youtube-dl/youtube_dl/extractor/chilloutzone.py
2014-02-07 12:00:25 +01:00

70 lines
2.5 KiB
Python

from __future__ import unicode_literals
import re
import base64
import json
from .common import InfoExtractor
from ..utils import clean_html
class ChilloutzoneIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?chilloutzone\.net/video/(?P<id>[\w|-]+)\.html'
_TEST = {
'url': 'http://www.chilloutzone.net/video/enemene-meck-alle-katzen-weg.html',
'md5': 'a76f3457e813ea0037e5244f509e66d1',
'info_dict': {
'id': 'enemene-meck-alle-katzen-weg',
'ext': 'mp4',
'title': 'Enemene Meck - Alle Katzen weg',
'description': 'Ist das der Umkehrschluss des Niesenden Panda-Babys?',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
base64_video_info = self._html_search_regex(
r'var cozVidData = "(.+?)";', webpage, 'video data')
decoded_video_info = base64.b64decode(base64_video_info).decode("utf-8")
video_info_dict = json.loads(decoded_video_info)
# get video information from dict
video_url = video_info_dict['mediaUrl']
description = clean_html(video_info_dict.get('description'))
title = video_info_dict['title']
native_platform = video_info_dict['nativePlatform']
native_video_id = video_info_dict['nativeVideoId']
source_priority = video_info_dict['sourcePriority']
# If nativePlatform is None a fallback mechanism is used (i.e. youtube embed)
if native_platform is None:
youtube_url = self._html_search_regex(
r'<iframe.* src="((?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
webpage, 'fallback video URL', default=None)
if youtube_url is not None:
return self.url_result(youtube_url, ie='Youtube')
# Non Fallback: Decide to use native source (e.g. youtube or vimeo) or
# the own CDN
if source_priority == 'native':
if native_platform == 'youtube':
return self.url_result(video_id, ie='Youtube')
if native_platform == 'vimeo':
return self.url_result(
'http://vimeo.com/' + native_video_id, ie='Vimeo')
if not video_url:
raise ExtractorError('No video found')
return {
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': title,
'description': description,
}