1
0
Fork 0
mirror of https://github.com/blackjack4494/yt-dlc.git synced 2024-12-25 01:07:19 +00:00
yt-dlc/youtube_dl/extractor/fktv.py
2015-09-25 17:51:48 +08:00

44 lines
1.3 KiB
Python

from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
clean_html,
determine_ext,
ExtractorError,
)
class FKTVIE(InfoExtractor):
IE_NAME = 'fernsehkritik.tv'
_VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<id>[0-9]+)(?:/.*)?'
_TEST = {
'url': 'http://fernsehkritik.tv/folge-1',
'md5': '21f0b0c99bce7d5b524eb1b17b1c6d79',
'info_dict': {
'id': '1',
'ext': 'mp4',
'title': 'Folge 1 vom 10. April 2007',
},
}
def _real_extract(self, url):
episode = self._match_id(url)
webpage = self._download_webpage('http://fernsehkritik.tv/folge-%s/play' % episode, episode)
title = clean_html(self._html_search_regex('<h3>([^<]+)</h3>', webpage, 'title'))
matches = re.search(r'(?s)<video[^>]+poster="([^"]+)"[^>]*>(.*)</video>', webpage)
if matches is None:
raise ExtractorError('Unable to extract the video')
poster, sources = matches.groups()
urls = re.findall(r'<source[^>]+src="([^"]+)"', sources)
formats = [{'url': url, 'format_id': determine_ext(url)} for url in urls]
return {
'id': episode,
'title': title,
'formats': formats,
'thumbnail': poster,
}