Mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-04 18:22:37 +01:00
Code Issues Releases Activity

[xxxymovies] Improve

Browse Source
This commit is contained in:
Sergey M․ 2014-12-29 21:05:21 +06:00
parent 00de9a9828
commit 6343a5f68e
1 changed files with 27 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
youtube_dl/extractor/xxxymovies.py
View File

@ -20,35 +20,51 @@ class XXXYMoviesIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': 'Ecstatic Orgasm Sofcore', 'title': 'Ecstatic Orgasm Sofcore',
'duration': 931, 'duration': 931,
'categories': list,
'view_count': int,
'like_count': int,
'dislike_count': int,
'age_limit': 18, 'age_limit': 18,
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
display_id = mobj.group('display_id') display_id = mobj.group('display_id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, display_id)
video_url = self._html_search_regex( video_url = self._search_regex(
r"video_url\s*:\s*'([^']+)'", webpage, 'video URL') r"video_url\s*:\s*'([^']+)'", webpage, 'video URL')
title = self._html_search_regex( title = self._html_search_regex(
r'<title>(.*?)\s*-\s*XXXYMovies.com</title>', webpage, 'title') [r'<div class="block_header">\s*<h1>([^<]+)</h1>',
r'<title>(.*?)\s*-\s*XXXYMovies\.com</title>'],
webpage, 'title')
thumbnail = self._html_search_regex( thumbnail = self._search_regex(
r'preview_url\s*:\s*\'(.*?)\'', webpage, 'thumbnail', fatal=False) r"preview_url\s*:\s*'([^']+)'",
webpage, 'thumbnail', fatal=False)
categories = self._html_search_meta( categories = self._html_search_meta(
'keywords', webpage, 'categories', default='').split(',') 'keywords', webpage, 'categories', default='').split(',')
duration = parse_duration(self._search_regex( duration = parse_duration(self._search_regex(
r'<span>Duration:</span>\s*(\d+:\d+)', webpage, 'duration', fatal=False)) r'<span>Duration:</span>\s*(\d+:\d+)',
webpage, 'duration', fatal=False))
view_count = int_or_none(self._html_search_regex( view_count = int_or_none(self._html_search_regex(
r'<div class="video_views">\s*(\d+)', webpage, 'view count', fatal=False)) r'<div class="video_views">\s*(\d+)',
webpage, 'view count', fatal=False))
like_count = int_or_none(self._search_regex(
r'>\s*Likes? <b>\((\d+)\)',
webpage, 'like count', fatal=False))
dislike_count = int_or_none(self._search_regex(
r'>\s*Dislike <b>\((\d+)\)</b>',
webpage, 'dislike count', fatal=False))
age_limit = self._rta_search(webpage)
return { return {
'id': video_id, 'id': video_id,
@ -59,5 +75,7 @@ def _real_extract(self, url):
'categories': categories, 'categories': categories,
'duration': duration, 'duration': duration,
'view_count': view_count, 'view_count': view_count,
'age_limit': 18, 'like_count': like_count,
'dislike_count': dislike_count,
'age_limit': age_limit,
} }