]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/xhamster.py
8938c0e4561d2c6163158e409106dd2e928e85bf
[youtubedl] / youtube_dl / extractor / xhamster.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..utils import (
7 unified_strdate,
8 str_to_int,
9 int_or_none,
10 parse_duration,
11 )
12
13
14 class XHamsterIE(InfoExtractor):
15 _VALID_URL = r'(?P<proto>https?)://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
16 _TESTS = [
17 {
18 'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
19 'info_dict': {
20 'id': '1509445',
21 'ext': 'mp4',
22 'title': 'FemaleAgent Shy beauty takes the bait',
23 'upload_date': '20121014',
24 'uploader': 'Ruseful2011',
25 'duration': 893,
26 'age_limit': 18,
27 }
28 },
29 {
30 'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
31 'info_dict': {
32 'id': '2221348',
33 'ext': 'mp4',
34 'title': 'Britney Spears Sexy Booty',
35 'upload_date': '20130914',
36 'uploader': 'jojo747400',
37 'duration': 200,
38 'age_limit': 18,
39 }
40 },
41 {
42 'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
43 'only_matching': True,
44 },
45 ]
46
47 def _real_extract(self, url):
48 def extract_video_url(webpage, name):
49 return self._search_regex(
50 [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
51 r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
52 r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
53 webpage, name, group='mp4')
54
55 def is_hd(webpage):
56 return '<div class=\'icon iconHD\'' in webpage
57
58 mobj = re.match(self._VALID_URL, url)
59
60 video_id = mobj.group('id')
61 seo = mobj.group('seo')
62 proto = mobj.group('proto')
63 mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo)
64 webpage = self._download_webpage(mrss_url, video_id)
65
66 title = self._html_search_regex(
67 [r'<title>(?P<title>.+?)(?:, (?:[^,]+? )?Porn: xHamster| - xHamster\.com)</title>',
68 r'<h1>([^<]+)</h1>'], webpage, 'title')
69
70 # Only a few videos have an description
71 mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
72 description = mobj.group(1) if mobj else None
73
74 upload_date = self._html_search_regex(r'hint=\'(\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}\'',
75 webpage, 'upload date', fatal=False)
76 if upload_date:
77 upload_date = unified_strdate(upload_date)
78
79 uploader = self._html_search_regex(
80 r"<a href='[^']+xhamster\.com/user/[^>]+>(?P<uploader>[^<]+)",
81 webpage, 'uploader', default='anonymous')
82
83 thumbnail = self._search_regex(
84 [r'''thumb\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
85 r'''<video[^>]+poster=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
86 webpage, 'thumbnail', fatal=False, group='thumbnail')
87
88 duration = parse_duration(self._html_search_regex(r'<span>Runtime:</span> (\d+:\d+)</div>',
89 webpage, 'duration', fatal=False))
90
91 view_count = self._html_search_regex(r'<span>Views:</span> ([^<]+)</div>', webpage, 'view count', fatal=False)
92 if view_count:
93 view_count = str_to_int(view_count)
94
95 mobj = re.search(r"hint='(?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes'", webpage)
96 (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
97
98 mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
99 comment_count = mobj.group('commentcount') if mobj else 0
100
101 age_limit = self._rta_search(webpage)
102
103 hd = is_hd(webpage)
104
105 format_id = 'hd' if hd else 'sd'
106
107 video_url = extract_video_url(webpage, format_id)
108 formats = [{
109 'url': video_url,
110 'format_id': 'hd' if hd else 'sd',
111 'preference': 1,
112 }]
113
114 if not hd:
115 mrss_url = self._search_regex(r'<link rel="canonical" href="([^"]+)', webpage, 'mrss_url')
116 webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage')
117 if is_hd(webpage):
118 video_url = extract_video_url(webpage, 'hd')
119 formats.append({
120 'url': video_url,
121 'format_id': 'hd',
122 'preference': 2,
123 })
124
125 self._sort_formats(formats)
126
127 return {
128 'id': video_id,
129 'title': title,
130 'description': description,
131 'upload_date': upload_date,
132 'uploader': uploader,
133 'thumbnail': thumbnail,
134 'duration': duration,
135 'view_count': view_count,
136 'like_count': int_or_none(like_count),
137 'dislike_count': int_or_none(dislike_count),
138 'comment_count': int_or_none(comment_count),
139 'age_limit': age_limit,
140 'formats': formats,
141 }
142
143
144 class XHamsterEmbedIE(InfoExtractor):
145 _VALID_URL = r'https?://(?:www\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)'
146 _TEST = {
147 'url': 'http://xhamster.com/xembed.php?video=3328539',
148 'info_dict': {
149 'id': '3328539',
150 'ext': 'mp4',
151 'title': 'Pen Masturbation',
152 'upload_date': '20140728',
153 'uploader_id': 'anonymous',
154 'duration': 5,
155 'age_limit': 18,
156 }
157 }
158
159 @staticmethod
160 def _extract_urls(webpage):
161 return [url for _, url in re.findall(
162 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
163 webpage)]
164
165 def _real_extract(self, url):
166 video_id = self._match_id(url)
167
168 webpage = self._download_webpage(url, video_id)
169
170 video_url = self._search_regex(
171 r'href="(https?://xhamster\.com/movies/%s/[^"]+\.html[^"]*)"' % video_id,
172 webpage, 'xhamster url')
173
174 return self.url_result(video_url, 'XHamster')