github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[chilloutzone] Simplify (#2338)

Browse source
This commit is contained in:
Philipp Hagemeister 2014-02-07 12:00:25 +01:00
parent 9f31be7000
commit 4a9540b6d2
1 changed files with 28 additions and 52 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

72
youtube_dl/extractor/chilloutzone.py
View file

@ -1,14 +1,15 @@
from __future__ import unicode_literals
import re import re
import base64 import base64
import urllib
import json import json
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import clean_html
video_container = ('.mp4', '.mkv', '.flv')
class ChilloutzoneIE(InfoExtractor): class ChilloutzoneIE(InfoExtractor):
_VALID_URL = r'(?:https?://)?(?:www\.)?chilloutzone\.net/video/(?P<id>[\w|-]+).html' _VALID_URL = r'https?://(?:www\.)?chilloutzone\.net/video/(?P<id>[\w|-]+)\.html'
_TEST = { _TEST = {
'url': 'http://www.chilloutzone.net/video/enemene-meck-alle-katzen-weg.html', 'url': 'http://www.chilloutzone.net/video/enemene-meck-alle-katzen-weg.html',
'md5': 'a76f3457e813ea0037e5244f509e66d1', 'md5': 'a76f3457e813ea0037e5244f509e66d1',
@ -16,6 +17,7 @@ class ChilloutzoneIE(InfoExtractor):
'id': 'enemene-meck-alle-katzen-weg', 'id': 'enemene-meck-alle-katzen-weg',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Enemene Meck - Alle Katzen weg', 'title': 'Enemene Meck - Alle Katzen weg',
'description': 'Ist das der Umkehrschluss des Niesenden Panda-Babys?',
}, },
} }
@ -23,71 +25,45 @@ def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
webpage_url = 'http://www.chilloutzone.net/video/' + video_id + '.html' webpage = self._download_webpage(url, video_id)
# Log that we are starting to download the page base64_video_info = self._html_search_regex(
self.report_download_webpage(webpage_url) r'var cozVidData = "(.+?)";', webpage, 'video data')
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") decoded_video_info = base64.b64decode(base64_video_info).decode("utf-8")
video_info_dict = json.loads(decoded_video_info) video_info_dict = json.loads(decoded_video_info)
# get video information from dict # get video information from dict
media_url = video_info_dict['mediaUrl'] video_url = video_info_dict['mediaUrl']
description = video_info_dict['description'] description = clean_html(video_info_dict.get('description'))
title = video_info_dict['title'] title = video_info_dict['title']
native_platform = video_info_dict['nativePlatform'] native_platform = video_info_dict['nativePlatform']
native_video_id = video_info_dict['nativeVideoId'] native_video_id = video_info_dict['nativeVideoId']
source_priority = video_info_dict['sourcePriority'] 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 nativePlatform is None a fallback mechanism is used (i.e. youtube embed)
if native_platform == None: if native_platform is None:
# Look for other video urls youtube_url = self._html_search_regex(
video_url = self._html_search_regex(r'<iframe.* src="(.+?)".*', webpage, u'fallback Video URL') r'<iframe.* src="((?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
if 'youtube' in video_url: webpage, 'fallback video URL', default=None)
self.to_screen(u'Youtube video detected:') if youtube_url is not None:
return self.url_result(video_url, ie='Youtube') return self.url_result(youtube_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 # Non Fallback: Decide to use native source (e.g. youtube or vimeo) or
# the own CDN # the own CDN
if source_priority == 'native': if source_priority == 'native':
if native_platform == 'youtube': if native_platform == 'youtube':
self.to_screen(u'Youtube video detected:') return self.url_result(video_id, ie='Youtube')
video_url = 'https://www.youtube.com/watch?v=' + native_video_id
return self.url_result(video_url, ie='Youtube')
if native_platform == 'vimeo': if native_platform == 'vimeo':
self.to_screen(u'Vimeo video detected:') return self.url_result(
video_url = 'http://vimeo.com/' + native_video_id 'http://vimeo.com/' + native_video_id, ie='Vimeo')
return self.url_result(video_url, ie='Vimeo')
# No redirect, use coz media url if not video_url:
video_url = media_url raise ExtractorError('No video found')
if video_url.endswith('.mp4') == False:
self.report_warning(u'Url does not contain a video container')
return []
return {
return [{
'id': video_id, 'id': video_id,
'url': video_url, 'url': video_url,
'ext': 'mp4', 'ext': 'mp4',
'title': title, 'title': title,
'description': description, 'description': description,
}] }