ytdl/youtube_dl/extractor/fktv.py

83 lines
2.7 KiB
Python
Raw Normal View History

2014-10-27 02:26:05 +01:00
from __future__ import unicode_literals
import re
import random
import json
from .common import InfoExtractor
from ..utils import (
get_element_by_id,
clean_html,
)
class FKTVIE(InfoExtractor):
2014-10-27 02:26:05 +01:00
IE_NAME = 'fernsehkritik.tv'
2015-01-08 16:03:13 +01:00
_VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<id>[0-9]+)(?:/.*)?'
_TEST = {
2014-10-27 02:26:05 +01:00
'url': 'http://fernsehkritik.tv/folge-1',
'info_dict': {
'id': '00011',
'ext': 'flv',
'title': 'Folge 1 vom 10. April 2007',
'description': 'md5:fb4818139c7cfe6907d4b83412a6864f',
},
}
def _real_extract(self, url):
2015-01-08 16:03:13 +01:00
episode = int(self._match_id(url))
2015-01-08 16:03:13 +01:00
video_thumbnail = 'http://fernsehkritik.tv/images/magazin/folge%s.jpg' % episode
start_webpage = self._download_webpage('http://fernsehkritik.tv/folge-%s/Start' % episode,
2014-11-23 21:39:15 +01:00
episode)
playlist = self._search_regex(r'playlist = (\[.*?\]);', start_webpage,
2014-11-23 21:39:15 +01:00
'playlist', flags=re.DOTALL)
files = json.loads(re.sub('{[^{}]*?}', '{}', playlist))
2015-01-08 16:03:13 +01:00
videos = []
for i, _ in enumerate(files, 1):
video_id = '%04d%d' % (episode, i)
2015-01-08 16:03:13 +01:00
video_url = 'http://fernsehkritik.tv/js/directme.php?file=%s%s.flv' % (episode, '' if i == 1 else '-%d' % i)
videos.append({
2015-01-08 16:03:13 +01:00
'ext': 'flv',
'id': video_id,
'url': video_url,
'title': clean_html(get_element_by_id('eptitle', start_webpage)),
'description': clean_html(get_element_by_id('contentlist', start_webpage)),
'thumbnail': video_thumbnail
})
2015-01-08 16:03:13 +01:00
return {
'_type': 'multi_video',
'entries': videos,
'id': 'folge-%s' % episode,
}
class FKTVPosteckeIE(InfoExtractor):
2014-10-27 02:26:05 +01:00
IE_NAME = 'fernsehkritik.tv:postecke'
_VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/inline-video/postecke\.php\?(.*&)?ep=(?P<ep>[0-9]+)(&|$)'
_TEST = {
2014-10-27 02:26:05 +01:00
'url': 'http://fernsehkritik.tv/inline-video/postecke.php?iframe=true&width=625&height=440&ep=120',
'md5': '262f0adbac80317412f7e57b4808e5c4',
'info_dict': {
'id': '0120',
'ext': 'flv',
'title': 'Postecke 120',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
episode = int(mobj.group('ep'))
server = random.randint(2, 4)
video_id = '%04d' % episode
video_url = 'http://dl%d.fernsehkritik.tv/postecke/postecke%d.flv' % (server, episode)
video_title = 'Postecke %d' % episode
return {
2014-10-27 02:26:05 +01:00
'id': video_id,
'url': video_url,
'title': video_title,
}