- webpage = self._download_webpage(url, user_id)
- page_count = self._int(
- 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', default=1),
- 'page count', fatal=True)
- PAGE_SIZE = 12
- title = self._html_search_regex(
- r'(?s)<h1>(.+?)</h1>', 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)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
- webpage, 'video content')
- paths = re.findall(
- r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
- for path in paths:
- yield {
- '_type': 'url',
- 'url': compat_urlparse.urljoin(page_url, path),
- }
-
- pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)