Update README.md

[youtubedl] / youtube_dl / extractor / youtube.py

diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index ce2212a7caa13111e1d2835fa65be371a4937847..02f3ab61aef7be11e68f7f16985823b9d908e70e 100644 (file)
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -77,7 +77,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
 
     def _set_language(self):
         self._set_cookie(
 
     def _set_language(self):
         self._set_cookie(

-            '.youtube.com', 'PREF', 'f1=50000000&hl=en',
+            '.youtube.com', 'PREF', 'f1=50000000&f6=8&hl=en',

             # YouTube sets the expire time to about two months
             expire_time=time.time() + 2 * 30 * 24 * 3600)
 
             # YouTube sets the expire time to about two months
             expire_time=time.time() + 2 * 30 * 24 * 3600)
 


@@ -303,7 +303,7 @@ class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
                     # Downloading page may result in intermittent 5xx HTTP error
                     # that is usually worked around with a retry
                     more = self._download_json(
                     # Downloading page may result in intermittent 5xx HTTP error
                     # that is usually worked around with a retry
                     more = self._download_json(

-                        'https://youtube.com/%s' % mobj.group('more'), playlist_id,
+                        'https://www.youtube.com/%s' % mobj.group('more'), playlist_id,

                         'Downloading page #%s%s'
                         % (page_num, ' (retry #%d)' % count if count else ''),
                         transform_source=uppercase_escape,
                         'Downloading page #%s%s'
                         % (page_num, ' (retry #%d)' % count if count else ''),
                         transform_source=uppercase_escape,


@@ -1264,7 +1264,23 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'params': {
                 'skip_download': True,
             },
             'params': {
                 'skip_download': True,
             },

-        }
+        },
+        {
+            # empty description results in an empty string
+            'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
+            'info_dict': {
+                'id': 'x41yOUIvK2k',
+                'ext': 'mp4',
+                'title': 'IMG 3456',
+                'description': '',
+                'upload_date': '20170613',
+                'uploader_id': 'ElevageOrVert',
+                'uploader': 'ElevageOrVert',
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },

     ]
 
     def __init__(self, *args, **kwargs):
     ]
 
     def __init__(self, *args, **kwargs):


@@ -1384,7 +1400,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         funcname = self._search_regex(
             (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
              r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
         funcname = self._search_regex(
             (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
              r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',

-             r'\b(?P<sig>[a-zA-Z0-9$]{2})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
+             r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',

              r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
              # Obsolete patterns
              r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
              r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
              # Obsolete patterns
              r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',


@@ -1825,7 +1841,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         # Get video info
         video_info = {}
         embed_webpage = None
         # Get video info
         video_info = {}
         embed_webpage = None

-        if re.search(r'player-age-gate-content">', video_webpage) is not None:
+        if (self._og_search_property('restrictions:age', video_webpage, default=None) == '18+'
+                or re.search(r'player-age-gate-content">', video_webpage) is not None):

             age_gate = True
             # We simulate the access to the video from www.youtube.com/v/{video_id}
             # this can be viewed without login into Youtube
             age_gate = True
             # We simulate the access to the video from www.youtube.com/v/{video_id}
             # this can be viewed without login into Youtube


@@ -1930,7 +1947,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             ''', replace_url, video_description)
             video_description = clean_html(video_description)
         else:
             ''', replace_url, video_description)
             video_description = clean_html(video_description)
         else:

-            video_description = self._html_search_meta('description', video_webpage) or video_details.get('shortDescription')
+            video_description = video_details.get('shortDescription')
+            if video_description is None:
+                video_description = self._html_search_meta('description', video_webpage)

 
         if not smuggled_data.get('force_singlefeed', False):
             if not self._downloader.params.get('noplaylist'):
 
         if not smuggled_data.get('force_singlefeed', False):
             if not self._downloader.params.get('noplaylist'):


@@ -2356,17 +2375,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         m_cat_container = self._search_regex(
             r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
             video_webpage, 'categories', default=None)
         m_cat_container = self._search_regex(
             r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
             video_webpage, 'categories', default=None)

+        category = None

         if m_cat_container:
             category = self._html_search_regex(
                 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
                 default=None)
         if m_cat_container:
             category = self._html_search_regex(
                 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
                 default=None)

-            video_categories = None if category is None else [category]
-        else:
-            video_categories = None
+        if not category:
+            category = try_get(
+                microformat, lambda x: x['category'], compat_str)
+        video_categories = None if category is None else [category]

 
         video_tags = [
             unescapeHTML(m.group('content'))
             for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
 
         video_tags = [
             unescapeHTML(m.group('content'))
             for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]

+        if not video_tags:
+            video_tags = try_get(video_details, lambda x: x['keywords'], list)

 
         def _extract_count(count_name):
             return str_to_int(self._search_regex(
 
         def _extract_count(count_name):
             return str_to_int(self._search_regex(


@@ -2772,7 +2795,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
         ids = []
         last_id = playlist_id[-11:]
         for n in itertools.count(1):
         ids = []
         last_id = playlist_id[-11:]
         for n in itertools.count(1):

-            url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
+            url = 'https://www.youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)

             webpage = self._download_webpage(
                 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
             new_ids = orderedSet(re.findall(
             webpage = self._download_webpage(
                 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
             new_ids = orderedSet(re.findall(


@@ -3004,7 +3027,7 @@ class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
 
 class YoutubeUserIE(YoutubeChannelIE):
     IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
 
 class YoutubeUserIE(YoutubeChannelIE):
     IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'

-    _VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:(?P<user>user|c)/)?(?!(?:attribution_link|watch|results|shared)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)'
+    _VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:(?P<user>user|c)/)?(?!(?:attribution_link|watch|results|shared)(?:$|[^a-z_A-Z0-9%-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_%-]+)'

     _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
     IE_NAME = 'youtube:user'
 
     _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
     IE_NAME = 'youtube:user'
 


@@ -3034,6 +3057,9 @@ class YoutubeUserIE(YoutubeChannelIE):
     }, {
         'url': 'https://www.youtube.com/c/gametrailers',
         'only_matching': True,
     }, {
         'url': 'https://www.youtube.com/c/gametrailers',
         'only_matching': True,

+    }, {
+        'url': 'https://www.youtube.com/c/Pawe%C5%82Zadro%C5%BCniak',
+        'only_matching': True,

     }, {
         'url': 'https://www.youtube.com/gametrailers',
         'only_matching': True,
     }, {
         'url': 'https://www.youtube.com/gametrailers',
         'only_matching': True,


@@ -3112,7 +3138,7 @@ class YoutubeLiveIE(YoutubeBaseInfoExtractor):
 
 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
     IE_DESC = 'YouTube.com user/channel playlists'
 
 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
     IE_DESC = 'YouTube.com user/channel playlists'

-    _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
+    _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel|c)/(?P<id>[^/]+)/playlists'

     IE_NAME = 'youtube:playlists'
 
     _TESTS = [{
     IE_NAME = 'youtube:playlists'
 
     _TESTS = [{


@@ -3138,6 +3164,9 @@ class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
             'title': 'Chem Player',
         },
         'skip': 'Blocked',
             'title': 'Chem Player',
         },
         'skip': 'Blocked',

+    }, {
+        'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
+        'only_matching': True,

     }]
 
 
     }]
 
 


@@ -3282,7 +3311,7 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
                 break
 
             more = self._download_json(
                 break
 
             more = self._download_json(

-                'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
+                'https://www.youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,

                 'Downloading page #%s' % page_num,
                 transform_source=uppercase_escape,
                 headers=self._YOUTUBE_CLIENT_HEADERS)
                 'Downloading page #%s' % page_num,
                 transform_source=uppercase_escape,
                 headers=self._YOUTUBE_CLIENT_HEADERS)