You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
youtube-dl/youtube_dl/extractor/fktv.py

52 lines
1.5 KiB
Python

10 years ago
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
clean_html,
determine_ext,
js_to_json,
)
class FKTVIE(InfoExtractor):
10 years ago
IE_NAME = 'fernsehkritik.tv'
_VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<id>[0-9]+)(?:/.*)?'
_TEST = {
10 years ago
'url': 'http://fernsehkritik.tv/folge-1',
'md5': '21f0b0c99bce7d5b524eb1b17b1c6d79',
10 years ago
'info_dict': {
'id': '1',
'ext': 'mp4',
10 years ago
'title': 'Folge 1 vom 10. April 2007',
'thumbnail': 're:^https?://.*\.jpg$',
},
}
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'))
thumbnail = self._search_regex(r'POSTER\s*=\s*"([^"]+)', webpage, 'thumbnail', fatal=False)
sources = self._parse_json(self._search_regex(r'(?s)MEDIA\s*=\s*(\[.+?\]);', webpage, 'media'), episode, js_to_json)
formats = []
for source in sources:
furl = source.get('src')
if furl:
formats.append({
'url': furl,
'format_id': determine_ext(furl),
})
self._sort_formats(formats)
return {
'id': episode,
'title': title,
'formats': formats,
'thumbnail': thumbnail,
}