aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/gorillavid.py
blob: 8c982d8e97861864e844f38df74c7e6026bb6860 (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
# -*- coding: utf-8 -*-
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import (
    compat_urllib_parse,
    compat_urllib_request,
)
from ..utils import (
    ExtractorError,
    encode_dict,
    int_or_none,
)


class GorillaVidIE(InfoExtractor):
    IE_DESC = 'GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net, filehoot.com and vidto.me'
    _VALID_URL = r'''(?x)
        https?://(?P<host>(?:www\.)?
            (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in|realvid\.net|filehoot\.com|vidto.\me))/
        (?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?
    '''

    _FILE_NOT_FOUND_REGEX = r'>(?:404 - )?File Not Found<'

    _TESTS = [{
        'url': 'http://gorillavid.in/06y9juieqpmi',
        'md5': '5ae4a3580620380619678ee4875893ba',
        'info_dict': {
            'id': '06y9juieqpmi',
            'ext': 'flv',
            'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ',
            'thumbnail': 're:http://.*\.jpg',
        },
    }, {
        'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
        'only_matching': True,
    }, {
        'url': 'http://daclips.in/3rso4kdn6f9m',
        'md5': '1ad8fd39bb976eeb66004d3a4895f106',
        'info_dict': {
            'id': '3rso4kdn6f9m',
            'ext': 'mp4',
            'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
            'thumbnail': 're:http://.*\.jpg',
        }
    }, {
        # video with countdown timeout
        'url': 'http://fastvideo.in/1qmdn1lmsmbw',
        'md5': '8b87ec3f6564a3108a0e8e66594842ba',
        'info_dict': {
            'id': '1qmdn1lmsmbw',
            'ext': 'mp4',
            'title': 'Man of Steel - Trailer',
            'thumbnail': 're:http://.*\.jpg',
        },
    }, {
        'url': 'http://realvid.net/ctn2y6p2eviw',
        'md5': 'b2166d2cf192efd6b6d764c18fd3710e',
        'info_dict': {
            'id': 'ctn2y6p2eviw',
            'ext': 'flv',
            'title': 'rdx 1955',
            'thumbnail': 're:http://.*\.jpg',
        },
    }, {
        'url': 'http://movpod.in/0wguyyxi1yca',
        'only_matching': True,
    }, {
        'url': 'http://filehoot.com/3ivfabn7573c.html',
        'info_dict': {
            'id': '3ivfabn7573c',
            'ext': 'mp4',
            'title': 'youtube-dl test video \'äBaW_jenozKc.mp4.mp4',
            'thumbnail': 're:http://.*\.jpg',
        }
    }, {
        'url': 'http://vidto.me/ku5glz52nqe1.html',
        'info_dict': {
            'id': 'ku5glz52nqe1',
            'ext': 'mp4',
            'title': 'test'
        }
    }]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        video_id = mobj.group('id')

        url = 'http://%s/%s' % (mobj.group('host'), video_id)
        webpage = self._download_webpage(url, video_id)

        if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
            raise ExtractorError('Video %s does not exist' % video_id, expected=True)

        fields = self._hidden_inputs(webpage)

        if fields['op'] == 'download1':
            countdown = int_or_none(self._search_regex(
                r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>',
                webpage, 'countdown', default=None))
            if countdown:
                self._sleep(countdown, video_id)

            post = compat_urllib_parse.urlencode(encode_dict(fields))

            req = compat_urllib_request.Request(url, post)
            req.add_header('Content-type', 'application/x-www-form-urlencoded')

            webpage = self._download_webpage(req, video_id, 'Downloading video page')

        title = (self._search_regex(
            [r'style="z-index: [0-9]+;">([^<]+)</span>',
             r'<td nowrap>([^<]+)</td>',
             r'>Watch (.+) ',
             r'<h2 class="video-page-head">([^<]+)</h2>'],
            webpage, 'title', default=None) or self._og_search_title(webpage)).strip()
        video_url = self._search_regex(
            [r'file\s*:\s*["\'](http[^"\']+)["\'],',
             r'file_link\s*=\s*\'(https?:\/\/[0-9a-zA-z.\/\-_]+)'],
            webpage, 'file url')
        thumbnail = self._search_regex(
            r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None)

        formats = [{
            'format_id': 'sd',
            'url': video_url,
            'quality': 1,
        }]

        return {
            'id': video_id,
            'title': title,
            'thumbnail': thumbnail,
            'formats': formats,
        }