mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2024-11-05 00:51:29 +00:00
49 lines
1.5 KiB
Python
49 lines
1.5 KiB
Python
|
from __future__ import unicode_literals
|
||
|
|
|
||
|
|
import re
|
||
|
|
|
||
|
|
from .common import InfoExtractor
|
||
|
|
|
||
|
|
|
||
|
|
class BeegIE(InfoExtractor):
|
||
|
|
_VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)'
|
||
|
|
_TEST = {
|
||
|
|
'url': 'http://beeg.com/5416503',
|
||
|
|
'md5': '634526ae978711f6b748fe0dd6c11f57',
|
||
|
|
'info_dict': {
|
||
|
|
'id': '5416503',
|
||
|
|
'ext': 'mp4',
|
||
|
|
'title': 'Sultry Striptease',
|
||
|
|
'description': 'md5:6db3c6177972822aaba18652ff59c773',
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
def _real_extract(self, url):
|
||
|
|
mobj = re.match(self._VALID_URL, url)
|
||
|
|
video_id = mobj.group('id')
|
||
|
|
|
||
|
|
webpage = self._download_webpage(url, video_id)
|
||
|
|
|
||
|
|
video_url = self._html_search_regex(r"'480p'\s*:\s*'([^']+)'", webpage, 'video URL')
|
||
|
|
|
||
|
|
title = self._html_search_regex(r'<title>([^<]+)\s*-\s*beeg\.?</title>', webpage, 'title')
|
||
|
|
|
||
|
|
description = self._html_search_regex(
|
||
|
|
r'<meta name="description" content="([^"]*)"', webpage, 'description', fatal=False)
|
||
|
|
|
||
|
|
thumbnail = self._html_search_regex(
|
||
|
|
r'\'previewer.url\'\s*:\s*"([^"]*)"', webpage, 'thumbnail', fatal=False)
|
||
|
|
|
||
|
|
categories_str = self._html_search_regex(
|
||
|
|
r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
|
||
|
|
categories = categories_str.split(',')
|
||
|
|
|
||
|
|
return {
|
||
|
|
'id': video_id,
|
||
|
|
'url': video_url,
|
||
|
|
'title': title,
|
||
|
|
'description': description,
|
||
|
|
'thumbnail': thumbnail,
|
||
|
|
'categories': categories,
|
||
|
|
}
|