[youtube:search] Support hashtag entries (#3265)

Authored-by: coletdjnz

yt_dlp/extractor/archiveorg.py

@@ -457,7 +457,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
     _OLDEST_CAPTURE_DATE = 20050214000000
     _NEWEST_CAPTURE_DATE = 20500101000000
 
-    def _call_cdx_api(self, item_id, url, filters: list = None, collapse: list = None, query: dict = None, note='Downloading CDX API JSON'):
+    def _call_cdx_api(self, item_id, url, filters: list = None, collapse: list = None, query: dict = None, note=None, fatal=False):
         # CDX docs: https://github.com/internetarchive/wayback/blob/master/wayback-cdx-server/README.md
         query = {
             'url': url,
@@ -468,7 +468,9 @@ class YoutubeWebArchiveIE(InfoExtractor):
             'collapse': collapse or [],
             **(query or {})
         }
-        res = self._download_json('https://web.archive.org/cdx/search/cdx', item_id, note, query=query)
+        res = self._download_json(
+            'https://web.archive.org/cdx/search/cdx', item_id,
+            note or 'Downloading CDX API JSON', query=query, fatal=fatal)
         if isinstance(res, list) and len(res) >= 2:
             # format response to make it easier to use
             return list(dict(zip(res[0], v)) for v in res[1:])

yt_dlp/extractor/nebula.py

@@ -86,7 +86,7 @@ class NebulaBaseIE(InfoExtractor):
             # if 401 or 403, attempt credential re-auth and retry
             if exc.cause and isinstance(exc.cause, urllib.error.HTTPError) and exc.cause.code in (401, 403):
                 self.to_screen(f'Reauthenticating to Nebula and retrying, because last {auth_type} call resulted in error {exc.cause.code}')
-                self._login()
+                self._perform_login()
                 return inner_call()
             else:
                 raise

yt_dlp/extractor/rai.py

@@ -118,7 +118,7 @@ class RaiBaseIE(InfoExtractor):
         })
 
     def _create_http_urls(self, relinker_url, fmts):
-        _RELINKER_REG = r'https?://(?P<host>[^/]+?)/(?:i/)?(?P<extra>[^/]+?)/(?P<path>.+?)/(?P<id>\d+)(?:_(?P<quality>[\d\,]+))?(?:\.mp4|/playlist\.m3u8).+?'
+        _RELINKER_REG = r'https?://(?P<host>[^/]+?)/(?:i/)?(?P<extra>[^/]+?)/(?P<path>.+?)/(?P<id>\w+)(?:_(?P<quality>[\d\,]+))?(?:\.mp4|/playlist\.m3u8).+?'
         _MP4_TMPL = '%s&overrideUserAgentRule=mp4-%s'
         _QUALITY = {
             # tbr: w, h

yt_dlp/extractor/youtube.py

@@ -3903,6 +3903,13 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
         if video_id:
             return self._extract_video(video_renderer)
 
+    def _hashtag_tile_entry(self, hashtag_tile_renderer):
+        url = urljoin('https://youtube.com', traverse_obj(
+            hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
+        if url:
+            return self.url_result(
+                url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
+
     def _post_thread_entries(self, post_thread_renderer):
         post_renderer = try_get(
             post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
@@ -3991,6 +3998,7 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
                     'videoRenderer': lambda x: [self._video_entry(x)],
                     'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
                     'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
+                    'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
                 }
                 for key, renderer in isr_content.items():
                     if key not in known_renderers:
@@ -5520,7 +5528,17 @@ class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
             'id': 'python',
             'title': 'python',
         }
-
+    }, {
+        'url': 'https://www.youtube.com/results?search_query=%23cats',
+        'playlist_mincount': 1,
+        'info_dict': {
+            'id': '#cats',
+            'title': '#cats',
+            'entries': [{
+                'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
+                'title': '#cats',
+            }],
+        },
     }, {
         'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
         'only_matching': True,