]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/xxxymovies.py
d/p/remove-autoupdate-mechanism.patch: Update patch with metadata at the top.
[youtubedl] / youtube_dl / extractor / xxxymovies.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..utils import (
7 parse_duration,
8 int_or_none,
9 )
10
11
12 class XXXYMoviesIE(InfoExtractor):
13 _VALID_URL = r'https?://(?:www\.)?xxxymovies\.com/videos/(?P<id>\d+)/(?P<display_id>[^/]+)'
14 _TEST = {
15 'url': 'http://xxxymovies.com/videos/138669/ecstatic-orgasm-sofcore/',
16 'md5': '810b1bdbbffff89dd13bdb369fe7be4b',
17 'info_dict': {
18 'id': '138669',
19 'display_id': 'ecstatic-orgasm-sofcore',
20 'ext': 'mp4',
21 'title': 'Ecstatic Orgasm Sofcore',
22 'duration': 931,
23 'categories': list,
24 'view_count': int,
25 'like_count': int,
26 'dislike_count': int,
27 'age_limit': 18,
28 }
29 }
30
31 def _real_extract(self, url):
32 mobj = re.match(self._VALID_URL, url)
33 video_id = mobj.group('id')
34 display_id = mobj.group('display_id')
35
36 webpage = self._download_webpage(url, display_id)
37
38 video_url = self._search_regex(
39 r"video_url\s*:\s*'([^']+)'", webpage, 'video URL')
40
41 title = self._html_search_regex(
42 [r'<div[^>]+\bclass="block_header"[^>]*>\s*<h1>([^<]+)<',
43 r'<title>(.*?)\s*-\s*(?:XXXYMovies\.com|XXX\s+Movies)</title>'],
44 webpage, 'title')
45
46 thumbnail = self._search_regex(
47 r"preview_url\s*:\s*'([^']+)'",
48 webpage, 'thumbnail', fatal=False)
49
50 categories = self._html_search_meta(
51 'keywords', webpage, 'categories', default='').split(',')
52
53 duration = parse_duration(self._search_regex(
54 r'<span>Duration:</span>\s*(\d+:\d+)',
55 webpage, 'duration', fatal=False))
56
57 view_count = int_or_none(self._html_search_regex(
58 r'<div class="video_views">\s*(\d+)',
59 webpage, 'view count', fatal=False))
60 like_count = int_or_none(self._search_regex(
61 r'>\s*Likes? <b>\((\d+)\)',
62 webpage, 'like count', fatal=False))
63 dislike_count = int_or_none(self._search_regex(
64 r'>\s*Dislike <b>\((\d+)\)</b>',
65 webpage, 'dislike count', fatal=False))
66
67 age_limit = self._rta_search(webpage)
68
69 return {
70 'id': video_id,
71 'display_id': display_id,
72 'url': video_url,
73 'title': title,
74 'thumbnail': thumbnail,
75 'categories': categories,
76 'duration': duration,
77 'view_count': view_count,
78 'like_count': like_count,
79 'dislike_count': dislike_count,
80 'age_limit': age_limit,
81 }