|
|
@ -107,46 +107,54 @@ class TwitterBaseIE(InfoExtractor):
|
|
|
|
'x-twitter-active-user': 'yes',
|
|
|
|
'x-twitter-active-user': 'yes',
|
|
|
|
})
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
|
|
result, last_error = None, None
|
|
|
|
last_error = None
|
|
|
|
for bearer_token in self._TOKENS:
|
|
|
|
for bearer_token in self._TOKENS:
|
|
|
|
headers['Authorization'] = f'Bearer {bearer_token}'
|
|
|
|
for first_attempt in (True, False):
|
|
|
|
|
|
|
|
headers['Authorization'] = f'Bearer {bearer_token}'
|
|
|
|
|
|
|
|
|
|
|
|
if not self.is_logged_in:
|
|
|
|
if not self.is_logged_in:
|
|
|
|
if not self._TOKENS[bearer_token]:
|
|
|
|
|
|
|
|
headers.pop('x-guest-token', None)
|
|
|
|
|
|
|
|
guest_token_response = self._download_json(
|
|
|
|
|
|
|
|
self._API_BASE + 'guest/activate.json', video_id,
|
|
|
|
|
|
|
|
'Downloading guest token', data=b'', headers=headers)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
self._TOKENS[bearer_token] = guest_token_response.get('guest_token')
|
|
|
|
|
|
|
|
if not self._TOKENS[bearer_token]:
|
|
|
|
if not self._TOKENS[bearer_token]:
|
|
|
|
raise ExtractorError('Could not retrieve guest token')
|
|
|
|
headers.pop('x-guest-token', None)
|
|
|
|
headers['x-guest-token'] = self._TOKENS[bearer_token]
|
|
|
|
guest_token_response = self._download_json(
|
|
|
|
|
|
|
|
self._API_BASE + 'guest/activate.json', video_id,
|
|
|
|
try:
|
|
|
|
'Downloading guest token', data=b'', headers=headers)
|
|
|
|
allowed_status = {400, 403, 404} if graphql else {403}
|
|
|
|
|
|
|
|
result = self._download_json(
|
|
|
|
self._TOKENS[bearer_token] = guest_token_response.get('guest_token')
|
|
|
|
(self._GRAPHQL_API_BASE if graphql else self._API_BASE) + path,
|
|
|
|
if not self._TOKENS[bearer_token]:
|
|
|
|
video_id, headers=headers, query=query, expected_status=allowed_status)
|
|
|
|
raise ExtractorError('Could not retrieve guest token')
|
|
|
|
break
|
|
|
|
|
|
|
|
|
|
|
|
headers['x-guest-token'] = self._TOKENS[bearer_token]
|
|
|
|
except ExtractorError as e:
|
|
|
|
|
|
|
|
if last_error:
|
|
|
|
try:
|
|
|
|
raise last_error
|
|
|
|
allowed_status = {400, 403, 404} if graphql else {403}
|
|
|
|
elif not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code != 404:
|
|
|
|
result = self._download_json(
|
|
|
|
raise
|
|
|
|
(self._GRAPHQL_API_BASE if graphql else self._API_BASE) + path,
|
|
|
|
last_error = e
|
|
|
|
video_id, headers=headers, query=query, expected_status=allowed_status)
|
|
|
|
self.report_warning(
|
|
|
|
|
|
|
|
'Twitter API gave 404 response, retrying with deprecated token. '
|
|
|
|
except ExtractorError as e:
|
|
|
|
'Only one media item can be extracted')
|
|
|
|
if last_error:
|
|
|
|
|
|
|
|
raise last_error
|
|
|
|
if result.get('errors'):
|
|
|
|
|
|
|
|
error_message = ', '.join(set(traverse_obj(
|
|
|
|
if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code != 404:
|
|
|
|
result, ('errors', ..., 'message'), expected_type=str))) or 'Unknown error'
|
|
|
|
raise
|
|
|
|
raise ExtractorError(f'Error(s) while querying api: {error_message}', expected=True)
|
|
|
|
|
|
|
|
|
|
|
|
last_error = e
|
|
|
|
assert result is not None
|
|
|
|
self.report_warning(
|
|
|
|
return result
|
|
|
|
'Twitter API gave 404 response, retrying with deprecated auth token. '
|
|
|
|
|
|
|
|
'Only one media item can be extracted')
|
|
|
|
|
|
|
|
break # continue outer loop with next bearer_token
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if result.get('errors'):
|
|
|
|
|
|
|
|
errors = traverse_obj(result, ('errors', ..., 'message'), expected_type=str)
|
|
|
|
|
|
|
|
if first_attempt and any('bad guest token' in error.lower() for error in errors):
|
|
|
|
|
|
|
|
self.to_screen('Guest token has expired. Refreshing guest token')
|
|
|
|
|
|
|
|
self._TOKENS[bearer_token] = None
|
|
|
|
|
|
|
|
continue
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
error_message = ', '.join(set(errors)) or 'Unknown error'
|
|
|
|
|
|
|
|
raise ExtractorError(f'Error(s) while querying API: {error_message}', expected=True)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
return result
|
|
|
|
|
|
|
|
|
|
|
|
def _build_graphql_query(self, media_id):
|
|
|
|
def _build_graphql_query(self, media_id):
|
|
|
|
raise NotImplementedError('Method must be implemented to support GraphQL')
|
|
|
|
raise NotImplementedError('Method must be implemented to support GraphQL')
|
|
|
@ -328,7 +336,7 @@ class TwitterIE(TwitterBaseIE):
|
|
|
|
'id': '665052190608723968',
|
|
|
|
'id': '665052190608723968',
|
|
|
|
'display_id': '665052190608723968',
|
|
|
|
'display_id': '665052190608723968',
|
|
|
|
'ext': 'mp4',
|
|
|
|
'ext': 'mp4',
|
|
|
|
'title': 'md5:3f57ab5d35116537a2ae7345cd0060d8',
|
|
|
|
'title': 'md5:55fef1d5b811944f1550e91b44abb82e',
|
|
|
|
'description': 'A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens. https://t.co/OkSqT2fjWJ',
|
|
|
|
'description': 'A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens. https://t.co/OkSqT2fjWJ',
|
|
|
|
'uploader_id': 'starwars',
|
|
|
|
'uploader_id': 'starwars',
|
|
|
|
'uploader': r're:Star Wars.*',
|
|
|
|
'uploader': r're:Star Wars.*',
|
|
|
@ -364,6 +372,7 @@ class TwitterIE(TwitterBaseIE):
|
|
|
|
# Test case of TwitterCardIE
|
|
|
|
# Test case of TwitterCardIE
|
|
|
|
'skip_download': True,
|
|
|
|
'skip_download': True,
|
|
|
|
},
|
|
|
|
},
|
|
|
|
|
|
|
|
'skip': 'Dead external link',
|
|
|
|
}, {
|
|
|
|
}, {
|
|
|
|
'url': 'https://twitter.com/jaydingeer/status/700207533655363584',
|
|
|
|
'url': 'https://twitter.com/jaydingeer/status/700207533655363584',
|
|
|
|
'info_dict': {
|
|
|
|
'info_dict': {
|
|
|
@ -568,10 +577,10 @@ class TwitterIE(TwitterBaseIE):
|
|
|
|
'id': '1577855447914409984',
|
|
|
|
'id': '1577855447914409984',
|
|
|
|
'display_id': '1577855540407197696',
|
|
|
|
'display_id': '1577855540407197696',
|
|
|
|
'ext': 'mp4',
|
|
|
|
'ext': 'mp4',
|
|
|
|
'title': 'oshtru \U0001faac\U0001f47d - gm \u2728\ufe0f now I can post image and video. nice update.',
|
|
|
|
'title': 'md5:9d198efb93557b8f8d5b78c480407214',
|
|
|
|
'description': 'gm \u2728\ufe0f now I can post image and video. nice update. https://t.co/cG7XgiINOm',
|
|
|
|
'description': 'md5:b9c3699335447391d11753ab21c70a74',
|
|
|
|
'upload_date': '20221006',
|
|
|
|
'upload_date': '20221006',
|
|
|
|
'uploader': 'oshtru \U0001faac\U0001f47d',
|
|
|
|
'uploader': 'oshtru',
|
|
|
|
'uploader_id': 'oshtru',
|
|
|
|
'uploader_id': 'oshtru',
|
|
|
|
'uploader_url': 'https://twitter.com/oshtru',
|
|
|
|
'uploader_url': 'https://twitter.com/oshtru',
|
|
|
|
'thumbnail': r're:^https?://.*\.jpg',
|
|
|
|
'thumbnail': r're:^https?://.*\.jpg',
|
|
|
@ -1096,7 +1105,6 @@ class TwitterBroadcastIE(TwitterBaseIE, PeriscopeBaseIE):
|
|
|
|
class TwitterSpacesIE(TwitterBaseIE):
|
|
|
|
class TwitterSpacesIE(TwitterBaseIE):
|
|
|
|
IE_NAME = 'twitter:spaces'
|
|
|
|
IE_NAME = 'twitter:spaces'
|
|
|
|
_VALID_URL = TwitterBaseIE._BASE_REGEX + r'i/spaces/(?P<id>[0-9a-zA-Z]{13})'
|
|
|
|
_VALID_URL = TwitterBaseIE._BASE_REGEX + r'i/spaces/(?P<id>[0-9a-zA-Z]{13})'
|
|
|
|
_TWITTER_GRAPHQL = 'https://twitter.com/i/api/graphql/HPEisOmj1epUNLCWTYhUWw/'
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
_TESTS = [{
|
|
|
|
_TESTS = [{
|
|
|
|
'url': 'https://twitter.com/i/spaces/1RDxlgyvNXzJL',
|
|
|
|
'url': 'https://twitter.com/i/spaces/1RDxlgyvNXzJL',
|
|
|
|