]> git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/addanime.py
[addanime] Add test for #5372
[youtube-dl] / youtube_dl / extractor / addanime.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..compat import (
7     compat_HTTPError,
8     compat_str,
9     compat_urllib_parse,
10     compat_urllib_parse_urlparse,
11 )
12 from ..utils import (
13     ExtractorError,
14     qualities,
15 )
16
17
18 class AddAnimeIE(InfoExtractor):
19     _VALID_URL = r'http://(?:\w+\.)?add-anime\.net/(?:watch_video\.php\?(?:.*?)v=|video/)(?P<id>[\w_]+)'
20     _TESTS = [{
21         'url': 'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
22         'md5': '72954ea10bc979ab5e2eb288b21425a0',
23         'info_dict': {
24             'id': '24MR3YO5SAS9',
25             'ext': 'mp4',
26             'description': 'One Piece 606',
27             'title': 'One Piece 606',
28         }
29     }, {
30         'url': 'http://add-anime.net/video/MDUGWYKNGBD8/One-Piece-687',
31         'only_matching': True,
32     }]
33
34     def _real_extract(self, url):
35         video_id = self._match_id(url)
36
37         try:
38             webpage = self._download_webpage(url, video_id)
39         except ExtractorError as ee:
40             if not isinstance(ee.cause, compat_HTTPError) or \
41                ee.cause.code != 503:
42                 raise
43
44             redir_webpage = ee.cause.read().decode('utf-8')
45             action = self._search_regex(
46                 r'<form id="challenge-form" action="([^"]+)"',
47                 redir_webpage, 'Redirect form')
48             vc = self._search_regex(
49                 r'<input type="hidden" name="jschl_vc" value="([^"]+)"/>',
50                 redir_webpage, 'redirect vc value')
51             av = re.search(
52                 r'a\.value = ([0-9]+)[+]([0-9]+)[*]([0-9]+);',
53                 redir_webpage)
54             if av is None:
55                 raise ExtractorError('Cannot find redirect math task')
56             av_res = int(av.group(1)) + int(av.group(2)) * int(av.group(3))
57
58             parsed_url = compat_urllib_parse_urlparse(url)
59             av_val = av_res + len(parsed_url.netloc)
60             confirm_url = (
61                 parsed_url.scheme + '://' + parsed_url.netloc +
62                 action + '?' +
63                 compat_urllib_parse.urlencode({
64                     'jschl_vc': vc, 'jschl_answer': compat_str(av_val)}))
65             self._download_webpage(
66                 confirm_url, video_id,
67                 note='Confirming after redirect')
68             webpage = self._download_webpage(url, video_id)
69
70         FORMATS = ('normal', 'hq')
71         quality = qualities(FORMATS)
72         formats = []
73         for format_id in FORMATS:
74             rex = r"var %s_video_file = '(.*?)';" % re.escape(format_id)
75             video_url = self._search_regex(rex, webpage, 'video file URLx',
76                                            fatal=False)
77             if not video_url:
78                 continue
79             formats.append({
80                 'format_id': format_id,
81                 'url': video_url,
82                 'quality': quality(format_id),
83             })
84         self._sort_formats(formats)
85         video_title = self._og_search_title(webpage)
86         video_description = self._og_search_description(webpage)
87
88         return {
89             '_type': 'video',
90             'id': video_id,
91             'formats': formats,
92             'title': video_title,
93             'description': video_description
94         }