aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/gorillavid.py
blob: 8c3ad8c7d03ab1ba087cba0723cc3531627b4a2c (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
# -*- coding: utf-8 -*-
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..utils import (
    determine_ext,
    compat_urllib_parse,
    compat_urllib_request,
)


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

    _TESTS = [{
        'url': 'http://gorillavid.in/06y9juieqpmi',
        'md5': '5ae4a3580620380619678ee4875893ba',
        'info_dict': {
            'id': '06y9juieqpmi',
            'ext': 'flv',
            'title': 'Rebecca Black My Moment Official Music Video Reaction',
            'thumbnail': 're:http://.*\.jpg',
        },
    }, {
        'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
        'md5': 'c9e293ca74d46cad638e199c3f3fe604',
        'info_dict': {
            'id': 'z08zf8le23c6',
            'ext': 'mp4',
            'title': 'Say something nice',
            'thumbnail': 're:http://.*\.jpg',
        },
    }, {
        'url': 'http://daclips.in/3rso4kdn6f9m',
        'md5': '1ad8fd39bb976eeb66004d3a4895f106',
        'info_dict': {
            'id': '3rso4kdn6f9m',
            'ext': 'mp4',
            'title': 'Micro Pig piglets ready on 16th July 2009',
            'thumbnail': 're:http://.*\.jpg',
        },
    }, {
        'url': 'http://movpod.in/0wguyyxi1yca',
        'only_matching': True,
    }]

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

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

        fields = dict(re.findall(r'''(?x)<input\s+
            type="hidden"\s+
            name="([^"]+)"\s+
            (?:id="[^"]+"\s+)?
            value="([^"]*)"
            ''', webpage))
        
        if fields['op'] == 'download1':
            post = compat_urllib_parse.urlencode(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]+;">([0-9a-zA-Z ]+)(?:-.+)?</span>', webpage, 'title')
        thumbnail = self._search_regex(r'image:\'(http[^\']+)\',', webpage, 'thumbnail')
        url = self._search_regex(r'file: \'(http[^\']+)\',', webpage, 'file url')

        formats = [{
            'format_id': 'sd',
            'url': url,
            'ext': determine_ext(url),
            'quality': 1,
        }]

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