1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-05 08:27:43 +00:00
youtube-dl/youtube_dl/extractor/chilloutzone.py

97 lines
3.4 KiB
Python
Raw Normal View History

2014-02-07 11:00:25 +00:00
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from .youtube import YoutubeIE
from ..compat import compat_b64decode
2014-02-07 11:03:19 +00:00
from ..utils import (
clean_html,
ExtractorError
)
class ChilloutzoneIE(InfoExtractor):
2014-02-07 11:00:25 +00:00
_VALID_URL = r'https?://(?:www\.)?chilloutzone\.net/video/(?P<id>[\w|-]+)\.html'
_TESTS = [{
'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',
2014-02-07 11:00:25 +00:00
'description': 'Ist das der Umkehrschluss des Niesenden Panda-Babys?',
},
}, {
'note': 'Video hosted at YouTube',
'url': 'http://www.chilloutzone.net/video/eine-sekunde-bevor.html',
'info_dict': {
'id': '1YVQaAgHyRU',
'ext': 'mp4',
'title': '16 Photos Taken 1 Second Before Disaster',
'description': 'md5:58a8fcf6a459fe0a08f54140f0ad1814',
'uploader': 'BuzzFeedVideo',
'uploader_id': 'BuzzFeedVideo',
'upload_date': '20131105',
},
}, {
'note': 'Video hosted at Vimeo',
'url': 'http://www.chilloutzone.net/video/icon-blending.html',
'md5': '2645c678b8dc4fefcc0e1b60db18dac1',
'info_dict': {
'id': '85523671',
'ext': 'mp4',
'title': 'The Sunday Times - Icons',
'description': 're:(?s)^Watch the making of - makingoficons.com.{300,}',
'uploader': 'Us',
'uploader_id': 'usfilms',
'upload_date': '20140131'
},
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
2014-02-07 11:00:25 +00:00
webpage = self._download_webpage(url, video_id)
2014-02-07 11:00:25 +00:00
base64_video_info = self._html_search_regex(
r'var cozVidData = "(.+?)";', webpage, 'video data')
decoded_video_info = compat_b64decode(base64_video_info).decode('utf-8')
video_info_dict = json.loads(decoded_video_info)
2014-02-07 11:00:25 +00:00
# get video information from dict
2014-02-07 11:00:25 +00:00
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)
2014-02-07 11:00:25 +00:00
if native_platform is None:
youtube_url = YoutubeIE._extract_url(webpage)
if youtube_url:
return self.url_result(youtube_url, ie=YoutubeIE.ie_key())
# 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(native_video_id, ie='Youtube')
if native_platform == 'vimeo':
2014-02-07 11:00:25 +00:00
return self.url_result(
'http://vimeo.com/' + native_video_id, ie='Vimeo')
2014-02-07 11:00:25 +00:00
if not video_url:
raise ExtractorError('No video found')
2014-02-07 11:00:25 +00:00
return {
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': title,
'description': description,
2014-02-07 11:00:25 +00:00
}