aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/redtube.py
blob: 843e45d3683038a28d5ac64a5c3675b11020f97d (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
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
    ExtractorError,
    int_or_none,
    str_to_int,
    unified_strdate,
)


class RedTubeIE(InfoExtractor):
    _VALID_URL = r'https?://(?:(?:www\.)?redtube\.com/|embed\.redtube\.com/\?.*?\bid=)(?P<id>[0-9]+)'
    _TESTS = [{
        'url': 'http://www.redtube.com/66418',
        'md5': '7b8c22b5e7098a3e1c09709df1126d2d',
        'info_dict': {
            'id': '66418',
            'ext': 'mp4',
            'title': 'Sucked on a toilet',
            'upload_date': '20120831',
            'duration': 596,
            'view_count': int,
            'age_limit': 18,
        }
    }, {
        'url': 'http://embed.redtube.com/?bgcolor=000000&id=1443286',
        'only_matching': True,
    }]

    @staticmethod
    def _extract_urls(webpage):
        return re.findall(
            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//embed\.redtube\.com/\?.*?\bid=\d+)',
            webpage)

    def _real_extract(self, url):
        video_id = self._match_id(url)
        webpage = self._download_webpage(
            'http://www.redtube.com/%s' % video_id, video_id)

        if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']):
            raise ExtractorError('Video %s has been removed' % video_id, expected=True)

        title = self._html_search_regex(
            (r'<h(\d)[^>]+class="(?:video_title_text|videoTitle)[^"]*">(?P<title>(?:(?!\1).)+)</h\1>',
             r'(?:videoTitle|title)\s*:\s*(["\'])(?P<title>(?:(?!\1).)+)\1',),
            webpage, 'title', group='title',
            default=None) or self._og_search_title(webpage)

        formats = []
        sources = self._parse_json(
            self._search_regex(
                r'sources\s*:\s*({.+?})', webpage, 'source', default='{}'),
            video_id, fatal=False)
        if sources and isinstance(sources, dict):
            for format_id, format_url in sources.items():
                if format_url:
                    formats.append({
                        'url': format_url,
                        'format_id': format_id,
                        'height': int_or_none(format_id),
                    })
        medias = self._parse_json(
            self._search_regex(
                r'mediaDefinition\s*:\s*(\[.+?\])', webpage,
                'media definitions', default='{}'),
            video_id, fatal=False)
        if medias and isinstance(medias, list):
            for media in medias:
                format_url = media.get('videoUrl')
                if not format_url or not isinstance(format_url, compat_str):
                    continue
                format_id = media.get('quality')
                formats.append({
                    'url': format_url,
                    'format_id': format_id,
                    'height': int_or_none(format_id),
                })
        if not formats:
            video_url = self._html_search_regex(
                r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL')
            formats.append({'url': video_url})
        self._sort_formats(formats)

        thumbnail = self._og_search_thumbnail(webpage)
        upload_date = unified_strdate(self._search_regex(
            r'<span[^>]+>ADDED ([^<]+)<',
            webpage, 'upload date', fatal=False))
        duration = int_or_none(self._search_regex(
            r'videoDuration\s*:\s*(\d+)', webpage, 'duration', default=None))
        view_count = str_to_int(self._search_regex(
            (r'<div[^>]*>Views</div>\s*<div[^>]*>\s*([\d,.]+)',
             r'<span[^>]*>VIEWS</span>\s*</td>\s*<td>\s*([\d,.]+)'),
            webpage, 'view count', fatal=False))

        # No self-labeling, but they describe themselves as
        # "Home of Videos Porno"
        age_limit = 18

        return {
            'id': video_id,
            'ext': 'mp4',
            'title': title,
            'thumbnail': thumbnail,
            'upload_date': upload_date,
            'duration': duration,
            'view_count': view_count,
            'age_limit': age_limit,
            'formats': formats,
        }