[youtube] Construct a playlist URL in case the page is missing one

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

diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index 0301682b8dd228cab336bc1e68eaf868660fd5c7..aacb999ce9044ba07af7597d03b34e1aa37ebddd 100644 (file)
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -1399,6 +1399,22 @@ class YoutubeChannelIE(InfoExtractor):
         channel_id = self._match_id(url)
 
         url = self._TEMPLATE_URL % channel_id
+
+        # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
+        # Workaround by extracting as a playlist if managed to obtain channel playlist URL
+        # otherwise fallback on channel by page extraction
+        channel_page = self._download_webpage(
+            url + '?view=57', channel_id,
+            'Downloading channel page', fatal=False)
+        channel_playlist_id = self._search_regex(
+            [r'<meta itemprop="channelId" content="([^"]+)">',
+             r'data-channel-external-id="([^"]+)"'],
+            channel_page, '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(
+                compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
+
         channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
         autogenerated = re.search(r'''(?x)
                 class="[^"]*?(?: