1
1
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-15 03:47:48 +01:00
youtube-dl/youtube_dl/extractor/beeg.py

66 lines
2.0 KiB
Python
Raw Normal View History

2014-08-31 11:57:10 +02:00
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',
2015-02-14 13:42:42 +01:00
'md5': '1bff67111adb785c51d1b42959ec10e5',
2014-08-31 11:57:10 +02:00
'info_dict': {
'id': '5416503',
'ext': 'mp4',
'title': 'Sultry Striptease',
'description': 'md5:6db3c6177972822aaba18652ff59c773',
2014-09-01 00:00:01 +02:00
'categories': list, # NSFW
'thumbnail': 're:https?://.*\.jpg$',
2014-09-01 23:13:04 +02:00
'age_limit': 18,
2014-08-31 11:57:10 +02:00
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
2014-09-02 15:54:00 +02:00
quality_arr = self._search_regex(
r'(?s)var\s+qualityArr\s*=\s*{\s*(.+?)\s*}', webpage, 'quality formats')
formats = [{
'url': fmt[1],
'format_id': fmt[0],
'height': int(fmt[0][:-1]),
} for fmt in re.findall(r"'([^']+)'\s*:\s*'([^']+)'", quality_arr)]
self._sort_formats(formats)
2014-08-31 11:57:10 +02:00
2014-09-01 00:00:01 +02:00
title = self._html_search_regex(
r'<title>([^<]+)\s*-\s*beeg\.?</title>', webpage, 'title')
2014-11-23 20:41:03 +01:00
2014-08-31 11:57:10 +02:00
description = self._html_search_regex(
2014-09-01 00:00:01 +02:00
r'<meta name="description" content="([^"]*)"',
webpage, 'description', fatal=False)
2014-08-31 11:57:10 +02:00
thumbnail = self._html_search_regex(
2014-09-01 00:00:01 +02:00
r'\'previewer.url\'\s*:\s*"([^"]*)"',
webpage, 'thumbnail', fatal=False)
2014-08-31 11:57:10 +02:00
categories_str = self._html_search_regex(
r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
2014-09-01 23:13:04 +02:00
categories = (
None if categories_str is None
else categories_str.split(','))
2014-08-31 11:57:10 +02:00
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'categories': categories,
2014-09-02 15:54:00 +02:00
'formats': formats,
2014-09-01 23:13:04 +02:00
'age_limit': 18,
2014-08-31 11:57:10 +02:00
}