yt_dlp/extractor/altcensored.py

@@ -33,7 +33,7 @@ class AltCensoredIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        res = self.url_result(f'https://archive.org/details/youtube-{video_id}', ArchiveOrgIE)
+        res = self.url_result('https://archive.org/details/youtube-%s' % video_id, ArchiveOrgIE)
         # Extractor indirection doesn't allow merging info from the original extractor.
         # Youtube view count or thumbnail extracted from altcensored can't be merge back
         # into underlying archive.org info json
@@ -41,7 +41,7 @@ class AltCensoredIE(InfoExtractor):
 
 
 class AltCensoredChannelIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)altcensored\.com/channel/(?!page|table)(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:www\.)altcensored\.com/channel/(?P<id>[^/?#]+)'
     _PAGE_SIZE = 24
     _TESTS = [{
         'url': 'https://www.altcensored.com/channel/UCFPTO55xxHqFqkzRZHu4kcw',
@@ -57,20 +57,20 @@ class AltCensoredChannelIE(InfoExtractor):
 
         webpage = self._download_webpage(url, channel_id, note='Download channel info',
                                          errnote='Unable to get channel info')
-        title = self._html_search_meta('altcen_title', webpage, 'title', fatal=False)
+        title = self._html_search_meta('og:title', webpage)
-        page_count = int_or_none(self._html_search_regex(
+        page_count = int(self._html_search_regex(r'<a href="/channel/\w+/page/(\d+)">(?:\1)</a>', webpage, 'page count'))
-            r'<a[^>]+href="/channel/\w+/page/(\d+)">(?:\1)</a>', webpage, 'page count', default='1'))
 
         def page_func(page_num):
-            page_num += 1
             webpage = self._download_webpage(
-                f'https://altcensored.com/channel/{channel_id}/page/{page_num}',
+                'https://altcensored.com/channel/%s/page/%d' % (channel_id, page_num + 1),
-                channel_id, note=f'Downloading page {page_num}')
+                channel_id, note='Download page #%d' % (page_num + 1),
+                errnote='Unable to get page #%d' % (page_num + 1),
+            )
 
             items = re.findall(r'<a[^>]+href="(/watch\?v=[^"]+)', webpage)
-            return [self.url_result(urljoin('https://www.altcensored.com', path), AltCensoredIE)
+            # deduplicate consecutive items (multiple <a> per video)
-                    for path in orderedSet(items)]
+            items = [self.url_result('https://www.altcensored.com' + key, AltCensoredIE) for key, _group in groupby(items)]
+            return items
 
-        return self.playlist_result(
+        entries = InAdvancePagedList(page_func, page_count, self._PAGE_SIZE)
-            InAdvancePagedList(page_func, page_count, self._PAGE_SIZE),
+        return self.playlist_result(entries, playlist_id=channel_id, playlist_title=title)
-            playlist_id=channel_id, playlist_title=title)