unsmuggle_url,
urlencode_postdata,
urljoin,
- unescapeHTML,
urlhandle_detect_ext,
)
_LOGIN_REQUIRED = False
_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):
webpage = self._download_webpage(
self._LOGIN_URL, None, 'Downloading login page')
def _set_vimeo_cookie(self, name, value):
self._set_cookie('vimeo.com', name, value)
- def _vimeo_sort_formats(self, formats):
- # Note: Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
- # at the same time without actual units specified.
- self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source'))
-
def _parse_config(self, config, video_id):
video_data = config['video']
- video_title = video_data['title']
+ video_title = video_data.get('title')
live_event = video_data.get('live_event') or {}
is_live = live_event.get('status') == 'started'
request = config.get('request') or {}
'formats': formats,
'subtitles': subtitles,
'is_live': is_live,
+ # Note: Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
+ # at the same time without actual units specified.
+ '_format_sort_fields': ('quality', 'res', 'fps', 'hdr:12', 'source'),
}
def _extract_original_format(self, url, video_id, unlisted_hash=None):
/?(?:[?&].*)?(?:[#].*)?$
'''
IE_NAME = 'vimeo'
+ _EMBED_REGEX = [
+ # iframe
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
+ # Embedded (swf embed) Vimeo player
+ r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
+ # Non-standard embedded Vimeo player
+ r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
+ ]
_TESTS = [
{
'url': 'http://vimeo.com/56015672#at=0',
# 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
- def _extract_urls(url, webpage):
- urls = []
- # Look for embedded (iframe) Vimeo player
- for mobj in re.finditer(
- r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
- webpage):
- urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url')), url))
- PLAIN_EMBED_RE = (
- # Look for embedded (swf embed) Vimeo player
- r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
- # Look more for non-standard embedded Vimeo player
- r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
- )
- for embed_re in PLAIN_EMBED_RE:
- for mobj in re.finditer(embed_re, webpage):
- urls.append(mobj.group('url'))
- return urls
+ @classmethod
+ def _extract_embed_urls(cls, url, webpage):
+ for embed_url in super()._extract_embed_urls(url, webpage):
+ yield cls._smuggle_referrer(embed_url, url)
- @staticmethod
- def _extract_url(url, webpage):
- urls = VimeoIE._extract_urls(url, webpage)
- return urls[0] if urls else None
+ @classmethod
+ def _extract_url(cls, url, webpage):
+ return next(cls._extract_embed_urls(url, webpage), None)
def _verify_player_video_password(self, url, video_id, headers):
password = self._get_video_password()
'Content-Type': 'application/x-www-form-urlencoded',
})
checked = self._download_json(
- url + '/check-password', video_id,
- 'Verifying the password', data=data, headers=headers)
+ f'{compat_urlparse.urlsplit(url)._replace(query=None).geturl()}/check-password',
+ video_id, 'Verifying the password', data=data, headers=headers)
if checked is False:
raise ExtractorError('Wrong video password', expected=True)
return checked
})
info = self._parse_config(self._download_json(
video['config_url'], video_id), video_id)
- self._vimeo_sort_formats(info['formats'])
get_timestamp = lambda x: parse_iso8601(video.get(x + '_time'))
info.update({
'description': video.get('description'),
raise
def _real_extract(self, url):
- url, data = unsmuggle_url(url, {})
- headers = self.get_param('http_headers').copy()
- if 'http_headers' in data:
- headers.update(data['http_headers'])
+ url, data, headers = self._unsmuggle_headers(url)
if 'Referer' not in headers:
headers['Referer'] = url
if '://player.vimeo.com/video/' in url:
config = self._parse_json(self._search_regex(
- r'\bconfig\s*=\s*({.+?})\s*;', webpage, 'info section'), video_id)
+ r'\b(?:playerC|c)onfig\s*=\s*({.+?})\s*;', webpage, 'info section'), video_id)
if config.get('view') == 4:
config = self._verify_player_video_password(
redirect_url, video_id, headers)
- info = self._parse_config(config, video_id)
- self._vimeo_sort_formats(info['formats'])
- return info
+ return self._parse_config(config, video_id)
if re.search(r'<form[^>]+?id="pw_form"', webpage):
video_password = self._get_video_password()
info_dict_config = self._parse_config(config, video_id)
formats.extend(info_dict_config['formats'])
- self._vimeo_sort_formats(formats)
+ info_dict['_format_sort_fields'] = info_dict_config['_format_sort_fields']
json_ld = self._search_json_ld(webpage, video_id, default={})
return merge_dicts(info_dict, info_dict_config, json_ld)
-class VimeoOndemandIE(VimeoIE):
+class VimeoOndemandIE(VimeoIE): # XXX: Do not subclass from concrete IE
IE_NAME = 'vimeo:ondemand'
_VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?:[^/]+/)?(?P<id>[^/?#&]+)'
_TESTS = [{
return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id)
-class VimeoUserIE(VimeoChannelIE):
+class VimeoUserIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE
IE_NAME = 'vimeo:user'
- _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos|[#?]|$)'
+ _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos)?/?(?:$|[?#])'
_TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
_TESTS = [{
'url': 'https://vimeo.com/nkistudio/videos',
'id': 'nkistudio',
},
'playlist_mincount': 66,
+ }, {
+ 'url': 'https://vimeo.com/nkistudio/',
+ 'only_matching': True,
}]
_BASE_URL_TEMPL = 'https://vimeo.com/%s'
entries, album_id, album.get('name'), album.get('description'))
-class VimeoGroupsIE(VimeoChannelIE):
+class VimeoGroupsIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE
IE_NAME = 'vimeo:group'
_VALID_URL = r'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)'
_TESTS = [{
page_url + '/action', video_id)
if source_format:
info_dict['formats'].append(source_format)
- self._vimeo_sort_formats(info_dict['formats'])
info_dict['description'] = clean_html(clip_data.get('description'))
return info_dict
-class VimeoWatchLaterIE(VimeoChannelIE):
+class VimeoWatchLaterIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE
IE_NAME = 'vimeo:watchlater'
- IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
+ IE_DESC = 'Vimeo watch later list, ":vimeowatchlater" keyword (requires authentication)'
_VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
_TITLE = 'Watch Later'
_LOGIN_REQUIRED = True
return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
-class VimeoLikesIE(VimeoChannelIE):
+class VimeoLikesIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE
_VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
IE_NAME = 'vimeo:likes'
IE_DESC = 'Vimeo user likes'
class VHXEmbedIE(VimeoBaseInfoExtractor):
IE_NAME = 'vhx:embed'
_VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
+ _EMBED_REGEX = [r'<iframe[^>]+src="(?P<url>https?://embed\.vhx\.tv/videos/\d+[^"]*)"']
- @staticmethod
- def _extract_url(webpage):
- mobj = re.search(
- r'<iframe[^>]+src="(https?://embed\.vhx\.tv/videos/\d+[^"]*)"', webpage)
- return unescapeHTML(mobj.group(1)) if mobj else None
+ @classmethod
+ def _extract_embed_urls(cls, url, webpage):
+ for embed_url in super()._extract_embed_urls(url, webpage):
+ yield cls._smuggle_referrer(embed_url, url)
def _real_extract(self, 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(
r'window\.OTTData\s*=\s*({.+})', webpage,
'ott data'), video_id, js_to_json)['config_url']
config = self._download_json(config_url, video_id)
info = self._parse_config(config, video_id)
info['id'] = video_id
- self._vimeo_sort_formats(info['formats'])
return info
projects / yt-dlp.git / blobdiff