Merge 13ed574168 into 70c55cb08f

Authored by: a13ssandr0, pzhlkj6612

Co-authored-by: Mozi <29089388+pzhlkj6612@users.noreply.github.com>

yt_dlp/extractor/_extractors.py

@@ -1649,6 +1649,7 @@ from .radiokapital import (
     RadioKapitalIE,
     RadioKapitalShowIE,
 )
+from .radioradicale import RadioRadicaleIE
 from .radiozet import RadioZetPodcastIE
 from .radlive import (
     RadLiveChannelIE,

yt_dlp/extractor/bilibili.py

@@ -165,14 +165,18 @@ class BilibiliBaseIE(InfoExtractor):
         params['w_rid'] = hashlib.md5(f'{query}{self._get_wbi_key(video_id)}'.encode()).hexdigest()
         return params
 
-    def _download_playinfo(self, bvid, cid, headers=None, qn=None):
+    def _download_playinfo(self, bvid, cid, headers=None, **kwargs):
-        params = {'bvid': bvid, 'cid': cid, 'fnval': 4048}
+        params = {'bvid': bvid, 'cid': cid, 'fnval': 4048, **kwargs}
-        if qn:
+        if self.is_logged_in:
-            params['qn'] = qn
+            params.pop('try_look', None)
+        if kwargs.get('qn'):
+            note = f'Downloading video format {kwargs["qn"]} for cid {cid}'
+        else:
+            note = f'Downloading video formats for cid {cid}'
+
         return self._download_json(
             'https://api.bilibili.com/x/player/wbi/playurl', bvid,
-            query=self._sign_wbi(params, bvid), headers=headers,
+            query=self._sign_wbi(params, bvid), headers=headers, note=note)['data']
-            note=f'Downloading video formats for cid {cid} {qn or ""}')['data']
 
     def json2srt(self, json_data):
         srt_data = ''
@@ -286,7 +290,7 @@ class BilibiliBaseIE(InfoExtractor):
             ('data', 'interaction', 'graph_version', {int_or_none}))
         cid_edges = self._get_divisions(video_id, graph_version, {1: {'cid': cid}}, 1)
         for cid, edges in cid_edges.items():
-            play_info = self._download_playinfo(video_id, cid, headers=headers)
+            play_info = self._download_playinfo(video_id, cid, headers=headers, try_look=1)
             yield {
                 **metainfo,
                 'id': f'{video_id}_{cid}',
@@ -688,11 +692,12 @@ class BiliBiliIE(BilibiliBaseIE):
         aid = video_data.get('aid')
         old_video_id = format_field(aid, None, f'%s_part{part_id or 1}')
         cid = traverse_obj(video_data, ('pages', part_id - 1, 'cid')) if part_id else video_data.get('cid')
+        if is_festival or not self.is_logged_in:
+            query = {'try_look': 1} if not self.is_logged_in else {}
+            play_info = self._download_playinfo(video_id, cid, headers=headers, **query)
 
         festival_info = {}
         if is_festival:
-            play_info = self._download_playinfo(video_id, cid, headers=headers)
-
             festival_info = traverse_obj(initial_state, {
                 'uploader': ('videoInfo', 'upName'),
                 'uploader_id': ('videoInfo', 'upMid', {str_or_none}),
@@ -730,7 +735,7 @@ class BiliBiliIE(BilibiliBaseIE):
         else:
             formats = self.extract_formats(play_info)
 
-            if not traverse_obj(play_info, ('dash')):
+            if not play_info.get('dash'):
                 # we only have legacy formats and need additional work
                 has_qn = lambda x: x in traverse_obj(formats, (..., 'quality'))
                 for qn in traverse_obj(play_info, ('accept_quality', lambda _, v: not has_qn(v), {int})):
@@ -860,10 +865,16 @@ class BiliBiliBangumiIE(BilibiliBaseIE):
             self.raise_login_required('This video is for premium members only')
 
         headers['Referer'] = url
+
+        play_info = self._search_json(
+            r'playurlSSRData\s*?=\s*?', webpage, 'embedded page info', episode_id,
+            end_pattern='\n', default=None)
+        if not play_info:
             play_info = self._download_json(
                 'https://api.bilibili.com/pgc/player/web/v2/playurl', episode_id,
-            'Extracting episode', query={'fnval': '4048', 'ep_id': episode_id},
+                'Extracting episode', query={'fnval': 12240, 'ep_id': episode_id},
                 headers=headers)
+
         premium_only = play_info.get('code') == -10403
         play_info = traverse_obj(play_info, ('result', 'video_info', {dict})) or {}
 

yt_dlp/extractor/radioradicale.py

@@ -0,0 +1,105 @@
+from .common import InfoExtractor
+from ..utils import url_or_none
+from ..utils.traversal import traverse_obj
+
+
+class RadioRadicaleIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?radioradicale\.it/scheda/(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'https://www.radioradicale.it/scheda/471591',
+        'md5': 'eb0fbe43a601f1a361cbd00f3c45af4a',
+        'info_dict': {
+            'id': '471591',
+            'ext': 'mp4',
+            'title': 'md5:e8fbb8de57011a3255db0beca69af73d',
+            'description': 'md5:5e15a789a2fe4d67da8d1366996e89ef',
+            'location': 'Napoli',
+            'duration': 2852.0,
+            'timestamp': 1459987200,
+            'upload_date': '20160407',
+            'thumbnail': 'https://www.radioradicale.it/photo400/0/0/9/0/1/00901768.jpg',
+        },
+    }, {
+        'url': 'https://www.radioradicale.it/scheda/742783/parlamento-riunito-in-seduta-comune-11a-della-xix-legislatura',
+        'info_dict': {
+            'id': '742783',
+            'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
+            'description': '-) Votazione per l\'elezione di un giudice della Corte Costituzionale (nono scrutinio)',
+            'location': 'CAMERA',
+            'duration': 5868.0,
+            'timestamp': 1730246400,
+            'upload_date': '20241030',
+        },
+        'playlist': [{
+            'md5': 'aa48de55dcc45478e4cd200f299aab7d',
+            'info_dict': {
+                'id': '742783-0',
+                'ext': 'mp4',
+                'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
+            },
+        }, {
+            'md5': 'be915c189c70ad2920e5810f32260ff5',
+            'info_dict': {
+                'id': '742783-1',
+                'ext': 'mp4',
+                'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
+            },
+        }, {
+            'md5': 'f0ee4047342baf8ed3128a8417ac5e0a',
+            'info_dict': {
+                'id': '742783-2',
+                'ext': 'mp4',
+                'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
+            },
+        }],
+    }]
+
+    def _entries(self, videos_info, page_id):
+        for idx, video in enumerate(traverse_obj(
+                videos_info, ('playlist', lambda _, v: v['sources']))):
+            video_id = f'{page_id}-{idx}'
+            formats = []
+            subtitles = {}
+
+            for m3u8_url in traverse_obj(video, ('sources', ..., 'src', {url_or_none})):
+                fmts, subs = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id)
+                formats.extend(fmts)
+                self._merge_subtitles(subs, target=subtitles)
+            for sub in traverse_obj(video, ('subtitles', ..., lambda _, v: url_or_none(v['src']))):
+                self._merge_subtitles({sub.get('srclang') or 'und': [{
+                    'url': sub['src'],
+                    'name': sub.get('label'),
+                }]}, target=subtitles)
+
+            yield {
+                'id': video_id,
+                'title': video.get('title'),
+                'formats': formats,
+                'subtitles': subtitles,
+            }
+
+    def _real_extract(self, url):
+        page_id = self._match_id(url)
+        webpage = self._download_webpage(url, page_id)
+
+        videos_info = self._search_json(
+            r'jQuery\.extend\(Drupal\.settings\s*,',
+            webpage, 'videos_info', page_id)['RRscheda']
+
+        entries = list(self._entries(videos_info, page_id))
+
+        common_info = {
+            'id': page_id,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'location': videos_info.get('luogo'),
+            **self._search_json_ld(webpage, page_id),
+        }
+
+        if len(entries) == 1:
+            return {
+                **entries[0],
+                **common_info,
+            }
+
+        return self.playlist_result(entries, multi_video=True, **common_info)