pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2025-04-14 19:14:51 +09:00
Code Issues Projects Releases Wiki Activity

Scrape actors urls

Browse Source
This commit is contained in:
DarkFighterLuke 2022-02-26 13:28:16 +01:00
parent 64f9e5f6b1
commit 055351fddb
1 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
youtube_dl/extractor/sxyprn.py
View File

@ -65,11 +65,12 @@ class SxyPrnIE(InfoExtractor):
tags = self._search_regex(r'<meta name="keywords".+content="(?P<tags>.+)"', webpage, 'tags', group='tags').split(', ') tags = self._search_regex(r'<meta name="keywords".+content="(?P<tags>.+)"', webpage, 'tags', group='tags').split(', ')
uploader = self._search_regex(r'<div class=\'pes_author_div pes_edit_div transition\'.+?>.+?<span class=\'a_name\'>(?P<uploader>.+?)<', webpage, 'uploader', group='uploader') uploader = self._search_regex(r'<div class=\'pes_author_div pes_edit_div transition\'.+?>.+?<span class=\'a_name\'>(?P<uploader>.+?)<', webpage, 'uploader', group='uploader')
uploader_url = urljoin(url, self._search_regex(r'<div class=\'pes_author_div pes_edit_div transition\'.+?><a href=\'(?P<uploader_url>.+?)\'.+?<span class=\'a_name\'>(?P<uploader>.+?)<', webpage, 'uploader_url', group='uploader_url')) uploader_url = urljoin(url, self._search_regex(r'<div class=\'pes_author_div pes_edit_div transition\'.+?><a href=\'(?P<uploader_url>.+?)\'.+?<span class=\'a_name\'>(?P<uploader>.+?)<', webpage, 'uploader_url', group='uploader_url'))
actors_names = re.findall(r'<span>·</span><b>(?P<actor>.+?)</b>', webpage) actors_data = re.findall(r'<a href=\'(?P<actor_url>.+?)\' class=\'tdn htag_rel_a\'><div class=\'htag_rel\'><span>·</span><b>(?P<actor_name>.+?)</b>', webpage)
actors = [] actors = []
for name in actors_names: for actor_tuple in actors_data:
actors.append({ actors.append({
'given_name': name 'given_name': actor_tuple[1],
'url': urljoin(url, actor_tuple[0])
}) })
views = int(self._search_regex(r'<div class=\'post_control_time\'>.+?</strong> (?P<views>.+) views</div>', webpage, 'views', group='views')) views = int(self._search_regex(r'<div class=\'post_control_time\'>.+?</strong> (?P<views>.+) views</div>', webpage, 'views', group='views'))