2 from __future__ import unicode_literals
6 from .common import InfoExtractor
7 from ..compat import compat_chr
16 class OpenloadIE(InfoExtractor):
17 _VALID_URL = r'https://openload.(?:co|io)/(?:f|embed)/(?P<id>[a-zA-Z0-9-]+)'
20 'url': 'https://openload.co/f/kUEfGclsU9o',
21 'md5': 'bf1c059b004ebc7a256f89408e65c36e',
25 'title': 'skyrim_no-audio_1080.mp4',
26 'thumbnail': 're:^https?://.*\.jpg$',
29 'url': 'https://openload.co/embed/kUEfGclsU9o/skyrim_no-audio_1080.mp4',
30 'only_matching': True,
32 'url': 'https://openload.io/f/ZAn6oz-VZGE/',
33 'only_matching': True,
35 # unavailable via https://openload.co/f/Sxz5sADo82g/, different layout
37 'url': 'https://openload.co/embed/Sxz5sADo82g/',
38 'only_matching': True,
42 def openload_level2_debase(m):
43 radix, num = int(m.group(1)) + 27, int(m.group(2))
44 return '"' + encode_base_n(num, radix) + '"'
47 def openload_level2(cls, txt):
48 # The function name is ǃ \u01c3
49 # Using escaped unicode literals does not work in Python 3.2
50 return re.sub(r'ǃ\((\d+),(\d+)\)', cls.openload_level2_debase, txt, re.UNICODE).replace('"+"', '')
52 # Openload uses a variant of aadecode
53 # openload_decode and related functions are originally written by
54 # vitas@matfyz.cz and released with public domain
55 # See https://github.com/rg3/youtube-dl/issues/8489
57 def openload_decode(cls, txt):
60 ('a', '(゚Д゚) [゚ω゚ノ]'),
61 ('b', '(゚Д゚) [゚Θ゚ノ]'),
62 ('c', '(゚Д゚) [\'c\']'),
63 ('d', '(゚Д゚) [゚ー゚ノ]'),
64 ('e', '(゚Д゚) [゚Д゚ノ]'),
67 ('o', '(゚Д゚) [\'o\']'),
69 ('c', '(゚Д゚) [\'c\']'),
71 ('7', '((゚ー゚) + (o^_^o))'),
72 ('6', '((o^_^o) +(o^_^o) +(c^_^o))'),
73 ('5', '((゚ー゚) + (゚Θ゚))'),
78 ('0', '((c^_^o)-(c^_^o))'),
82 for aachar in txt.split(delim):
83 for val, pat in symbol_table:
84 aachar = aachar.replace(pat, val)
85 aachar = aachar.replace('+ ', '')
86 m = re.match(r'^\d+', aachar)
88 ret += compat_chr(int(m.group(0), 8))
90 m = re.match(r'^u([\da-f]+)', aachar)
92 ret += compat_chr(int(m.group(1), 16))
93 return cls.openload_level2(ret)
95 def _real_extract(self, url):
96 video_id = self._match_id(url)
97 webpage = self._download_webpage(url, video_id)
99 if 'File not found' in webpage:
100 raise ExtractorError('File not found', expected=True)
102 code = self._search_regex(
103 r'<video[^>]+>\s*<script[^>]+>([^<]+)</script>',
106 decoded = self.openload_decode(code)
108 video_url = self._search_regex(
109 r'return\s+"(https?://[^"]+)"', decoded, 'video URL')
111 title = self._og_search_title(webpage, default=None) or self._search_regex(
112 r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
113 'title', default=None) or self._html_search_meta(
114 'description', webpage, 'title', fatal=True)
116 ext = mimetype2ext(self._search_regex(
117 r'window\.vt\s*=\s*(["\'])(?P<mimetype>.+?)\1', decoded,
118 'mimetype', default=None, group='mimetype')) or determine_ext(
125 'thumbnail': self._og_search_thumbnail(webpage, default=None),