]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/openload.py
Prepare to release.
[youtubedl] / youtube_dl / extractor / openload.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..compat import compat_chr
8 from ..utils import (
9 determine_ext,
10 ExtractorError,
11 )
12
13
14 class OpenloadIE(InfoExtractor):
15 _VALID_URL = r'https?://(?:openload\.(?:co|io)|oload\.tv)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
16
17 _TESTS = [{
18 'url': 'https://openload.co/f/kUEfGclsU9o',
19 'md5': 'bf1c059b004ebc7a256f89408e65c36e',
20 'info_dict': {
21 'id': 'kUEfGclsU9o',
22 'ext': 'mp4',
23 'title': 'skyrim_no-audio_1080.mp4',
24 'thumbnail': r're:^https?://.*\.jpg$',
25 },
26 }, {
27 'url': 'https://openload.co/embed/rjC09fkPLYs',
28 'info_dict': {
29 'id': 'rjC09fkPLYs',
30 'ext': 'mp4',
31 'title': 'movie.mp4',
32 'thumbnail': r're:^https?://.*\.jpg$',
33 'subtitles': {
34 'en': [{
35 'ext': 'vtt',
36 }],
37 },
38 },
39 'params': {
40 'skip_download': True, # test subtitles only
41 },
42 }, {
43 'url': 'https://openload.co/embed/kUEfGclsU9o/skyrim_no-audio_1080.mp4',
44 'only_matching': True,
45 }, {
46 'url': 'https://openload.io/f/ZAn6oz-VZGE/',
47 'only_matching': True,
48 }, {
49 'url': 'https://openload.co/f/_-ztPaZtMhM/',
50 'only_matching': True,
51 }, {
52 # unavailable via https://openload.co/f/Sxz5sADo82g/, different layout
53 # for title and ext
54 'url': 'https://openload.co/embed/Sxz5sADo82g/',
55 'only_matching': True,
56 }, {
57 'url': 'https://oload.tv/embed/KnG-kKZdcfY/',
58 'only_matching': True,
59 }]
60
61 @staticmethod
62 def _extract_urls(webpage):
63 return re.findall(
64 r'<iframe[^>]+src=["\']((?:https?://)?(?:openload\.(?:co|io)|oload\.tv)/embed/[a-zA-Z0-9-_]+)',
65 webpage)
66
67 def _real_extract(self, url):
68 video_id = self._match_id(url)
69 webpage = self._download_webpage('https://openload.co/embed/%s/' % video_id, video_id)
70
71 if 'File not found' in webpage or 'deleted by the owner' in webpage:
72 raise ExtractorError('File not found', expected=True)
73
74 ol_id = self._search_regex(
75 '<span[^>]+id="[^"]+"[^>]*>([0-9A-Za-z]+)</span>',
76 webpage, 'openload ID')
77
78 video_url_chars = []
79
80 first_char = ord(ol_id[0])
81 key = first_char - 55
82 maxKey = max(2, key)
83 key = min(maxKey, len(ol_id) - 38)
84 t = ol_id[key:key + 36]
85
86 hashMap = {}
87 v = ol_id.replace(t, '')
88 h = 0
89
90 while h < len(t):
91 f = t[h:h + 3]
92 i = int(f, 8)
93 hashMap[h / 3] = i
94 h += 3
95
96 h = 0
97 H = 0
98 while h < len(v):
99 B = ''
100 C = ''
101 if len(v) >= h + 2:
102 B = v[h:h + 2]
103 if len(v) >= h + 3:
104 C = v[h:h + 3]
105 i = int(B, 16)
106 h += 2
107 if H % 3 == 0:
108 i = int(C, 8)
109 h += 1
110 elif H % 2 == 0 and H != 0 and ord(v[H - 1]) < 60:
111 i = int(C, 10)
112 h += 1
113 index = H % 7
114
115 A = hashMap[index]
116 i ^= 213
117 i ^= A
118 video_url_chars.append(compat_chr(i))
119 H += 1
120
121 video_url = 'https://openload.co/stream/%s?mime=true'
122 video_url = video_url % (''.join(video_url_chars))
123
124 title = self._og_search_title(webpage, default=None) or self._search_regex(
125 r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
126 'title', default=None) or self._html_search_meta(
127 'description', webpage, 'title', fatal=True)
128
129 entries = self._parse_html5_media_entries(url, webpage, video_id)
130 subtitles = entries[0]['subtitles'] if entries else None
131
132 info_dict = {
133 'id': video_id,
134 'title': title,
135 'thumbnail': self._og_search_thumbnail(webpage, default=None),
136 'url': video_url,
137 # Seems all videos have extensions in their titles
138 'ext': determine_ext(title, 'mp4'),
139 'subtitles': subtitles,
140 }
141 return info_dict