youtube-dl/youtube_dl/extractor/vidzi.py

66 lines
2.0 KiB
Python
Raw Normal View History

2014-11-23 11:41:03 -08:00
# coding: utf-8
2014-10-24 06:17:17 -07:00
from __future__ import unicode_literals
import re
from .common import InfoExtractor
2016-02-25 22:26:07 -08:00
from ..utils import (
decode_packed_codes,
2016-02-25 22:26:07 -08:00
js_to_json,
NO_DEFAULT,
PACKED_CODES_RE,
2016-02-25 22:26:07 -08:00
)
2014-10-24 06:17:17 -07:00
2016-02-25 22:26:07 -08:00
class VidziIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?vidzi\.(?:tv|cc|si)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
_TESTS = [{
'url': 'http://vidzi.tv/cghql9yq6emu.html',
'md5': '4f16c71ca0c8c8635ab6932b5f3f1660',
2014-10-17 09:38:16 -07:00
'info_dict': {
'id': 'cghql9yq6emu',
2014-10-17 09:38:16 -07:00
'ext': 'mp4',
'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
},
}, {
'url': 'http://vidzi.tv/embed-4z2yb0rzphe9-600x338.html',
'only_matching': True,
2017-02-22 06:29:53 -08:00
}, {
'url': 'http://vidzi.cc/cghql9yq6emu.html',
'only_matching': True,
}, {
'url': 'https://vidzi.si/rph9gztxj1et.html',
'only_matching': 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
webpage = self._download_webpage(
'http://vidzi.tv/%s' % video_id, video_id)
2014-10-24 06:17:17 -07:00
title = self._html_search_regex(
r'(?s)<h2 class="video-title">(.*?)</h2>', webpage, 'title')
2014-11-23 11:41:03 -08:00
2017-04-21 09:37:06 -07:00
codes = [webpage]
codes.extend([
decode_packed_codes(mobj.group(0)).replace('\\\'', '\'')
for mobj in re.finditer(PACKED_CODES_RE, webpage)])
for num, code in enumerate(codes, 1):
jwplayer_data = self._parse_json(
self._search_regex(
r'setup\(([^)]+)\)', code, 'jwplayer data',
2017-04-21 09:37:06 -07:00
default=NO_DEFAULT if num == len(codes) else '{}'),
2018-06-15 15:08:44 -07:00
video_id, transform_source=lambda s: js_to_json(
re.sub(r'\s*\+\s*window\[.+?\]', '', s)))
if jwplayer_data:
break
2016-02-25 22:26:07 -08:00
info_dict = self._parse_jwplayer_data(jwplayer_data, video_id, require_title=False)
info_dict['title'] = title
return info_dict