]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/beeg.py
b38057f2f500f520829ff9c5d7324e66558eb356
[youtubedl] / youtube_dl / extractor / beeg.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6
7
8 class BeegIE(InfoExtractor):
9 _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)'
10 _TEST = {
11 'url': 'http://beeg.com/5416503',
12 'md5': '1bff67111adb785c51d1b42959ec10e5',
13 'info_dict': {
14 'id': '5416503',
15 'ext': 'mp4',
16 'title': 'Sultry Striptease',
17 'description': 'md5:6db3c6177972822aaba18652ff59c773',
18 'categories': list, # NSFW
19 'thumbnail': 're:https?://.*\.jpg$',
20 'age_limit': 18,
21 }
22 }
23
24 def _real_extract(self, url):
25 mobj = re.match(self._VALID_URL, url)
26 video_id = mobj.group('id')
27
28 webpage = self._download_webpage(url, video_id)
29
30 quality_arr = self._search_regex(
31 r'(?s)var\s+qualityArr\s*=\s*{\s*(.+?)\s*}', webpage, 'quality formats')
32
33 formats = [{
34 'url': fmt[1],
35 'format_id': fmt[0],
36 'height': int(fmt[0][:-1]),
37 } for fmt in re.findall(r"'([^']+)'\s*:\s*'([^']+)'", quality_arr)]
38
39 self._sort_formats(formats)
40
41 title = self._html_search_regex(
42 r'<title>([^<]+)\s*-\s*beeg\.?</title>', webpage, 'title')
43
44 description = self._html_search_regex(
45 r'<meta name="description" content="([^"]*)"',
46 webpage, 'description', fatal=False)
47 thumbnail = self._html_search_regex(
48 r'\'previewer.url\'\s*:\s*"([^"]*)"',
49 webpage, 'thumbnail', fatal=False)
50
51 categories_str = self._html_search_regex(
52 r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
53 categories = (
54 None if categories_str is None
55 else categories_str.split(','))
56
57 return {
58 'id': video_id,
59 'title': title,
60 'description': description,
61 'thumbnail': thumbnail,
62 'categories': categories,
63 'formats': formats,
64 'age_limit': 18,
65 }