+ 'upload_date': video_upload_date,
+ 'title': video_title,
+ 'thumbnail': video_thumbnail,
+ 'description': video_description,
+ 'duration': video_duration,
+ '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>[^/]+)/?(\?.*)?$'
+ _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
+ _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
+
+ def _page_url(self, base_url, pagenum):
+ return '%s/videos/page:%d/' % (base_url, pagenum)
+
+ def _extract_list_title(self, webpage):
+ return self._html_search_regex(self._TITLE_RE, webpage, 'list title')
+
+ def _extract_videos(self, list_id, base_url):
+ video_ids = []
+ for pagenum in itertools.count(1):
+ webpage = self._download_webpage(
+ self._page_url(base_url, pagenum), list_id,
+ 'Downloading page %s' % pagenum)
+ video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage))
+ if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
+ break
+
+ entries = [self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo')
+ for video_id in video_ids]
+ return {'_type': 'playlist',
+ 'id': list_id,
+ 'title': self._extract_list_title(webpage),
+ 'entries': entries,
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ channel_id = mobj.group('id')
+ return self._extract_videos(channel_id, 'http://vimeo.com/channels/%s' % channel_id)
+
+
+class VimeoUserIE(VimeoChannelIE):
+ IE_NAME = 'vimeo:user'
+ _VALID_URL = r'(?:https?://)?vimeo\.com/(?P<name>[^/]+)(?:/videos|[#?]|$)'
+ _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
+
+ @classmethod
+ def suitable(cls, url):
+ if VimeoChannelIE.suitable(url) or VimeoIE.suitable(url) or VimeoAlbumIE.suitable(url) or VimeoGroupsIE.suitable(url):
+ return False
+ return super(VimeoUserIE, cls).suitable(url)
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ name = mobj.group('name')
+ return self._extract_videos(name, 'http://vimeo.com/%s' % name)
+
+
+class VimeoAlbumIE(VimeoChannelIE):
+ IE_NAME = 'vimeo:album'
+ _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):
+ return '%s/page:%d/' % (base_url, pagenum)
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ album_id = mobj.group('id')
+ return self._extract_videos(album_id, 'http://vimeo.com/album/%s' % album_id)
+
+
+class VimeoGroupsIE(VimeoAlbumIE):
+ IE_NAME = 'vimeo:group'
+ _VALID_URL = r'(?:https?://)?vimeo\.com/groups/(?P<name>[^/]+)'
+
+ def _extract_list_title(self, webpage):
+ return self._og_search_title(webpage)
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ name = mobj.group('name')
+ return self._extract_videos(name, 'http://vimeo.com/groups/%s' % name)
+
+
+class VimeoReviewIE(InfoExtractor):
+ IE_NAME = 'vimeo:review'
+ IE_DESC = 'Review pages on vimeo'
+ _VALID_URL = r'(?:https?://)?vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
+ _TEST = {
+ 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
+ 'file': '75524534.mp4',
+ 'md5': 'c507a72f780cacc12b2248bb4006d253',
+ 'info_dict': {
+ 'title': "DICK HARDWICK 'Comedian'",
+ 'uploader': 'Richard Hardwick',
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ 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')
Rapsys Git / youtubedl / blobdiff