github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[sunporno] Extract all formats and metadata

Browse source
This commit is contained in:
Sergey M․ 2014-09-01 01:08:19 +07:00
parent 43fd392413
commit ae7246e7d5
1 changed files with 21 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

31
youtube_dl/extractor/sunporno.py
View file

@ -6,6 +6,8 @@
from ..utils import ( from ..utils import (
parse_duration, parse_duration,
int_or_none, int_or_none,
qualities,
determine_ext,
) )
@ -19,6 +21,7 @@ class SunPornoIE(InfoExtractor):
'ext': 'flv', 'ext': 'flv',
'title': 'md5:0a400058e8105d39e35c35e7c5184164', 'title': 'md5:0a400058e8105d39e35c35e7c5184164',
'description': 'md5:a31241990e1bd3a64e72ae99afb325fb', 'description': 'md5:a31241990e1bd3a64e72ae99afb325fb',
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 302, 'duration': 302,
} }
} }
@ -29,29 +32,37 @@ def _real_extract(self, url):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
video_url = self._html_search_regex( title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, 'title')
r'videoSource\s*=\s*\'<source\s*src="([^"]*)"', webpage, 'video URL') description = self._html_search_meta('description', webpage, 'description')
title = self._html_search_regex(r'<title>([^<]*)</title>', webpage, 'title')
description = self._html_search_regex(
r'<meta name="description" content="([^"]*)"', webpage, 'description', fatal=False)
thumbnail = self._html_search_regex( thumbnail = self._html_search_regex(
r'poster="([^"]*)"', webpage, 'thumbnail', fatal=False) r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
duration = parse_duration(self._search_regex( duration = parse_duration(self._search_regex(
r'<span>Duration: (\d+:\d+)</span>', webpage, 'duration', fatal=False)) r'<span>Duration: (\d+:\d+)</span>', webpage, 'duration', fatal=False))
view_count = int_or_none(self._html_search_regex( view_count = int_or_none(self._html_search_regex(
r'<span class="views">(\d+)</span>', webpage, 'view count', fatal=False)) r'<span class="views">(\d+)</span>', webpage, 'view count', fatal=False))
comment_count = int_or_none(self._html_search_regex(
r'(\d+)</b> Comments?', webpage, 'comment count', fatal=False))
formats = []
quality = qualities(['mp4', 'flv'])
for video_url in re.findall(r'<source src="([^"]+)"', webpage):
video_ext = determine_ext(video_url)
formats.append({
'url': video_url,
'format_id': video_ext,
'quality': quality(video_ext),
})
self._sort_formats(formats)
return { return {
'id': video_id, 'id': video_id,
'url': video_url,
'title': title, 'title': title,
'description': description, 'description': description,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'duration': duration, 'duration': duration,
'view_count': view_count, 'view_count': view_count,
'comment_count': comment_count,
'formats': formats,
} }