yt_dlp/extractor/altcensored.py

@@ -4,7 +4,6 @@ from .common import InfoExtractor
 from .archiveorg import ArchiveOrgIE
 from ..utils import (
     int_or_none,
-    str_to_int,
     orderedSet,
     urljoin,
     InAdvancePagedList,
@@ -17,9 +16,9 @@ class AltCensoredIE(InfoExtractor):
     _TESTS = [{
         'url': 'https://www.altcensored.com/watch?v=k0srjLSkga8',
         'info_dict': {
-            'id': 'youtube-k0srjLSkga8',
+            "id": "youtube-k0srjLSkga8",
-            'ext': 'webm',
+            "ext": "webm",
-            'title': "QUELLES SONT LES CONSÉQUENCES DE L'HYPERSEXUALISATION DE LA SOCIÉTÉ ?",
+            "title": "QUELLES SONT LES CONSÉQUENCES DE L'HYPERSEXUALISATION DE LA SOCIÉTÉ ?",
             'display_id': 'k0srjLSkga8.webm',
             'release_date': '20180403',
             'creator': 'Virginie Vota',
@@ -38,12 +37,16 @@ class AltCensoredIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+        # Use most data from archive.org (extractor indirection)
+        # But try first to gather a couple of useful information from altcensored
         webpage = self._download_webpage(url, video_id)
-        yt_views = str_to_int(self._html_search_regex(r'YouTube Views:(?:\s| )*([\d,]+)', webpage, 'view count', default=''))
+        yt_views = int_or_none(self._html_search_regex(
-        category = self._html_search_regex(r'<a href="/category/\d+">\s*\n?\s*([^<]+)</a>', webpage, 'category', fatal=False)
+            r'YouTube Views:.*?([0-9,.]+)', webpage, 'view count', default='0').replace(',', ''))
-
+        category = self._html_search_regex(r'<a href="/category/.*?\n\s+([^<]+)', webpage, 'category')
-        return self.url_result(f'https://archive.org/details/youtube-{video_id}', ArchiveOrgIE, url_transparent=True,
+        # Hardcoded (very unlikely to need a change in a foreseeable future)
-                               view_count=yt_views, categories=[category])
+        res = self.url_result(f'https://archive.org/details/youtube-{video_id}', ArchiveOrgIE, url_transparent=True,
+                              yt_views=yt_views, category=category)
+        return res
 
 
 class AltCensoredChannelIE(InfoExtractor):