Merge branch 'lecture2go' of https://github.com/nichdu/youtube-dl into nichdu-lecture2go
[youtube-dl] / youtube_dl / extractor / vporn.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     str_to_int,
9 )
10
11
12 class VpornIE(InfoExtractor):
13     _VALID_URL = r'https?://(?:www\.)?vporn\.com/[^/]+/(?P<display_id>[^/]+)/(?P<id>\d+)'
14     _TESTS = [
15         {
16             'url': 'http://www.vporn.com/masturbation/violet-on-her-th-birthday/497944/',
17             'md5': 'facf37c1b86546fa0208058546842c55',
18             'info_dict': {
19                 'id': '497944',
20                 'display_id': 'violet-on-her-th-birthday',
21                 'ext': 'mp4',
22                 'title': 'Violet on her 19th birthday',
23                 'description': 'Violet dances in front of the camera which is sure to get you horny.',
24                 'thumbnail': 're:^https?://.*\.jpg$',
25                 'uploader': 'kileyGrope',
26                 'categories': ['Masturbation', 'Teen'],
27                 'duration': 393,
28                 'age_limit': 18,
29                 'view_count': int,
30             }
31         },
32         {
33             'url': 'http://www.vporn.com/female/hana-shower/523564/',
34             'md5': 'ced35a4656198a1664cf2cda1575a25f',
35             'info_dict': {
36                 'id': '523564',
37                 'display_id': 'hana-shower',
38                 'ext': 'mp4',
39                 'title': 'Hana Shower',
40                 'description': 'Hana showers at the bathroom.',
41                 'thumbnail': 're:^https?://.*\.jpg$',
42                 'uploader': 'Hmmmmm',
43                 'categories': ['Big Boobs', 'Erotic', 'Teen', 'Female'],
44                 'duration': 588,
45                 'age_limit': 18,
46                 'view_count': int,
47             }
48         },
49     ]
50
51     def _real_extract(self, url):
52         mobj = re.match(self._VALID_URL, url)
53         video_id = mobj.group('id')
54         display_id = mobj.group('display_id')
55
56         webpage = self._download_webpage(url, display_id)
57
58         title = self._html_search_regex(
59             r'videoname\s*=\s*\'([^\']+)\'', webpage, 'title').strip()
60         description = self._html_search_regex(
61             r'class="(?:descr|description_txt)">(.*?)</div>',
62             webpage, 'description', fatal=False)
63         thumbnail = self._html_search_regex(
64             r'flashvars\.imageUrl\s*=\s*"([^"]+)"', webpage, 'description', fatal=False, default=None)
65         if thumbnail:
66             thumbnail = 'http://www.vporn.com' + thumbnail
67
68         uploader = self._html_search_regex(
69             r'(?s)Uploaded by:.*?<a href="/user/[^"]+"[^>]*>(.+?)</a>',
70             webpage, 'uploader', fatal=False)
71
72         categories = re.findall(r'<a href="/cat/[^"]+"[^>]*>([^<]+)</a>', webpage)
73
74         duration = parse_duration(self._search_regex(
75             r'Runtime:\s*</span>\s*(\d+ min \d+ sec)',
76             webpage, 'duration', fatal=False))
77
78         view_count = str_to_int(self._search_regex(
79             r'class="views">([\d,\.]+) [Vv]iews<',
80             webpage, 'view count', fatal=False))
81         comment_count = str_to_int(self._html_search_regex(
82             r"'Comments \(([\d,\.]+)\)'",
83             webpage, 'comment count', default=None))
84
85         formats = []
86
87         for video in re.findall(r'flashvars\.videoUrl([^=]+?)\s*=\s*"(https?://[^"]+)"', webpage):
88             video_url = video[1]
89             fmt = {
90                 'url': video_url,
91                 'format_id': video[0],
92             }
93             m = re.search(r'_(?P<width>\d+)x(?P<height>\d+)_(?P<vbr>\d+)k\.mp4$', video_url)
94             if m:
95                 fmt.update({
96                     'width': int(m.group('width')),
97                     'height': int(m.group('height')),
98                     'vbr': int(m.group('vbr')),
99                 })
100             formats.append(fmt)
101
102         self._sort_formats(formats)
103
104         return {
105             'id': video_id,
106             'display_id': display_id,
107             'title': title,
108             'description': description,
109             'thumbnail': thumbnail,
110             'uploader': uploader,
111             'categories': categories,
112             'duration': duration,
113             'view_count': view_count,
114             'comment_count': comment_count,
115             'age_limit': 18,
116             'formats': formats,
117         }