[ie/vimeo] Fix API headers (#9125)

Closes #9124
Authored by: bashonly

yt_dlp/extractor/_extractors.py

@@ -1394,6 +1394,7 @@ from .ora import OraTVIE
 from .orf import (
     ORFTVthekIE,
     ORFFM4StoryIE,
+    ORFONIE,
     ORFRadioIE,
     ORFPodcastIE,
     ORFIPTVIE,
@@ -2496,6 +2497,7 @@ from .zee5 import (
     Zee5SeriesIE,
 )
 from .zeenews import ZeeNewsIE
+from .zetland import ZetlandDKArticleIE
 from .zhihu import ZhihuIE
 from .zingmp3 import (
     ZingMp3IE,

yt_dlp/extractor/bilibili.py

@@ -7,6 +7,7 @@ import math
 import re
 import time
 import urllib.parse
+import uuid
 
 from .common import InfoExtractor, SearchInfoExtractor
 from ..dependencies import Cryptodome
@@ -1464,8 +1465,37 @@ class BiliBiliSearchIE(SearchInfoExtractor):
     IE_DESC = 'Bilibili video search'
     _MAX_RESULTS = 100000
     _SEARCH_KEY = 'bilisearch'
+    _TESTS = [{
+        'url': 'bilisearch3:靡烟 出道一年，我怎么还在等你单推的女人睡觉后开播啊',
+        'playlist_count': 3,
+        'info_dict': {
+            'id': '靡烟 出道一年，我怎么还在等你单推的女人睡觉后开播啊',
+            'title': '靡烟 出道一年，我怎么还在等你单推的女人睡觉后开播啊',
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': 'BV1n44y1Q7sc',
+                'ext': 'mp4',
+                'title': '“出道一年，我怎么还在等你单推的女人睡觉后开播啊？”【一分钟了解靡烟miya】',
+                'timestamp': 1669889987,
+                'upload_date': '20221201',
+                'description': 'md5:43343c0973defff527b5a4b403b4abf9',
+                'tags': list,
+                'uploader': '靡烟miya',
+                'duration': 123.156,
+                'uploader_id': '1958703906',
+                'comment_count': int,
+                'view_count': int,
+                'like_count': int,
+                'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
+                '_old_archive_ids': ['bilibili 988222410_part1'],
+            },
+        }],
+    }]
 
     def _search_results(self, query):
+        if not self._get_cookies('https://api.bilibili.com').get('buvid3'):
+            self._set_cookie('.bilibili.com', 'buvid3', f'{uuid.uuid4()}infoc')
         for page_num in itertools.count(1):
             videos = self._download_json(
                 'https://api.bilibili.com/x/web-interface/search/type', query,

yt_dlp/extractor/orf.py

@@ -1,3 +1,4 @@
+import base64
 import functools
 import re
 
@@ -565,3 +566,66 @@ class ORFFM4StoryIE(InfoExtractor):
             })
 
         return self.playlist_result(entries)
+
+
+class ORFONIE(InfoExtractor):
+    IE_NAME = 'orf:on'
+    _VALID_URL = r'https?://on\.orf\.at/video/(?P<id>\d{8})/(?P<slug>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://on.orf.at/video/14210000/school-of-champions-48',
+        'info_dict': {
+            'id': '14210000',
+            'ext': 'mp4',
+            'duration': 2651.08,
+            'thumbnail': 'https://api-tvthek.orf.at/assets/segments/0167/98/thumb_16697671_segments_highlight_teaser.jpeg',
+            'title': 'School of Champions (4/8)',
+            'description': 'md5:d09ad279fc2e8502611e7648484b6afd',
+            'media_type': 'episode',
+            'timestamp': 1706472362,
+            'upload_date': '20240128',
+        }
+    }]
+
+    def _extract_video(self, video_id, display_id):
+        encrypted_id = base64.b64encode(f'3dSlfek03nsLKdj4Jsd{video_id}'.encode()).decode()
+        api_json = self._download_json(
+            f'https://api-tvthek.orf.at/api/v4.3/public/episode/encrypted/{encrypted_id}', display_id)
+
+        formats, subtitles = [], {}
+        for manifest_type in traverse_obj(api_json, ('sources', {dict.keys}, ...)):
+            for manifest_url in traverse_obj(api_json, ('sources', manifest_type, ..., 'src', {url_or_none})):
+                if manifest_type == 'hls':
+                    fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                        manifest_url, display_id, fatal=False, m3u8_id='hls')
+                elif manifest_type == 'dash':
+                    fmts, subs = self._extract_mpd_formats_and_subtitles(
+                        manifest_url, display_id, fatal=False, mpd_id='dash')
+                else:
+                    continue
+                formats.extend(fmts)
+                self._merge_subtitles(subs, target=subtitles)
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'subtitles': subtitles,
+            **traverse_obj(api_json, {
+                'duration': ('duration_second', {float_or_none}),
+                'title': (('title', 'headline'), {str}),
+                'description': (('description', 'teaser_text'), {str}),
+                'media_type': ('video_type', {str}),
+            }, get_all=False),
+        }
+
+    def _real_extract(self, url):
+        video_id, display_id = self._match_valid_url(url).group('id', 'slug')
+        webpage = self._download_webpage(url, display_id)
+
+        return {
+            'id': video_id,
+            'title': self._html_search_meta(['og:title', 'twitter:title'], webpage, default=None),
+            'description': self._html_search_meta(
+                ['description', 'og:description', 'twitter:description'], webpage, default=None),
+            **self._search_json_ld(webpage, display_id, fatal=False),
+            **self._extract_video(video_id, display_id),
+        }

yt_dlp/extractor/vimeo.py

@@ -269,7 +269,7 @@ class VimeoBaseInfoExtractor(InfoExtractor):
             'https://vimeo.com/_rv/viewer', video_id, note='Downloading jwt token', fatal=False) or {}
         if not jwt_response.get('jwt'):
             return
-        headers = {'Authorization': 'jwt %s' % jwt_response['jwt']}
+        headers = {'Authorization': 'jwt %s' % jwt_response['jwt'], 'Accept': 'application/json'}
         original_response = self._download_json(
             f'https://api.vimeo.com/videos/{video_id}', video_id,
             headers=headers, fatal=False, expected_status=(403, 404)) or {}
@@ -751,6 +751,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
         video = self._download_json(
             api_url, video_id, headers={
                 'Authorization': 'jwt ' + token,
+                'Accept': 'application/json',
             }, query={
                 'fields': 'config_url,created_time,description,license,metadata.connections.comments.total,metadata.connections.likes.total,release_time,stats.plays',
             })
@@ -785,7 +786,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
         jwt = viewer['jwt']
         album = self._download_json(
             'https://api.vimeo.com/albums/' + album_id,
-            album_id, headers={'Authorization': 'jwt ' + jwt},
+            album_id, headers={'Authorization': 'jwt ' + jwt, 'Accept': 'application/json'},
             query={'fields': 'description,name,privacy'})
         if try_get(album, lambda x: x['privacy']['view']) == 'password':
             password = self.get_param('videopassword')
@@ -1147,10 +1148,12 @@ class VimeoAlbumIE(VimeoBaseInfoExtractor):
                 'https://api.vimeo.com/albums/%s/videos' % album_id,
                 album_id, 'Downloading page %d' % api_page, query=query, headers={
                     'Authorization': 'jwt ' + authorization,
+                    'Accept': 'application/json',
                 })['data']
         except ExtractorError as e:
             if isinstance(e.cause, HTTPError) and e.cause.status == 400:
                 return
+            raise
         for video in videos:
             link = video.get('link')
             if not link:
@@ -1171,7 +1174,7 @@ class VimeoAlbumIE(VimeoBaseInfoExtractor):
         jwt = viewer['jwt']
         album = self._download_json(
             'https://api.vimeo.com/albums/' + album_id,
-            album_id, headers={'Authorization': 'jwt ' + jwt},
+            album_id, headers={'Authorization': 'jwt ' + jwt, 'Accept': 'application/json'},
             query={'fields': 'description,name,privacy'})
         hashed_pass = None
         if try_get(album, lambda x: x['privacy']['view']) == 'password':

yt_dlp/extractor/zetland.py

@@ -0,0 +1,71 @@
+from .common import InfoExtractor
+from ..utils import merge_dicts, unified_timestamp, url_or_none
+from ..utils.traversal import traverse_obj
+
+
+class ZetlandDKArticleIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.zetland\.dk/\w+/(?P<id>(?P<story_id>\w{8})-(?P<uploader_id>\w{8})-(?:\w{5}))'
+    _TESTS = [{
+        'url': 'https://www.zetland.dk/historie/sO9aq2MY-a81VP3BY-66e69?utm_source=instagram&utm_medium=linkibio&utm_campaign=artikel',
+        'info_dict': {
+            'id': 'sO9aq2MY-a81VP3BY-66e69',
+            'ext': 'mp3',
+            'modified_date': '20240118',
+            'title': 'Afsnit 1: “Det føltes som en kidnapning.” ',
+            'upload_date': '20240116',
+            'uploader_id': 'a81VP3BY',
+            'modified_timestamp': 1705568739,
+            'release_timestamp': 1705377592,
+            'uploader_url': 'https://www.zetland.dk/skribent/a81VP3BY',
+            'uploader': 'Helle Fuusager',
+            'release_date': '20240116',
+            'thumbnail': r're:https://zetland\.imgix\.net/2aafe500-b14e-11ee-bf83-65d5e1283a57/Zetland_Image_1\.jpg',
+            'description': 'md5:9619d426772c133f5abb26db27f26a01',
+            'timestamp': 1705377592,
+            'series_id': '62d54630-e87b-4ab1-a255-8de58dbe1b14',
+        }
+
+    }]
+
+    def _real_extract(self, url):
+        display_id, uploader_id = self._match_valid_url(url).group('id', 'uploader_id')
+        webpage = self._download_webpage(url, display_id)
+
+        next_js_data = self._search_nextjs_data(webpage, display_id)['props']['pageProps']
+        story_data = traverse_obj(next_js_data, ('initialState', 'consume', 'story', 'story'))
+
+        formats = []
+        for audio_url in traverse_obj(story_data, ('story_content', 'meta', 'audioFiles', ..., {url_or_none})):
+            formats.append({
+                'url': audio_url,
+                'vcodec': 'none',
+            })
+
+        return merge_dicts({
+            'id': display_id,
+            'formats': formats,
+            'uploader_id': uploader_id
+        }, traverse_obj(story_data, {
+            'title': ((('story_content', 'content', 'title'), 'title'), {str}),
+            'uploader': ('sharer', 'name'),
+            'uploader_id': ('sharer', 'sharer_id'),
+            'description': ('story_content', 'content', 'socialDescription'),
+            'series_id': ('story_content', 'meta', 'seriesId'),
+            'release_timestamp': ('published_at', {unified_timestamp}),
+            'modified_timestamp': ('revised_at', {unified_timestamp}),
+        }, get_all=False), traverse_obj(next_js_data, ('metaInfo', {
+            'title': ((('meta', 'title'), ('ld', 'headline'), ('og', 'og:title'), ('og', 'twitter:title')), {str}),
+            'description': ((('meta', 'description'), ('ld', 'description'), ('og', 'og:description'), ('og', 'twitter:description')), {str}),
+            'uploader': ((('meta', 'author'), ('ld', 'author', 'name')), {str}),
+            'uploader_url': ('ld', 'author', 'url', {url_or_none}),
+            'thumbnail': ((('ld', 'image'), ('og', 'og:image'), ('og', 'twitter:image')), {url_or_none}),
+            'modified_timestamp': ('ld', 'dateModified', {unified_timestamp}),
+            'release_timestamp': ('ld', 'datePublished', {unified_timestamp}),
+            'timestamp': ('ld', 'dateCreated', {unified_timestamp}),
+        }), get_all=False), {
+            'title': self._html_search_meta(['title', 'og:title', 'twitter:title'], webpage),
+            'description': self._html_search_meta(['description', 'og:description', 'twitter:description'], webpage),
+            'thumbnail': self._html_search_meta(['og:image', 'twitter:image'], webpage),
+            'uploader': self._html_search_meta(['author'], webpage),
+            'release_timestamp': unified_timestamp(self._html_search_meta(['article:published_time'], webpage)),
+        }, self._search_json_ld(webpage, display_id, fatal=False))