Fix TT blocking

Add TikTokVM
Partial fix for TikTokUser

youtube_dl/extractor/extractors.py

@@ -1249,6 +1249,7 @@ from .threeqsdn import ThreeQSDNIE
 from .tiktok import (
     TikTokIE,
     TikTokUserIE,
+    TikTokVMIE,
 )
 from .tinypic import TinyPicIE
 from .tmz import (

youtube_dl/extractor/tiktok.py

@@ -1,15 +1,18 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
+from .generic import GenericIE
 from ..compat import (
-    compat_str,
+    compat_kwargs,
-    compat_urllib_request,
 )
 from ..utils import (
+    dict_get,
     ExtractorError,
     float_or_none,
-    HEADRequest,
+    get_element_by_id,
     int_or_none,
     str_or_none,
     try_get,
@@ -17,24 +20,37 @@ from ..utils import (
 )
 
 
+# decorator enforces UA that TT doesn't block
+def vanilla_UA_request(func):
+
+    vanilla_UA = 'Mozilla/5.0'
+
+    def wrapped(*args, **kwargs):
+        headers = kwargs.get('headers', {})
+        if 'User-Agent' not in headers:
+            headers['User-Agent'] = vanilla_UA
+            kwargs.update({'headers': headers, })
+            kwargs = compat_kwargs(kwargs)
+        return func(*args, **kwargs)
+
+    return wrapped
+
+
 class TikTokBaseIE(InfoExtractor):
-    def _download_webpage(
+    IE_DESC = 'Abstract base for TikTok extractors'
-            self, url_or_request, video_id, note=None, errnote=None,
+    IE_NAME = 'tiktok:base'
-            fatal=True, tries=1, timeout=5, encoding=None, data=None,
-            headers={}, query={}, expected_status=None, setup=True):
 
-        if setup:
+    @vanilla_UA_request
-            url = url_or_request.geturl() if isinstance(url_or_request, compat_urllib_request.Request) else url_or_request
+    def _request_webpage(self, *args, **kwargs):
-            # dummy request to set cookies
+        return super(TikTokBaseIE, self)._request_webpage(*args, **kwargs)
-            self._request_webpage(
-                HEADRequest(url), video_id,
-                note=False, errnote='Could not send HEAD request to %s' % url,
-                fatal=False, headers=headers)
 
-        return super(TikTokBaseIE, self)._download_webpage(
+    def _get_SIGI_STATE(self, video_id, html):
-            url_or_request, video_id, note=note, errnote=errnote,
+        state = self._parse_json(
-            fatal=fatal, tries=tries, timeout=timeout, encoding=encoding, data=data,
+            get_element_by_id('SIGI_STATE', html)
-            headers=headers, query=query, expected_status=expected_status)
+            or self._search_regex(
+                r'''(?s)<script\s[^>]*?\bid\s*=\s*(?P<q>"|'|\b)sigi-persisted-data(?P=q)[^>]*>[^=]*=\s*(?P<json>{.+?})\s*(?:;[^<]+)?</script''',
+                html, 'sigi data', default='{}', group='json'), video_id)
+        return state if isinstance(state, dict) else {}
 
     def _extract_video(self, data, video_id=None):
         video = try_get(data, lambda x: x['video'], dict)
@@ -102,18 +118,20 @@ class TikTokBaseIE(InfoExtractor):
 
 
 class TikTokIE(TikTokBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?tiktok\.com/@[^/]+/video/(?P<id>\d+)'
+    IE_DESC = 'TikTok video extractor'
+    IE_NAME = 'tiktok'
+    _VALID_URL = r'(?:https?://(?:(?:www|m)\.)?tiktok\.com/@[^/]+/video/|tiktok:(?P<user_id>[^/?#&]+):)(?P<id>\d+)'
     _TESTS = [{
         'url': 'https://www.tiktok.com/@zureeal/video/6606727368545406213',
         'md5': '163ceff303bb52de60e6887fe399e6cd',
         'info_dict': {
             'id': '6606727368545406213',
             'ext': 'mp4',
-            'title': 'md5:24acc456b62b938a7e2dd88e978b20d9',
+            'title': 'md5:363e08ccb6c691314710429f379bffe5',
             'description': '#bowsette#mario#cosplay#uk#lgbt#gaming#asian#bowsettecosplay',
             'thumbnail': r're:^https?://.*',
             'duration': 15,
-            'uploader': 'md5:24acc456b62b938a7e2dd88e978b20d9',
+            'uploader': 'md5:363e08ccb6c691314710429f379bffe5',
             'uploader_id': '188294915489964032',
             'timestamp': 1538248586,
             'upload_date': '20180929',
@@ -124,78 +142,85 @@ class TikTokIE(TikTokBaseIE):
         }
     }]
 
+    def _real_initialize(self):
+        # Setup session (will set necessary cookies)
+        self._request_webpage(
+            'https://www.tiktok.com/', None, note='Setting up session')
+
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        m = re.match(self._VALID_URL, url).groupdict()
+        video_id = m['id']
+        if 'user_id' in m:
+            url = 'https://www.tiktok.com/@%(user_id)s/video/%(id)s/' % m
 
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(url.replace('://m.', '://www.'), video_id)
 
-        page_props = self._parse_json(self._search_regex(
+        page_props = self._get_SIGI_STATE(video_id, webpage)
-            r'''(?s)<script\s[^>]*?\bid\s*=\s*(?P<q>"|'|\b)sigi-persisted-data(?P=q)[^>]*>[^=]*=\s*(?P<json>{.+?})\s*(?:;[^<]+)?</script''',
+        if try_get(page_props, lambda x: x['ItemModule'][video_id]['video'], dict):
-            webpage, 'sigi data', default='{}', group='json'), video_id)
-        data = try_get(page_props, lambda x: x['ItemModule'][video_id]['video'], dict)
-        if data:
             data = page_props['ItemModule'][video_id]
             if data.get('privateItem'):
                 raise ExtractorError('This video is private', expected=True)
             return self._extract_video(data, video_id)
 
-        page_props = self._parse_json(self._search_regex(
+        # old page format - may still be served?
-            r'<script[^>]+\bid=["\']__NEXT_DATA__[^>]+>\s*({.+?})\s*</script',
+        page_props = self._parse_json(
-            webpage, 'data'), video_id)['props']['pageProps']
+            get_element_by_id('__NEXT_DATA__', webpage),
+            video_id)['props']['pageProps']
         data = try_get(page_props, lambda x: x['itemInfo']['itemStruct'], dict)
         if not data and page_props.get('statusCode') == 10216:
             raise ExtractorError('This video is private', expected=True)
         return self._extract_video(data, video_id)
 
 
-class TikTokUserIE(TikTokBaseIE):
+class TikTokUserIE(TikTokIE):
-    _VALID_URL = r'https://(?:www\.)?tiktok\.com/@(?P<id>[^/?#&]+)'
+    IE_DESC = 'TikTok user profile extractor'
+    IE_NAME = 'tiktok:user'
+    _VALID_URL = r'https?://(?:(?:www|m)\.)?tiktok\.com/@(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'https://www.tiktok.com/@zureeal',
         'info_dict': {
             'id': '188294915489964032',
         },
-        'playlist_mincount': 24,
+        'playlist_mincount': 30,
+        'expected_warnings': [
+            'More videos are available',
+        ],
     }]
 
     @classmethod
     def suitable(cls, url):
-        return False if TikTokIE.suitable(url) else super(TikTokUserIE, cls).suitable(url)
+        return False if TikTokIE.suitable(url) else super(TikTokBaseIE, cls).suitable(url)
 
     def _real_extract(self, url):
         user_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, user_id)
+        webpage = self._download_webpage(url.replace('://m.', '://www.'), user_id)
-        page_props = self._parse_json(self._search_regex(
+
-            r'''(?s)<script\s[^>]*?\bid\s*=\s*(?P<q>"|'|\b)sigi-persisted-data(?P=q)[^>]*>[^=]*=\s*(?P<json>{.+?})\s*(?:;[^<]+)?</script''',
+        page_props = self._get_SIGI_STATE(user_id, webpage)
-            webpage, 'sigi data', default='{}', group='json'), user_id)
         user_data = try_get(page_props, lambda x: x['UserModule']['users'], dict)
-        entries = []
         if user_data:
             num_id = try_get(
                 user_data.values(),
-                lambda x: [user['id'] for user in x if user['uniqueId'] == user_id][0],
+                lambda x: [user['id'] for user in x if user['uniqueId'] == user_id and user['id'].isdigit()][0])
-                compat_str)
+            item_data = try_get(page_props, lambda x: x['ItemList']['user-post'], dict) or {}
-            item_data = try_get(page_props, lambda x: x['ItemModule'], dict)
+            item_list = dict_get(item_data, ('list', 'browserList'))
-            if item_data:
+            if not item_list:
-                item_data = item_data.values()
+                item_list = try_get(item_data, lambda x: [y['id'] for y in x['preloadList']], list)
-            for data in item_data or []:
+            entries = ['tiktok:%s:%s' % (user_id, x, ) for x in item_list or []]
-                if data.get('privateItem'):
+            if item_data.get('hasMore', False):
-                    continue
+                self._downloader.report_warning('More videos are available but the current extractor doesn\'t know how to find them')
-                item = self._extract_video(data, user_id)
+
-                if item:
+            result = entries and self.playlist_from_matches(entries, num_id, ie='TikTok')
-                    entries.append(item)
-            result = entries and self.playlist_result(entries, num_id)
-            if not result:
-                item_data = try_get(page_props, lambda x: x['ItemList']['user-post']['list'], list)
-                result = self.playlist_from_matches(item_data, playlist_id=num_id, getter=lambda m: 'tiktok:%s' % (m, ))
             if result:
                 result['display_id'] = user_id
                 return result
 
+        """
+        # this no longer works 2022-01
         data = self._download_json(
             'https://m.tiktok.com/h5/share/usr/list/%s/' % user_id, user_id,
             query={'_signature': '_'})
+        entries = []
         for aweme in data['aweme_list']:
             try:
                 entry = self._extract_video(aweme)
@@ -205,3 +230,27 @@ class TikTokUserIE(TikTokBaseIE):
             entries.append(entry)
 
         return self.playlist_result(entries, user_id)
+        """
+
+
+class TikTokVMIE(GenericIE):
+    IE_DESC = 'Resolver for TikTok shortcuts'
+    IE_NAME = 'tiktok:shortcut'
+    _VALID_URL = r'https?://(?:vm\.tiktok\.com|m\.tiktok\.com/v)/(?P<id>[^/?#&.]+)'
+    _TESTS = [{
+        'url': 'https://vm.tiktok.com/ZMLesneqK/',
+        'info_dict': {
+            'id': '7054218882072055046',
+            'ext': 'mp4',
+            'title': 'EddY',
+            'upload_date': '20220117',
+            'description': 'Hilft bestimmt gegen nervige Anrufer! 😂 #telefon #call #prank #fail #sprecher #stimme #voice #band #ansage #sound #comedy #unterhaltung #scammer #fy',
+            'timestamp': 1642438324,
+            'uploader': 'EddY',
+            'uploader_id': '6850021004246467590',
+        },
+    }]
+
+    @vanilla_UA_request
+    def _request_webpage(self, *args, **kwargs):
+        return super(GenericIE, self)._request_webpage(*args, **kwargs)