mirrors/yt-dlp
1
1
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 02:42:30 +00:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

[youtube:search_url] Reimplement in terms of youtube:playlistbase

Browse Source
This commit is contained in:
Sergey M․ 2016-04-26 22:29:29 +06:00
parent f1f879098a
commit 175c2e9ec3
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 3 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
youtube_dl/extractor/youtube.py
View File

@ -2139,10 +2139,11 @@ class YoutubeSearchDateIE(YoutubeSearchIE):
_EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'} _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
class YoutubeSearchURLIE(InfoExtractor): class YoutubeSearchURLIE(YoutubePlaylistBaseInfoExtractor):
IE_DESC = 'YouTube.com search URLs' IE_DESC = 'YouTube.com search URLs'
IE_NAME = 'youtube:search_url' IE_NAME = 'youtube:search_url'
_VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)' _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
_VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
_TESTS = [{ _TESTS = [{
'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
'playlist_mincount': 5, 'playlist_mincount': 5,
@ -2157,32 +2158,8 @@ class YoutubeSearchURLIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
query = compat_urllib_parse_unquote_plus(mobj.group('query')) query = compat_urllib_parse_unquote_plus(mobj.group('query'))
webpage = self._download_webpage(url, query) webpage = self._download_webpage(url, query)
result_code = self._search_regex( return self.playlist_result(self._process_page(webpage), playlist_title=query)
r'(?s)<ol[^>]+class="item-section"(.*?)</ol>', webpage, 'result HTML')
part_codes = re.findall(
r'(?s)<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*>(.*?)</h3>', result_code)
entries = []
for part_code in part_codes:
part_title = self._html_search_regex(
[r'(?s)title="([^"]+)"', r'>([^<]+)</a>'], part_code, 'item title', fatal=False)
part_url_snippet = self._html_search_regex(
r'(?s)href="([^"]+)"', part_code, 'item URL')
part_url = compat_urlparse.urljoin(
'https://www.youtube.com/', part_url_snippet)
entries.append({
'_type': 'url',
'url': part_url,
'title': part_title,
})
return {
'_type': 'playlist',
'entries': entries,
'title': query,
}
class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor): class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):