2014-11-23 11:41:03 -08:00
|
|
|
# coding: utf-8
|
2014-10-24 06:17:17 -07:00
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
2016-02-25 22:26:07 -08:00
|
|
|
import re
|
2014-10-17 09:38:16 -07:00
|
|
|
|
2016-02-25 22:26:07 -08:00
|
|
|
from .jwplatform import JWPlatformBaseIE
|
|
|
|
from ..utils import (
|
2016-02-25 22:37:20 -08:00
|
|
|
base_n,
|
2016-02-25 22:26:07 -08:00
|
|
|
js_to_json,
|
|
|
|
)
|
2014-10-24 06:17:17 -07:00
|
|
|
|
2016-02-25 22:26:07 -08:00
|
|
|
|
|
|
|
class VidziIE(JWPlatformBaseIE):
|
2014-10-17 09:38:16 -07:00
|
|
|
_VALID_URL = r'https?://(?:www\.)?vidzi\.tv/(?P<id>\w+)'
|
|
|
|
_TEST = {
|
2014-10-24 06:27:02 -07:00
|
|
|
'url': 'http://vidzi.tv/cghql9yq6emu.html',
|
|
|
|
'md5': '4f16c71ca0c8c8635ab6932b5f3f1660',
|
2014-10-17 09:38:16 -07:00
|
|
|
'info_dict': {
|
2014-10-24 06:27:02 -07:00
|
|
|
'id': 'cghql9yq6emu',
|
2014-10-17 09:38:16 -07:00
|
|
|
'ext': 'mp4',
|
2014-10-24 06:27:02 -07:00
|
|
|
'title': 'youtube-dl test video 1\\\\2\'3/4<5\\\\6ä7↭',
|
2016-02-01 01:03:31 -08:00
|
|
|
},
|
|
|
|
'params': {
|
|
|
|
# m3u8 download
|
|
|
|
'skip_download': True,
|
2014-10-17 09:38:16 -07:00
|
|
|
},
|
|
|
|
}
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2014-10-24 06:17:17 -07:00
|
|
|
video_id = self._match_id(url)
|
2014-11-23 11:41:03 -08:00
|
|
|
|
2014-10-24 06:17:17 -07:00
|
|
|
webpage = self._download_webpage(url, video_id)
|
|
|
|
title = self._html_search_regex(
|
2014-10-24 06:27:02 -07:00
|
|
|
r'(?s)<h2 class="video-title">(.*?)</h2>', webpage, 'title')
|
2014-11-23 11:41:03 -08:00
|
|
|
|
2016-02-25 22:26:07 -08:00
|
|
|
mobj = re.search(r"}\('(.+)',36,(\d+),'([^']+)'\.split\('\|'\)", webpage)
|
|
|
|
code, count, symbols = mobj.groups()
|
|
|
|
|
|
|
|
count = int(count)
|
|
|
|
symbols = symbols.split('|')
|
|
|
|
|
|
|
|
while count:
|
|
|
|
count -= 1
|
|
|
|
if symbols[count]:
|
2016-02-25 22:37:20 -08:00
|
|
|
code = re.sub(r'\b%s\b' % base_n(count, 36), symbols[count], code)
|
2016-02-25 22:26:07 -08:00
|
|
|
|
|
|
|
code = code.replace('\\\'', '\'')
|
|
|
|
jwplayer_data = self._parse_json(
|
|
|
|
self._search_regex(r'setup\(([^)]+)\)', code, 'jwplayer data'),
|
|
|
|
video_id, transform_source=js_to_json)
|
|
|
|
|
|
|
|
info_dict = self._parse_jwplayer_data(jwplayer_data, video_id, require_title=False)
|
|
|
|
info_dict['title'] = title
|
|
|
|
|
|
|
|
return info_dict
|