X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fyoutube.py;h=facd837ad3fb0a239d2736d234ba6d429a09dcdc;hb=2c919adb74893544ab6def1d56ff8ed37c282ecb;hp=4c449fd741ba3d0445060204e13f0fc5e378b97e;hpb=000b6b5ae5cc214906effe4ac5b78b579bc7db70;p=youtube-dl.git

diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index 4c449fd74..facd837ad 100644
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -33,9 +33,11 @@ from ..utils import (
     int_or_none,
     orderedSet,
     parse_duration,
+    smuggle_url,
     str_to_int,
     unescapeHTML,
     unified_strdate,
+    unsmuggle_url,
     uppercase_escape,
     ISO3166Utils,
 )
@@ -211,7 +213,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                              |(?:                                             # or the v= param in all its forms
                                  (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)?  # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
                                  (?:\?|\#!?)                                  # the params delimiter ? or # or #!
-                                 (?:.*?&)?                                    # any other preceding param (like /?s=tuff&v=xxxx)
+                                 (?:.*?&)??                                   # any other preceding param (like /?s=tuff&v=xxxx)
                                  v=
                              )
                          ))
@@ -363,6 +365,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'description': 'md5:64249768eec3bc4276236606ea996373',
                 'uploader': 'justintimberlakeVEVO',
                 'uploader_id': 'justintimberlakeVEVO',
+                'age_limit': 18,
             }
         },
         {
@@ -378,6 +381,26 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_id': 'setindia'
             }
         },
+        {
+            'url': 'http://www.youtube.com/watch?v=BaW_jenozKcj&v=UxxajLWwzqY',
+            'note': 'Use the first video ID in the URL',
+            'info_dict': {
+                'id': 'BaW_jenozKc',
+                'ext': 'mp4',
+                'title': 'youtube-dl test video "\'/\\ä↭𝕐',
+                'uploader': 'Philipp Hagemeister',
+                'uploader_id': 'phihag',
+                '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,
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
         {
             'url': 'http://www.youtube.com/watch?v=a9LDPn-MO4I',
             'note': '256k DASH audio (format 141) via DASH manifest',
@@ -419,7 +442,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'id': 'nfWlot6h_JM',
                 'ext': 'm4a',
                 'title': 'Taylor Swift - Shake It Off',
-                'description': 'md5:2acfda1b285bdd478ccec22f9918199d',
+                'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3',
                 'uploader': 'TaylorSwiftVEVO',
                 'uploader_id': 'TaylorSwiftVEVO',
                 'upload_date': '20140818',
@@ -453,6 +476,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader': 'The Witcher',
                 'uploader_id': 'WitcherGame',
                 'upload_date': '20140605',
+                'age_limit': 18,
             },
         },
         # Age-gate video with encrypted signature
@@ -466,6 +490,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader': 'LloydVEVO',
                 'uploader_id': 'LloydVEVO',
                 'upload_date': '20110629',
+                'age_limit': 18,
             },
         },
         # video_info is None (https://github.com/rg3/youtube-dl/issues/4421)
@@ -490,7 +515,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'info_dict': {
                 'id': 'lqQg6PlCWgI',
                 'ext': 'mp4',
-                'upload_date': '20120731',
+                'upload_date': '20120724',
                 'uploader_id': 'olympic',
                 'description': 'HO09  - Women -  GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
                 'uploader': 'Olympics',
@@ -519,7 +544,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'url': 'qEJwOuvDf7I',
             'info_dict': {
                 'id': 'qEJwOuvDf7I',
-                'ext': 'mp4',
+                'ext': 'webm',
                 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
                 'description': '',
                 'upload_date': '20150404',
@@ -562,6 +587,59 @@ 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):
@@ -893,6 +971,8 @@ 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')
@@ -1009,6 +1089,55 @@ 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:
@@ -1034,13 +1163,6 @@ 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="(.*?)">',
@@ -1080,26 +1202,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             unescapeHTML(m.group('content'))
             for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
 
-        # 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 = ''
-
         def _extract_count(count_name):
             return str_to_int(self._search_regex(
                 r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'