youtube-dl/youtube_dl/extractor/fktv.py

49 lines
1.5 KiB
Python
Raw Normal View History

2014-10-27 01:26:05 +00:00
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
clean_html,
2015-09-09 09:42:47 +00:00
determine_ext,
ExtractorError,
)
class FKTVIE(InfoExtractor):
2014-10-27 01:26:05 +00:00
IE_NAME = 'fernsehkritik.tv'
2015-01-08 15:03:13 +00:00
_VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<id>[0-9]+)(?:/.*)?'
_TEST = {
2014-10-27 01:26:05 +00:00
'url': 'http://fernsehkritik.tv/folge-1',
2015-09-09 09:42:47 +00:00
'md5': '21f0b0c99bce7d5b524eb1b17b1c6d79',
2014-10-27 01:26:05 +00:00
'info_dict': {
2015-09-09 09:42:47 +00:00
'id': '1',
'ext': 'mp4',
2014-10-27 01:26:05 +00:00
'title': 'Folge 1 vom 10. April 2007',
'thumbnail': 're:^https?://.*\.jpg$',
},
}
def _real_extract(self, url):
2015-09-09 09:42:47 +00:00
episode = self._match_id(url)
webpage = self._download_webpage('http://fernsehkritik.tv/folge-%s/play' % episode, episode)
2015-09-25 09:51:48 +00:00
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()
if poster is None:
self.report_warning('unable to extract thumbnail')
2015-09-25 09:51:48 +00:00
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,
}