[ie/matchtv] Fix extractor (#10190)

[yt-dlp.git] / yt_dlp / extractor / tiktok.py

diff --git a/yt_dlp/extractor/tiktok.py b/yt_dlp/extractor/tiktok.py
index dc74d4a1f5ae7522b42c31f3970fdbb321c41646..c3505b14fe93da483898faac57a8aa42c029311b 100644 (file)
--- a/yt_dlp/extractor/tiktok.py
+++ b/yt_dlp/extractor/tiktok.py
@@ -30,6 +30,7 @@
     try_call,
     try_get,
     url_or_none,
+    urlencode_postdata,
 )
 
 
@@ -43,8 +44,8 @@ class TikTokBaseIE(InfoExtractor):
         'iid': None,
         # TikTok (KR/PH/TW/TH/VN) = trill, TikTok (rest of world) = musical_ly, Douyin = aweme
         'app_name': 'musical_ly',
-        'app_version': '34.1.2',
-        'manifest_app_version': '2023401020',
+        'app_version': '35.1.3',
+        'manifest_app_version': '2023501030',
         # "app id": aweme = 1128, trill = 1180, musical_ly = 1233, universal = 0
         'aid': '0',
     }
@@ -114,7 +115,7 @@ def _get_universal_data(self, webpage, display_id):
             'universal data', display_id, end_pattern=r'</script>', default={}),
             ('__DEFAULT_SCOPE__', {dict})) or {}
 
-    def _call_api_impl(self, ep, query, video_id, fatal=True,
+    def _call_api_impl(self, ep, video_id, query=None, data=None, headers=None, fatal=True,
                        note='Downloading API JSON', errnote='Unable to download API page'):
         self._set_cookie(self._API_HOSTNAME, 'odin_tt', ''.join(random.choices('0123456789abcdef', k=160)))
         webpage_cookies = self._get_cookies(self._WEBPAGE_HOST)
@@ -125,7 +126,8 @@ def _call_api_impl(self, ep, query, video_id, fatal=True,
             fatal=fatal, note=note, errnote=errnote, headers={
                 'User-Agent': self._APP_USER_AGENT,
                 'Accept': 'application/json',
-            }, query=query)
+                **(headers or {}),
+            }, query=query, data=data)
 
     def _build_api_query(self, query):
         return filter_dict({
@@ -174,7 +176,7 @@ def _build_api_query(self, query):
             'openudid': ''.join(random.choices('0123456789abcdef', k=16)),
         })
 
-    def _call_api(self, ep, query, video_id, fatal=True,
+    def _call_api(self, ep, video_id, query=None, data=None, headers=None, fatal=True,
                   note='Downloading API JSON', errnote='Unable to download API page'):
         if not self._APP_INFO and not self._get_next_app_info():
             message = 'No working app info is available'
@@ -187,9 +189,11 @@ def _call_api(self, ep, query, video_id, fatal=True,
         max_tries = len(self._APP_INFO_POOL) + 1  # _APP_INFO_POOL + _APP_INFO
         for count in itertools.count(1):
             self.write_debug(str(self._APP_INFO))
-            real_query = self._build_api_query(query)
+            real_query = self._build_api_query(query or {})
             try:
-                return self._call_api_impl(ep, real_query, video_id, fatal, note, errnote)
+                return self._call_api_impl(
+                    ep, video_id, query=real_query, data=data, headers=headers,
+                    fatal=fatal, note=note, errnote=errnote)
             except ExtractorError as e:
                 if isinstance(e.cause, json.JSONDecodeError) and e.cause.pos == 0:
                     message = str(e.cause or e.msg)
@@ -204,17 +208,29 @@ def _call_api(self, ep, query, video_id, fatal=True,
                 raise
 
     def _extract_aweme_app(self, aweme_id):
-        feed_list = self._call_api(
-            'feed', {'aweme_id': aweme_id}, aweme_id, note='Downloading video feed',
-            errnote='Unable to download video feed').get('aweme_list') or []
-        aweme_detail = next((aweme for aweme in feed_list if str(aweme.get('aweme_id')) == aweme_id), None)
+        aweme_detail = traverse_obj(
+            self._call_api('multi/aweme/detail', aweme_id, data=urlencode_postdata({
+                'aweme_ids': f'[{aweme_id}]',
+                'request_source': '0',
+            }), headers={'X-Argus': ''}), ('aweme_details', 0, {dict}))
         if not aweme_detail:
-            raise ExtractorError('Unable to find video in feed', video_id=aweme_id)
+            raise ExtractorError('Unable to extract aweme detail info', video_id=aweme_id)
         return self._parse_aweme_video_app(aweme_detail)
 
     def _extract_web_data_and_status(self, url, video_id, fatal=True):
-        webpage = self._download_webpage(url, video_id, headers={'User-Agent': 'Mozilla/5.0'}, fatal=fatal) or ''
-        video_data, status = {}, None
+        video_data, status = {}, -1
+
+        res = self._download_webpage_handle(url, video_id, fatal=fatal, headers={'User-Agent': 'Mozilla/5.0'})
+        if res is False:
+            return video_data, status
+
+        webpage, urlh = res
+        if urllib.parse.urlparse(urlh.url).path == '/login':
+            message = 'TikTok is requiring login for access to this content'
+            if fatal:
+                self.raise_login_required(message)
+            self.report_warning(f'{message}. {self._login_hint()}')
+            return video_data, status
 
         if universal_data := self._get_universal_data(webpage, video_id):
             self.write_debug('Found universal data for rehydration')
@@ -1026,7 +1042,8 @@ def _entries(self, list_id, display_id):
             for retry in self.RetryManager():
                 try:
                     post_list = self._call_api(
-                        self._API_ENDPOINT, query, display_id, note=f'Downloading video list page {page}',
+                        self._API_ENDPOINT, display_id, query=query,
+                        note=f'Downloading video list page {page}',
                         errnote='Unable to download video list')
                 except ExtractorError as e:
                     if isinstance(e.cause, json.JSONDecodeError) and e.cause.pos == 0: