ExtractorError,
InAdvancePagedList,
int_or_none,
+ merge_dicts,
NO_DEFAULT,
RegexNotFoundError,
sanitized_Request,
_LOGIN_URL = 'https://vimeo.com/log_in'
def _login(self):
- (username, password) = self._get_login_info()
+ username, password = self._get_login_info()
if username is None:
if self._LOGIN_REQUIRED:
raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
return
- self.report_login()
- webpage = self._download_webpage(self._LOGIN_URL, None, False)
+ webpage = self._download_webpage(
+ self._LOGIN_URL, None, 'Downloading login page')
token, vuid = self._extract_xsrft_and_vuid(webpage)
- data = urlencode_postdata({
+ data = {
'action': 'login',
'email': username,
'password': password,
'service': 'vimeo',
'token': token,
- })
- login_request = sanitized_Request(self._LOGIN_URL, data)
- login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
- login_request.add_header('Referer', self._LOGIN_URL)
+ }
self._set_vimeo_cookie('vuid', vuid)
- self._download_webpage(login_request, None, False, 'Wrong login info')
+ try:
+ self._download_webpage(
+ self._LOGIN_URL, None, 'Logging in',
+ data=urlencode_postdata(data), headers={
+ 'Content-Type': 'application/x-www-form-urlencoded',
+ 'Referer': self._LOGIN_URL,
+ })
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError) and e.cause.code == 418:
+ raise ExtractorError(
+ 'Unable to log in: bad username or password',
+ expected=True)
+ raise ExtractorError('Unable to log in')
def _verify_video_password(self, url, video_id, webpage):
password = self._downloader.params.get('videopassword')
else:
mpd_manifest_urls = [(format_id, manifest_url)]
for f_id, m_url in mpd_manifest_urls:
- formats.extend(self._extract_mpd_formats(
+ mpd_formats = self._extract_mpd_formats(
m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
'Downloading %s MPD information' % cdn_name,
- fatal=False))
+ fatal=False)
+ for f in mpd_formats:
+ if f.get('vcodec') == 'none':
+ f['preference'] = -50
+ elif f.get('acodec') == 'none':
+ f['preference'] = -40
+ formats.extend(mpd_formats)
subtitles = {}
text_tracks = config['request'].get('text_tracks')
'id': '56015672',
'ext': 'mp4',
'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
- 'description': 'md5:2d3305bad981a06ff79f027f19865021',
+ 'description': 'md5:509a9ad5c9bf97c60faee9203aca4479',
'timestamp': 1355990239,
'upload_date': '20121220',
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
urls = []
# Look for embedded (iframe) Vimeo player
for mobj in re.finditer(
- r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1',
+ 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 = (
request = sanitized_Request(url, headers=headers)
try:
webpage, urlh = self._download_webpage_handle(request, video_id)
+ redirect_url = compat_str(urlh.geturl())
# Some URLs redirect to ondemand can't be extracted with
# this extractor right away thus should be passed through
# ondemand extractor (e.g. https://vimeo.com/73445910)
- if VimeoOndemandIE.suitable(urlh.geturl()):
- return self.url_result(urlh.geturl(), VimeoOndemandIE.ie_key())
+ if VimeoOndemandIE.suitable(redirect_url):
+ return self.url_result(redirect_url, VimeoOndemandIE.ie_key())
except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
errmsg = ee.cause.read()
if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
if '_video_password_verified' in data:
raise ExtractorError('video password verification failed!')
- self._verify_video_password(url, video_id, webpage)
+ self._verify_video_password(redirect_url, video_id, webpage)
return self._real_extract(
- smuggle_url(url, {'_video_password_verified': 'verified'}))
+ smuggle_url(redirect_url, {'_video_password_verified': 'verified'}))
else:
raise ExtractorError('Unable to extract info section',
cause=e)
else:
if config.get('view') == 4:
- config = self._verify_player_video_password(url, video_id)
+ config = self._verify_player_video_password(redirect_url, video_id)
def is_rented():
if '>You rented this title.<' in webpage:
if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
source_name = source_file.get('public_name', 'Original')
if self._is_valid_url(download_url, video_id, '%s video' % source_name):
- ext = source_file.get('extension', determine_ext(download_url)).lower()
+ ext = (try_get(
+ source_file, lambda x: x['extension'],
+ compat_str) or determine_ext(
+ download_url, None) or 'mp4').lower()
formats.append({
'url': download_url,
'ext': ext,
'preference': 1,
})
- info_dict = self._parse_config(config, video_id)
- formats.extend(info_dict['formats'])
+ info_dict_config = self._parse_config(config, video_id)
+ formats.extend(info_dict_config['formats'])
self._vimeo_sort_formats(formats)
+ json_ld = self._search_json_ld(webpage, video_id, default={})
+
if not cc_license:
cc_license = self._search_regex(
r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
webpage, 'license', default=None, group='license')
- info_dict.update({
+ info_dict = {
'id': video_id,
'formats': formats,
'timestamp': unified_timestamp(timestamp),
'like_count': like_count,
'comment_count': comment_count,
'license': cc_license,
- })
+ }
+
+ info_dict = merge_dicts(info_dict, info_dict_config, json_ld)
return info_dict
class VimeoLikesIE(InfoExtractor):
- _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
+ _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
IE_NAME = 'vimeo:likes'
IE_DESC = 'Vimeo user likes'
- _TEST = {
+ _TESTS = [{
'url': 'https://vimeo.com/user755559/likes/',
'playlist_mincount': 293,
'info_dict': {
'description': 'See all the videos urza likes',
'title': 'Videos urza likes',
},
- }
+ }, {
+ 'url': 'https://vimeo.com/stormlapse/likes',
+ 'only_matching': True,
+ }]
def _real_extract(self, url):
user_id = self._match_id(url)
self._search_regex(
r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
.*?</a></li>\s*<li\s+class="pagination_next">
- ''', webpage, 'page count'),
+ ''', webpage, 'page count', default=1),
'page count', fatal=True)
PAGE_SIZE = 12
title = self._html_search_regex(
description = self._html_search_meta('description', webpage)
def _get_page(idx):
- page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % (
+ page_url = 'https://vimeo.com/%s/likes/page:%d/sort:date' % (
user_id, idx + 1)
webpage = self._download_webpage(
page_url, user_id,
return {
'_type': 'playlist',
- 'id': 'user%s_likes' % user_id,
+ 'id': '%s_likes' % user_id,
'title': title,
'description': description,
'entries': pl,
Rapsys Git / youtubedl / blobdiff