youtube-dl/youtube_dl/extractor/vidzi.py

56 lines
1.6 KiB
Python
Raw Normal View History

2014-11-24 04:41:03 +09:00
# coding: utf-8
2014-10-24 22:17:17 +09:00
from __future__ import unicode_literals
2016-02-26 15:26:07 +09:00
import re
2014-10-18 01:38:16 +09:00
2016-02-26 15:26:07 +09:00
from .jwplatform import JWPlatformBaseIE
from ..utils import (
2016-02-26 15:37:20 +09:00
base_n,
2016-02-26 15:26:07 +09:00
js_to_json,
)
2014-10-24 22:17:17 +09:00
2016-02-26 15:26:07 +09:00
class VidziIE(JWPlatformBaseIE):
2014-10-18 01:38:16 +09:00
_VALID_URL = r'https?://(?:www\.)?vidzi\.tv/(?P<id>\w+)'
_TEST = {
'url': 'http://vidzi.tv/cghql9yq6emu.html',
'md5': '4f16c71ca0c8c8635ab6932b5f3f1660',
2014-10-18 01:38:16 +09:00
'info_dict': {
'id': 'cghql9yq6emu',
2014-10-18 01:38:16 +09:00
'ext': 'mp4',
'title': 'youtube-dl test video 1\\\\2\'3/4<5\\\\6ä7↭',
2016-02-01 18:03:31 +09:00
},
'params': {
# m3u8 download
'skip_download': True,
2014-10-18 01:38:16 +09:00
},
}
def _real_extract(self, url):
2014-10-24 22:17:17 +09:00
video_id = self._match_id(url)
2014-11-24 04:41:03 +09:00
2014-10-24 22:17:17 +09:00
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(
r'(?s)<h2 class="video-title">(.*?)</h2>', webpage, 'title')
2014-11-24 04:41:03 +09:00
2016-02-26 15:26:07 +09:00
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]:
2016-02-26 15:37:20 +09:00
code = re.sub(r'\b%s\b' % base_n(count, 36), symbols[count], code)
2016-02-26 15:26:07 +09:00
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