from .common import InfoExtractor
from .subtitles import SubtitlesInfoExtractor
from ..utils import (
+ compat_HTTPError,
compat_urllib_parse,
compat_urllib_request,
clean_html,
RegexNotFoundError,
std_headers,
unsmuggle_url,
+ urlencode_postdata,
)
-class VimeoIE(SubtitlesInfoExtractor):
+class VimeoBaseInfoExtractor(InfoExtractor):
+ _NETRC_MACHINE = 'vimeo'
+ _LOGIN_REQUIRED = False
+
+ def _login(self):
+ (username, password) = self._get_login_info()
+ if username is None:
+ if self._LOGIN_REQUIRED:
+ raise ExtractorError(u'No login info available, needed for using %s.' % self.IE_NAME, expected=True)
+ return
+ self.report_login()
+ login_url = 'https://vimeo.com/log_in'
+ webpage = self._download_webpage(login_url, None, False)
+ token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token')
+ data = urlencode_postdata({
+ 'email': username,
+ 'password': password,
+ 'action': 'login',
+ 'service': 'vimeo',
+ 'token': token,
+ })
+ login_request = compat_urllib_request.Request(login_url, data)
+ login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+ login_request.add_header('Cookie', 'xsrft=%s' % token)
+ self._download_webpage(login_request, None, False, 'Wrong login info')
+
+
+class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
"""Information extractor for vimeo.com."""
# _VALID_URL matches Vimeo URLs
(?:videos?/)?
(?P<id>[0-9]+)
/?(?:[?&].*)?(?:[#].*)?$'''
- _NETRC_MACHINE = 'vimeo'
IE_NAME = 'vimeo'
_TESTS = [
{
},
]
- def _login(self):
- (username, password) = self._get_login_info()
- if username is None:
- return
- self.report_login()
- login_url = 'https://vimeo.com/log_in'
- webpage = self._download_webpage(login_url, None, False)
- token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token')
- data = compat_urllib_parse.urlencode({'email': username,
- 'password': password,
- 'action': 'login',
- 'service': 'vimeo',
- 'token': token,
- })
- login_request = compat_urllib_request.Request(login_url, data)
- login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
- login_request.add_header('Cookie', 'xsrft=%s' % token)
- self._download_webpage(login_request, None, False, 'Wrong login info')
+ @classmethod
+ def suitable(cls, url):
+ if VimeoChannelIE.suitable(url):
+ # Otherwise channel urls like http://vimeo.com/channels/31259 would
+ # match
+ return False
+ else:
+ return super(VimeoIE, cls).suitable(url)
def _verify_video_password(self, url, video_id, webpage):
password = self._downloader.params.get('videopassword', None)
# Retrieve video webpage to extract further information
request = compat_urllib_request.Request(url, None, headers)
- webpage = self._download_webpage(request, video_id)
+ try:
+ webpage = self._download_webpage(request, video_id)
+ except ExtractorError as ee:
+ if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
+ errmsg = ee.cause.read()
+ if b'Because of its privacy settings, this video cannot be played here' in errmsg:
+ raise ExtractorError(
+ 'Cannot download embed-only video without embedding '
+ 'URL. Please call youtube-dl with the URL of the page '
+ 'that embeds this video.',
+ expected=True)
+ raise
# Now we begin extracting as much information as we can from what we
# retrieved. First we extract the information common to all extractors,
class VimeoChannelIE(InfoExtractor):
IE_NAME = 'vimeo:channel'
- _VALID_URL = r'(?:https?://)?vimeo\.com/channels/(?P<id>[^/]+)'
+ _VALID_URL = r'(?:https?://)?vimeo\.com/channels/(?P<id>[^/]+)/?(\?.*)?$'
_MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
_TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
video_id = mobj.group('id')
player_url = 'https://player.vimeo.com/player/' + video_id
return self.url_result(player_url, 'Vimeo', video_id)
+
+
+class VimeoWatchLaterIE(VimeoBaseInfoExtractor, VimeoChannelIE):
+ IE_NAME = 'vimeo:watchlater'
+ IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
+ _VALID_URL = r'https?://vimeo\.com/home/watchlater|:vimeowatchlater'
+ _LOGIN_REQUIRED = True
+ _TITLE_RE = r'href="/home/watchlater".*?>(.*?)<'
+
+ def _real_initialize(self):
+ self._login()
+
+ def _page_url(self, base_url, pagenum):
+ url = '%s/page:%d/' % (base_url, pagenum)
+ request = compat_urllib_request.Request(url)
+ # Set the header to get a partial html page with the ids,
+ # the normal page doesn't contain them.
+ request.add_header('X-Requested-With', 'XMLHttpRequest')
+ return request
+
+ def _real_extract(self, url):
+ return self._extract_videos('watchlater', 'https://vimeo.com/home/watchlater')