aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/addanime.py
blob: 45aac15c328ba30b655178e860d9abcfbba0b682 (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
import re

from .common import InfoExtractor
from ..utils import (
    compat_HTTPError,
    compat_str,
    compat_urllib_parse,
    compat_urllib_parse_urlparse,

    ExtractorError,
    RegexNotFoundError,
)


class AddAnimeIE(InfoExtractor):

    _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)'
    IE_NAME = u'AddAnime'
    _TEST = {
        u'url': u'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
        u'file': u'24MR3YO5SAS9.mp4',
        u'md5': u'3f8e232ad52163c87fa23897e736cb2c',
        u'info_dict': {
            u"description": u"One Piece 606",
            u"title": u"One Piece 606"
        }
    }

    def _real_extract(self, url):
        try:
            mobj = re.match(self._VALID_URL, url)
            video_id = mobj.group('video_id')
            webpage = self._download_webpage(url, video_id)
        except ExtractorError as ee:
            if not isinstance(ee.cause, compat_HTTPError):
                raise

            redir_webpage = ee.cause.read().decode('utf-8')
            action = self._search_regex(
                r'<form id="challenge-form" action="([^"]+)"',
                redir_webpage, u'Redirect form')
            vc = self._search_regex(
                r'<input type="hidden" name="jschl_vc" value="([^"]+)"/>',
                redir_webpage, u'redirect vc value')
            av = re.search(
                r'a\.value = ([0-9]+)[+]([0-9]+)[*]([0-9]+);',
                redir_webpage)
            if av is None:
                raise ExtractorError(u'Cannot find redirect math task')
            av_res = int(av.group(1)) + int(av.group(2)) * int(av.group(3))

            parsed_url = compat_urllib_parse_urlparse(url)
            av_val = av_res + len(parsed_url.netloc)
            confirm_url = (
                parsed_url.scheme + u'://' + parsed_url.netloc +
                action + '?' +
                compat_urllib_parse.urlencode({
                    'jschl_vc': vc, 'jschl_answer': compat_str(av_val)}))
            self._download_webpage(
                confirm_url, video_id,
                note=u'Confirming after redirect')
            webpage = self._download_webpage(url, video_id)

        try:
            video_url = self._search_regex(r"var hq_video_file = '(.*?)';",
                                           webpage, u'video file URL')
        except RegexNotFoundError:
            video_url = self._search_regex(r"var normal_video_file = '(.*?)';",
                                           webpage, u'video file URL')
        
        video_extension = video_url[-3:]  # mp4 or flv ?
        video_title = self._og_search_title(webpage)
        video_description = self._og_search_description(webpage)

        return {
            '_type': 'video',
            'id':  video_id,
            'url': video_url,
            'ext': video_extension,
            'title': video_title,
            'description': video_description
        }