[youtube] Move more tests to Playlist IE, and simply suitable.

[youtube-dl] / youtube_dl / extractor / youtube.py

diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index c77f09aace1b3c46a870121041b966baa930e7bb..47ff53a35fa2bd08d46e60d0958ba1581ef45212 100644 (file)
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -221,6 +221,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                          )
                      )?                                                       # all until now is optional -> you can pass the naked ID
                      ([0-9A-Za-z_-]{11})                                      # here is it! the YouTube video ID
+                     (?!.*?&list=)                                            # combined list/video URLs are handled by the playlist IE
                      (?(1).+)?                                                # if we found the ID, everything can follow
                      $"""
     _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
@@ -387,13 +388,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
         },
     ]
 
-
-    @classmethod
-    def suitable(cls, url):
-        """Receives a URL and returns True if suitable for this IE."""
-        if YoutubePlaylistIE.suitable(url): return False
-        return re.match(cls._VALID_URL, url) is not None
-
     def __init__(self, *args, **kwargs):
         super(YoutubeIE, self).__init__(*args, **kwargs)
         self._player_cache = {}
@@ -1020,6 +1014,46 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
     _MORE_PAGES_INDICATOR = r'data-link-type="next"'
     _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)'
     IE_NAME = u'youtube:playlist'
+    _TESTS = [{
+        'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
+        'info_dict': {
+            'title': 'ytdl test PL',
+        },
+        'playlist_count': 3,
+    }, {
+        'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
+        'info_dict': {
+            'title': 'YDL_Empty_List',
+        },
+        'playlist_count': 0,
+    }, {
+        'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
+        'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
+        'info_dict': {
+            'title': '29C3: Not my department',
+        },
+        'playlist_count': 95,
+    }, {
+        'note': 'issue #673',
+        'url': 'PLBB231211A4F62143',
+        'info_dict': {
+            'title': 'Team Fortress 2 (Class-based LP)',
+        },
+        'playlist_mincount': 26,
+    }, {
+        'note': 'Large playlist',
+        'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
+        'info_dict': {
+            'title': 'Uploads from Cauchemar',
+        },
+        'playlist_mincount': 799,
+    }, {
+        'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
+        'info_dict': {
+            'title': 'YDL_safe_search',
+        },
+        'playlist_count': 2,
+    }]
 
     def _real_initialize(self):
         self._login()
@@ -1118,6 +1152,7 @@ class YoutubeTopListIE(YoutubePlaylistIE):
     IE_DESC = (u'YouTube.com top lists, "yttoplist:{channel}:{list title}"'
         u' (Example: "yttoplist:music:Top Tracks")')
     _VALID_URL = r'yttoplist:(?P<chann>.*?):(?P<title>.*?)$'
+    _TESTS = []
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -1397,6 +1432,7 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
                                           u'%s feed' % self._FEED_NAME,
                                           u'Downloading page %s' % i)
             feed_html = info.get('feed_html') or info.get('content_html')
+            load_more_widget_html = info.get('load_more_widget_html') or feed_html
             m_ids = re.finditer(r'"/watch\?v=(.*?)["&]', feed_html)
             ids = orderedSet(m.group(1) for m in m_ids)
             feed_entries.extend(
@@ -1404,7 +1440,7 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
                 for video_id in ids)
             mobj = re.search(
                 r'data-uix-load-more-href="/?[^"]+paging=(?P<paging>\d+)',
-                feed_html)
+                load_more_widget_html)
             if mobj is None:
                 break
             paging = mobj.group('paging')
@@ -1446,6 +1482,7 @@ class YoutubeSubscriptionsIE(YoutubePlaylistIE):
     IE_NAME = u'youtube:subscriptions'
     IE_DESC = u'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
     _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
+    _TESTS = []
 
     def _real_extract(self, url):
         title = u'Youtube Subscriptions'