Merge pull request #11122 from kasper93/openload

[openload] Fix extraction.
This commit is contained in:
Yen Chi Hsuan 2016-11-16 20:43:19 +08:00 committed by GitHub
commit eceba9f805
3 changed files with 67 additions and 9 deletions

View File

@ -104,6 +104,13 @@ class TestJSInterpreter(unittest.TestCase):
}''') }''')
self.assertEqual(jsi.call_function('x'), [20, 20, 30, 40, 50]) self.assertEqual(jsi.call_function('x'), [20, 20, 30, 40, 50])
def test_call(self):
jsi = JSInterpreter('''
function x() { return 2; }
function y(a) { return x() + a; }
function z() { return y(3); }
''')
self.assertEqual(jsi.call_function('z'), 5)
if __name__ == '__main__': if __name__ == '__main__':
unittest.main() unittest.main()

View File

@ -1,6 +1,8 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals, division from __future__ import unicode_literals, division
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_chr, compat_chr,
@ -10,6 +12,10 @@ from ..utils import (
determine_ext, determine_ext,
ExtractorError, ExtractorError,
) )
from ..jsinterp import (
JSInterpreter,
_NAME_RE
)
class OpenloadIE(InfoExtractor): class OpenloadIE(InfoExtractor):
@ -56,6 +62,44 @@ class OpenloadIE(InfoExtractor):
'only_matching': True, 'only_matching': True,
}] }]
def openload_decode(self, txt):
symbol_dict = {
'(゚Д゚) [゚Θ゚]': '_',
'(゚Д゚) [゚ω゚ノ]': 'a',
'(゚Д゚) [゚Θ゚ノ]': 'b',
'(゚Д゚) [\'c\']': 'c',
'(゚Д゚) [゚ー゚ノ]': 'd',
'(゚Д゚) [゚Д゚ノ]': 'e',
'(゚Д゚) [1]': 'f',
'(゚Д゚) [\'o\']': 'o',
'(o゚ー゚o)': 'u',
'(゚Д゚) [\'c\']': 'c',
'((゚ー゚) + (o^_^o))': '7',
'((o^_^o) +(o^_^o) +(c^_^o))': '6',
'((゚ー゚) + (゚Θ゚))': '5',
'(-~3)': '4',
'(-~-~1)': '3',
'(-~1)': '2',
'(-~0)': '1',
'((c^_^o)-(c^_^o))': '0',
}
delim = '(゚Д゚)[゚ε゚]+'
end_token = '(゚Д゚)[゚o゚]'
symbols = '|'.join(map(re.escape, symbol_dict.keys()))
txt = re.sub('(%s)\+\s?' % symbols, lambda m: symbol_dict[m.group(1)], txt)
ret = ''
for aacode in re.findall(r'{0}\+\s?{1}(.*?){0}'.format(re.escape(end_token), re.escape(delim)), txt):
for aachar in aacode.split(delim):
if aachar.isdigit():
ret += compat_chr(int(aachar, 8))
else:
m = re.match(r'^u([\da-f]{4})$', aachar)
if m:
ret += compat_chr(int(m.group(1), 16))
else:
self.report_warning("Cannot decode: %s" % aachar)
return ret
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage('https://openload.co/embed/%s/' % video_id, video_id) webpage = self._download_webpage('https://openload.co/embed/%s/' % video_id, video_id)
@ -70,19 +114,26 @@ class OpenloadIE(InfoExtractor):
r'<span[^>]*>([^<]+)</span>\s*<span[^>]*>[^<]+</span>\s*<span[^>]+id="streamurl"', r'<span[^>]*>([^<]+)</span>\s*<span[^>]*>[^<]+</span>\s*<span[^>]+id="streamurl"',
webpage, 'encrypted data') webpage, 'encrypted data')
magic = compat_ord(enc_data[-1]) enc_code = self._html_search_regex(r'<script[^>]+>(゚ω゚[^<]+)</script>',
webpage, 'encrypted code')
js_code = self.openload_decode(enc_code)
jsi = JSInterpreter(js_code)
m_offset_fun = self._search_regex(r'slice\(0\s*-\s*(%s)\(\)' % _NAME_RE, js_code, 'javascript offset function')
m_diff_fun = self._search_regex(r'charCodeAt\(0\)\s*\+\s*(%s)\(\)' % _NAME_RE, js_code, 'javascript diff function')
offset = jsi.call_function(m_offset_fun)
diff = jsi.call_function(m_diff_fun)
video_url_chars = [] video_url_chars = []
for idx, c in enumerate(enc_data): for idx, c in enumerate(enc_data):
j = compat_ord(c) j = compat_ord(c)
if j == magic:
j -= 1
elif j == magic - 1:
j += 1
if j >= 33 and j <= 126: if j >= 33 and j <= 126:
j = ((j + 14) % 94) + 33 j = ((j + 14) % 94) + 33
if idx == len(enc_data) - 1: if idx == len(enc_data) - offset:
j += 3 j += diff
video_url_chars += compat_chr(j) video_url_chars += compat_chr(j)
video_url = 'https://openload.co/stream/%s?mime=true' % ''.join(video_url_chars) video_url = 'https://openload.co/stream/%s?mime=true' % ''.join(video_url_chars)

View File

@ -198,12 +198,12 @@ class JSInterpreter(object):
return opfunc(x, y) return opfunc(x, y)
m = re.match( m = re.match(
r'^(?P<func>%s)\((?P<args>[a-zA-Z0-9_$,]+)\)$' % _NAME_RE, expr) r'^(?P<func>%s)\((?P<args>[a-zA-Z0-9_$,]*)\)$' % _NAME_RE, expr)
if m: if m:
fname = m.group('func') fname = m.group('func')
argvals = tuple([ argvals = tuple([
int(v) if v.isdigit() else local_vars[v] int(v) if v.isdigit() else local_vars[v]
for v in m.group('args').split(',')]) for v in m.group('args').split(',')]) if len(m.group('args')) > 0 else tuple()
if fname not in self._functions: if fname not in self._functions:
self._functions[fname] = self.extract_function(fname) self._functions[fname] = self.extract_function(fname)
return self._functions[fname](argvals) return self._functions[fname](argvals)