aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/xhamster.py
blob: de9ec9b9e5346e5ba4437a66d1547a2cf14dc7c7 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..utils import (
    clean_html,
    dict_get,
    ExtractorError,
    int_or_none,
    parse_duration,
    unified_strdate,
)


class XHamsterIE(InfoExtractor):
    _VALID_URL = r'''(?x)
                    https?://
                        (?:.+?\.)?xhamster\.com/
                        (?:
                            movies/(?P<id>\d+)/(?P<display_id>[^/]*)\.html|
                            videos/(?P<display_id_2>[^/]*)-(?P<id_2>\d+)
                        )
                    '''

    _TESTS = [{
        'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
        'md5': '8281348b8d3c53d39fffb377d24eac4e',
        'info_dict': {
            'id': '1509445',
            'ext': 'mp4',
            'title': 'FemaleAgent Shy beauty takes the bait',
            'upload_date': '20121014',
            'uploader': 'Ruseful2011',
            'duration': 893,
            'age_limit': 18,
            'categories': ['Fake Hub', 'Amateur', 'MILFs', 'POV', 'Boss', 'Office', 'Oral', 'Reality', 'Sexy'],
        },
    }, {
        'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
        'info_dict': {
            'id': '2221348',
            'ext': 'mp4',
            'title': 'Britney Spears  Sexy Booty',
            'upload_date': '20130914',
            'uploader': 'jojo747400',
            'duration': 200,
            'age_limit': 18,
            'categories': ['Britney Spears', 'Celebrities', 'HD Videos', 'Sexy', 'Sexy Booty'],
        },
        'params': {
            'skip_download': True,
        },
    }, {
        # empty seo
        'url': 'http://xhamster.com/movies/5667973/.html',
        'info_dict': {
            'id': '5667973',
            'ext': 'mp4',
            'title': '....',
            'upload_date': '20160208',
            'uploader': 'parejafree',
            'duration': 72,
            'age_limit': 18,
            'categories': ['Amateur', 'Blowjobs'],
        },
        'params': {
            'skip_download': True,
        },
    }, {
        'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
        'only_matching': True,
    }, {
        # This video is visible for marcoalfa123456's friends only
        'url': 'https://it.xhamster.com/movies/7263980/la_mia_vicina.html',
        'only_matching': True,
    }, {
        # new URL schema
        'url': 'https://pt.xhamster.com/videos/euro-pedal-pumping-7937821',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        def extract_video_url(webpage, name):
            return self._search_regex(
                [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
                 r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
                 r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
                webpage, name, group='mp4')

        def is_hd(webpage):
            return '<div class=\'icon iconHD\'' in webpage

        mobj = re.match(self._VALID_URL, url)

        video_id = mobj.group('id') or mobj.group('id_2')
        display_id = mobj.group('display_id') or mobj.group('display_id_2')

        webpage = self._download_webpage(url, video_id)

        error = self._html_search_regex(
            r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
            webpage, 'error', default=None)
        if error:
            raise ExtractorError(error, expected=True)

        title = self._html_search_regex(
            [r'<h1[^>]*>([^<]+)</h1>',
             r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
             r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
            webpage, 'title')

        # Only a few videos have an description
        mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
        description = mobj.group(1) if mobj else None

        upload_date = unified_strdate(self._search_regex(
            r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
            webpage, 'upload date', fatal=False))

        uploader = self._html_search_regex(
            r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',
            webpage, 'uploader', default='anonymous')

        thumbnail = self._search_regex(
            [r'''thumb\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
             r'''<video[^>]+poster=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
            webpage, 'thumbnail', fatal=False, group='thumbnail')

        duration = parse_duration(self._search_regex(
            r'Runtime:\s*</span>\s*([\d:]+)', webpage,
            'duration', fatal=False))

        view_count = int_or_none(self._search_regex(
            r'content=["\']User(?:View|Play)s:(\d+)',
            webpage, 'view count', fatal=False))

        mobj = re.search(r'hint=[\'"](?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes', webpage)
        (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)

        mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
        comment_count = mobj.group('commentcount') if mobj else 0

        age_limit = self._rta_search(webpage)

        hd = is_hd(webpage)

        format_id = 'hd' if hd else 'sd'

        video_url = extract_video_url(webpage, format_id)
        formats = [{
            'url': video_url,
            'format_id': 'hd' if hd else 'sd',
            'preference': 1,
        }]

        if not hd:
            mrss_url = self._search_regex(r'<link rel="canonical" href="([^"]+)', webpage, 'mrss_url')
            webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage')
            if is_hd(webpage):
                video_url = extract_video_url(webpage, 'hd')
                formats.append({
                    'url': video_url,
                    'format_id': 'hd',
                    'preference': 2,
                })

        self._sort_formats(formats)

        categories_html = self._search_regex(
            r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
            'categories', default=None)
        categories = [clean_html(category) for category in re.findall(
            r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None

        return {
            'id': video_id,
            'title': title,
            'description': description,
            'upload_date': upload_date,
            'uploader': uploader,
            'thumbnail': thumbnail,
            'duration': duration,
            'view_count': view_count,
            'like_count': int_or_none(like_count),
            'dislike_count': int_or_none(dislike_count),
            'comment_count': int_or_none(comment_count),
            'age_limit': age_limit,
            'categories': categories,
            'formats': formats,
        }


class XHamsterEmbedIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)'
    _TEST = {
        'url': 'http://xhamster.com/xembed.php?video=3328539',
        'info_dict': {
            'id': '3328539',
            'ext': 'mp4',
            'title': 'Pen Masturbation',
            'upload_date': '20140728',
            'uploader_id': 'anonymous',
            'duration': 5,
            'age_limit': 18,
        }
    }

    @staticmethod
    def _extract_urls(webpage):
        return [url for _, url in re.findall(
            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
            webpage)]

    def _real_extract(self, url):
        video_id = self._match_id(url)

        webpage = self._download_webpage(url, video_id)

        video_url = self._search_regex(
            r'href="(https?://xhamster\.com/movies/%s/[^"]*\.html[^"]*)"' % video_id,
            webpage, 'xhamster url', default=None)

        if not video_url:
            vars = self._parse_json(
                self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
                video_id)
            video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))

        return self.url_result(video_url, 'XHamster')