kumi/yt-dlp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[vimeo] Fix extractors

Browse source 
Closes #3037, Closes #2858, Closes #2880, Closes #3712
May also fix #3602, #3360
This commit is contained in:
pukkandan 2022-05-18 05:11:47 +05:30
parent d6bf1161db
commit aedaa455d9
No known key found for this signature in database
GPG key ID: 7EEE9E1E817D0A39
3 changed files with 21 additions and 15 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
yt_dlp/extractor/dropout.py
View file

@ -137,7 +137,7 @@ class DropoutIE(InfoExtractor):
return { return {
'_type': 'url_transparent', '_type': 'url_transparent',
'ie_key': VHXEmbedIE.ie_key(), 'ie_key': VHXEmbedIE.ie_key(),
'url': embed_url, 'url': VHXEmbedIE._smuggle_referrer(embed_url, 'https://www.dropout.tv'),
'id': self._search_regex(r'embed\.vhx\.tv/videos/(.+?)\?', embed_url, 'id'), 'id': self._search_regex(r'embed\.vhx\.tv/videos/(.+?)\?', embed_url, 'id'),
'display_id': display_id, 'display_id': display_id,
'title': title, 'title': title,

2
yt_dlp/extractor/generic.py
View file

@ -2954,7 +2954,7 @@ class GenericIE(InfoExtractor):
if vimeo_urls: if vimeo_urls:
return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key()) return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
vhx_url = VHXEmbedIE._extract_url(webpage) vhx_url = VHXEmbedIE._extract_url(url, webpage)
if vhx_url: if vhx_url:
return self.url_result(vhx_url, VHXEmbedIE.ie_key()) return self.url_result(vhx_url, VHXEmbedIE.ie_key())

32
yt_dlp/extractor/vimeo.py
View file

@ -40,6 +40,18 @@ class VimeoBaseInfoExtractor(InfoExtractor):
_LOGIN_REQUIRED = False _LOGIN_REQUIRED = False
_LOGIN_URL = 'https://vimeo.com/log_in' _LOGIN_URL = 'https://vimeo.com/log_in'
@staticmethod
def _smuggle_referrer(url, referrer_url):
return smuggle_url(url, {'http_headers': {'Referer': referrer_url}})
def _unsmuggle_headers(self, url):
"""@returns (url, smuggled_data, headers)"""
url, data = unsmuggle_url(url, {})
headers = self.get_param('http_headers').copy()
if 'http_headers' in data:
headers.update(data['http_headers'])
return url, data, headers
def _perform_login(self, username, password): def _perform_login(self, username, password):
webpage = self._download_webpage( webpage = self._download_webpage(
self._LOGIN_URL, None, 'Downloading login page') self._LOGIN_URL, None, 'Downloading login page')
@ -717,10 +729,6 @@ class VimeoIE(VimeoBaseInfoExtractor):
# vimeo embed with check-password page protected by Referer header # vimeo embed with check-password page protected by Referer header
] ]
@staticmethod
def _smuggle_referrer(url, referrer_url):
return smuggle_url(url, {'http_headers': {'Referer': referrer_url}})
@staticmethod @staticmethod
def _extract_urls(url, webpage): def _extract_urls(url, webpage):
urls = [] urls = []
@ -754,8 +762,8 @@ class VimeoIE(VimeoBaseInfoExtractor):
'Content-Type': 'application/x-www-form-urlencoded', 'Content-Type': 'application/x-www-form-urlencoded',
}) })
checked = self._download_json( checked = self._download_json(
url + '/check-password', video_id, f'{compat_urlparse.urlsplit(url)._replace(query=None).geturl()}/check-password',
'Verifying the password', data=data, headers=headers) video_id, 'Verifying the password', data=data, headers=headers)
if checked is False: if checked is False:
raise ExtractorError('Wrong video password', expected=True) raise ExtractorError('Wrong video password', expected=True)
return checked return checked
@ -830,10 +838,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
raise raise
def _real_extract(self, url): def _real_extract(self, url):
url, data = unsmuggle_url(url, {}) url, data, headers = self._unsmuggle_headers(url)
headers = self.get_param('http_headers').copy()
if 'http_headers' in data:
headers.update(data['http_headers'])
if 'Referer' not in headers: if 'Referer' not in headers:
headers['Referer'] = url headers['Referer'] = url
@ -1383,14 +1388,15 @@ class VHXEmbedIE(VimeoBaseInfoExtractor):
_VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)' _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
@staticmethod @staticmethod
def _extract_url(webpage): def _extract_url(url, webpage):
mobj = re.search( mobj = re.search(
r'<iframe[^>]+src="(https?://embed\.vhx\.tv/videos/\d+[^"]*)"', webpage) r'<iframe[^>]+src="(https?://embed\.vhx\.tv/videos/\d+[^"]*)"', webpage)
return unescapeHTML(mobj.group(1)) if mobj else None return VimeoIE._smuggle_referrer(unescapeHTML(mobj.group(1)), url) if mobj else None
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) url, _, headers = self._unsmuggle_headers(url)
webpage = self._download_webpage(url, video_id, headers=headers)
config_url = self._parse_json(self._search_regex( config_url = self._parse_json(self._search_regex(
r'window\.OTTData\s*=\s*({.+})', webpage, r'window\.OTTData\s*=\s*({.+})', webpage,
'ott data'), video_id, js_to_json)['config_url'] 'ott data'), video_id, js_to_json)['config_url']