]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/xvideos.py
Imported Upstream version 2015.11.27.1
[youtubedl] / youtube_dl / extractor / xvideos.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..compat import compat_urllib_parse_unquote
7 from ..utils import (
8 clean_html,
9 ExtractorError,
10 determine_ext,
11 sanitized_Request,
12 )
13
14
15 class XVideosIE(InfoExtractor):
16 _VALID_URL = r'https?://(?:www\.)?xvideos\.com/video(?P<id>[0-9]+)(?:.*)'
17 _TEST = {
18 'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl',
19 'md5': '4b46ae6ea5e6e9086e714d883313c0c9',
20 'info_dict': {
21 'id': '4588838',
22 'ext': 'flv',
23 'title': 'Biker Takes his Girl',
24 'age_limit': 18,
25 }
26 }
27
28 _ANDROID_USER_AGENT = 'Mozilla/5.0 (Linux; Android 4.0.4; Galaxy Nexus Build/IMM76B) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.133 Mobile Safari/535.19'
29
30 def _real_extract(self, url):
31 video_id = self._match_id(url)
32 webpage = self._download_webpage(url, video_id)
33
34 mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage)
35 if mobj:
36 raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True)
37
38 video_url = compat_urllib_parse_unquote(
39 self._search_regex(r'flv_url=(.+?)&', webpage, 'video URL'))
40 video_title = self._html_search_regex(
41 r'<title>(.*?)\s+-\s+XVID', webpage, 'title')
42 video_thumbnail = self._search_regex(
43 r'url_bigthumb=(.+?)&amp', webpage, 'thumbnail', fatal=False)
44
45 formats = [{
46 'url': video_url,
47 }]
48
49 android_req = sanitized_Request(url)
50 android_req.add_header('User-Agent', self._ANDROID_USER_AGENT)
51 android_webpage = self._download_webpage(android_req, video_id, fatal=False)
52
53 if android_webpage is not None:
54 player_params_str = self._search_regex(
55 'mobileReplacePlayerDivTwoQual\(([^)]+)\)',
56 android_webpage, 'player parameters', default='')
57 player_params = list(map(lambda s: s.strip(' \''), player_params_str.split(',')))
58 if player_params:
59 formats.extend([{
60 'url': param,
61 'preference': -10,
62 } for param in player_params if determine_ext(param) == 'mp4'])
63
64 self._sort_formats(formats)
65
66 return {
67 'id': video_id,
68 'formats': formats,
69 'title': video_title,
70 'ext': 'flv',
71 'thumbnail': video_thumbnail,
72 'age_limit': 18,
73 }