1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
|
import re
import base64
import urllib
import json
from .common import InfoExtractor
video_container = ('.mp4', '.mkv', '.flv')
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',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage_url = 'http://www.chilloutzone.net/video/' + video_id + '.html'
# Log that we are starting to download the page
self.report_download_webpage(webpage_url)
webpage = self._download_webpage(webpage_url, video_id)
# Log that we are starting to parse the page
self.report_extraction(video_id)
# Find base64 decoded file info
base64_video_info = self._html_search_regex(r'var cozVidData = "(.+?)";', webpage, u'video Data')
# decode string and find video file
decoded_video_info = base64.b64decode(base64_video_info).decode("utf-8")
video_info_dict = json.loads(decoded_video_info)
# get video information from dict
media_url = video_info_dict['mediaUrl']
description = video_info_dict['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']
# Start video extraction
video_url = ''
# If nativePlatform is None a fallback mechanism is used (i.e. youtube embed)
if native_platform == None:
# Look for other video urls
video_url = self._html_search_regex(r'<iframe.* src="(.+?)".*', webpage, u'fallback Video URL')
if 'youtube' in video_url:
self.to_screen(u'Youtube video detected:')
return self.url_result(video_url, ie='Youtube')
# For debugging purposes
#print video_info_dict
#print native_platform
#print native_video_id
#print source_priority
#print media_url
# Non Fallback: Decide to use native source (e.g. youtube or vimeo) or
# the own CDN
if source_priority == 'native':
if native_platform == 'youtube':
self.to_screen(u'Youtube video detected:')
video_url = 'https://www.youtube.com/watch?v=' + native_video_id
return self.url_result(video_url, ie='Youtube')
if native_platform == 'vimeo':
self.to_screen(u'Vimeo video detected:')
video_url = 'http://vimeo.com/' + native_video_id
return self.url_result(video_url, ie='Vimeo')
# No redirect, use coz media url
video_url = media_url
if video_url.endswith('.mp4') == False:
self.report_warning(u'Url does not contain a video container')
return []
return [{
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': title,
'description': description,
}]
|
