import itertools
from .common import InfoExtractor
+from .subtitles import SubtitlesInfoExtractor
from ..utils import (
+ compat_HTTPError,
compat_urllib_parse,
compat_urllib_request,
-
clean_html,
get_element_by_attribute,
ExtractorError,
RegexNotFoundError,
std_headers,
unsmuggle_url,
+ urlencode_postdata,
)
-class VimeoIE(InfoExtractor):
+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
_VALID_URL = r'''(?x)
- (?P<proto>https?://)?
+ (?P<proto>(?:https?:)?//)?
(?:(?:www|(?P<player>player))\.)?
vimeo(?P<pro>pro)?\.com/
(?:.*?/)?
(?:videos?/)?
(?P<id>[0-9]+)
/?(?:[?&].*)?(?:[#].*)?$'''
- _NETRC_MACHINE = 'vimeo'
IE_NAME = 'vimeo'
_TESTS = [
{
'url': 'http://vimeo.com/56015672#at=0',
- 'file': '56015672.mp4',
'md5': '8879b6cc097e987f02484baf890129e5',
'info_dict': {
- "upload_date": "20121220",
- "description": "This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
- "uploader_id": "user7108434",
- "uploader": "Filippo Valsorda",
+ 'id': '56015672',
+ 'ext': 'mp4',
+ "upload_date": "20121220",
+ "description": "This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
+ "uploader_id": "user7108434",
+ "uploader": "Filippo Valsorda",
"title": "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
},
},
'videopassword': 'youtube-dl',
},
},
+ {
+ 'url': 'http://vimeo.com/76979871',
+ 'md5': '3363dd6ffebe3784d56f4132317fd446',
+ 'note': 'Video with subtitles',
+ 'info_dict': {
+ 'id': '76979871',
+ 'ext': 'mp4',
+ 'title': 'The New Vimeo Player (You Know, For Videos)',
+ 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
+ 'upload_date': '20131015',
+ 'uploader_id': 'staff',
+ 'uploader': 'Vimeo Staff',
+ }
+ },
]
- 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)
# Extract ID from URL
mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError('Invalid URL: %s' % url)
-
video_id = mobj.group('id')
if mobj.group('pro') or mobj.group('player'):
url = 'http://player.vimeo.com/video/' + video_id
# 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,
# Extract video thumbnail
video_thumbnail = config["video"].get("thumbnail")
if video_thumbnail is None:
- _, video_thumbnail = sorted((int(width), t_url) for (width, t_url) in config["video"]["thumbs"].items())[-1]
+ video_thumbs = config["video"].get("thumbs")
+ if video_thumbs and isinstance(video_thumbs, dict):
+ _, video_thumbnail = sorted((int(width), t_url) for (width, t_url) in video_thumbs.items())[-1]
# Extract video description
video_description = None
if len(formats) == 0:
raise ExtractorError('No known codec found')
+ subtitles = {}
+ text_tracks = config['request'].get('text_tracks')
+ if text_tracks:
+ for tt in text_tracks:
+ subtitles[tt['lang']] = 'http://vimeo.com' + tt['url']
+
+ video_subtitles = self.extract_subtitles(video_id, subtitles)
+ if self._downloader.params.get('listsubtitles', False):
+ self._list_available_subtitles(video_id, subtitles)
+ return
+
return {
- 'id': video_id,
+ 'id': video_id,
'uploader': video_uploader,
'uploader_id': video_uploader_id,
- 'upload_date': video_upload_date,
- 'title': video_title,
- 'thumbnail': video_thumbnail,
- 'description': video_description,
+ 'upload_date': video_upload_date,
+ 'title': video_title,
+ 'thumbnail': video_thumbnail,
+ 'description': video_description,
'formats': formats,
'webpage_url': url,
'view_count': view_count,
'like_count': like_count,
'comment_count': comment_count,
+ 'subtitles': video_subtitles,
}
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="(.*?)"'
class VimeoUserIE(VimeoChannelIE):
IE_NAME = 'vimeo:user'
- _VALID_URL = r'(?:https?://)?vimeo.\com/(?P<name>[^/]+)(?:/videos|[#?]|$)'
+ _VALID_URL = r'(?:https?://)?vimeo\.com/(?P<name>[^/]+)(?:/videos|[#?]|$)'
_TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
@classmethod
class VimeoAlbumIE(VimeoChannelIE):
IE_NAME = 'vimeo:album'
- _VALID_URL = r'(?:https?://)?vimeo.\com/album/(?P<id>\d+)'
+ _VALID_URL = r'(?:https?://)?vimeo\.com/album/(?P<id>\d+)'
_TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
def _page_url(self, base_url, pagenum):
class VimeoGroupsIE(VimeoAlbumIE):
IE_NAME = 'vimeo:group'
- _VALID_URL = r'(?:https?://)?vimeo.\com/groups/(?P<name>[^/]+)'
+ _VALID_URL = r'(?:https?://)?vimeo\.com/groups/(?P<name>[^/]+)'
def _extract_list_title(self, webpage):
return self._og_search_title(webpage)
class VimeoReviewIE(InfoExtractor):
IE_NAME = 'vimeo:review'
IE_DESC = 'Review pages on vimeo'
- _VALID_URL = r'(?:https?://)?vimeo.\com/[^/]+/review/(?P<id>[^/]+)'
+ _VALID_URL = r'(?:https?://)?vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
_TEST = {
'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
'file': '75524534.mp4',
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')
projects / youtube-dl / blobdiff