aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authorAndreas Schmitz <aschmitz@posteo.de>2014-02-06 21:31:04 +0100
committerAndreas Schmitz <aschmitz@posteo.de>2014-02-06 21:31:04 +0100
commitcd8662de220911f89960550ef02c1e3bae327922 (patch)
tree1797a265eceadb9ca6218164dfff1c5f07994cc8 /youtube_dl/extractor
parent46a073bfac5ff2eb9b31d2b27b64d6fb6895566c (diff)
[chilloutzone] Bug fix, runs against tests
Fixes a bug with python3.3 and made the extractor run successfully against tox
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/chilloutzone.py131
1 files changed, 62 insertions, 69 deletions
diff --git a/youtube_dl/extractor/chilloutzone.py b/youtube_dl/extractor/chilloutzone.py
index 31618e4c9..59a188746 100644
--- a/youtube_dl/extractor/chilloutzone.py
+++ b/youtube_dl/extractor/chilloutzone.py
@@ -9,92 +9,85 @@ video_container = ('.mp4', '.mkv', '.flv')
class ChilloutzoneIE(InfoExtractor):
_VALID_URL = r'(?:https?://)?(?:www\.)?chilloutzone\.net/video/(?P<id>[\w|-]+).html'
-
_TEST = {
- u'url': u'http://www.chilloutzone.net/video/enemene-meck-alle-katzen-weg.html',
- u'file': u'18088-enemene-meck-alle-katzen-weg.mp4',
- u'md5': u'a76f3457e813ea0037e5244f509e66d1',
- u'info_dict': {
- u"id": u"18088",
- u"ext": u"mp4",
- u"title": u"Enemene Meck - Alle Katzen weg"
- }
- }
+ '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)
- 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:')
- print video_url
- 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':
+ 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
- print video_url
return self.url_result(video_url, ie='Youtube')
if native_platform == 'vimeo':
- self.to_screen(u'Vimeo video detected:')
+ self.to_screen(u'Vimeo video detected:')
video_url = 'http://vimeo.com/' + native_video_id
- print video_url
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 []
+ 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
- }]
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'title': title,
+ 'description': description,
+ }]