version 2020.11.08

ChangeLog

@@ -1,11 +1,18 @@
+version 2020.11.08
+Extractors
+* [youtube] age-gate fixes
+* [aliexpress] Added extractor
+* [polskieradio] Fixed title extraction
+* [tiktok] Added extractor
+
 version 2020.11.06
 Extractors
-* youtube fixes
-* Added onnetwork extractor
+* [youtube] fixes
+* [onnetwork] Added extractor
 
 version 2020.11.01.01
 Extractors
-* fixed youtube?
+* [youtube] fixes like/dislike extraction
 
 version 2020.11.01
 Core

haruhi_dl/extractor/polskieradio.py

@@ -78,9 +78,11 @@ class PolskieRadioIE(InfoExtractor):
 
         media_urls = set()
 
+        title = self._og_search_title(webpage).strip()
+
         for data_media in re.findall(r'<[^>]+data-media=({[^>]+})', content):
             media = self._parse_json(data_media, playlist_id, fatal=False)
-            if not media.get('file') or not media.get('desc'):
+            if not media.get('file'):
                 continue
             media_url = self._proto_relative_url(media['file'], 'http:')
             if media_url in media_urls:
@@ -89,14 +91,13 @@ class PolskieRadioIE(InfoExtractor):
             entries.append({
                 'id': compat_str(media['id']),
                 'url': media_url,
-                'title': compat_urllib_parse_unquote(media['desc']),
+                'title': compat_urllib_parse_unquote(media['desc']) or title,
                 'duration': int_or_none(media.get('length')),
                 'vcodec': 'none' if media.get('provider') == 'audio' else None,
                 'timestamp': timestamp,
                 'thumbnail': thumbnail_url
             })
 
-        title = self._og_search_title(webpage).strip()
         description = strip_or_none(self._og_search_description(webpage))
 
         return self.playlist_result(entries, playlist_id, title, description)

haruhi_dl/extractor/youtube.py

@@ -1680,8 +1680,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             data = compat_urllib_parse_urlencode({
                 'video_id': video_id,
                 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
-                'sts': self._search_regex(
-                    r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
+#                'sts': self._search_regex(
+ #                   r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
             })
             video_info_url = proto + '://www.youtube.com/get_video_info?' + data
             try:
@@ -1931,11 +1931,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                             player_url = self._search_regex(
                                 ASSETS_RE, embed_webpage, 'JS player URL')
 
-                        if player_url is None:
-                            player_url_json = self._search_regex(
-                                r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
-                                video_webpage, 'age gate player URL')
-                            player_url = json.loads(player_url_json)
+                        #if player_url is None:
+                        #    player_url_json = self._search_regex(
+                        #        r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
+                        #        video_webpage, 'age gate player URL')
+                        #    player_url = json.loads(player_url_json)
 
                     if 'sig' in url_data:
                         url += '&signature=' + url_data['sig'][0]

haruhi_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2020.11.06'
+__version__ = '2020.11.08'