[vimeo:likes] Implement extrator in terms of channel extractor

This allows to obtain videos' ids before extraction (#21493)
This commit is contained in:
Sergey M․ 2019-06-23 02:13:46 +07:00
parent 9634de178d
commit 091c9b4316
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D

View File

@ -16,7 +16,6 @@ from ..utils import (
determine_ext, determine_ext,
ExtractorError, ExtractorError,
js_to_json, js_to_json,
InAdvancePagedList,
int_or_none, int_or_none,
merge_dicts, merge_dicts,
NO_DEFAULT, NO_DEFAULT,
@ -1065,7 +1064,7 @@ class VimeoWatchLaterIE(VimeoChannelIE):
return self._extract_videos('watchlater', 'https://vimeo.com/watchlater') return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
class VimeoLikesIE(InfoExtractor): class VimeoLikesIE(VimeoChannelIE):
_VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)' _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
IE_NAME = 'vimeo:likes' IE_NAME = 'vimeo:likes'
IE_DESC = 'Vimeo user likes' IE_DESC = 'Vimeo user likes'
@ -1073,55 +1072,20 @@ class VimeoLikesIE(InfoExtractor):
'url': 'https://vimeo.com/user755559/likes/', 'url': 'https://vimeo.com/user755559/likes/',
'playlist_mincount': 293, 'playlist_mincount': 293,
'info_dict': { 'info_dict': {
'id': 'user755559_likes', 'id': 'user755559',
'description': 'See all the videos urza likes', 'title': 'urzas Likes',
'title': 'Videos urza likes',
}, },
}, { }, {
'url': 'https://vimeo.com/stormlapse/likes', 'url': 'https://vimeo.com/stormlapse/likes',
'only_matching': True, 'only_matching': True,
}] }]
def _page_url(self, base_url, pagenum):
return '%s/page:%d/' % (base_url, pagenum)
def _real_extract(self, url): def _real_extract(self, url):
user_id = self._match_id(url) user_id = self._match_id(url)
webpage = self._download_webpage(url, user_id) return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % 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)
return {
'_type': 'playlist',
'id': '%s_likes' % user_id,
'title': title,
'description': description,
'entries': pl,
}
class VHXEmbedIE(InfoExtractor): class VHXEmbedIE(InfoExtractor):