Merge branch 'master' of https://github.com/rg3/youtube-dl

.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 *2016.07.05*. 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 Issues with outdated version will be rejected.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 **2016.07.05**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.07.06*. 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 Issues with outdated version will be rejected.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 **2016.07.06**
 
 ### 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 2016.07.05
+[debug] youtube-dl version 2016.07.06
 [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: {}

docs/supportedsites.md

@@ -857,6 +857,7 @@
  - **youtube:search**: YouTube.com searches
  - **youtube:search:date**: YouTube.com searches, newest videos first
  - **youtube:search_url**: YouTube.com search URLs
+ - **youtube:shared**
  - **youtube:show**: YouTube.com (multi-season) shows
  - **youtube:subscriptions**: YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)
  - **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword)

test/test_utils.py

@@ -33,6 +33,7 @@ from youtube_dl.utils import (
     ExtractorError,
     find_xpath_attr,
     fix_xml_ampersands,
+    get_element_by_class,
     InAdvancePagedList,
     intlist_to_bytes,
     is_html,
@@ -1027,5 +1028,13 @@ The first line
         self.assertEqual(urshift(3, 1), 1)
         self.assertEqual(urshift(-3, 1), 2147483646)
 
+    def test_get_element_by_class(self):
+        html = '''
+            <span class="foo bar">nice</span>
+        '''
+
+        self.assertEqual(get_element_by_class('foo', html), 'nice')
+        self.assertEqual(get_element_by_class('no-such-class', html), None)
+
 if __name__ == '__main__':
     unittest.main()

youtube_dl/extractor/amp.py

@@ -5,6 +5,8 @@ from .common import InfoExtractor
 from ..utils import (
     int_or_none,
     parse_iso8601,
+    mimetype2ext,
+    determine_ext,
 )
 
 
@@ -50,21 +52,25 @@ class AMPIE(InfoExtractor):
         if isinstance(media_content, dict):
             media_content = [media_content]
         for media_data in media_content:
-            media = media_data['@attributes']
-            media_type = media['type']
-            if media_type in ('video/f4m', 'application/f4m+xml'):
+            media = media_data.get('@attributes', {})
+            media_url = media.get('url')
+            if not media_url:
+                continue
+            ext = mimetype2ext(media.get('type')) or determine_ext(media_url)
+            if ext == 'f4m':
                 formats.extend(self._extract_f4m_formats(
-                    media['url'] + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124',
+                    media_url + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124',
                     video_id, f4m_id='hds', fatal=False))
-            elif media_type == 'application/x-mpegURL':
+            elif ext == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(
-                    media['url'], video_id, 'mp4', m3u8_id='hls', fatal=False))
+                    media_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
             else:
                 formats.append({
                     'format_id': media_data.get('media-category', {}).get('@attributes', {}).get('label'),
                     'url': media['url'],
                     'tbr': int_or_none(media.get('bitrate')),
                     'filesize': int_or_none(media.get('fileSize')),
+                    'ext': ext,
                 })
 
         self._sort_formats(formats)

youtube_dl/extractor/cliprs.py

@@ -1,16 +1,10 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    float_or_none,
-    int_or_none,
-    parse_iso8601,
-)
+from .onet import OnetBaseIE
 
 
-class ClipRsIE(InfoExtractor):
+class ClipRsIE(OnetBaseIE):
     _VALID_URL = r'https?://(?:www\.)?clip\.rs/(?P<id>[^/]+)/\d+'
     _TEST = {
         'url': 'http://www.clip.rs/premijera-frajle-predstavljaju-novi-spot-za-pesmu-moli-me-moli/3732',
@@ -27,64 +21,13 @@ class ClipRsIE(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)
 
-        video_id = self._search_regex(
-            r'id=(["\'])mvp:(?P<id>.+?)\1', webpage, 'mvp id', group='id')
+        mvp_id = self._search_mvp_id(webpage)
 
-        response = self._download_json(
-            'http://qi.ckm.onetapi.pl/', video_id,
-            query={
-                'body[id]': video_id,
-                'body[jsonrpc]': '2.0',
-                'body[method]': 'get_asset_detail',
-                'body[params][ID_Publikacji]': video_id,
-                'body[params][Service]': 'www.onet.pl',
-                'content-type': 'application/jsonp',
-                'x-onet-app': 'player.front.onetapi.pl',
-            })
+        info_dict = self._extract_from_id(mvp_id, webpage)
+        info_dict['display_id'] = display_id
 
-        error = response.get('error')
-        if error:
-            raise ExtractorError(
-                '%s said: %s' % (self.IE_NAME, error['message']), expected=True)
-
-        video = response['result'].get('0')
-
-        formats = []
-        for _, formats_dict in video['formats'].items():
-            if not isinstance(formats_dict, dict):
-                continue
-            for format_id, format_list in formats_dict.items():
-                if not isinstance(format_list, list):
-                    continue
-                for f in format_list:
-                    if not f.get('url'):
-                        continue
-                    formats.append({
-                        'url': f['url'],
-                        'format_id': format_id,
-                        'height': int_or_none(f.get('vertical_resolution')),
-                        'width': int_or_none(f.get('horizontal_resolution')),
-                        'abr': float_or_none(f.get('audio_bitrate')),
-                        'vbr': float_or_none(f.get('video_bitrate')),
-                    })
-        self._sort_formats(formats)
-
-        meta = video.get('meta', {})
-
-        title = self._og_search_title(webpage, default=None) or meta['title']
-        description = self._og_search_description(webpage, default=None) or meta.get('description')
-        duration = meta.get('length') or meta.get('lenght')
-        timestamp = parse_iso8601(meta.get('addDate'), ' ')
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'duration': duration,
-            'timestamp': timestamp,
-            'formats': formats,
-        }
+        return info_dict

youtube_dl/extractor/dailymotion.py

@@ -16,6 +16,7 @@ from ..utils import (
     sanitized_Request,
     str_to_int,
     unescapeHTML,
+    mimetype2ext,
 )
 
 
@@ -153,18 +154,19 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                     type_ = media.get('type')
                     if type_ == 'application/vnd.lumberjack.manifest':
                         continue
-                    ext = determine_ext(media_url)
-                    if type_ == 'application/x-mpegURL' or ext == 'm3u8':
+                    ext = mimetype2ext(type_) or determine_ext(media_url)
+                    if ext == 'm3u8':
                         formats.extend(self._extract_m3u8_formats(
                             media_url, video_id, 'mp4', preference=-1,
                             m3u8_id='hls', fatal=False))
-                    elif type_ == 'application/f4m' or ext == 'f4m':
+                    elif ext == 'f4m':
                         formats.extend(self._extract_f4m_formats(
                             media_url, video_id, preference=-1, f4m_id='hds', fatal=False))
                     else:
                         f = {
                             'url': media_url,
                             'format_id': 'http-%s' % quality,
+                            'ext': ext,
                         }
                         m = re.search(r'H264-(?P<width>\d+)x(?P<height>\d+)', media_url)
                         if m:

youtube_dl/extractor/extractors.py

@@ -139,9 +139,9 @@ from .chirbit import (
     ChirbitProfileIE,
 )
 from .cinchcast import CinchcastIE
-from .cliprs import ClipRsIE
 from .clipfish import ClipfishIE
 from .cliphunter import CliphunterIE
+from .cliprs import ClipRsIE
 from .clipsyndicate import ClipsyndicateIE
 from .closertotruth import CloserToTruthIE
 from .cloudy import CloudyIE
@@ -581,6 +581,10 @@ from .nytimes import (
 from .nuvid import NuvidIE
 from .odnoklassniki import OdnoklassnikiIE
 from .oktoberfesttv import OktoberfestTVIE
+from .onet import (
+    OnetIE,
+    OnetChannelIE,
+)
 from .onionstudios import OnionStudiosIE
 from .ooyala import (
     OoyalaIE,

youtube_dl/extractor/metacafe.py

@@ -11,13 +11,14 @@ from ..utils import (
     determine_ext,
     ExtractorError,
     int_or_none,
-    sanitized_Request,
     urlencode_postdata,
+    get_element_by_attribute,
+    mimetype2ext,
 )
 
 
 class MetacafeIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
+    _VALID_URL = r'https?://(?:www\.)?metacafe\.com/watch/(?P<video_id>[^/]+)/(?P<display_id>[^/?#]+)'
     _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
     _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
     IE_NAME = 'metacafe'
@@ -47,6 +48,7 @@ class MetacafeIE(InfoExtractor):
                 'uploader': 'ign',
                 'description': 'Sony released a massive FAQ on the PlayStation Blog detailing the PS4\'s capabilities and limitations.',
             },
+            'skip': 'Page is temporarily unavailable.',
         },
         # AnyClip video
         {
@@ -55,8 +57,8 @@ class MetacafeIE(InfoExtractor):
                 'id': 'an-dVVXnuY7Jh77J',
                 'ext': 'mp4',
                 'title': 'The Andromeda Strain (1971): Stop the Bomb Part 3',
-                'uploader': 'anyclip',
-                'description': 'md5:38c711dd98f5bb87acf973d573442e67',
+                'uploader': 'AnyClip',
+                'description': 'md5:cbef0460d31e3807f6feb4e7a5952e5b',
             },
         },
         # age-restricted video
@@ -110,28 +112,25 @@ class MetacafeIE(InfoExtractor):
     def report_disclaimer(self):
         self.to_screen('Retrieving disclaimer')
 
-    def _real_initialize(self):
+    def _confirm_age(self):
         # Retrieve disclaimer
         self.report_disclaimer()
         self._download_webpage(self._DISCLAIMER, None, False, 'Unable to retrieve disclaimer')
 
         # Confirm age
-        disclaimer_form = {
-            'filters': '0',
-            'submit': "Continue - I'm over 18",
-        }
-        request = sanitized_Request(self._FILTER_POST, urlencode_postdata(disclaimer_form))
-        request.add_header('Content-Type', 'application/x-www-form-urlencoded')
         self.report_age_confirmation()
-        self._download_webpage(request, None, False, 'Unable to confirm age')
+        self._download_webpage(
+            self._FILTER_POST, None, False, 'Unable to confirm age',
+            data=urlencode_postdata({
+                'filters': '0',
+                'submit': "Continue - I'm over 18",
+            }), headers={
+                'Content-Type': 'application/x-www-form-urlencoded',
+            })
 
     def _real_extract(self, url):
         # Extract id and simplified title from URL
-        mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError('Invalid URL: %s' % url)
-
-        video_id = mobj.group(1)
+        video_id, display_id = re.match(self._VALID_URL, url).groups()
 
         # the video may come from an external site
         m_external = re.match('^(\w{2})-(.*)$', video_id)
@@ -144,15 +143,24 @@ class MetacafeIE(InfoExtractor):
             if prefix == 'cb':
                 return self.url_result('theplatform:%s' % ext_id, 'ThePlatform')
 
-        # Retrieve video webpage to extract further information
-        req = sanitized_Request('http://www.metacafe.com/watch/%s/' % video_id)
+        # self._confirm_age()
 
         # AnyClip videos require the flashversion cookie so that we get the link
         # to the mp4 file
-        mobj_an = re.match(r'^an-(.*?)$', video_id)
-        if mobj_an:
-            req.headers['Cookie'] = 'flashVersion=0;'
-        webpage = self._download_webpage(req, video_id)
+        headers = {}
+        if video_id.startswith('an-'):
+            headers['Cookie'] = 'flashVersion=0;'
+
+        # Retrieve video webpage to extract further information
+        webpage = self._download_webpage(url, video_id, headers=headers)
+
+        error = get_element_by_attribute(
+            'class', 'notfound-page-title', webpage)
+        if error:
+            raise ExtractorError(error, expected=True)
+
+        video_title = self._html_search_meta(
+            ['og:title', 'twitter:title'], webpage, 'title', default=None) or self._search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
 
         # Extract URL, uploader and title from webpage
         self.report_extraction(video_id)
@@ -216,20 +224,40 @@ class MetacafeIE(InfoExtractor):
                         'player_url': player_url,
                         'ext': play_path.partition(':')[0],
                     })
+        if video_url is None:
+            flashvars = self._parse_json(self._search_regex(
+                r'flashvars\s*=\s*({.*});', webpage, 'flashvars',
+                default=None), video_id, fatal=False)
+            if flashvars:
+                video_url = []
+                for source in flashvars.get('sources'):
+                    source_url = source.get('src')
+                    if not source_url:
+                        continue
+                    ext = mimetype2ext(source.get('type')) or determine_ext(source_url)
+                    if ext == 'm3u8':
+                        video_url.extend(self._extract_m3u8_formats(
+                            source_url, video_id, 'mp4',
+                            'm3u8_native', m3u8_id='hls', fatal=False))
+                    else:
+                        video_url.append({
+                            'url': source_url,
+                            'ext': ext,
+                        })
 
         if video_url is None:
             raise ExtractorError('Unsupported video type')
 
-        video_title = self._html_search_regex(
-            r'(?im)<title>(.*) - Video</title>', webpage, 'title')
-        description = self._og_search_description(webpage)
-        thumbnail = self._og_search_thumbnail(webpage)
+        description = self._html_search_meta(
+            ['og:description', 'twitter:description', 'description'],
+            webpage, 'title', fatal=False)
+        thumbnail = self._html_search_meta(
+            ['og:image', 'twitter:image'], webpage, 'title', fatal=False)
         video_uploader = self._html_search_regex(
             r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);',
             webpage, 'uploader nickname', fatal=False)
         duration = int_or_none(
-            self._html_search_meta('video:duration', webpage))
-
+            self._html_search_meta('video:duration', webpage, default=None))
         age_limit = (
             18
             if re.search(r'(?:"contentRating":|"rating",)"restricted"', webpage)
@@ -242,10 +270,11 @@ class MetacafeIE(InfoExtractor):
                 'url': video_url,
                 'ext': video_ext,
             }]
-
         self._sort_formats(formats)
+
         return {
             'id': video_id,
+            'display_id': display_id,
             'description': description,
             'uploader': video_uploader,
             'title': video_title,

youtube_dl/extractor/onet.py

@@ -0,0 +1,172 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    ExtractorError,
+    float_or_none,
+    get_element_by_class,
+    int_or_none,
+    js_to_json,
+    parse_iso8601,
+    remove_start,
+    strip_or_none,
+    url_basename,
+)
+
+
+class OnetBaseIE(InfoExtractor):
+    def _search_mvp_id(self, webpage):
+        return self._search_regex(
+            r'id=(["\'])mvp:(?P<id>.+?)\1', webpage, 'mvp id', group='id')
+
+    def _extract_from_id(self, video_id, webpage):
+        response = self._download_json(
+            'http://qi.ckm.onetapi.pl/', video_id,
+            query={
+                'body[id]': video_id,
+                'body[jsonrpc]': '2.0',
+                'body[method]': 'get_asset_detail',
+                'body[params][ID_Publikacji]': video_id,
+                'body[params][Service]': 'www.onet.pl',
+                'content-type': 'application/jsonp',
+                'x-onet-app': 'player.front.onetapi.pl',
+            })
+
+        error = response.get('error')
+        if error:
+            raise ExtractorError(
+                '%s said: %s' % (self.IE_NAME, error['message']), expected=True)
+
+        video = response['result'].get('0')
+
+        formats = []
+        for _, formats_dict in video['formats'].items():
+            if not isinstance(formats_dict, dict):
+                continue
+            for format_id, format_list in formats_dict.items():
+                if not isinstance(format_list, list):
+                    continue
+                for f in format_list:
+                    video_url = f.get('url')
+                    if not video_url:
+                        continue
+                    ext = determine_ext(video_url)
+                    if format_id == 'ism':
+                        # TODO: Support Microsoft Smooth Streaming
+                        continue
+                    elif ext == 'mpd':
+                        # TODO: Current DASH formats are broken - $Time$ pattern in
+                        # <SegmentTemplate> not implemented yet
+                        # formats.extend(self._extract_mpd_formats(
+                        #    video_url, video_id, mpd_id='dash', fatal=False))
+                        continue
+                    else:
+                        formats.append({
+                            'url': video_url,
+                            'format_id': format_id,
+                            'height': int_or_none(f.get('vertical_resolution')),
+                            'width': int_or_none(f.get('horizontal_resolution')),
+                            'abr': float_or_none(f.get('audio_bitrate')),
+                            'vbr': float_or_none(f.get('video_bitrate')),
+                        })
+        self._sort_formats(formats)
+
+        meta = video.get('meta', {})
+
+        title = self._og_search_title(webpage, default=None) or meta['title']
+        description = self._og_search_description(webpage, default=None) or meta.get('description')
+        duration = meta.get('length') or meta.get('lenght')
+        timestamp = parse_iso8601(meta.get('addDate'), ' ')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'timestamp': timestamp,
+            'formats': formats,
+        }
+
+
+class OnetIE(OnetBaseIE):
+    _VALID_URL = 'https?://(?:www\.)?onet\.tv/[a-z]/[a-z]+/(?P<display_id>[0-9a-z-]+)/(?P<id>[0-9a-z]+)'
+    IE_NAME = 'onet.tv'
+
+    _TEST = {
+        'url': 'http://onet.tv/k/openerfestival/open-er-festival-2016-najdziwniejsze-wymagania-gwiazd/qbpyqc',
+        'md5': 'e3ffbf47590032ac3f27249204173d50',
+        'info_dict': {
+            'id': 'qbpyqc',
+            'display_id': 'open-er-festival-2016-najdziwniejsze-wymagania-gwiazd',
+            'ext': 'mp4',
+            'title': 'Open\'er Festival 2016: najdziwniejsze wymagania gwiazd',
+            'description': 'Trzy samochody, których nigdy nie użyto, prywatne spa, hotel dekorowany czarnym suknem czy nielegalne używki. Organizatorzy koncertów i festiwali muszą stawać przed nie lada wyzwaniem zapraszając gwia...',
+            'upload_date': '20160705',
+            'timestamp': 1467721580,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id, video_id = mobj.group('display_id', 'id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        mvp_id = self._search_mvp_id(webpage)
+
+        info_dict = self._extract_from_id(mvp_id, webpage)
+        info_dict.update({
+            'id': video_id,
+            'display_id': display_id,
+        })
+
+        return info_dict
+
+
+class OnetChannelIE(OnetBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?onet\.tv/[a-z]/(?P<id>[a-z]+)(?:[?#]|$)'
+    IE_NAME = 'onet.tv:channel'
+
+    _TEST = {
+        'url': 'http://onet.tv/k/openerfestival',
+        'info_dict': {
+            'id': 'openerfestival',
+            'title': 'Open\'er Festival Live',
+            'description': 'Dziękujemy, że oglądaliście transmisje. Zobaczcie nasze relacje i wywiady z artystami.',
+        },
+        'playlist_mincount': 46,
+    }
+
+    def _real_extract(self, url):
+        channel_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, channel_id)
+
+        current_clip_info = self._parse_json(self._search_regex(
+            r'var\s+currentClip\s*=\s*({[^}]+})', webpage, 'video info'), channel_id,
+            transform_source=lambda s: js_to_json(re.sub(r'\'\s*\+\s*\'', '', s)))
+        video_id = remove_start(current_clip_info['ckmId'], 'mvp:')
+        video_name = url_basename(current_clip_info['url'])
+
+        if self._downloader.params.get('noplaylist'):
+            self.to_screen(
+                'Downloading just video %s because of --no-playlist' % video_name)
+            return self._extract_from_id(video_id, webpage)
+
+        self.to_screen(
+            'Downloading channel %s - add --no-playlist to just download video %s' % (
+                channel_id, video_name))
+        matches = re.findall(
+            r'<a[^>]+href=[\'"](https?://(?:www\.)?onet\.tv/[a-z]/[a-z]+/[0-9a-z-]+/[0-9a-z]+)',
+            webpage)
+        entries = [
+            self.url_result(video_link, OnetIE.ie_key())
+            for video_link in matches]
+
+        channel_title = strip_or_none(get_element_by_class('o_channelName', webpage))
+        channel_description = strip_or_none(get_element_by_class('o_channelDesc', webpage))
+        return self.playlist_result(entries, channel_id, channel_title, channel_description)

youtube_dl/extractor/onionstudios.py

@@ -7,6 +7,8 @@ from .common import InfoExtractor
 from ..utils import (
     determine_ext,
     int_or_none,
+    float_or_none,
+    mimetype2ext,
 )
 
 
@@ -15,15 +17,14 @@ class OnionStudiosIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.onionstudios.com/videos/hannibal-charges-forward-stops-for-a-cocktail-2937',
-        'md5': 'd4851405d31adfadf71cd7a487b765bb',
+        'md5': 'e49f947c105b8a78a675a0ee1bddedfe',
         'info_dict': {
             'id': '2937',
             'ext': 'mp4',
             'title': 'Hannibal charges forward, stops for a cocktail',
-            'description': 'md5:e786add7f280b7f0fe237b64cc73df76',
             'thumbnail': 're:^https?://.*\.jpg$',
             'uploader': 'The A.V. Club',
-            'uploader_id': 'TheAVClub',
+            'uploader_id': 'the-av-club',
         },
     }, {
         'url': 'http://www.onionstudios.com/embed?id=2855&autoplay=true',
@@ -40,50 +41,38 @@ class OnionStudiosIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(
-            'http://www.onionstudios.com/embed?id=%s' % video_id, video_id)
+        video_data = self._download_json(
+            'http://www.onionstudios.com/video/%s.json' % video_id, video_id)
+
+        title = video_data['title']
 
         formats = []
-        for src in re.findall(r'<source[^>]+src="([^"]+)"', webpage):
-            ext = determine_ext(src)
+        for source in video_data.get('sources', []):
+            source_url = source.get('url')
+            if not source_url:
+                continue
+            ext = mimetype2ext(source.get('content_type')) or determine_ext(source_url)
             if ext == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(
-                    src, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
+                    source_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
             else:
-                height = int_or_none(self._search_regex(
-                    r'/(\d+)\.%s' % ext, src, 'height', default=None))
+                tbr = int_or_none(source.get('bitrate'))
                 formats.append({
-                    'format_id': ext + ('-%sp' % height if height else ''),
-                    'url': src,
-                    'height': height,
+                    'format_id': ext + ('-%d' % tbr if tbr else ''),
+                    'url': source_url,
+                    'width': int_or_none(source.get('width')),
+                    'tbr': tbr,
                     'ext': ext,
-                    'preference': 1,
                 })
         self._sort_formats(formats)
 
-        title = self._search_regex(
-            r'share_title\s*=\s*(["\'])(?P<title>[^\1]+?)\1',
-            webpage, 'title', group='title')
-        description = self._search_regex(
-            r'share_description\s*=\s*(["\'])(?P<description>[^\'"]+?)\1',
-            webpage, 'description', default=None, group='description')
-        thumbnail = self._search_regex(
-            r'poster\s*=\s*(["\'])(?P<thumbnail>[^\1]+?)\1',
-            webpage, 'thumbnail', default=False, group='thumbnail')
-
-        uploader_id = self._search_regex(
-            r'twitter_handle\s*=\s*(["\'])(?P<uploader_id>[^\1]+?)\1',
-            webpage, 'uploader id', fatal=False, group='uploader_id')
-        uploader = self._search_regex(
-            r'window\.channelName\s*=\s*(["\'])Embedded:(?P<uploader>[^\1]+?)\1',
-            webpage, 'uploader', default=False, group='uploader')
-
         return {
             'id': video_id,
             'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'uploader': uploader,
-            'uploader_id': uploader_id,
+            'thumbnail': video_data.get('poster_url'),
+            'uploader': video_data.get('channel_name'),
+            'uploader_id': video_data.get('channel_slug'),
+            'duration': float_or_none(video_data.get('duration', 1000)),
+            'tags': video_data.get('tags'),
             'formats': formats,
         }

youtube_dl/extractor/prosiebensat1.py

@@ -5,7 +5,7 @@ import re
 
 from hashlib import sha1
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse_urlencode
+from ..compat import compat_str
 from ..utils import (
     ExtractorError,
     determine_ext,
@@ -71,6 +71,7 @@ class ProSiebenSat1IE(InfoExtractor):
                 # rtmp download
                 'skip_download': True,
             },
+            'skip': 'This video is unavailable',
         },
         {
             'url': 'http://www.sixx.de/stars-style/video/sexy-laufen-in-ugg-boots-clip',
@@ -86,6 +87,7 @@ class ProSiebenSat1IE(InfoExtractor):
                 # rtmp download
                 'skip_download': True,
             },
+            'skip': 'This video is unavailable',
         },
         {
             'url': 'http://www.sat1.de/film/der-ruecktritt/video/im-interview-kai-wiesinger-clip',
@@ -101,6 +103,7 @@ class ProSiebenSat1IE(InfoExtractor):
                 # rtmp download
                 'skip_download': True,
             },
+            'skip': 'This video is unavailable',
         },
         {
             'url': 'http://www.kabeleins.de/tv/rosins-restaurants/videos/jagd-auf-fertigkost-im-elsthal-teil-2-ganze-folge',
@@ -116,6 +119,7 @@ class ProSiebenSat1IE(InfoExtractor):
                 # rtmp download
                 'skip_download': True,
             },
+            'skip': 'This video is unavailable',
         },
         {
             'url': 'http://www.ran.de/fussball/bundesliga/video/schalke-toennies-moechte-raul-zurueck-ganze-folge',
@@ -131,6 +135,7 @@ class ProSiebenSat1IE(InfoExtractor):
                 # rtmp download
                 'skip_download': True,
             },
+            'skip': 'This video is unavailable',
         },
         {
             'url': 'http://www.the-voice-of-germany.de/video/31-andreas-kuemmert-rocket-man-clip',
@@ -227,70 +232,42 @@ class ProSiebenSat1IE(InfoExtractor):
     ]
 
     def _extract_clip(self, url, webpage):
-        clip_id = self._html_search_regex(self._CLIPID_REGEXES, webpage, 'clip id')
+        clip_id = self._html_search_regex(
+            self._CLIPID_REGEXES, webpage, 'clip id')
 
         access_token = 'prosieben'
         client_name = 'kolibri-2.0.19-splec4'
         client_location = url
 
-        videos_api_url = 'http://vas.sim-technik.de/vas/live/v2/videos?%s' % compat_urllib_parse_urlencode({
-            'access_token': access_token,
-            'client_location': client_location,
-            'client_name': client_name,
-            'ids': clip_id,
-        })
-
-        video = self._download_json(videos_api_url, clip_id, 'Downloading videos JSON')[0]
+        video = self._download_json(
+            'http://vas.sim-technik.de/vas/live/v2/videos',
+            clip_id, 'Downloading videos JSON', query={
+                'access_token': access_token,
+                'client_location': client_location,
+                'client_name': client_name,
+                'ids': clip_id,
+            })[0]
 
         if video.get('is_protected') is True:
             raise ExtractorError('This video is DRM protected.', expected=True)
 
         duration = float_or_none(video.get('duration'))
-        source_ids = [source['id'] for source in video['sources']]
-        source_ids_str = ','.join(map(str, source_ids))
+        source_ids = [compat_str(source['id']) for source in video['sources']]
 
         g = '01!8d8F_)r9]4s[qeuXfP%'
+        client_id = g[:2] + sha1(''.join([clip_id, g, access_token, client_location, g, client_name]).encode('utf-8')).hexdigest()
 
-        client_id = g[:2] + sha1(''.join([clip_id, g, access_token, client_location, g, client_name])
-                                 .encode('utf-8')).hexdigest()
-
-        sources_api_url = 'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources?%s' % (clip_id, compat_urllib_parse_urlencode({
-            'access_token': access_token,
-            'client_id': client_id,
-            'client_location': client_location,
-            'client_name': client_name,
-        }))
-
-        sources = self._download_json(sources_api_url, clip_id, 'Downloading sources JSON')
+        sources = self._download_json(
+            'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources' % clip_id,
+            clip_id, 'Downloading sources JSON', query={
+                'access_token': access_token,
+                'client_id': client_id,
+                'client_location': client_location,
+                'client_name': client_name,
+            })
         server_id = sources['server_id']
 
-        client_id = g[:2] + sha1(''.join([g, clip_id, access_token, server_id,
-                                          client_location, source_ids_str, g, client_name])
-                                 .encode('utf-8')).hexdigest()
-
-        url_api_url = 'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources/url?%s' % (clip_id, compat_urllib_parse_urlencode({
-            'access_token': access_token,
-            'client_id': client_id,
-            'client_location': client_location,
-            'client_name': client_name,
-            'server_id': server_id,
-            'source_ids': source_ids_str,
-        }))
-
-        urls = self._download_json(url_api_url, clip_id, 'Downloading urls JSON')
-
         title = self._html_search_regex(self._TITLE_REGEXES, webpage, 'title')
-        description = self._html_search_regex(self._DESCRIPTION_REGEXES, webpage, 'description', fatal=False)
-        thumbnail = self._og_search_thumbnail(webpage)
-
-        upload_date = unified_strdate(self._html_search_regex(
-            self._UPLOAD_DATE_REGEXES, webpage, 'upload date', default=None))
-
-        formats = []
-
-        urls_sources = urls['sources']
-        if isinstance(urls_sources, dict):
-            urls_sources = urls_sources.values()
 
         def fix_bitrate(bitrate):
             bitrate = int_or_none(bitrate)
@@ -298,37 +275,73 @@ class ProSiebenSat1IE(InfoExtractor):
                 return None
             return (bitrate // 1000) if bitrate % 1000 == 0 else bitrate
 
-        for source in urls_sources:
-            protocol = source['protocol']
-            source_url = source['url']
-            if protocol == 'rtmp' or protocol == 'rtmpe':
-                mobj = re.search(r'^(?P<url>rtmpe?://[^/]+)/(?P<path>.+)$', source_url)
-                if not mobj:
+        formats = []
+        for source_id in source_ids:
+            client_id = g[:2] + sha1(''.join([g, clip_id, access_token, server_id, client_location, source_id, g, client_name]).encode('utf-8')).hexdigest()
+            urls = self._download_json(
+                'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources/url' % clip_id,
+                clip_id, 'Downloading urls JSON', fatal=False, query={
+                    'access_token': access_token,
+                    'client_id': client_id,
+                    'client_location': client_location,
+                    'client_name': client_name,
+                    'server_id': server_id,
+                    'source_ids': source_id,
+                })
+            if not urls:
+                continue
+            if urls.get('status_code') != 0:
+                raise ExtractorError('This video is unavailable', expected=True)
+            urls_sources = urls['sources']
+            if isinstance(urls_sources, dict):
+                urls_sources = urls_sources.values()
+            for source in urls_sources:
+                source_url = source.get('url')
+                if not source_url:
                     continue
-                path = mobj.group('path')
-                mp4colon_index = path.rfind('mp4:')
-                app = path[:mp4colon_index]
-                play_path = path[mp4colon_index:]
-                formats.append({
-                    'url': '%s/%s' % (mobj.group('url'), app),
-                    'app': app,
-                    'play_path': play_path,
-                    'player_url': 'http://livepassdl.conviva.com/hf/ver/2.79.0.17083/LivePassModuleMain.swf',
-                    'page_url': 'http://www.prosieben.de',
-                    'vbr': fix_bitrate(source['bitrate']),
-                    'ext': 'mp4',
-                    'format_id': '%s_%s' % (source['cdn'], source['bitrate']),
-                })
-            elif 'f4mgenerator' in source_url or determine_ext(source_url) == 'f4m':
-                formats.extend(self._extract_f4m_formats(source_url, clip_id))
-            else:
-                formats.append({
-                    'url': source_url,
-                    'vbr': fix_bitrate(source['bitrate']),
-                })
-
+                protocol = source.get('protocol')
+                mimetype = source.get('mimetype')
+                if mimetype == 'application/f4m+xml' or 'f4mgenerator' in source_url or determine_ext(source_url) == 'f4m':
+                    formats.extend(self._extract_f4m_formats(
+                        source_url, clip_id, f4m_id='hds', fatal=False))
+                elif mimetype == 'application/x-mpegURL':
+                    formats.extend(self._extract_m3u8_formats(
+                        source_url, clip_id, 'mp4', 'm3u8_native',
+                        m3u8_id='hls', fatal=False))
+                else:
+                    tbr = fix_bitrate(source['bitrate'])
+                    if protocol in ('rtmp', 'rtmpe'):
+                        mobj = re.search(r'^(?P<url>rtmpe?://[^/]+)/(?P<path>.+)$', source_url)
+                        if not mobj:
+                            continue
+                        path = mobj.group('path')
+                        mp4colon_index = path.rfind('mp4:')
+                        app = path[:mp4colon_index]
+                        play_path = path[mp4colon_index:]
+                        formats.append({
+                            'url': '%s/%s' % (mobj.group('url'), app),
+                            'app': app,
+                            'play_path': play_path,
+                            'player_url': 'http://livepassdl.conviva.com/hf/ver/2.79.0.17083/LivePassModuleMain.swf',
+                            'page_url': 'http://www.prosieben.de',
+                            'tbr': tbr,
+                            'ext': 'flv',
+                            'format_id': 'rtmp%s' % ('-%d' % tbr if tbr else ''),
+                        })
+                    else:
+                        formats.append({
+                            'url': source_url,
+                            'tbr': tbr,
+                            'format_id': 'http%s' % ('-%d' % tbr if tbr else ''),
+                        })
         self._sort_formats(formats)
 
+        description = self._html_search_regex(
+            self._DESCRIPTION_REGEXES, webpage, 'description', fatal=False)
+        thumbnail = self._og_search_thumbnail(webpage)
+        upload_date = unified_strdate(self._html_search_regex(
+            self._UPLOAD_DATE_REGEXES, webpage, 'upload date', default=None))
+
         return {
             'id': clip_id,
             'title': title,

youtube_dl/extractor/rtvnh.py

@@ -9,7 +9,7 @@ class RTVNHIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?rtvnh\.nl/video/(?P<id>[0-9]+)'
     _TEST = {
         'url': 'http://www.rtvnh.nl/video/131946',
-        'md5': '6e1d0ab079e2a00b6161442d3ceacfc1',
+        'md5': 'cdbec9f44550763c8afc96050fa747dc',
         'info_dict': {
             'id': '131946',
             'ext': 'mp4',
@@ -29,15 +29,29 @@ class RTVNHIE(InfoExtractor):
             raise ExtractorError(
                 '%s returned error code %d' % (self.IE_NAME, status), expected=True)
 
-        formats = self._extract_smil_formats(
-            'http://www.rtvnh.nl/video/smil?m=' + video_id, video_id, fatal=False)
+        formats = []
+        rtmp_formats = self._extract_smil_formats(
+            'http://www.rtvnh.nl/video/smil?m=' + video_id, video_id)
+        formats.extend(rtmp_formats)
 
-        for item in meta['source']['fb']:
-            if item.get('type') == 'hls':
-                formats.extend(self._extract_m3u8_formats(
-                    item['file'], video_id, ext='mp4', entry_protocol='m3u8_native'))
-            elif item.get('type') == '':
-                formats.append({'url': item['file']})
+        for rtmp_format in rtmp_formats:
+            rtmp_url = '%s/%s' % (rtmp_format['url'], rtmp_format['play_path'])
+            rtsp_format = rtmp_format.copy()
+            del rtsp_format['play_path']
+            del rtsp_format['ext']
+            rtsp_format.update({
+                'format_id': rtmp_format['format_id'].replace('rtmp', 'rtsp'),
+                'url': rtmp_url.replace('rtmp://', 'rtsp://'),
+                'protocol': 'rtsp',
+            })
+            formats.append(rtsp_format)
+            http_base_url = rtmp_url.replace('rtmp://', 'http://')
+            formats.extend(self._extract_m3u8_formats(
+                http_base_url + '/playlist.m3u8', video_id, 'mp4',
+                'm3u8_native', m3u8_id='hls', fatal=False))
+            formats.extend(self._extract_f4m_formats(
+                http_base_url + '/manifest.f4m',
+                video_id, f4m_id='hds', fatal=False))
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/sandia.py

@@ -1,18 +1,12 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import itertools
 import json
-import re
 
 from .common import InfoExtractor
-from ..compat import compat_urlparse
 from ..utils import (
     int_or_none,
-    js_to_json,
     mimetype2ext,
-    sanitized_Request,
-    unified_strdate,
 )
 
 
@@ -27,7 +21,8 @@ class SandiaIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Xyce Software Training - Section 1',
             'description': 're:(?s)SAND Number: SAND 2013-7800.{200,}',
-            'upload_date': '20120904',
+            'upload_date': '20120409',
+            'timestamp': 1333983600,
             'duration': 7794,
         }
     }
@@ -35,81 +30,36 @@ class SandiaIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        req = sanitized_Request(url)
-        req.add_header('Cookie', 'MediasitePlayerCaps=ClientPlugins=4')
-        webpage = self._download_webpage(req, video_id)
+        presentation_data = self._download_json(
+            'http://digitalops.sandia.gov/Mediasite/PlayerService/PlayerService.svc/json/GetPlayerOptions',
+            video_id, data=json.dumps({
+                'getPlayerOptionsRequest': {
+                    'ResourceId': video_id,
+                    'QueryString': '',
+                }
+            }), headers={
+                'Content-Type': 'application/json; charset=utf-8',
+            })['d']['Presentation']
 
-        js_path = self._search_regex(
-            r'<script type="text/javascript" src="(/Mediasite/FileServer/Presentation/[^"]+)"',
-            webpage, 'JS code URL')
-        js_url = compat_urlparse.urljoin(url, js_path)
-
-        js_code = self._download_webpage(
-            js_url, video_id, note='Downloading player')
-
-        def extract_str(key, **args):
-            return self._search_regex(
-                r'Mediasite\.PlaybackManifest\.%s\s*=\s*(.+);\s*?\n' % re.escape(key),
-                js_code, key, **args)
-
-        def extract_data(key, **args):
-            data_json = extract_str(key, **args)
-            if data_json is None:
-                return data_json
-            return self._parse_json(
-                data_json, video_id, transform_source=js_to_json)
+        title = presentation_data['Title']
 
         formats = []
-        for i in itertools.count():
-            fd = extract_data('VideoUrls[%d]' % i, default=None)
-            if fd is None:
-                break
-            formats.append({
-                'format_id': '%s' % i,
-                'format_note': fd['MimeType'].partition('/')[2],
-                'ext': mimetype2ext(fd['MimeType']),
-                'url': fd['Location'],
-                'protocol': 'f4m' if fd['MimeType'] == 'video/x-mp4-fragmented' else None,
-            })
+        for stream in presentation_data.get('Streams', []):
+            for fd in stream.get('VideoUrls', []):
+                formats.append({
+                    'format_id': fd['MediaType'],
+                    'format_note': fd['MimeType'].partition('/')[2],
+                    'ext': mimetype2ext(fd['MimeType']),
+                    'url': fd['Location'],
+                    'protocol': 'f4m' if fd['MimeType'] == 'video/x-mp4-fragmented' else None,
+                })
         self._sort_formats(formats)
 
-        slide_baseurl = compat_urlparse.urljoin(
-            url, extract_data('SlideBaseUrl'))
-        slide_template = slide_baseurl + re.sub(
-            r'\{0:D?([0-9+])\}', r'%0\1d', extract_data('SlideImageFileNameTemplate'))
-        slides = []
-        last_slide_time = 0
-        for i in itertools.count(1):
-            sd = extract_str('Slides[%d]' % i, default=None)
-            if sd is None:
-                break
-            timestamp = int_or_none(self._search_regex(
-                r'^Mediasite\.PlaybackManifest\.CreateSlide\("[^"]*"\s*,\s*([0-9]+),',
-                sd, 'slide %s timestamp' % i, fatal=False))
-            slides.append({
-                'url': slide_template % i,
-                'duration': timestamp - last_slide_time,
-            })
-            last_slide_time = timestamp
-        formats.append({
-            'format_id': 'slides',
-            'protocol': 'slideshow',
-            'url': json.dumps(slides),
-            'preference': -10000,  # Downloader not yet written
-        })
-        self._sort_formats(formats)
-
-        title = extract_data('Title')
-        description = extract_data('Description', fatal=False)
-        duration = int_or_none(extract_data(
-            'Duration', fatal=False), scale=1000)
-        upload_date = unified_strdate(extract_data('AirDate', fatal=False))
-
         return {
             'id': video_id,
             'title': title,
-            'description': description,
+            'description': presentation_data.get('Description'),
             'formats': formats,
-            'upload_date': upload_date,
-            'duration': duration,
+            'timestamp': int_or_none(presentation_data.get('UnixTime'), 1000),
+            'duration': int_or_none(presentation_data.get('Duration'), 1000),
         }

youtube_dl/extractor/sixplay.py

@@ -5,6 +5,8 @@ from .common import InfoExtractor
 from ..utils import (
     qualities,
     int_or_none,
+    mimetype2ext,
+    determine_ext,
 )
 
 
@@ -34,19 +36,21 @@ class SixPlayIE(InfoExtractor):
             source_type, source_url = source.get('type'), source.get('src')
             if not source_url or source_type == 'hls/primetime':
                 continue
-            if source_type == 'application/vnd.apple.mpegURL':
+            ext = mimetype2ext(source_type) or determine_ext(source_url)
+            if ext == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(
                     source_url, video_id, 'mp4', 'm3u8_native',
                     m3u8_id='hls', fatal=False))
                 formats.extend(self._extract_f4m_formats(
                     source_url.replace('.m3u8', '.f4m'),
                     video_id, f4m_id='hds', fatal=False))
-            elif source_type == 'video/mp4':
+            elif ext == 'mp4':
                 quality = source.get('quality')
                 formats.append({
                     'url': source_url,
                     'format_id': quality,
                     'quality': quality_key(quality),
+                    'ext': ext,
                 })
         self._sort_formats(formats)
 

youtube_dl/extractor/slideshare.py

@@ -9,6 +9,7 @@ from ..compat import (
 )
 from ..utils import (
     ExtractorError,
+    get_element_by_id,
 )
 
 
@@ -40,7 +41,7 @@ class SlideshareIE(InfoExtractor):
         bucket = info['jsplayer']['video_bucket']
         ext = info['jsplayer']['video_extension']
         video_url = compat_urlparse.urljoin(bucket, doc + '-SD.' + ext)
-        description = self._html_search_regex(
+        description = get_element_by_id('slideshow-description-paragraph', webpage) or self._html_search_regex(
             r'(?s)<p[^>]+itemprop="description"[^>]*>(.+?)</p>', webpage,
             'description', fatal=False)
 
@@ -51,5 +52,5 @@ class SlideshareIE(InfoExtractor):
             'ext': ext,
             'url': video_url,
             'thumbnail': info['slideshow']['pin_image_url'],
-            'description': description,
+            'description': description.strip() if description else None,
         }

youtube_dl/extractor/spiegel.py

@@ -4,8 +4,13 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urlparse
 from .spiegeltv import SpiegeltvIE
+from ..compat import compat_urlparse
+from ..utils import (
+    extract_attributes,
+    unified_strdate,
+    get_element_by_attribute,
+)
 
 
 class SpiegelIE(InfoExtractor):
@@ -19,6 +24,7 @@ class SpiegelIE(InfoExtractor):
             'title': 'Vulkanausbruch in Ecuador: Der "Feuerschlund" ist wieder aktiv',
             'description': 'md5:8029d8310232196eb235d27575a8b9f4',
             'duration': 49,
+            'upload_date': '20130311',
         },
     }, {
         'url': 'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html',
@@ -29,6 +35,7 @@ class SpiegelIE(InfoExtractor):
             'title': 'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers',
             'description': 'md5:c2322b65e58f385a820c10fa03b2d088',
             'duration': 983,
+            'upload_date': '20131115',
         },
     }, {
         'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-embed.html',
@@ -38,6 +45,7 @@ class SpiegelIE(InfoExtractor):
             'ext': 'mp4',
             'description': 'SPIEGEL ONLINE-Nutzer durften den deutschen Astronauten Alexander Gerst über sein Leben auf der ISS-Station befragen. Hier kommen seine Antworten auf die besten sechs Fragen.',
             'title': 'Fragen an Astronaut Alexander Gerst: "Bekommen Sie die Tageszeiten mit?"',
+            'upload_date': '20140904',
         }
     }, {
         'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-iframe.html',
@@ -52,10 +60,10 @@ class SpiegelIE(InfoExtractor):
         if SpiegeltvIE.suitable(handle.geturl()):
             return self.url_result(handle.geturl(), 'Spiegeltv')
 
-        title = re.sub(r'\s+', ' ', self._html_search_regex(
-            r'(?s)<(?:h1|div) class="module-title"[^>]*>(.*?)</(?:h1|div)>',
-            webpage, 'title'))
-        description = self._html_search_meta('description', webpage, 'description')
+        video_data = extract_attributes(self._search_regex(r'(<div[^>]+id="spVideoElements"[^>]+>)', webpage, 'video element', default=''))
+
+        title = video_data.get('data-video-title') or get_element_by_attribute('class', 'module-title', webpage)
+        description = video_data.get('data-video-teaser') or self._html_search_meta('description', webpage, 'description')
 
         base_url = self._search_regex(
             [r'server\s*:\s*(["\'])(?P<url>.+?)\1', r'var\s+server\s*=\s*"(?P<url>[^"]+)\"'],
@@ -87,8 +95,9 @@ class SpiegelIE(InfoExtractor):
         return {
             'id': video_id,
             'title': title,
-            'description': description,
+            'description': description.strip() if description else None,
             'duration': duration,
+            'upload_date': unified_strdate(video_data.get('data-video-date')),
             'formats': formats,
         }
 
@@ -104,6 +113,7 @@ class SpiegelArticleIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Faszination Badminton: Nennt es bloß nicht Federball',
             'description': 're:^Patrick Kämnitz gehört.{100,}',
+            'upload_date': '20140825',
         },
     }, {
         'url': 'http://www.spiegel.de/wissenschaft/weltall/astronaut-alexander-gerst-antwortet-spiegel-online-lesern-a-989876.html',

youtube_dl/extractor/stitcher.py

@@ -56,7 +56,7 @@ class StitcherIE(InfoExtractor):
 
         episode = self._parse_json(
             js_to_json(self._search_regex(
-                r'(?s)var\s+stitcher\s*=\s*({.+?});\n', webpage, 'episode config')),
+                r'(?s)var\s+stitcher(?:Config)?\s*=\s*({.+?});\n', webpage, 'episode config')),
             display_id)['config']['episode']
 
         title = unescapeHTML(episode['title'])

youtube_dl/extractor/threeqsdn.py

@@ -92,12 +92,11 @@ class ThreeQSDNIE(InfoExtractor):
             if not item_url or item_url in urls:
                 return
             urls.add(item_url)
-            type_ = item.get('type')
-            ext = determine_ext(item_url, default_ext=None)
-            if type_ == 'application/dash+xml' or ext == 'mpd':
+            ext = mimetype2ext(item.get('type')) or determine_ext(item_url, default_ext=None)
+            if ext == 'mpd':
                 formats.extend(self._extract_mpd_formats(
                     item_url, video_id, mpd_id='mpd', fatal=False))
-            elif type_ in ('application/vnd.apple.mpegURL', 'application/x-mpegurl') or ext == 'm3u8':
+            elif ext == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(
                     item_url, video_id, 'mp4',
                     entry_protocol='m3u8' if live else 'm3u8_native',
@@ -111,7 +110,7 @@ class ThreeQSDNIE(InfoExtractor):
                 formats.append({
                     'url': item_url,
                     'format_id': item.get('quality'),
-                    'ext': 'mp4' if item_url.startswith('rtsp') else mimetype2ext(type_) or ext,
+                    'ext': 'mp4' if item_url.startswith('rtsp') else ext,
                     'vcodec': 'none' if stream_type == 'audio' else None,
                 })
 

youtube_dl/extractor/youtube.py

@@ -1995,9 +1995,13 @@ class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
             channel_playlist_id = self._html_search_meta(
                 'channelId', channel_page, 'channel id', default=None)
             if not channel_playlist_id:
-                channel_playlist_id = self._search_regex(
-                    r'data-(?:channel-external-|yt)id="([^"]+)"',
-                    channel_page, 'channel id', default=None)
+                channel_url = self._html_search_meta(
+                    ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
+                    channel_page, 'channel url', default=None)
+                if channel_url:
+                    channel_playlist_id = self._search_regex(
+                        r'vnd\.youtube://user/([0-9A-Za-z_-]+)',
+                        channel_url, 'channel id', default=None)
         if channel_playlist_id and channel_playlist_id.startswith('UC'):
             playlist_id = 'UU' + channel_playlist_id[2:]
             return self.url_result(
@@ -2020,6 +2024,15 @@ class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
                 for video_id, video_title in self.extract_videos_from_page(channel_page)]
             return self.playlist_result(entries, channel_id)
 
+        try:
+            next(self._entries(channel_page, channel_id))
+        except StopIteration:
+            alert_message = self._html_search_regex(
+                r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>',
+                channel_page, 'alert', default=None, group='alert')
+            if alert_message:
+                raise ExtractorError('Youtube said: %s' % alert_message, expected=True)
+
         return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
 
 
@@ -2033,7 +2046,8 @@ class YoutubeUserIE(YoutubeChannelIE):
         'url': 'https://www.youtube.com/user/TheLinuxFoundation',
         'playlist_mincount': 320,
         'info_dict': {
-            'title': 'TheLinuxFoundation',
+            'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ',
+            'title': 'Uploads from The Linux Foundation',
         }
     }, {
         'url': 'ytuser:phihag',
@@ -2041,6 +2055,10 @@ class YoutubeUserIE(YoutubeChannelIE):
     }, {
         'url': 'https://www.youtube.com/c/gametrailers',
         'only_matching': True,
+    }, {
+        # This channel is not available.
+        'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
+        'only_matching': True,
     }]
 
     @classmethod

youtube_dl/utils.py

@@ -310,9 +310,17 @@ def get_element_by_id(id, html):
     return get_element_by_attribute('id', id, html)
 
 
-def get_element_by_attribute(attribute, value, html):
+def get_element_by_class(class_name, html):
+    return get_element_by_attribute(
+        'class', r'[^\'"]*\b%s\b[^\'"]*' % re.escape(class_name),
+        html, escape_value=False)
+
+
+def get_element_by_attribute(attribute, value, html, escape_value=True):
     """Return the content of the tag with the specified attribute in the passed HTML document"""
 
+    value = re.escape(value) if escape_value else value
+
     m = re.search(r'''(?xs)
         <([a-zA-Z0-9:._-]+)
          (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'))*?
@@ -321,7 +329,7 @@ def get_element_by_attribute(attribute, value, html):
         \s*>
         (?P<content>.*?)
         </\1>
-    ''' % (re.escape(attribute), re.escape(value)), html)
+    ''' % (re.escape(attribute), value), html)
 
     if not m:
         return None
@@ -2097,6 +2105,7 @@ def mimetype2ext(mt):
         return ext
 
     _, _, res = mt.rpartition('/')
+    res = res.lower()
 
     return {
         '3gpp': '3gp',
@@ -2108,6 +2117,12 @@ def mimetype2ext(mt):
         'x-flv': 'flv',
         'x-mp4-fragmented': 'mp4',
         'x-ms-wmv': 'wmv',
+        'mpegurl': 'm3u8',
+        'x-mpegurl': 'm3u8',
+        'vnd.apple.mpegurl': 'm3u8',
+        'dash+xml': 'mpd',
+        'f4m': 'f4m',
+        'f4m+xml': 'f4m',
     }.get(res, res)
 
 

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2016.07.05'
+__version__ = '2016.07.06'