2016-03-20 07:54:58 +00:00
|
|
|
|
# coding: utf-8
|
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
|
|
|
|
import re
|
|
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
|
|
|
|
from ..compat import compat_chr
|
2016-03-20 08:49:44 +00:00
|
|
|
|
from ..utils import (
|
2016-04-24 18:03:29 +00:00
|
|
|
|
determine_ext,
|
2016-03-20 08:49:44 +00:00
|
|
|
|
encode_base_n,
|
|
|
|
|
ExtractorError,
|
2016-04-24 18:03:29 +00:00
|
|
|
|
mimetype2ext,
|
2016-03-20 08:49:44 +00:00
|
|
|
|
)
|
2016-03-20 07:54:58 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class OpenloadIE(InfoExtractor):
|
2016-03-20 08:49:44 +00:00
|
|
|
|
_VALID_URL = r'https://openload.(?:co|io)/(?:f|embed)/(?P<id>[a-zA-Z0-9-]+)'
|
2016-03-20 07:54:58 +00:00
|
|
|
|
|
2016-03-20 08:49:44 +00:00
|
|
|
|
_TESTS = [{
|
2016-03-20 07:54:58 +00:00
|
|
|
|
'url': 'https://openload.co/f/kUEfGclsU9o',
|
|
|
|
|
'md5': 'bf1c059b004ebc7a256f89408e65c36e',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'kUEfGclsU9o',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'skyrim_no-audio_1080.mp4',
|
2016-03-20 08:49:44 +00:00
|
|
|
|
'thumbnail': 're:^https?://.*\.jpg$',
|
2016-03-20 07:54:58 +00:00
|
|
|
|
},
|
2016-03-20 08:49:44 +00:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://openload.co/embed/kUEfGclsU9o/skyrim_no-audio_1080.mp4',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://openload.io/f/ZAn6oz-VZGE/',
|
|
|
|
|
'only_matching': True,
|
2016-04-24 18:22:55 +00:00
|
|
|
|
}, {
|
|
|
|
|
# unavailable via https://openload.co/f/Sxz5sADo82g/, different layout
|
|
|
|
|
# for title and ext
|
|
|
|
|
'url': 'https://openload.co/embed/Sxz5sADo82g/',
|
|
|
|
|
'only_matching': True,
|
2016-03-20 08:49:44 +00:00
|
|
|
|
}]
|
2016-03-20 07:54:58 +00:00
|
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
|
def openload_level2_debase(m):
|
|
|
|
|
radix, num = int(m.group(1)) + 27, int(m.group(2))
|
|
|
|
|
return '"' + encode_base_n(num, radix) + '"'
|
|
|
|
|
|
|
|
|
|
@classmethod
|
|
|
|
|
def openload_level2(cls, txt):
|
|
|
|
|
# The function name is ǃ \u01c3
|
|
|
|
|
# Using escaped unicode literals does not work in Python 3.2
|
|
|
|
|
return re.sub(r'ǃ\((\d+),(\d+)\)', cls.openload_level2_debase, txt, re.UNICODE).replace('"+"', '')
|
|
|
|
|
|
|
|
|
|
# Openload uses a variant of aadecode
|
|
|
|
|
# openload_decode and related functions are originally written by
|
|
|
|
|
# vitas@matfyz.cz and released with public domain
|
|
|
|
|
# See https://github.com/rg3/youtube-dl/issues/8489
|
|
|
|
|
@classmethod
|
|
|
|
|
def openload_decode(cls, txt):
|
|
|
|
|
symbol_table = [
|
|
|
|
|
('_', '(゚Д゚) [゚Θ゚]'),
|
|
|
|
|
('a', '(゚Д゚) [゚ω゚ノ]'),
|
|
|
|
|
('b', '(゚Д゚) [゚Θ゚ノ]'),
|
|
|
|
|
('c', '(゚Д゚) [\'c\']'),
|
|
|
|
|
('d', '(゚Д゚) [゚ー゚ノ]'),
|
|
|
|
|
('e', '(゚Д゚) [゚Д゚ノ]'),
|
|
|
|
|
('f', '(゚Д゚) [1]'),
|
|
|
|
|
|
|
|
|
|
('o', '(゚Д゚) [\'o\']'),
|
|
|
|
|
('u', '(o゚ー゚o)'),
|
|
|
|
|
('c', '(゚Д゚) [\'c\']'),
|
|
|
|
|
|
|
|
|
|
('7', '((゚ー゚) + (o^_^o))'),
|
|
|
|
|
('6', '((o^_^o) +(o^_^o) +(c^_^o))'),
|
|
|
|
|
('5', '((゚ー゚) + (゚Θ゚))'),
|
|
|
|
|
('4', '(-~3)'),
|
|
|
|
|
('3', '(-~-~1)'),
|
|
|
|
|
('2', '(-~1)'),
|
|
|
|
|
('1', '(-~0)'),
|
|
|
|
|
('0', '((c^_^o)-(c^_^o))'),
|
|
|
|
|
]
|
|
|
|
|
delim = '(゚Д゚)[゚ε゚]+'
|
|
|
|
|
ret = ''
|
|
|
|
|
for aachar in txt.split(delim):
|
|
|
|
|
for val, pat in symbol_table:
|
|
|
|
|
aachar = aachar.replace(pat, val)
|
|
|
|
|
aachar = aachar.replace('+ ', '')
|
|
|
|
|
m = re.match(r'^\d+', aachar)
|
|
|
|
|
if m:
|
|
|
|
|
ret += compat_chr(int(m.group(0), 8))
|
|
|
|
|
else:
|
|
|
|
|
m = re.match(r'^u([\da-f]+)', aachar)
|
|
|
|
|
if m:
|
|
|
|
|
ret += compat_chr(int(m.group(1), 16))
|
|
|
|
|
return cls.openload_level2(ret)
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
video_id = self._match_id(url)
|
|
|
|
|
webpage = self._download_webpage(url, video_id)
|
2016-03-20 08:49:44 +00:00
|
|
|
|
|
|
|
|
|
if 'File not found' in webpage:
|
|
|
|
|
raise ExtractorError('File not found', expected=True)
|
|
|
|
|
|
2016-03-20 07:54:58 +00:00
|
|
|
|
code = self._search_regex(
|
|
|
|
|
r'<video[^>]+>\s*<script[^>]+>([^<]+)</script>',
|
|
|
|
|
webpage, 'JS code')
|
|
|
|
|
|
2016-04-24 18:03:29 +00:00
|
|
|
|
decoded = self.openload_decode(code)
|
|
|
|
|
|
2016-03-20 07:54:58 +00:00
|
|
|
|
video_url = self._search_regex(
|
2016-04-24 18:03:29 +00:00
|
|
|
|
r'return\s+"(https?://[^"]+)"', decoded, 'video URL')
|
2016-03-20 07:54:58 +00:00
|
|
|
|
|
2016-04-24 18:01:37 +00:00
|
|
|
|
title = self._og_search_title(webpage, default=None) or self._search_regex(
|
|
|
|
|
r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
|
|
|
|
|
'title', default=None) or self._html_search_meta(
|
|
|
|
|
'description', webpage, 'title', fatal=True)
|
|
|
|
|
|
2016-04-24 18:03:29 +00:00
|
|
|
|
ext = mimetype2ext(self._search_regex(
|
|
|
|
|
r'window\.vt\s*=\s*(["\'])(?P<mimetype>.+?)\1', decoded,
|
|
|
|
|
'mimetype', default=None, group='mimetype')) or determine_ext(
|
|
|
|
|
video_url, 'mp4')
|
|
|
|
|
|
2016-03-20 07:54:58 +00:00
|
|
|
|
return {
|
|
|
|
|
'id': video_id,
|
2016-04-24 18:01:37 +00:00
|
|
|
|
'title': title,
|
2016-04-24 18:03:29 +00:00
|
|
|
|
'ext': ext,
|
2016-03-20 08:49:44 +00:00
|
|
|
|
'thumbnail': self._og_search_thumbnail(webpage),
|
2016-03-20 07:54:58 +00:00
|
|
|
|
'url': video_url,
|
|
|
|
|
}
|