From 091c9b43164f6f3b31f5f911c88a4aeaa0358429 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 23 Jun 2019 02:13:46 +0700 Subject: [PATCH] [vimeo:likes] Implement extrator in terms of channel extractor This allows to obtain videos' ids before extraction (#21493) --- youtube_dl/extractor/vimeo.py | 50 +++++------------------------------ 1 file changed, 7 insertions(+), 43 deletions(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index a41178bab..aeee7df8f 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -16,7 +16,6 @@ from ..utils import ( determine_ext, ExtractorError, js_to_json, - InAdvancePagedList, int_or_none, merge_dicts, NO_DEFAULT, @@ -1065,7 +1064,7 @@ class VimeoWatchLaterIE(VimeoChannelIE): return self._extract_videos('watchlater', 'https://vimeo.com/watchlater') -class VimeoLikesIE(InfoExtractor): +class VimeoLikesIE(VimeoChannelIE): _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P[^/]+)/likes/?(?:$|[?#]|sort:)' IE_NAME = 'vimeo:likes' IE_DESC = 'Vimeo user likes' @@ -1073,55 +1072,20 @@ class VimeoLikesIE(InfoExtractor): 'url': 'https://vimeo.com/user755559/likes/', 'playlist_mincount': 293, 'info_dict': { - 'id': 'user755559_likes', - 'description': 'See all the videos urza likes', - 'title': 'Videos urza likes', + 'id': 'user755559', + 'title': 'urza’s Likes', }, }, { 'url': 'https://vimeo.com/stormlapse/likes', 'only_matching': True, }] + def _page_url(self, base_url, pagenum): + return '%s/page:%d/' % (base_url, pagenum) + def _real_extract(self, url): user_id = self._match_id(url) - webpage = self._download_webpage(url, user_id) - page_count = self._int( - self._search_regex( - r'''(?x)
  • - .*?
  • \s* - ''', webpage, 'page count', default=1), - 'page count', fatal=True) - PAGE_SIZE = 12 - title = self._html_search_regex( - r'(?s)

    (.+?)

    ', webpage, 'title', fatal=False) - description = self._html_search_meta('description', webpage) - - def _get_page(idx): - page_url = 'https://vimeo.com/%s/likes/page:%d/sort:date' % ( - user_id, idx + 1) - webpage = self._download_webpage( - page_url, user_id, - note='Downloading page %d/%d' % (idx + 1, page_count)) - video_list = self._search_regex( - r'(?s)
      ]*>(.*?)
    ', - webpage, 'video content') - paths = re.findall( - r']*>\s*