diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2014-02-07 11:50:26 +0100 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2014-02-07 11:50:26 +0100 |
commit | 9f31be70004d7a34fd8f9dee33a534156327aa01 (patch) | |
tree | 49cbf3033f522652de5497fb18be7f3f1a0c6254 | |
parent | 41fa1b627dfa68303389c422f6a4527905c6477a (diff) | |
parent | cd8662de220911f89960550ef02c1e3bae327922 (diff) |
Merge remote-tracking branch 'Fnordlab/chilloutzone'
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/chilloutzone.py | 93 |
2 files changed, 94 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index a13b5cfb8..c0a57c73d 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -25,6 +25,7 @@ from .canalplus import CanalplusIE from .canalc2 import Canalc2IE from .cbs import CBSIE from .channel9 import Channel9IE +from .chilloutzone import ChilloutzoneIE from .cinemassacre import CinemassacreIE from .clipfish import ClipfishIE from .cliphunter import CliphunterIE diff --git a/youtube_dl/extractor/chilloutzone.py b/youtube_dl/extractor/chilloutzone.py new file mode 100644 index 000000000..59a188746 --- /dev/null +++ b/youtube_dl/extractor/chilloutzone.py @@ -0,0 +1,93 @@ +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, + }] + + + |