X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fyoutube.py;h=67a1df9a0a1bebeaea4577411ff0c65f99d0166f;hb=34866b4836eab8dd2fcaae88dc1ed5c79a742c92;hp=3d8b31f9830b218e02021b41214010b4f61d29a9;hpb=3f724339dbe61fe84dd8e66e9c3b74ba6a9c6ddf;p=youtube-dl

diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index 3d8b31f98..67a1df9a0 100644
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -19,6 +19,7 @@ from ..compat import (
     compat_urllib_parse,
     compat_urllib_parse_unquote,
     compat_urllib_parse_unquote_plus,
+    compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urlparse,
     compat_str,
@@ -31,9 +32,12 @@ from ..utils import (
     get_element_by_id,
     int_or_none,
     orderedSet,
+    parse_duration,
+    smuggle_url,
     str_to_int,
     unescapeHTML,
     unified_strdate,
+    unsmuggle_url,
     uppercase_escape,
     ISO3166Utils,
 )
@@ -279,13 +283,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'},
 
         # Dash webm
-        '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
-        '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
-        '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
-        '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
-        '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
-        '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
-        '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'container': 'webm', 'vcodec': 'VP9'},
+        '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
+        '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
+        '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
+        '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
+        '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
+        '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
+        '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'container': 'webm', 'vcodec': 'vp9'},
         '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
         '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
         '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
@@ -295,11 +299,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
         '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
         '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
-        '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'},
-        '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'},
-        '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'},
-        '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'VP9'},
-        '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'},
+        '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'},
+        '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'},
+        '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'},
+        '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'vp9'},
+        '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'},
 
         # Dash webm audio
         '171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50},
@@ -317,7 +321,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
     IE_NAME = 'youtube'
     _TESTS = [
         {
-            'url': 'http://www.youtube.com/watch?v=BaW_jenozKc',
+            'url': 'http://www.youtube.com/watch?v=BaW_jenozKcj&t=1s&end=9',
             'info_dict': {
                 'id': 'BaW_jenozKc',
                 'ext': 'mp4',
@@ -327,8 +331,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'upload_date': '20121002',
                 'description': 'test chars:  "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
                 'categories': ['Science & Technology'],
+                'tags': ['youtube-dl'],
                 'like_count': int,
                 'dislike_count': int,
+                'start_time': 1,
+                'end_time': 9,
             }
         },
         {
@@ -339,7 +346,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'ext': 'mp4',
                 'upload_date': '20120506',
                 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
-                'description': 'md5:fea86fda2d5a5784273df5c7cc994d9f',
+                'description': 'md5:782e8651347686cba06e58f71ab51773',
+                'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
+                         'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
+                         'iconic ep', 'iconic', 'love', 'it'],
                 'uploader': 'Icona Pop',
                 'uploader_id': 'IconaPop',
             }
@@ -554,6 +564,59 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'format': '135',  # bestvideo
             }
         },
+        {
+            # Multifeed videos (multiple cameras), URL is for Main Camera
+            'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
+            'info_dict': {
+                'id': 'jqWvoWXjCVs',
+                'title': 'teamPGP: Rocket League Noob Stream',
+                'description': 'md5:dc7872fb300e143831327f1bae3af010',
+            },
+            'playlist': [{
+                'info_dict': {
+                    'id': 'jqWvoWXjCVs',
+                    'ext': 'mp4',
+                    'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
+                    'description': 'md5:dc7872fb300e143831327f1bae3af010',
+                    'upload_date': '20150721',
+                    'uploader': 'Beer Games Beer',
+                    'uploader_id': 'beergamesbeer',
+                },
+            }, {
+                'info_dict': {
+                    'id': '6h8e8xoXJzg',
+                    'ext': 'mp4',
+                    'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
+                    'description': 'md5:dc7872fb300e143831327f1bae3af010',
+                    'upload_date': '20150721',
+                    'uploader': 'Beer Games Beer',
+                    'uploader_id': 'beergamesbeer',
+                },
+            }, {
+                'info_dict': {
+                    'id': 'PUOgX5z9xZw',
+                    'ext': 'mp4',
+                    'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
+                    'description': 'md5:dc7872fb300e143831327f1bae3af010',
+                    'upload_date': '20150721',
+                    'uploader': 'Beer Games Beer',
+                    'uploader_id': 'beergamesbeer',
+                },
+            }, {
+                'info_dict': {
+                    'id': 'teuwxikvS5k',
+                    'ext': 'mp4',
+                    'title': 'teamPGP: Rocket League Noob Stream (zim)',
+                    'description': 'md5:dc7872fb300e143831327f1bae3af010',
+                    'upload_date': '20150721',
+                    'uploader': 'Beer Games Beer',
+                    'uploader_id': 'beergamesbeer',
+                },
+            }],
+            'params': {
+                'skip_download': True,
+            },
+        }
     ]
 
     def __init__(self, *args, **kwargs):
@@ -885,10 +948,24 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         return formats
 
     def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
+
         proto = (
             'http' if self._downloader.params.get('prefer_insecure', False)
             else 'https')
 
+        start_time = None
+        end_time = None
+        parsed_url = compat_urllib_parse_urlparse(url)
+        for component in [parsed_url.fragment, parsed_url.query]:
+            query = compat_parse_qs(component)
+            if start_time is None and 't' in query:
+                start_time = parse_duration(query['t'][0])
+            if start_time is None and 'start' in query:
+                start_time = parse_duration(query['start'][0])
+            if end_time is None and 'end' in query:
+                end_time = parse_duration(query['end'][0])
+
         # Extract original video URL from URL with redirection, like age verification, using next_url parameter
         mobj = re.search(self._NEXT_URL_RE, url)
         if mobj:
@@ -967,7 +1044,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                         video_id, note=False,
                         errnote='unable to download video info webpage')
                     get_video_info = compat_parse_qs(video_info_webpage)
-                    add_dash_mpd(get_video_info)
+                    if get_video_info.get('use_cipher_signature') != ['True']:
+                        add_dash_mpd(get_video_info)
                     if not video_info:
                         video_info = get_video_info
                     if 'token' in get_video_info:
@@ -976,7 +1054,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             if 'reason' in video_info:
                 if 'The uploader has not made this video available in your country.' in video_info['reason']:
                     regions_allowed = self._html_search_meta('regionsAllowed', video_webpage, default=None)
-                    if regions_allowed is not None:
+                    if regions_allowed:
                         raise ExtractorError('YouTube said: This video is available in %s only' % (
                             ', '.join(map(ISO3166Utils.short2full, regions_allowed.split(',')))),
                             expected=True)
@@ -988,6 +1066,55 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     '"token" parameter not in video info for unknown reason',
                     video_id=video_id)
 
+        # title
+        if 'title' in video_info:
+            video_title = video_info['title'][0]
+        else:
+            self._downloader.report_warning('Unable to extract video title')
+            video_title = '_'
+
+        # description
+        video_description = get_element_by_id("eow-description", video_webpage)
+        if video_description:
+            video_description = re.sub(r'''(?x)
+                <a\s+
+                    (?:[a-zA-Z-]+="[^"]+"\s+)*?
+                    title="([^"]+)"\s+
+                    (?:[a-zA-Z-]+="[^"]+"\s+)*?
+                    class="yt-uix-redirect-link"\s*>
+                [^<]+
+                </a>
+            ''', r'\1', video_description)
+            video_description = clean_html(video_description)
+        else:
+            fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
+            if fd_mobj:
+                video_description = unescapeHTML(fd_mobj.group(1))
+            else:
+                video_description = ''
+
+        if 'multifeed_metadata_list' in video_info and not smuggled_data.get('force_singlefeed', False):
+            if not self._downloader.params.get('noplaylist'):
+                entries = []
+                feed_ids = []
+                multifeed_metadata_list = compat_urllib_parse_unquote_plus(video_info['multifeed_metadata_list'][0])
+                for feed in multifeed_metadata_list.split(','):
+                    feed_data = compat_parse_qs(feed)
+                    entries.append({
+                        '_type': 'url_transparent',
+                        'ie_key': 'Youtube',
+                        'url': smuggle_url(
+                            '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
+                            {'force_singlefeed': True}),
+                        'title': '%s (%s)' % (video_title, feed_data['title'][0]),
+                    })
+                    feed_ids.append(feed_data['id'][0])
+                self.to_screen(
+                    'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
+                    % (', '.join(feed_ids), video_id))
+                return self.playlist_result(entries, video_id, video_title, video_description)
+            self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
+
         if 'view_count' in video_info:
             view_count = int(video_info['view_count'][0])
         else:
@@ -1013,13 +1140,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         else:
             self._downloader.report_warning('unable to extract uploader nickname')
 
-        # title
-        if 'title' in video_info:
-            video_title = video_info['title'][0]
-        else:
-            self._downloader.report_warning('Unable to extract video title')
-            video_title = '_'
-
         # thumbnail image
         # We try first to get a high quality image:
         m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
@@ -1055,25 +1175,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         else:
             video_categories = None
 
-        # description
-        video_description = get_element_by_id("eow-description", video_webpage)
-        if video_description:
-            video_description = re.sub(r'''(?x)
-                <a\s+
-                    (?:[a-zA-Z-]+="[^"]+"\s+)*?
-                    title="([^"]+)"\s+
-                    (?:[a-zA-Z-]+="[^"]+"\s+)*?
-                    class="yt-uix-redirect-link"\s*>
-                [^<]+
-                </a>
-            ''', r'\1', video_description)
-            video_description = clean_html(video_description)
-        else:
-            fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
-            if fd_mobj:
-                video_description = unescapeHTML(fd_mobj.group(1))
-            else:
-                video_description = ''
+        video_tags = [
+            unescapeHTML(m.group('content'))
+            for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
 
         def _extract_count(count_name):
             return str_to_int(self._search_regex(
@@ -1243,6 +1347,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'thumbnail': video_thumbnail,
             'description': video_description,
             'categories': video_categories,
+            'tags': video_tags,
             'subtitles': video_subtitles,
             'automatic_captions': automatic_captions,
             'duration': video_duration,
@@ -1255,6 +1360,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]),
             'formats': formats,
             'is_live': is_live,
+            'start_time': start_time,
+            'end_time': end_time,
         }