2 from __future__ import unicode_literals
6 from .common import InfoExtractor
7 from ..compat import compat_chr
14 class OpenloadIE(InfoExtractor):
15 _VALID_URL = r'https://openload.(?:co|io)/(?:f|embed)/(?P<id>[a-zA-Z0-9-]+)'
18 'url': 'https://openload.co/f/kUEfGclsU9o',
19 'md5': 'bf1c059b004ebc7a256f89408e65c36e',
23 'title': 'skyrim_no-audio_1080.mp4',
24 'thumbnail': 're:^https?://.*\.jpg$',
27 'url': 'https://openload.co/embed/kUEfGclsU9o/skyrim_no-audio_1080.mp4',
28 'only_matching': True,
30 'url': 'https://openload.io/f/ZAn6oz-VZGE/',
31 'only_matching': True,
35 def openload_level2_debase(m):
36 radix, num = int(m.group(1)) + 27, int(m.group(2))
37 return '"' + encode_base_n(num, radix) + '"'
40 def openload_level2(cls, txt):
41 # The function name is ǃ \u01c3
42 # Using escaped unicode literals does not work in Python 3.2
43 return re.sub(r'ǃ\((\d+),(\d+)\)', cls.openload_level2_debase, txt, re.UNICODE).replace('"+"', '')
45 # Openload uses a variant of aadecode
46 # openload_decode and related functions are originally written by
47 # vitas@matfyz.cz and released with public domain
48 # See https://github.com/rg3/youtube-dl/issues/8489
50 def openload_decode(cls, txt):
53 ('a', '(゚Д゚) [゚ω゚ノ]'),
54 ('b', '(゚Д゚) [゚Θ゚ノ]'),
55 ('c', '(゚Д゚) [\'c\']'),
56 ('d', '(゚Д゚) [゚ー゚ノ]'),
57 ('e', '(゚Д゚) [゚Д゚ノ]'),
60 ('o', '(゚Д゚) [\'o\']'),
62 ('c', '(゚Д゚) [\'c\']'),
64 ('7', '((゚ー゚) + (o^_^o))'),
65 ('6', '((o^_^o) +(o^_^o) +(c^_^o))'),
66 ('5', '((゚ー゚) + (゚Θ゚))'),
71 ('0', '((c^_^o)-(c^_^o))'),
75 for aachar in txt.split(delim):
76 for val, pat in symbol_table:
77 aachar = aachar.replace(pat, val)
78 aachar = aachar.replace('+ ', '')
79 m = re.match(r'^\d+', aachar)
81 ret += compat_chr(int(m.group(0), 8))
83 m = re.match(r'^u([\da-f]+)', aachar)
85 ret += compat_chr(int(m.group(1), 16))
86 return cls.openload_level2(ret)
88 def _real_extract(self, url):
89 video_id = self._match_id(url)
90 webpage = self._download_webpage(url, video_id)
92 if 'File not found' in webpage:
93 raise ExtractorError('File not found', expected=True)
95 code = self._search_regex(
96 r'<video[^>]+>\s*<script[^>]+>([^<]+)</script>',
99 video_url = self._search_regex(
100 r'return\s+"(https?://[^"]+)"', self.openload_decode(code), 'video URL')
104 'title': self._og_search_title(webpage),
105 'thumbnail': self._og_search_thumbnail(webpage),