext': 'mp4',
-            'title': 'První republika: Zpěvačka z Dupárny Bobina',
+            'title': 'Hyde Park Civilizace: Bonus 01 - En',
-            'description': 'Sága mapující atmosféru první republiky od r. 1918 do r. 1945.',
+            'description': 'English Subtittles',
             'thumbnail': 're:^https?://.*\.jpg',
-            'duration': 88.4,
+            'duration': 81.3,
         },
         'params': {
             # m3u8 download
             'skip_download': True,
         },
+    }, {
+        # live stream
+        'url': 'http://www.ceskatelevize.cz/ivysilani/zive/ct4/',
+        'info_dict': {
+            'id': 402,
+            'ext': 'mp4',
+            'title': 're:^ČT Sport \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
+            'is_live': True,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+        'skip': 'Georestricted to Czech Republic',
     }, {
         # video with 18+ caution trailer
         'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/',
@@ -118,19 +132,21 @@ class CeskaTelevizeIE(InfoExtractor):
         req = sanitized_Request(compat_urllib_parse_unquote(playlist_url))
         req.add_header('Referer', url)
 
-        playlist_title = self._og_search_title(webpage)
+        playlist_title = self._og_search_title(webpage, default=None)
-        playlist_description = self._og_search_description(webpage)
+        playlist_description = self._og_search_description(webpage, default=None)
 
         playlist = self._download_json(req, playlist_id)['playlist']
         playlist_len = len(playlist)
 
         entries = []
         for item in playlist:
+            is_live = item.get('type') == 'LIVE'
             formats = []
             for format_id, stream_url in item['streamUrls'].items():
                 formats.extend(self._extract_m3u8_formats(
                     stream_url, playlist_id, 'mp4',
-                    entry_protocol='m3u8_native', fatal=False))
+                    entry_protocol='m3u8' if is_live else 'm3u8_native',
+                    fatal=False))
             self._sort_formats(formats)
 
             item_id = item.get('id') or item['assetId']
@@ -145,14 +161,22 @@ class CeskaTelevizeIE(InfoExtractor):
                 if subs:
                     subtitles = self.extract_subtitles(episode_id, subs)
 
+            if playlist_len == 1:
+                final_title = playlist_title or title
+                if is_live:
+                    final_title = self._live_title(final_title)
+            else:
+                final_title = '%s (%s)' % (playlist_title, title)
+
             entries.append({
                 'id': item_id,
-                'title': playlist_title if playlist_len == 1 else '%s (%s)' % (playlist_title, title),
+                'title': final_title,
                 'description': playlist_description if playlist_len == 1 else None,
                 'thumbnail': thumbnail,
                 'duration': duration,
                 'formats': formats,
                 'subtitles': subtitles,
+                'is_live': is_live,
             })
 
         return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)

youtube_dl/extractor/common.py

@@ -163,7 +163,7 @@ class InfoExtractor(object):
     description:    Full video description.
     uploader:       Full name of the video uploader.
     license:        License name the video is licensed under.
-    creator:        The main artist who created the video.
+    creator:        The creator of the video.
     release_date:   The date (YYYYMMDD) when the video was released.
     timestamp:      UNIX timestamp of the moment the video became available.
     upload_date:    Video upload date (YYYYMMDD).

youtube_dl/extractor/dailymail.py

@@ -0,0 +1,61 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    determine_protocol,
+)
+
+
+class DailyMailIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?dailymail\.co\.uk/video/[^/]+/video-(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.dailymail.co.uk/video/sciencetech/video-1288527/Turn-video-impressionist-masterpiece.html',
+        'md5': '2f639d446394f53f3a33658b518b6615',
+        'info_dict': {
+            'id': '1288527',
+            'ext': 'mp4',
+            'title': 'Turn any video into an impressionist masterpiece',
+            'description': 'md5:88ddbcb504367987b2708bb38677c9d2',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        video_data = self._parse_json(self._search_regex(
+            r"data-opts='({.+?})'", webpage, 'video data'), video_id)
+        title = video_data['title']
+        video_sources = self._download_json(video_data.get(
+            'sources', {}).get('url') or 'http://www.dailymail.co.uk/api/player/%s/video-sources.json' % video_id, video_id)
+
+        formats = []
+        for rendition in video_sources['renditions']:
+            rendition_url = rendition.get('url')
+            if not rendition_url:
+                continue
+            tbr = int_or_none(rendition.get('encodingRate'), 1000)
+            container = rendition.get('videoContainer')
+            is_hls = container == 'M2TS'
+            protocol = 'm3u8_native' if is_hls else determine_protocol({'url': rendition_url})
+            formats.append({
+                'format_id': ('hls' if is_hls else protocol) + ('-%d' % tbr if tbr else ''),
+                'url': rendition_url,
+                'width': int_or_none(rendition.get('frameWidth')),
+                'height': int_or_none(rendition.get('frameHeight')),
+                'tbr': tbr,
+                'vcodec': rendition.get('videoCodec'),
+                'container': container,
+                'protocol': protocol,
+                'ext': 'mp4' if is_hls else None,
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': video_data.get('descr'),
+            'thumbnail': video_data.get('poster') or video_data.get('thumbnail'),
+            'formats': formats,
+        }

youtube_dl/extractor/discovery.py

@@ -71,7 +71,7 @@ class DiscoveryIE(InfoExtractor):
         entries = []
 
         for idx, video_info in enumerate(info['playlist']):
-            subtitles = []
+            subtitles = {}
             caption_url = video_info.get('captionsUrl')
             if caption_url:
                 subtitles = {

youtube_dl/extractor/extractors.py

@@ -75,6 +75,7 @@ from .bigflix import BigflixIE
 from .bild import BildIE
 from .bilibili import BiliBiliIE
 from .biobiochiletv import BioBioChileTVIE
+from .biqle import BIQLEIE
 from .bleacherreport import (
     BleacherReportIE,
     BleacherReportCMSIE,
@@ -157,6 +158,7 @@ from .cspan import CSpanIE
 from .ctsnews import CtsNewsIE
 from .cultureunplugged import CultureUnpluggedIE
 from .cwtv import CWTVIE
+from .dailymail import DailyMailIE
 from .dailymotion import (
     DailymotionIE,
     DailymotionPlaylistIE,
@@ -382,6 +384,7 @@ from .limelight import (
     LimelightChannelIE,
     LimelightChannelListIE,
 )
+from .litv import LiTVIE
 from .liveleak import LiveLeakIE
 from .livestream import (
     LivestreamIE,
@@ -406,6 +409,10 @@ from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
 from .mgoon import MgoonIE
 from .mgtv import MGTVIE
+from .microsoftvirtualacademy import (
+    MicrosoftVirtualAcademyIE,
+    MicrosoftVirtualAcademyCourseIE,
+)
 from .minhateca import MinhatecaIE
 from .ministrygrid import MinistryGridIE
 from .minoto import MinotoIE
@@ -560,7 +567,10 @@ from .parliamentliveuk import ParliamentLiveUKIE
 from .patreon import PatreonIE
 from .pbs import PBSIE
 from .people import PeopleIE
-from .periscope import PeriscopeIE
+from .periscope import (
+    PeriscopeIE,
+    PeriscopeUserIE,
+)
 from .philharmoniedeparis import PhilharmonieDeParisIE
 from .phoenix import PhoenixIE
 from .photobucket import PhotobucketIE
@@ -724,7 +734,10 @@ from .svt import (
 from .swrmediathek import SWRMediathekIE
 from .syfy import SyfyIE
 from .sztvhu import SztvHuIE
-from .tagesschau import TagesschauIE
+from .tagesschau import (
+    TagesschauPlayerIE,
+    TagesschauIE,
+)
 from .tapely import TapelyIE
 from .tass import TassIE
 from .tdslifeway import TDSLifewayIE
@@ -846,7 +859,10 @@ from .veehd import VeeHDIE
 from .veoh import VeohIE
 from .vessel import VesselIE
 from .vesti import VestiIE
-from .vevo import VevoIE
+from .vevo import (
+    VevoIE,
+    VevoPlaylistIE,
+)
 from .vgtv import (
     BTArticleIE,
     BTVestlendingenIE,

youtube_dl/extractor/fczenit.py

@@ -1,20 +1,19 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
+from ..compat import compat_urlparse
 
 
 class FczenitIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?fc-zenit\.ru/video/gl(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?fc-zenit\.ru/video/(?P<id>[0-9]+)'
     _TEST = {
-        'url': 'http://fc-zenit.ru/video/gl6785/',
+        'url': 'http://fc-zenit.ru/video/41044/',
-        'md5': '458bacc24549173fe5a5aa29174a5606',
+        'md5': '0e3fab421b455e970fa1aa3891e57df0',
         'info_dict': {
-            'id': '6785',
+            'id': '41044',
             'ext': 'mp4',
-            'title': '«Зенит-ТВ»: как Олег Шатов играл против «Урала»',
+            'title': 'Так пишется история: казанский разгром ЦСКА на «Зенит-ТВ»',
         },
     }
 
@@ -22,15 +21,23 @@ class FczenitIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        video_title = self._html_search_regex(r'<div class=\"photoalbum__title\">([^<]+)', webpage, 'title')
+        video_title = self._html_search_regex(
+            r'<[^>]+class=\"photoalbum__title\">([^<]+)', webpage, 'title')
 
-        bitrates_raw = self._html_search_regex(r'bitrates:.*\n(.*)\]', webpage, 'video URL')
+        video_items = self._parse_json(self._search_regex(
-        bitrates = re.findall(r'url:.?\'(.+?)\'.*?bitrate:.?([0-9]{3}?)', bitrates_raw)
+            r'arrPath\s*=\s*JSON\.parse\(\'(.+)\'\)', webpage, 'video items'),
+            video_id)
+
+        def merge_dicts(*dicts):
+            ret = {}
+            for a_dict in dicts:
+                ret.update(a_dict)
+            return ret
 
         formats = [{
-            'url': furl,
+            'url': compat_urlparse.urljoin(url, video_url),
-            'tbr': tbr,
+            'tbr': int(tbr),
-        } for furl, tbr in bitrates]
+        } for tbr, video_url in merge_dicts(*video_items).items()]
 
         self._sort_formats(formats)
 

youtube_dl/extractor/flickr.py

@@ -24,13 +24,28 @@ class FlickrIE(InfoExtractor):
             'upload_date': '20110423',
             'uploader_id': '10922353@N03',
             'uploader': 'Forest Wander',
+            'uploader_url': 'https://www.flickr.com/photos/forestwander-nature-pictures/',
             'comment_count': int,
             'view_count': int,
             'tags': list,
+            'license': 'Attribution-ShareAlike',
         }
     }
-
     _API_BASE_URL = 'https://api.flickr.com/services/rest?'
+    # https://help.yahoo.com/kb/flickr/SLN25525.html
+    _LICENSES = {
+        '0': 'All Rights Reserved',
+        '1': 'Attribution-NonCommercial-ShareAlike',
+        '2': 'Attribution-NonCommercial',
+        '3': 'Attribution-NonCommercial-NoDerivs',
+        '4': 'Attribution',
+        '5': 'Attribution-ShareAlike',
+        '6': 'Attribution-NoDerivs',
+        '7': 'No known copyright restrictions',
+        '8': 'United States government work',
+        '9': 'Public Domain Dedication (CC0)',
+        '10': 'Public Domain Work',
+    }
 
     def _call_api(self, method, video_id, api_key, note, secret=None):
         query = {
@@ -75,6 +90,9 @@ class FlickrIE(InfoExtractor):
             self._sort_formats(formats)
 
             owner = video_info.get('owner', {})
+            uploader_id = owner.get('nsid')
+            uploader_path = owner.get('path_alias') or uploader_id
+            uploader_url = 'https://www.flickr.com/photos/%s/' % uploader_path if uploader_path else None
 
             return {
                 'id': video_id,
@@ -83,11 +101,13 @@ class FlickrIE(InfoExtractor):
                 '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_id': uploader_id,
                 'uploader': owner.get('realname'),
+                'uploader_url': uploader_url,
                 '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', [])]
+                'tags': [tag.get('_content') for tag in video_info.get('tags', {}).get('tag', [])],
+                'license': self._LICENSES.get(video_info.get('license')),
             }
         else:
             raise ExtractorError('not a video', expected=True)

youtube_dl/extractor/kuwo.py

@@ -283,6 +283,8 @@ class KuwoCategoryIE(InfoExtractor):
         category_desc = remove_start(
             get_element_by_id('intro', webpage).strip(),
             '%s简介：' % category_name)
+        if category_desc == '暂无':
+            category_desc = None
 
         jsonm = self._parse_json(self._html_search_regex(
             r'var\s+jsonm\s*=\s*([^;]+);', webpage, 'category songs'), category_id)

youtube_dl/extractor/litv.py

@@ -0,0 +1,137 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    smuggle_url,
+    unsmuggle_url,
+)
+
+
+class LiTVIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.litv\.tv/vod/[^/]+/content\.do\?.*?\bid=(?P<id>[^&]+)'
+
+    _URL_TEMPLATE = 'https://www.litv.tv/vod/%s/content.do?id=%s'
+
+    _TESTS = [{
+        'url': 'https://www.litv.tv/vod/drama/content.do?brc_id=root&id=VOD00041610&isUHEnabled=true&autoPlay=1',
+        'info_dict': {
+            'id': 'VOD00041606',
+            'title': '花千骨',
+        },
+        'playlist_count': 50,
+    }, {
+        'url': 'https://www.litv.tv/vod/drama/content.do?brc_id=root&id=VOD00041610&isUHEnabled=true&autoPlay=1',
+        'info_dict': {
+            'id': 'VOD00041610',
+            'ext': 'mp4',
+            'title': '花千骨第1集',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'description': 'md5:c7017aa144c87467c4fb2909c4b05d6f',
+            'episode_number': 1,
+        },
+        'params': {
+            'noplaylist': True,
+            'skip_download': True,  # m3u8 download
+        },
+        'skip': 'Georestricted to Taiwan',
+    }]
+
+    def _extract_playlist(self, season_list, video_id, vod_data, view_data, prompt=True):
+        episode_title = view_data['title']
+        content_id = season_list['contentId']
+
+        if prompt:
+            self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (content_id, video_id))
+
+        all_episodes = [
+            self.url_result(smuggle_url(
+                self._URL_TEMPLATE % (view_data['contentType'], episode['contentId']),
+                {'force_noplaylist': True}))  # To prevent infinite recursion
+            for episode in season_list['episode']]
+
+        return self.playlist_result(all_episodes, content_id, episode_title)
+
+    def _real_extract(self, url):
+        url, data = unsmuggle_url(url, {})
+
+        video_id = self._match_id(url)
+
+        noplaylist = self._downloader.params.get('noplaylist')
+        noplaylist_prompt = True
+        if 'force_noplaylist' in data:
+            noplaylist = data['force_noplaylist']
+            noplaylist_prompt = False
+
+        webpage = self._download_webpage(url, video_id)
+
+        view_data = dict(map(lambda t: (t[0], t[2]), re.findall(
+            r'viewData\.([a-zA-Z]+)\s*=\s*(["\'])([^"\']+)\2',
+            webpage)))
+
+        vod_data = self._parse_json(self._search_regex(
+            'var\s+vod\s*=\s*([^;]+)', webpage, 'VOD data', default='{}'),
+            video_id)
+
+        season_list = list(vod_data.get('seasonList', {}).values())
+        if season_list:
+            if not noplaylist:
+                return self._extract_playlist(
+                    season_list[0], video_id, vod_data, view_data,
+                    prompt=noplaylist_prompt)
+
+            if noplaylist_prompt:
+                self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
+
+        # In browsers `getMainUrl` request is always issued. Usually this
+        # endpoint gives the same result as the data embedded in the webpage.
+        # If georestricted, there are no embedded data, so an extra request is
+        # necessary to get the error code
+        video_data = self._parse_json(self._search_regex(
+            r'uiHlsUrl\s*=\s*testBackendData\(([^;]+)\);',
+            webpage, 'video data', default='{}'), video_id)
+        if not video_data:
+            payload = {
+                'assetId': view_data['assetId'],
+                'watchDevices': vod_data['watchDevices'],
+                'contentType': view_data['contentType'],
+            }
+            video_data = self._download_json(
+                'https://www.litv.tv/vod/getMainUrl', video_id,
+                data=json.dumps(payload).encode('utf-8'),
+                headers={'Content-Type': 'application/json'})
+
+        if not video_data.get('fullpath'):
+            error_msg = video_data.get('errorMessage')
+            if error_msg == 'vod.error.outsideregionerror':
+                self.raise_geo_restricted('This video is available in Taiwan only')
+            if error_msg:
+                raise ExtractorError('%s said: %s' % (self.IE_NAME, error_msg), expected=True)
+            raise ExtractorError('Unexpected result from %s' % self.IE_NAME)
+
+        formats = self._extract_m3u8_formats(
+            video_data['fullpath'], video_id, ext='mp4', m3u8_id='hls')
+        for a_format in formats:
+            # LiTV HLS segments doesn't like compressions
+            a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = True
+
+        title = view_data['title'] + view_data.get('secondaryMark', '')
+        description = view_data.get('description')
+        thumbnail = view_data.get('imageFile')
+        categories = [item['name'] for item in vod_data.get('category', [])]
+        episode = int_or_none(view_data.get('episode'))
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'categories': categories,
+            'episode_number': episode,
+        }

youtube_dl/extractor/liveleak.py

@@ -17,7 +17,8 @@ class LiveLeakIE(InfoExtractor):
             'ext': 'flv',
             'description': 'extremely bad day for this guy..!',
             'uploader': 'ljfriel2',
-            'title': 'Most unlucky car accident'
+            'title': 'Most unlucky car accident',
+            'thumbnail': 're:^https?://.*\.jpg$'
         }
     }, {
         'url': 'http://www.liveleak.com/view?i=f93_1390833151',
@@ -28,6 +29,7 @@ class LiveLeakIE(InfoExtractor):
             'description': 'German Television Channel NDR does an exclusive interview with Edward Snowden.\r\nUploaded on LiveLeak cause German Television thinks the rest of the world isn\'t intereseted in Edward Snowden.',
             'uploader': 'ARD_Stinkt',
             'title': 'German Television does first Edward Snowden Interview (ENGLISH)',
+            'thumbnail': 're:^https?://.*\.jpg$'
         }
     }, {
         'url': 'http://www.liveleak.com/view?i=4f7_1392687779',
@@ -49,7 +51,8 @@ class LiveLeakIE(InfoExtractor):
             'ext': 'mp4',
             'description': 'Happened on 27.7.2014. \r\nAt 0:53 you can see people still swimming at near beach.',
             'uploader': 'bony333',
-            'title': 'Crazy Hungarian tourist films close call waterspout in Croatia'
+            'title': 'Crazy Hungarian tourist films close call waterspout in Croatia',
+            'thumbnail': 're:^https?://.*\.jpg$'
         }
     }]
 
@@ -72,6 +75,7 @@ class LiveLeakIE(InfoExtractor):
         age_limit = int_or_none(self._search_regex(
             r'you confirm that you are ([0-9]+) years and over.',
             webpage, 'age limit', default=None))
+        video_thumbnail = self._og_search_thumbnail(webpage)
 
         sources_raw = self._search_regex(
             r'(?s)sources:\s*(\[.*?\]),', webpage, 'video URLs', default=None)
@@ -124,4 +128,5 @@ class LiveLeakIE(InfoExtractor):
             'uploader': video_uploader,
             'formats': formats,
             'age_limit': age_limit,
+            'thumbnail': video_thumbnail,
         }

youtube_dl/extractor/microsoftvirtualacademy.py

@@ -0,0 +1,192 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_xpath,
+)
+from ..utils import (
+    int_or_none,
+    parse_duration,
+    smuggle_url,
+    unsmuggle_url,
+    xpath_text,
+)
+
+
+class MicrosoftVirtualAcademyBaseIE(InfoExtractor):
+    def _extract_base_url(self, course_id, display_id):
+        return self._download_json(
+            'https://api-mlxprod.microsoft.com/services/products/anonymous/%s' % course_id,
+            display_id, 'Downloading course base URL')
+
+    def _extract_chapter_and_title(self, title):
+        if not title:
+            return None, None
+        m = re.search(r'(?P<chapter>\d+)\s*\|\s*(?P<title>.+)', title)
+        return (int(m.group('chapter')), m.group('title')) if m else (None, title)
+
+
+class MicrosoftVirtualAcademyIE(MicrosoftVirtualAcademyBaseIE):
+    IE_NAME = 'mva'
+    IE_DESC = 'Microsoft Virtual Academy videos'
+    _VALID_URL = r'(?:%s:|https?://(?:mva\.microsoft|(?:www\.)?microsoftvirtualacademy)\.com/[^/]+/training-courses/[^/?#&]+-)(?P<course_id>\d+)(?::|\?l=)(?P<id>[\da-zA-Z]+_\d+)' % IE_NAME
+
+    _TESTS = [{
+        'url': 'https://mva.microsoft.com/en-US/training-courses/microsoft-azure-fundamentals-virtual-machines-11788?l=gfVXISmEB_6804984382',
+        'md5': '7826c44fc31678b12ad8db11f6b5abb9',
+        'info_dict': {
+            'id': 'gfVXISmEB_6804984382',
+            'ext': 'mp4',
+            'title': 'Course Introduction',
+            'formats': 'mincount:3',
+            'subtitles': {
+                'en': [{
+                    'ext': 'ttml',
+                }],
+            },
+        }
+    }, {
+        'url': 'mva:11788:gfVXISmEB_6804984382',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
+
+        mobj = re.match(self._VALID_URL, url)
+        course_id = mobj.group('course_id')
+        video_id = mobj.group('id')
+
+        base_url = smuggled_data.get('base_url') or self._extract_base_url(course_id, video_id)
+
+        settings = self._download_xml(
+            '%s/content/content_%s/videosettings.xml?v=1' % (base_url, video_id),
+            video_id, 'Downloading video settings XML')
+
+        _, title = self._extract_chapter_and_title(xpath_text(
+            settings, './/Title', 'title', fatal=True))
+
+        formats = []
+
+        for sources in settings.findall(compat_xpath('.//MediaSources')):
+            if sources.get('videoType') == 'smoothstreaming':
+                continue
+            for source in sources.findall(compat_xpath('./MediaSource')):
+                video_url = source.text
+                if not video_url or not video_url.startswith('http'):
+                    continue
+                video_mode = source.get('videoMode')
+                height = int_or_none(self._search_regex(
+                    r'^(\d+)[pP]$', video_mode or '', 'height', default=None))
+                codec = source.get('codec')
+                acodec, vcodec = [None] * 2
+                if codec:
+                    codecs = codec.split(',')
+                    if len(codecs) == 2:
+                        acodec, vcodec = codecs
+                    elif len(codecs) == 1:
+                        vcodec = codecs[0]
+                formats.append({
+                    'url': video_url,
+                    'format_id': video_mode,
+                    'height': height,
+                    'acodec': acodec,
+                    'vcodec': vcodec,
+                })
+        self._sort_formats(formats)
+
+        subtitles = {}
+        for source in settings.findall(compat_xpath('.//MarkerResourceSource')):
+            subtitle_url = source.text
+            if not subtitle_url:
+                continue
+            subtitles.setdefault('en', []).append({
+                'url': '%s/%s' % (base_url, subtitle_url),
+                'ext': source.get('type'),
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'subtitles': subtitles,
+            'formats': formats
+        }
+
+
+class MicrosoftVirtualAcademyCourseIE(MicrosoftVirtualAcademyBaseIE):
+    IE_NAME = 'mva:course'
+    IE_DESC = 'Microsoft Virtual Academy courses'
+    _VALID_URL = r'(?:%s:|https?://(?:mva\.microsoft|(?:www\.)?microsoftvirtualacademy)\.com/[^/]+/training-courses/(?P<display_id>[^/?#&]+)-)(?P<id>\d+)' % IE_NAME
+
+    _TESTS = [{
+        'url': 'https://mva.microsoft.com/en-US/training-courses/microsoft-azure-fundamentals-virtual-machines-11788',
+        'info_dict': {
+            'id': '11788',
+            'title': 'Microsoft Azure Fundamentals: Virtual Machines',
+        },
+        'playlist_count': 36,
+    }, {
+        # with emphasized chapters
+        'url': 'https://mva.microsoft.com/en-US/training-courses/developing-windows-10-games-with-construct-2-16335',
+        'info_dict': {
+            'id': '16335',
+            'title': 'Developing Windows 10 Games with Construct 2',
+        },
+        'playlist_count': 10,
+    }, {
+        'url': 'https://www.microsoftvirtualacademy.com/en-US/training-courses/microsoft-azure-fundamentals-virtual-machines-11788',
+        'only_matching': True,
+    }, {
+        'url': 'mva:course:11788',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if MicrosoftVirtualAcademyIE.suitable(url) else super(
+            MicrosoftVirtualAcademyCourseIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        course_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        base_url = self._extract_base_url(course_id, display_id)
+
+        manifest = self._download_json(
+            '%s/imsmanifestlite.json' % base_url,
+            display_id, 'Downloading course manifest JSON')['manifest']
+
+        organization = manifest['organizations']['organization'][0]
+
+        entries = []
+        for chapter in organization['item']:
+            chapter_number, chapter_title = self._extract_chapter_and_title(chapter.get('title'))
+            chapter_id = chapter.get('@identifier')
+            for item in chapter.get('item', []):
+                item_id = item.get('@identifier')
+                if not item_id:
+                    continue
+                metadata = item.get('resource', {}).get('metadata') or {}
+                if metadata.get('learningresourcetype') != 'Video':
+                    continue
+                _, title = self._extract_chapter_and_title(item.get('title'))
+                duration = parse_duration(metadata.get('duration'))
+                description = metadata.get('description')
+                entries.append({
+                    '_type': 'url_transparent',
+                    'url': smuggle_url(
+                        'mva:%s:%s' % (course_id, item_id), {'base_url': base_url}),
+                    'title': title,
+                    'description': description,
+                    'duration': duration,
+                    'chapter': chapter_title,
+                    'chapter_number': chapter_number,
+                    'chapter_id': chapter_id,
+                })
+
+        title = organization.get('title') or manifest.get('metadata', {}).get('title')
+
+        return self.playlist_result(entries, course_id, title)

youtube_dl/extractor/periscope.py

@@ -7,6 +7,7 @@ from ..utils import parse_iso8601
 
 class PeriscopeIE(InfoExtractor):
     IE_DESC = 'Periscope'
+    IE_NAME = 'periscope'
     _VALID_URL = r'https?://(?:www\.)?periscope\.tv/[^/]+/(?P<id>[^/?#]+)'
     # Alive example URLs can be found here http://onperiscope.com/
     _TESTS = [{
@@ -79,3 +80,39 @@ class PeriscopeIE(InfoExtractor):
             'thumbnails': thumbnails,
             'formats': formats,
         }
+
+
+class PeriscopeUserIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.periscope\.tv/(?P<id>[^/]+)/?$'
+    IE_DESC = 'Periscope user videos'
+    IE_NAME = 'periscope:user'
+
+    _TEST = {
+        'url': 'https://www.periscope.tv/LularoeHusbandMike/',
+        'info_dict': {
+            'id': 'LularoeHusbandMike',
+            'title': 'LULAROE HUSBAND MIKE',
+        },
+        # Periscope only shows videos in the last 24 hours, so it's possible to
+        # get 0 videos
+        'playlist_mincount': 0,
+    }
+
+    def _real_extract(self, url):
+        user_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, user_id)
+
+        broadcast_data = self._parse_json(self._html_search_meta(
+            'broadcast-data', webpage, default='{}'), user_id)
+        username = broadcast_data.get('user', {}).get('display_name')
+        user_broadcasts = self._parse_json(
+            self._html_search_meta('user-broadcasts', webpage, default='{}'),
+            user_id)
+
+        entries = [
+            self.url_result(
+                'https://www.periscope.tv/%s/%s' % (user_id, broadcast['id']))
+            for broadcast in user_broadcasts.get('broadcasts', [])]
+
+        return self.playlist_result(entries, user_id, username)

youtube_dl/extractor/redtube.py

@@ -1,7 +1,12 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    str_to_int,
+    unified_strdate,
+)
 
 
 class RedTubeIE(InfoExtractor):
@@ -13,6 +18,9 @@ class RedTubeIE(InfoExtractor):
             'id': '66418',
             'ext': 'mp4',
             'title': 'Sucked on a toilet',
+            'upload_date': '20120831',
+            'duration': 596,
+            'view_count': int,
             'age_limit': 18,
         }
     }
@@ -24,12 +32,39 @@ class RedTubeIE(InfoExtractor):
         if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']):
             raise ExtractorError('Video %s has been removed' % video_id, expected=True)
 
-        video_url = self._html_search_regex(
+        title = self._html_search_regex(
-            r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL')
+            (r'<h1 class="videoTitle[^"]*">(?P<title>.+?)</h1>',
-        video_title = self._html_search_regex(
+             r'videoTitle\s*:\s*(["\'])(?P<title>)\1'),
-            r'<h1 class="videoTitle[^"]*">(.+?)</h1>',
+            webpage, 'title', group='title')
-            webpage, 'title')
+
-        video_thumbnail = self._og_search_thumbnail(webpage)
+        formats = []
+        sources = self._parse_json(
+            self._search_regex(
+                r'sources\s*:\s*({.+?})', webpage, 'source', default='{}'),
+            video_id, fatal=False)
+        if sources and isinstance(sources, dict):
+            for format_id, format_url in sources.items():
+                if format_url:
+                    formats.append({
+                        'url': format_url,
+                        'format_id': format_id,
+                        'height': int_or_none(format_id),
+                    })
+        else:
+            video_url = self._html_search_regex(
+                r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL')
+            formats.append({'url': video_url})
+        self._sort_formats(formats)
+
+        thumbnail = self._og_search_thumbnail(webpage)
+        upload_date = unified_strdate(self._search_regex(
+            r'<span[^>]+class="added-time"[^>]*>ADDED ([^<]+)<',
+            webpage, 'upload date', fatal=False))
+        duration = int_or_none(self._search_regex(
+            r'videoDuration\s*:\s*(\d+)', webpage, 'duration', fatal=False))
+        view_count = str_to_int(self._search_regex(
+            r'<span[^>]*>VIEWS</span></td>\s*<td>([\d,.]+)',
+            webpage, 'view count', fatal=False))
 
         # No self-labeling, but they describe themselves as
         # "Home of Videos Porno"
@@ -37,9 +72,12 @@ class RedTubeIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'url': video_url,
             'ext': 'mp4',
-            'title': video_title,
+            'title': title,
-            'thumbnail': video_thumbnail,
+            'thumbnail': thumbnail,
+            'upload_date': upload_date,
+            'duration': duration,
+            'view_count': view_count,
             'age_limit': age_limit,
+            'formats': formats,
         }

youtube_dl/extractor/tagesschau.py

@@ -4,42 +4,178 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import parse_filesize
+from ..utils import (
+    determine_ext,
+    js_to_json,
+    parse_iso8601,
+    parse_filesize,
+)
+
+
+class TagesschauPlayerIE(InfoExtractor):
+    IE_NAME = 'tagesschau:player'
+    _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/multimedia/(?P<kind>audio|video)/(?P=kind)-(?P<id>\d+)~player(?:_[^/?#&]+)?\.html'
+
+    _TESTS = [{
+        'url': 'http://www.tagesschau.de/multimedia/video/video-179517~player.html',
+        'md5': '8d09548d5c15debad38bee3a4d15ca21',
+        'info_dict': {
+            'id': '179517',
+            'ext': 'mp4',
+            'title': 'Marie Kristin Boese, ARD Berlin, über den zukünftigen Kurs der AfD',
+            'thumbnail': 're:^https?:.*\.jpg$',
+            'formats': 'mincount:6',
+        },
+    }, {
+        'url': 'https://www.tagesschau.de/multimedia/audio/audio-29417~player.html',
+        'md5': '76e6eec6ebd40740671cf0a2c88617e5',
+        'info_dict': {
+            'id': '29417',
+            'ext': 'mp3',
+            'title': 'Trabi - Bye, bye Rennpappe',
+            'thumbnail': 're:^https?:.*\.jpg$',
+            'formats': 'mincount:2',
+        },
+    }, {
+        'url': 'http://www.tagesschau.de/multimedia/audio/audio-29417~player_autoplay-true.html',
+        'only_matching': True,
+    }]
+
+    _FORMATS = {
+        'xs': {'quality': 0},
+        's': {'width': 320, 'height': 180, 'quality': 1},
+        'm': {'width': 512, 'height': 288, 'quality': 2},
+        'l': {'width': 960, 'height': 540, 'quality': 3},
+        'xl': {'width': 1280, 'height': 720, 'quality': 4},
+        'xxl': {'quality': 5},
+    }
+
+    def _extract_via_api(self, kind, video_id):
+        info = self._download_json(
+            'https://www.tagesschau.de/api/multimedia/{0}/{0}-{1}.json'.format(kind, video_id),
+            video_id)
+        title = info['headline']
+        formats = []
+        for media in info['mediadata']:
+            for format_id, format_url in media.items():
+                if determine_ext(format_url) == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        format_url, video_id, 'mp4',
+                        entry_protocol='m3u8_native', m3u8_id='hls'))
+                else:
+                    formats.append({
+                        'url': format_url,
+                        'format_id': format_id,
+                        'vcodec': 'none' if kind == 'audio' else None,
+                    })
+        self._sort_formats(formats)
+        timestamp = parse_iso8601(info.get('date'))
+        return {
+            'id': video_id,
+            'title': title,
+            'timestamp': timestamp,
+            'formats': formats,
+        }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        # kind = mobj.group('kind').lower()
+        # if kind == 'video':
+        #     return self._extract_via_api(kind, video_id)
+
+        # JSON api does not provide some audio formats (e.g. ogg) thus
+        # extractiong audio via webpage
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._og_search_title(webpage).strip()
+        formats = []
+
+        for media_json in re.findall(r'({src\s*:\s*["\']http[^}]+type\s*:[^}]+})', webpage):
+            media = self._parse_json(js_to_json(media_json), video_id, fatal=False)
+            if not media:
+                continue
+            src = media.get('src')
+            if not src:
+                return
+            quality = media.get('quality')
+            kind = media.get('type', '').split('/')[0]
+            ext = determine_ext(src)
+            f = {
+                'url': src,
+                'format_id': '%s_%s' % (quality, ext) if quality else ext,
+                'ext': ext,
+                'vcodec': 'none' if kind == 'audio' else None,
+            }
+            f.update(self._FORMATS.get(quality, {}))
+            formats.append(f)
+
+        self._sort_formats(formats)
+
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }
 
 
 class TagesschauIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/multimedia/(?:[^/]+/)*?[^/#?]+?(?P<id>-?[0-9]+)(?:~_?[^/#?]+?)?\.html'
+    _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/(?P<path>[^/]+/(?:[^/]+/)*?(?P<id>[^/#?]+?(?:-?[0-9]+)?))(?:~_?[^/#?]+?)?\.html'
 
     _TESTS = [{
         'url': 'http://www.tagesschau.de/multimedia/video/video-102143.html',
-        'md5': '917a228bc7df7850783bc47979673a09',
+        'md5': 'f7c27a0eff3bfe8c7727e65f8fe1b1e6',
         'info_dict': {
-            'id': '102143',
+            'id': 'video-102143',
             'ext': 'mp4',
             'title': 'Regierungsumbildung in Athen: Neue Minister in Griechenland vereidigt',
-            'description': 'md5:171feccd9d9b3dd54d05d501568f6359',
+            'description': '18.07.2015 20:10 Uhr',
             'thumbnail': 're:^https?:.*\.jpg$',
         },
     }, {
         'url': 'http://www.tagesschau.de/multimedia/sendung/ts-5727.html',
         'md5': '3c54c1f6243d279b706bde660ceec633',
         'info_dict': {
-            'id': '5727',
+            'id': 'ts-5727',
             'ext': 'mp4',
-            'description': 'md5:695c01bfd98b7e313c501386327aea59',
             'title': 'Sendung: tagesschau \t04.12.2014 20:00 Uhr',
+            'description': 'md5:695c01bfd98b7e313c501386327aea59',
             'thumbnail': 're:^https?:.*\.jpg$',
         },
     }, {
-        'url': 'http://www.tagesschau.de/multimedia/politikimradio/audio-18407.html',
+        # exclusive audio
-        'md5': 'aef45de271c4bf0a5db834aa40bf774c',
+        'url': 'http://www.tagesschau.de/multimedia/audio/audio-29417.html',
+        'md5': '76e6eec6ebd40740671cf0a2c88617e5',
         'info_dict': {
-            'id': '18407',
+            'id': 'audio-29417',
             'ext': 'mp3',
-            'title': 'Flüchtlingsdebatte: Hitzig, aber wenig hilfreich',
+            'title': 'Trabi - Bye, bye Rennpappe',
-            'description': 'Flüchtlingsdebatte: Hitzig, aber wenig hilfreich',
+            'description': 'md5:8687dda862cbbe2cfb2df09b56341317',
             'thumbnail': 're:^https?:.*\.jpg$',
         },
+    }, {
+        # audio in article
+        'url': 'http://www.tagesschau.de/inland/bnd-303.html',
+        'md5': 'e0916c623e85fc1d2b26b78f299d3958',
+        'info_dict': {
+            'id': 'bnd-303',
+            'ext': 'mp3',
+            'title': 'Viele Baustellen für neuen BND-Chef',
+            'description': 'md5:1e69a54be3e1255b2b07cdbce5bcd8b4',
+            'thumbnail': 're:^https?:.*\.jpg$',
+        },
+    }, {
+        'url': 'http://www.tagesschau.de/inland/afd-parteitag-135.html',
+        'info_dict': {
+            'id': 'afd-parteitag-135',
+            'title': 'Möchtegern-Underdog mit Machtanspruch',
+        },
+        'playlist_count': 2,
     }, {
         'url': 'http://www.tagesschau.de/multimedia/sendung/tsg-3771.html',
         'only_matching': True,
@@ -62,93 +198,107 @@ class TagesschauIE(InfoExtractor):
         'url': 'http://www.tagesschau.de/multimedia/video/video-102303~_bab-sendung-211.html',
         'only_matching': True,
     }, {
-        'url': 'http://www.tagesschau.de/multimedia/video/video-179517~player.html',
+        'url': 'http://www.tagesschau.de/100sekunden/index.html',
+        'only_matching': True,
+    }, {
+        # playlist article with collapsing sections
+        'url': 'http://www.tagesschau.de/wirtschaft/faq-freihandelszone-eu-usa-101.html',
         'only_matching': True,
     }]
 
-    _FORMATS = {
+    @classmethod
-        'xs': {'quality': 0},
+    def suitable(cls, url):
-        's': {'width': 320, 'height': 180, 'quality': 1},
+        return False if TagesschauPlayerIE.suitable(url) else super(TagesschauIE, cls).suitable(url)
-        'm': {'width': 512, 'height': 288, 'quality': 2},
+
-        'l': {'width': 960, 'height': 540, 'quality': 3},
+    def _extract_formats(self, download_text, media_kind):
-        'xl': {'width': 1280, 'height': 720, 'quality': 4},
+        links = re.finditer(
-        'xxl': {'quality': 5},
+            r'<div class="button" title="(?P<title>[^"]*)"><a href="(?P<url>[^"]+)">(?P<name>.+?)</a></div>',
-    }
+            download_text)
+        formats = []
+        for l in links:
+            link_url = l.group('url')
+            if not link_url:
+                continue
+            format_id = self._search_regex(
+                r'.*/[^/.]+\.([^/]+)\.[^/.]+$', link_url, 'format ID',
+                default=determine_ext(link_url))
+            format = {
+                'format_id': format_id,
+                'url': l.group('url'),
+                'format_name': l.group('name'),
+            }
+            title = l.group('title')
+            if title:
+                if media_kind.lower() == 'video':
+                    m = re.match(
+                        r'''(?x)
+                            Video:\s*(?P<vcodec>[a-zA-Z0-9/._-]+)\s*&\#10;
+                            (?P<width>[0-9]+)x(?P<height>[0-9]+)px&\#10;
+                            (?P<vbr>[0-9]+)kbps&\#10;
+                            Audio:\s*(?P<abr>[0-9]+)kbps,\s*(?P<audio_desc>[A-Za-z\.0-9]+)&\#10;
+                            Gr&ouml;&szlig;e:\s*(?P<filesize_approx>[0-9.,]+\s+[a-zA-Z]*B)''',
+                        title)
+                    if m:
+                        format.update({
+                            'format_note': m.group('audio_desc'),
+                            'vcodec': m.group('vcodec'),
+                            'width': int(m.group('width')),
+                            'height': int(m.group('height')),
+                            'abr': int(m.group('abr')),
+                            'vbr': int(m.group('vbr')),
+                            'filesize_approx': parse_filesize(m.group('filesize_approx')),
+                        })
+                else:
+                    m = re.match(
+                        r'(?P<format>.+?)-Format\s*:\s*(?P<abr>\d+)kbps\s*,\s*(?P<note>.+)',
+                        title)
+                    if m:
+                        format.update({
+                            'format_note': '%s, %s' % (m.group('format'), m.group('note')),
+                            'vcodec': 'none',
+                            'abr': int(m.group('abr')),
+                        })
+            formats.append(format)
+        self._sort_formats(formats)
+        return formats
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id') or mobj.group('path')
         display_id = video_id.lstrip('-')
+
         webpage = self._download_webpage(url, display_id)
 
-        player_url = self._html_search_meta(
+        title = self._html_search_regex(
-            'twitter:player', webpage, 'player URL', default=None)
+            r'<span[^>]*class="headline"[^>]*>(.+?)</span>',
-        if player_url:
+            webpage, 'title', default=None) or self._og_search_title(webpage)
-            playerpage = self._download_webpage(
-                player_url, display_id, 'Downloading player page')
 
-            formats = []
+        DOWNLOAD_REGEX = r'(?s)<p>Wir bieten dieses (?P<kind>Video|Audio) in folgenden Formaten zum Download an:</p>\s*<div class="controls">(?P<links>.*?)</div>\s*<p>'
-            for media in re.finditer(
+
-                    r'''(?x)
+        webpage_type = self._og_search_property('type', webpage, default=None)
-                        (?P<q_url>["\'])(?P<url>http://media.+?)(?P=q_url)
+        if webpage_type == 'website':  # Article
-                        ,\s*type:(?P<q_type>["\'])(?P<type>video|audio)/(?P<ext>.+?)(?P=q_type)
+            entries = []
-                        (?:,\s*quality:(?P<q_quality>["\'])(?P<quality>.+?)(?P=q_quality))?
+            for num, (entry_title, media_kind, download_text) in enumerate(re.findall(
-                    ''', playerpage):
+                    r'(?s)<p[^>]+class="infotext"[^>]*>\s*(?:<a[^>]+>)?\s*<strong>(.+?)</strong>.*?</p>.*?%s' % DOWNLOAD_REGEX,
-                url = media.group('url')
+                    webpage), 1):
-                type_ = media.group('type')
+                entries.append({
-                ext = media.group('ext')
+                    'id': '%s-%d' % (display_id, num),
-                res = media.group('quality')
+                    'title': '%s' % entry_title,
-                f = {
+                    'formats': self._extract_formats(download_text, media_kind),
-                    'format_id': '%s_%s' % (res, ext) if res else ext,
+                })
-                    'url': url,
+            if len(entries) > 1:
-                    'ext': ext,
+                return self.playlist_result(entries, display_id, title)
-                    'vcodec': 'none' if type_ == 'audio' else None,
+            formats = entries[0]['formats']
-                }
+        else:  # Assume single video
-                f.update(self._FORMATS.get(res, {}))
-                formats.append(f)
-            thumbnail = self._og_search_thumbnail(playerpage)
-            title = self._og_search_title(webpage).strip()
-            description = self._og_search_description(webpage).strip()
-        else:
             download_text = self._search_regex(
-                r'(?s)<p>Wir bieten dieses Video in folgenden Formaten zum Download an:</p>\s*<div class="controls">(.*?)</div>\s*<p>',
+                DOWNLOAD_REGEX, webpage, 'download links', group='links')
-                webpage, 'download links')
+            media_kind = self._search_regex(
-            links = re.finditer(
+                DOWNLOAD_REGEX, webpage, 'media kind', default='Video', group='kind')
-                r'<div class="button" title="(?P<title>[^"]*)"><a href="(?P<url>[^"]+)">(?P<name>.+?)</a></div>',
+            formats = self._extract_formats(download_text, media_kind)
-                download_text)
+        thumbnail = self._og_search_thumbnail(webpage)
-            formats = []
+        description = self._html_search_regex(
-            for l in links:
+            r'(?s)<p class="teasertext">(.*?)</p>',
-                format_id = self._search_regex(
+            webpage, 'description', default=None)
-                    r'.*/[^/.]+\.([^/]+)\.[^/.]+', l.group('url'), 'format ID')
-                format = {
-                    'format_id': format_id,
-                    'url': l.group('url'),
-                    'format_name': l.group('name'),
-                }
-                m = re.match(
-                    r'''(?x)
-                        Video:\s*(?P<vcodec>[a-zA-Z0-9/._-]+)\s*&\#10;
-                        (?P<width>[0-9]+)x(?P<height>[0-9]+)px&\#10;
-                        (?P<vbr>[0-9]+)kbps&\#10;
-                        Audio:\s*(?P<abr>[0-9]+)kbps,\s*(?P<audio_desc>[A-Za-z\.0-9]+)&\#10;
-                        Gr&ouml;&szlig;e:\s*(?P<filesize_approx>[0-9.,]+\s+[a-zA-Z]*B)''',
-                    l.group('title'))
-                if m:
-                    format.update({
-                        'format_note': m.group('audio_desc'),
-                        'vcodec': m.group('vcodec'),
-                        'width': int(m.group('width')),
-                        'height': int(m.group('height')),
-                        'abr': int(m.group('abr')),
-                        'vbr': int(m.group('vbr')),
-                        'filesize_approx': parse_filesize(m.group('filesize_approx')),
-                    })
-                formats.append(format)
-            thumbnail = self._og_search_thumbnail(webpage)
-            description = self._html_search_regex(
-                r'(?s)<p class="teasertext">(.*?)</p>',
-                webpage, 'description', default=None)
-            title = self._html_search_regex(
-                r'<span class="headline".*?>(.*?)</span>', webpage, 'title')
 
         self._sort_formats(formats)
 

youtube_dl/extractor/telegraaf.py

@@ -2,14 +2,16 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import remove_end
+from ..utils import (
+    determine_ext,
+    remove_end,
+)
 
 
 class TelegraafIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?telegraaf\.nl/tv/(?:[^/]+/)+(?P<id>\d+)/[^/]+\.html'
     _TEST = {
         'url': 'http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html',
-        'md5': '83245a9779bcc4a24454bfd53c65b6dc',
         'info_dict': {
             'id': '24353229',
             'ext': 'mp4',
@@ -18,18 +20,60 @@ class TelegraafIE(InfoExtractor):
             'thumbnail': 're:^https?://.*\.jpg$',
             'duration': 33,
         },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
     }
 
     def _real_extract(self, url):
-        playlist_id = self._match_id(url)
+        video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, playlist_id)
+        webpage = self._download_webpage(url, video_id)
 
+        player_url = self._html_search_regex(
+            r'<iframe[^>]+src="([^"]+")', webpage, 'player URL')
+        player_page = self._download_webpage(
+            player_url, video_id, note='Download player webpage')
         playlist_url = self._search_regex(
-            r"iframe\.loadPlayer\('([^']+)'", webpage, 'player')
+            r'playlist\s*:\s*"([^"]+)"', player_page, 'playlist URL')
+        playlist_data = self._download_json(playlist_url, video_id)
+
+        item = playlist_data['items'][0]
+        formats = []
+        locations = item['locations']
+        for location in locations.get('adaptive', []):
+            manifest_url = location['src']
+            ext = determine_ext(manifest_url)
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    manifest_url, video_id, ext='mp4', m3u8_id='hls'))
+            elif ext == 'mpd':
+                # TODO: Current DASH formats are broken - $Time$ pattern in
+                # <SegmentTemplate> not implemented yet
+                continue
+            else:
+                self.report_warning('Unknown adaptive format %s' % ext)
+        for location in locations.get('progressive', []):
+            formats.append({
+                'url': location['sources'][0]['src'],
+                'width': location.get('width'),
+                'height': location.get('height'),
+                'format_id': 'http-%s' % location['label'],
+            })
+
+        self._sort_formats(formats)
 
-        entries = self._extract_xspf_playlist(playlist_url, playlist_id)
         title = remove_end(self._og_search_title(webpage), ' - VIDEO')
         description = self._og_search_description(webpage)
+        duration = item.get('duration')
+        thumbnail = item.get('poster')
 
-        return self.playlist_result(entries, playlist_id, title, description)
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'formats': formats,
+            'duration': duration,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/udemy.py

@@ -5,7 +5,6 @@ import re
 from .common import InfoExtractor
 from ..compat import (
     compat_HTTPError,
-    compat_urllib_parse_urlencode,
     compat_urllib_request,
     compat_urlparse,
 )
@@ -84,18 +83,19 @@ class UdemyIE(InfoExtractor):
         if enroll_url:
             webpage = self._download_webpage(
                 combine_url(base_url, enroll_url),
-                course_id, 'Enrolling in the course')
+                course_id, 'Enrolling in the course',
+                headers={'Referer': base_url})
             if '>You have enrolled in' in webpage:
                 self.to_screen('%s: Successfully enrolled in the course' % course_id)
 
     def _download_lecture(self, course_id, lecture_id):
         return self._download_json(
-            'https://www.udemy.com/api-2.0/users/me/subscribed-courses/%s/lectures/%s?%s' % (
+            'https://www.udemy.com/api-2.0/users/me/subscribed-courses/%s/lectures/%s?'
-                course_id, lecture_id, compat_urllib_parse_urlencode({
+            % (course_id, lecture_id),
-                    'fields[lecture]': 'title,description,view_html,asset',
+            lecture_id, 'Downloading lecture JSON', query={
-                    'fields[asset]': 'asset_type,stream_url,thumbnail_url,download_urls,data',
+                'fields[lecture]': 'title,description,view_html,asset',
-                })),
+                'fields[asset]': 'asset_type,stream_url,thumbnail_url,download_urls,data',
-            lecture_id, 'Downloading lecture JSON')
+            })
 
     def _handle_error(self, response):
         if not isinstance(response, dict):
@@ -155,13 +155,13 @@ class UdemyIE(InfoExtractor):
             'password': password,
         })
 
-        request = sanitized_Request(
-            self._LOGIN_URL, urlencode_postdata(login_form))
-        request.add_header('Referer', self._ORIGIN_URL)
-        request.add_header('Origin', self._ORIGIN_URL)
-
         response = self._download_webpage(
-            request, None, 'Logging in as %s' % username)
+            self._LOGIN_URL, None, 'Logging in as %s' % username,
+            data=urlencode_postdata(login_form),
+            headers={
+                'Referer': self._ORIGIN_URL,
+                'Origin': self._ORIGIN_URL,
+            })
 
         if not is_logged(response):
             error = self._html_search_regex(

youtube_dl/extractor/vevo.py

@@ -3,7 +3,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_etree_fromstring
+from ..compat import (
+    compat_etree_fromstring,
+    compat_str,
+    compat_urlparse,
+)
 from ..utils import (
     ExtractorError,
     int_or_none,
@@ -12,13 +16,22 @@ from ..utils import (
 )
 
 
-class VevoIE(InfoExtractor):
+class VevoBaseIE(InfoExtractor):
+    def _extract_json(self, webpage, video_id, item):
+        return self._parse_json(
+            self._search_regex(
+                r'window\.__INITIAL_STORE__\s*=\s*({.+?});\s*</script>',
+                webpage, 'initial store'),
+            video_id)['default'][item]
+
+
+class VevoIE(VevoBaseIE):
     '''
     Accepts urls from vevo.com or in the format 'vevo:{id}'
     (currently used by MTVIE and MySpaceIE)
     '''
     _VALID_URL = r'''(?x)
-        (?:https?://www\.vevo\.com/watch/(?:[^/]+/(?:[^/]+/)?)?|
+        (?:https?://www\.vevo\.com/watch/(?!playlist|genre)(?:[^/]+/(?:[^/]+/)?)?|
            https?://cache\.vevo\.com/m/html/embed\.html\?video=|
            https?://videoplayer\.vevo\.com/embed/embedded\?videoId=|
            vevo:)
@@ -30,11 +43,15 @@ class VevoIE(InfoExtractor):
         'info_dict': {
             'id': 'GB1101300280',
             'ext': 'mp4',
-            'title': 'Somebody to Die For',
+            'title': 'Hurts - Somebody to Die For',
+            'timestamp': 1372057200,
             'upload_date': '20130624',
             'uploader': 'Hurts',
-            'timestamp': 1372057200,
+            'track': 'Somebody to Die For',
+            'artist': 'Hurts',
+            'genre': 'Pop',
         },
+        'expected_warnings': ['Unable to download SMIL file'],
     }, {
         'note': 'v3 SMIL format',
         'url': 'http://www.vevo.com/watch/cassadee-pope/i-wish-i-could-break-your-heart/USUV71302923',
@@ -42,23 +59,31 @@ class VevoIE(InfoExtractor):
         'info_dict': {
             'id': 'USUV71302923',
             'ext': 'mp4',
-            'title': 'I Wish I Could Break Your Heart',
+            'title': 'Cassadee Pope - I Wish I Could Break Your Heart',
+            'timestamp': 1392796919,
             'upload_date': '20140219',
             'uploader': 'Cassadee Pope',
-            'timestamp': 1392796919,
+            'track': 'I Wish I Could Break Your Heart',
+            'artist': 'Cassadee Pope',
+            'genre': 'Country',
         },
+        'expected_warnings': ['Unable to download SMIL file'],
     }, {
         'note': 'Age-limited video',
         'url': 'https://www.vevo.com/watch/justin-timberlake/tunnel-vision-explicit/USRV81300282',
         'info_dict': {
             'id': 'USRV81300282',
             'ext': 'mp4',
-            'title': 'Tunnel Vision (Explicit)',
+            'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
-            'upload_date': '20130703',
             'age_limit': 18,
-            'uploader': 'Justin Timberlake',
             'timestamp': 1372888800,
+            'upload_date': '20130703',
+            'uploader': 'Justin Timberlake',
+            'track': 'Tunnel Vision (Explicit)',
+            'artist': 'Justin Timberlake',
+            'genre': 'Pop',
         },
+        'expected_warnings': ['Unable to download SMIL file'],
     }, {
         'note': 'No video_info',
         'url': 'http://www.vevo.com/watch/k-camp-1/Till-I-Die/USUV71503000',
@@ -66,12 +91,36 @@ class VevoIE(InfoExtractor):
         'info_dict': {
             'id': 'USUV71503000',
             'ext': 'mp4',
-            'title': 'Till I Die',
+            'title': 'K Camp - Till I Die',
-            'upload_date': '20151207',
             'age_limit': 18,
-            'uploader': 'K Camp',
             'timestamp': 1449468000,
+            'upload_date': '20151207',
+            'uploader': 'K Camp',
+            'track': 'Till I Die',
+            'artist': 'K Camp',
+            'genre': 'Rap/Hip-Hop',
         },
+    }, {
+        'note': 'Only available via webpage',
+        'url': 'http://www.vevo.com/watch/GBUV71600656',
+        'md5': '67e79210613865b66a47c33baa5e37fe',
+        'info_dict': {
+            'id': 'GBUV71600656',
+            'ext': 'mp4',
+            'title': 'ABC - Viva Love',
+            'age_limit': 0,
+            'timestamp': 1461830400,
+            'upload_date': '20160428',
+            'uploader': 'ABC',
+            'track': 'Viva Love',
+            'artist': 'ABC',
+            'genre': 'Pop',
+        },
+        'expected_warnings': ['Failed to download video versions info'],
+    }, {
+        # no genres available
+        'url': 'http://www.vevo.com/watch/INS171400764',
+        'only_matching': True,
     }]
     _SMIL_BASE_URL = 'http://smil.lvl3.vevo.com'
     _SOURCE_TYPES = {
@@ -140,30 +189,31 @@ class VevoIE(InfoExtractor):
             errnote='Unable to retrieve oauth token')
 
         if 'THIS PAGE IS CURRENTLY UNAVAILABLE IN YOUR REGION' in webpage:
-            raise ExtractorError(
+            self.raise_geo_restricted(
-                '%s said: This page is currently unavailable in your region.' % self.IE_NAME, expected=True)
+                '%s said: This page is currently unavailable in your region' % self.IE_NAME)
 
         auth_info = self._parse_json(webpage, video_id)
         self._api_url_template = self.http_scheme() + '//apiv2.vevo.com/%s?token=' + auth_info['access_token']
 
-    def _call_api(self, path, video_id, note, errnote, fatal=True):
+    def _call_api(self, path, *args, **kwargs):
-        return self._download_json(self._api_url_template % path, video_id, note, errnote)
+        return self._download_json(self._api_url_template % path, *args, **kwargs)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         json_url = 'http://api.vevo.com/VideoService/AuthenticateVideo?isrc=%s' % video_id
         response = self._download_json(
-            json_url, video_id, 'Downloading video info', 'Unable to download info')
+            json_url, video_id, 'Downloading video info',
+            'Unable to download info', fatal=False) or {}
         video_info = response.get('video') or {}
-        video_versions = video_info.get('videoVersions')
+        artist = None
+        featured_artist = None
         uploader = None
-        timestamp = None
         view_count = None
         formats = []
 
         if not video_info:
-            if response.get('statusCode') != 909:
+            if response and response.get('statusCode') != 909:
                 ytid = response.get('errorInfo', {}).get('ytid')
                 if ytid:
                     self.report_warning(
@@ -183,12 +233,19 @@ class VevoIE(InfoExtractor):
             video_versions = self._call_api(
                 'video/%s/streams' % video_id, video_id,
                 'Downloading video versions info',
-                'Failed to download video versions info')
+                'Failed to download video versions info',
+                fatal=False)
+
+            # Some videos are only available via webpage (e.g.
+            # https://github.com/rg3/youtube-dl/issues/9366)
+            if not video_versions:
+                webpage = self._download_webpage(url, video_id)
+                video_versions = self._extract_json(webpage, video_id, 'streams')[video_id][0]
 
             timestamp = parse_iso8601(video_info.get('releaseDate'))
             artists = video_info.get('artists')
             if artists:
-                uploader = artists[0]['name']
+                artist = uploader = artists[0]['name']
             view_count = int_or_none(video_info.get('views', {}).get('total'))
 
             for video_version in video_versions:
@@ -241,7 +298,11 @@ class VevoIE(InfoExtractor):
                 scale=1000)
             artists = video_info.get('mainArtists')
             if artists:
-                uploader = artists[0]['artistName']
+                artist = uploader = artists[0]['artistName']
+
+            featured_artists = video_info.get('featuredArtists')
+            if featured_artists:
+                featured_artist = featured_artists[0]['artistName']
 
             smil_parsed = False
             for video_version in video_info['videoVersions']:
@@ -278,7 +339,15 @@ class VevoIE(InfoExtractor):
                         smil_parsed = True
         self._sort_formats(formats)
 
-        title = video_info['title']
+        track = video_info['title']
+        if featured_artist:
+            artist = '%s ft. %s' % (artist, featured_artist)
+        title = '%s - %s' % (artist, track) if artist else track
+
+        genres = video_info.get('genres')
+        genre = (
+            genres[0] if genres and isinstance(genres, list) and
+            isinstance(genres[0], compat_str) else None)
 
         is_explicit = video_info.get('isExplicit')
         if is_explicit is True:
@@ -300,4 +369,75 @@ class VevoIE(InfoExtractor):
             'duration': duration,
             'view_count': view_count,
             'age_limit': age_limit,
+            'track': track,
+            'artist': uploader,
+            'genre': genre,
         }
+
+
+class VevoPlaylistIE(VevoBaseIE):
+    _VALID_URL = r'https?://www\.vevo\.com/watch/(?P<kind>playlist|genre)/(?P<id>[^/?#&]+)'
+
+    _TESTS = [{
+        'url': 'http://www.vevo.com/watch/playlist/dadbf4e7-b99f-4184-9670-6f0e547b6a29',
+        'info_dict': {
+            'id': 'dadbf4e7-b99f-4184-9670-6f0e547b6a29',
+            'title': 'Best-Of: Birdman',
+        },
+        'playlist_count': 10,
+    }, {
+        'url': 'http://www.vevo.com/watch/genre/rock',
+        'info_dict': {
+            'id': 'rock',
+            'title': 'Rock',
+        },
+        'playlist_count': 20,
+    }, {
+        'url': 'http://www.vevo.com/watch/playlist/dadbf4e7-b99f-4184-9670-6f0e547b6a29?index=0',
+        'md5': '32dcdfddddf9ec6917fc88ca26d36282',
+        'info_dict': {
+            'id': 'USCMV1100073',
+            'ext': 'mp4',
+            'title': 'Birdman - Y.U. MAD',
+            'timestamp': 1323417600,
+            'upload_date': '20111209',
+            'uploader': 'Birdman',
+            'track': 'Y.U. MAD',
+            'artist': 'Birdman',
+            'genre': 'Rap/Hip-Hop',
+        },
+        'expected_warnings': ['Unable to download SMIL file'],
+    }, {
+        'url': 'http://www.vevo.com/watch/genre/rock?index=0',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        playlist_id = mobj.group('id')
+        playlist_kind = mobj.group('kind')
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
+        index = qs.get('index', [None])[0]
+
+        if index:
+            video_id = self._search_regex(
+                r'<meta[^>]+content=(["\'])vevo://video/(?P<id>.+?)\1[^>]*>',
+                webpage, 'video id', default=None, group='id')
+            if video_id:
+                return self.url_result('vevo:%s' % video_id, VevoIE.ie_key())
+
+        playlists = self._extract_json(webpage, playlist_id, '%ss' % playlist_kind)
+
+        playlist = (list(playlists.values())[0]
+                    if playlist_kind == 'playlist' else playlists[playlist_id])
+
+        entries = [
+            self.url_result('vevo:%s' % src, VevoIE.ie_key())
+            for src in playlist['isrcs']]
+
+        return self.playlist_result(
+            entries, playlist.get('playlistId') or playlist_id,
+            playlist.get('name'), playlist.get('description'))

youtube_dl/extractor/vk.py

@@ -26,12 +26,16 @@ class VKIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                     https?://
                         (?:
-                            (?:m\.)?vk\.com/video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|
+                            (?:
+                                (?:m\.)?vk\.com/video_|
+                                (?:www\.)?daxab.com/
+                            )
+                            ext\.php\?(?P<embed_query>.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+).*)|
                             (?:
                                 (?:m\.)?vk\.com/(?:.+?\?.*?z=)?video|
-                                (?:www\.)?biqle\.ru/watch/
+                                (?:www\.)?daxab.com/embed/
                             )
-                            (?P<videoid>[^s].*?)(?:\?(?:.*\blist=(?P<list_id>[\da-f]+))?|%2F|$)
+                            (?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>[\da-f]+))?
                         )
                     '''
     _NETRC_MACHINE = 'vk'
@@ -75,7 +79,8 @@ class VKIE(InfoExtractor):
                 'duration': 101,
                 'upload_date': '20120730',
                 'view_count': int,
-            }
+            },
+            'skip': 'This video has been removed from public access.',
         },
         {
             # VIDEO NOW REMOVED
@@ -142,7 +147,7 @@ class VKIE(InfoExtractor):
                 'id': 'V3K4mi0SYkc',
                 'ext': 'webm',
                 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
-                'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',
+                'description': 'md5:d9903938abdc74c738af77f527ca0596',
                 'duration': 178,
                 'upload_date': '20130116',
                 'uploader': "Children's Joy Foundation",
@@ -173,11 +178,6 @@ class VKIE(InfoExtractor):
             'url': 'https://vk.com/video205387401_164765225',
             'only_matching': True,
         },
-        {
-            # vk wrapper
-            'url': 'http://www.biqle.ru/watch/847655_160197695',
-            'only_matching': True,
-        },
         {
             # pladform embed
             'url': 'https://vk.com/video-76116461_171554880',
@@ -217,20 +217,22 @@ class VKIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('videoid')
 
-        if not video_id:
+        info_url = url
+        if video_id:
+            info_url = 'https://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
+            # Some videos (removed?) can only be downloaded with list id specified
+            list_id = mobj.group('list_id')
+            if list_id:
+                info_url += '&list=%s' % list_id
+        else:
+            info_url = 'http://vk.com/video_ext.php?' + mobj.group('embed_query')
             video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
 
-        info_url = 'https://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
-
-        # Some videos (removed?) can only be downloaded with list id specified
-        list_id = mobj.group('list_id')
-        if list_id:
-            info_url += '&list=%s' % list_id
-
         info_page = self._download_webpage(info_url, video_id)
 
         error_message = self._html_search_regex(
-            r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
+            [r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
+                r'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'],
             info_page, 'error message', default=None)
         if error_message:
             raise ExtractorError(error_message, expected=True)
@@ -305,17 +307,17 @@ class VKIE(InfoExtractor):
         view_count = None
         views = self._html_search_regex(
             r'"mv_views_count_number"[^>]*>(.+?\bviews?)<',
-            info_page, 'view count', fatal=False)
+            info_page, 'view count', default=None)
         if views:
             view_count = str_to_int(self._search_regex(
                 r'([\d,.]+)', views, 'view count', fatal=False))
 
         formats = []
         for k, v in data.items():
-            if not k.startswith('url') and k != 'extra_data' or not v:
+            if not k.startswith('url') and not k.startswith('cache') and k != 'extra_data' or not v:
                 continue
             height = int_or_none(self._search_regex(
-                r'^url(\d+)', k, 'height', default=None))
+                r'^(?:url|cache)(\d+)', k, 'height', default=None))
             formats.append({
                 'format_id': k,
                 'url': v,

youtube_dl/extractor/xfileshare.py

@@ -13,12 +13,21 @@ from ..utils import (
 
 
 class XFileShareIE(InfoExtractor):
-    IE_DESC = 'XFileShare based sites: GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net, filehoot.com and vidto.me'
+    _SITES = (
-    _VALID_URL = r'''(?x)
+        ('daclips.in', 'DaClips'),
-        https?://(?P<host>(?:www\.)?
+        ('filehoot.com', 'FileHoot'),
-            (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in|realvid\.net|filehoot\.com|vidto\.me|powerwatch\.pw))/
+        ('gorillavid.in', 'GorillaVid'),
-        (?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?
+        ('movpod.in', 'MovPod'),
-    '''
+        ('powerwatch.pw', 'PowerWatch'),
+        ('rapidvideo.ws', 'Rapidvideo.ws'),
+        ('thevideobee.to', 'TheVideoBee'),
+        ('vidto.me', 'Vidto'),
+        ('streamin.to', 'Streamin.To'),
+    )
+
+    IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1])
+    _VALID_URL = (r'https?://(?P<host>(?:www\.)?(?:%s))/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
+                  % '|'.join(re.escape(site) for site in list(zip(*_SITES))[0]))
 
     _FILE_NOT_FOUND_REGEX = r'>(?:404 - )?File Not Found<'
 
@@ -43,25 +52,6 @@ class XFileShareIE(InfoExtractor):
             'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
             'thumbnail': 're:http://.*\.jpg',
         }
-    }, {
-        # video with countdown timeout
-        'url': 'http://fastvideo.in/1qmdn1lmsmbw',
-        'md5': '8b87ec3f6564a3108a0e8e66594842ba',
-        'info_dict': {
-            'id': '1qmdn1lmsmbw',
-            'ext': 'mp4',
-            'title': 'Man of Steel - Trailer',
-            'thumbnail': 're:http://.*\.jpg',
-        },
-    }, {
-        'url': 'http://realvid.net/ctn2y6p2eviw',
-        'md5': 'b2166d2cf192efd6b6d764c18fd3710e',
-        'info_dict': {
-            'id': 'ctn2y6p2eviw',
-            'ext': 'flv',
-            'title': 'rdx 1955',
-            'thumbnail': 're:http://.*\.jpg',
-        },
     }, {
         'url': 'http://movpod.in/0wguyyxi1yca',
         'only_matching': True,

youtube_dl/extractor/xiami.py

@@ -9,6 +9,11 @@ from ..utils import int_or_none
 class XiamiBaseIE(InfoExtractor):
     _API_BASE_URL = 'http://www.xiami.com/song/playlist/cat/json/id'
 
+    def _download_webpage(self, *args, **kwargs):
+        webpage = super(XiamiBaseIE, self)._download_webpage(*args, **kwargs)
+        if '>Xiami is currently not available in your country.<' in webpage:
+            self.raise_geo_restricted('Xiami is currently not available in your country')
+
     def _extract_track(self, track, track_id=None):
         title = track['title']
         track_url = self._decrypt(track['location'])
@@ -81,7 +86,8 @@ class XiamiSongIE(XiamiBaseIE):
                     'ext': 'lrc',
                 }],
             },
-        }
+        },
+        'skip': 'Georestricted',
     }, {
         'url': 'http://www.xiami.com/song/1775256504',
         'md5': '932a3abd45c6aa2b1fdbe028fcb4c4fc',
@@ -100,7 +106,8 @@ class XiamiSongIE(XiamiBaseIE):
                     'ext': 'lrc',
                 }],
             },
-        }
+        },
+        'skip': 'Georestricted',
     }]
 
     def _real_extract(self, url):
@@ -124,6 +131,7 @@ class XiamiAlbumIE(XiamiPlaylistBaseIE):
             'id': '2100300444',
         },
         'playlist_count': 10,
+        'skip': 'Georestricted',
     }, {
         'url': 'http://www.xiami.com/album/512288?spm=a1z1s.6843761.1110925389.6.hhE9p9',
         'only_matching': True,
@@ -141,6 +149,7 @@ class XiamiArtistIE(XiamiPlaylistBaseIE):
             'id': '2132',
         },
         'playlist_count': 20,
+        'skip': 'Georestricted',
     }
 
 
@@ -155,4 +164,5 @@ class XiamiCollectionIE(XiamiPlaylistBaseIE):
             'id': '156527391',
         },
         'playlist_mincount': 29,
+        'skip': 'Georestricted',
     }

youtube_dl/extractor/yandexmusic.py

@@ -10,8 +10,6 @@ from ..utils import (
     ExtractorError,
     int_or_none,
     float_or_none,
-    sanitized_Request,
-    urlencode_postdata,
 )
 
 
@@ -177,7 +175,7 @@ class YandexMusicAlbumIE(YandexMusicPlaylistBaseIE):
 class YandexMusicPlaylistIE(YandexMusicPlaylistBaseIE):
     IE_NAME = 'yandexmusic:playlist'
     IE_DESC = 'Яндекс.Музыка - Плейлист'
-    _VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/users/[^/]+/playlists/(?P<id>\d+)'
+    _VALID_URL = r'https?://music\.yandex\.(?P<tld>ru|kz|ua|by)/users/(?P<user>[^/]+)/playlists/(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://music.yandex.ru/users/music.partners/playlists/1245',
@@ -196,47 +194,64 @@ class YandexMusicPlaylistIE(YandexMusicPlaylistBaseIE):
             'id': '1036',
             'title': 'Музыка 90-х',
         },
-        'playlist_count': 310,
+        'playlist_mincount': 300,
         'skip': 'Travis CI servers blocked by YandexMusic',
     }]
 
     def _real_extract(self, url):
-        playlist_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        tld = mobj.group('tld')
+        user = mobj.group('user')
+        playlist_id = mobj.group('id')
 
-        webpage = self._download_webpage(url, playlist_id)
+        playlist = self._download_json(
+            'https://music.yandex.%s/handlers/playlist.jsx' % tld,
+            playlist_id, 'Downloading missing tracks JSON',
+            fatal=False,
+            headers={
+                'Referer': url,
+                'X-Requested-With': 'XMLHttpRequest',
+                'X-Retpath-Y': url,
+            },
+            query={
+                'owner': user,
+                'kinds': playlist_id,
+                'light': 'true',
+                'lang': tld,
+                'external-domain': 'music.yandex.%s' % tld,
+                'overembed': 'false',
+            })['playlist']
 
-        mu = self._parse_json(
+        tracks, track_ids = playlist['tracks'], map(compat_str, playlist['trackIds'])
-            self._search_regex(
-                r'var\s+Mu\s*=\s*({.+?});\s*</script>', webpage, 'player'),
-            playlist_id)
 
-        playlist = mu['pageData']['playlist']
+        # tracks dictionary shipped with playlist.jsx API is limited to 150 tracks,
-        tracks, track_ids = playlist['tracks'], playlist['trackIds']
-
-        # tracks dictionary shipped with webpage is limited to 150 tracks,
         # missing tracks should be retrieved manually.
         if len(tracks) < len(track_ids):
-            present_track_ids = set([compat_str(track['id']) for track in tracks if track.get('id')])
+            present_track_ids = set([
-            missing_track_ids = set(map(compat_str, track_ids)) - set(present_track_ids)
+                compat_str(track['id'])
-            request = sanitized_Request(
+                for track in tracks if track.get('id')])
-                'https://music.yandex.ru/handlers/track-entries.jsx',
+            missing_track_ids = [
-                urlencode_postdata({
+                track_id for track_id in track_ids
-                    'entries': ','.join(missing_track_ids),
+                if track_id not in present_track_ids]
-                    'lang': mu.get('settings', {}).get('lang', 'en'),
-                    'external-domain': 'music.yandex.ru',
-                    'overembed': 'false',
-                    'sign': mu.get('authData', {}).get('user', {}).get('sign'),
-                    'strict': 'true',
-                }))
-            request.add_header('Referer', url)
-            request.add_header('X-Requested-With', 'XMLHttpRequest')
-
             missing_tracks = self._download_json(
-                request, playlist_id, 'Downloading missing tracks JSON', fatal=False)
+                'https://music.yandex.%s/handlers/track-entries.jsx' % tld,
+                playlist_id, 'Downloading missing tracks JSON',
+                fatal=False,
+                headers={
+                    'Referer': url,
+                    'X-Requested-With': 'XMLHttpRequest',
+                },
+                query={
+                    'entries': ','.join(missing_track_ids),
+                    'lang': tld,
+                    'external-domain': 'music.yandex.%s' % tld,
+                    'overembed': 'false',
+                    'strict': 'true',
+                })
             if missing_tracks:
                 tracks.extend(missing_tracks)
 
         return self.playlist_result(
             self._build_playlist(tracks),
             compat_str(playlist_id),
-            playlist['title'], playlist.get('description'))
+            playlist.get('title'), playlist.get('description'))

youtube_dl/extractor/youtube.py

@@ -1326,9 +1326,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         if video_description:
             video_description = re.sub(r'''(?x)
                 <a\s+
-                    (?:[a-zA-Z-]+="[^"]+"\s+)*?
+                    (?:[a-zA-Z-]+="[^"]*"\s+)*?
                     (?:title|href)="([^"]+)"\s+
-                    (?:[a-zA-Z-]+="[^"]+"\s+)*?
+                    (?:[a-zA-Z-]+="[^"]*"\s+)*?
                     class="(?:yt-uix-redirect-link|yt-uix-sessionlink[^"]*)"[^>]*>
                 [^<]+\.{3}\s*
                 </a>

youtube_dl/postprocessor/ffmpeg.py

@@ -389,23 +389,30 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
 class FFmpegMetadataPP(FFmpegPostProcessor):
     def run(self, info):
         metadata = {}
-        if info.get('title') is not None:
+
-            metadata['title'] = info['title']
+        def add(meta_list, info_list=None):
-        if info.get('upload_date') is not None:
+            if not info_list:
-            metadata['date'] = info['upload_date']
+                info_list = meta_list
-        if info.get('artist') is not None:
+            if not isinstance(meta_list, (list, tuple)):
-            metadata['artist'] = info['artist']
+                meta_list = (meta_list,)
-        elif info.get('uploader') is not None:
+            if not isinstance(info_list, (list, tuple)):
-            metadata['artist'] = info['uploader']
+                info_list = (info_list,)
-        elif info.get('uploader_id') is not None:
+            for info_f in info_list:
-            metadata['artist'] = info['uploader_id']
+                if info.get(info_f) is not None:
-        if info.get('description') is not None:
+                    for meta_f in meta_list:
-            metadata['description'] = info['description']
+                        metadata[meta_f] = info[info_f]
-            metadata['comment'] = info['description']
+                    break
-        if info.get('webpage_url') is not None:
+
-            metadata['purl'] = info['webpage_url']
+        add('title', ('track', 'title'))
-        if info.get('album') is not None:
+        add('date', 'upload_date')
-            metadata['album'] = info['album']
+        add(('description', 'comment'), 'description')
+        add('purl', 'webpage_url')
+        add('track', 'track_number')
+        add('artist', ('artist', 'creator', 'uploader', 'uploader_id'))
+        add('genre')
+        add('album')
+        add('album_artist')
+        add('disc', 'disc_number')
 
         if not metadata:
             self._downloader.to_screen('[ffmpeg] There isn\'t any metadata to add')

youtube_dl/utils.py

@@ -14,8 +14,8 @@ import email.utils
 import errno
 import functools
 import gzip
-import itertools
 import io
+import itertools
 import json
 import locale
 import math
@@ -24,8 +24,8 @@ import os
 import pipes
 import platform
 import re
-import ssl
 import socket
+import ssl
 import struct
 import subprocess
 import sys
@@ -89,6 +89,11 @@ KNOWN_EXTENSIONS = (
     'wav',
     'f4f', 'f4m', 'm3u8', 'smil')
 
+# needed for sanitizing filenames in restricted mode
+ACCENT_CHARS = dict(zip('ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ',
+                        itertools.chain('AAAAAA', ['AE'], 'CEEEEIIIIDNOOOOOOUUUUYP', ['ss'],
+                                        'aaaaaa', ['ae'], 'ceeeeiiiionoooooouuuuypy')))
+
 
 def preferredencoding():
     """Get preferred encoding.
@@ -251,9 +256,9 @@ def get_element_by_attribute(attribute, value, html):
 
     m = re.search(r'''(?xs)
         <([a-zA-Z0-9:._-]+)
-         (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]+|="[^"]+"|='[^']+'))*?
+         (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'))*?
          \s+%s=['"]?%s['"]?
-         (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]+|="[^"]+"|='[^']+'))*?
+         (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'))*?
         \s*>
         (?P<content>.*?)
         </\1>
@@ -365,6 +370,8 @@ def sanitize_filename(s, restricted=False, is_id=False):
     Set is_id if this is not an arbitrary string, but an ID that should be kept if possible
     """
     def replace_insane(char):
+        if restricted and char in ACCENT_CHARS:
+            return ACCENT_CHARS[char]
         if char == '?' or ord(char) < 32 or ord(char) == 127:
             return ''
         elif char == '"':

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2016.04.24'
+__version__ = '2016.05.01'