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

Merge remote-tracking branch 'kwbr/master'

Browse source
This commit is contained in:
Philipp Hagemeister 2014-04-21 02:48:04 +02:00
commit 117a7d1944
1 changed files with 26 additions and 23 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

49
youtube_dl/extractor/infoq.py
View file

@ -11,16 +11,16 @@
class InfoQIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?infoq\.com/[^/]+/(?P<id>[^/]+)$'
_TEST = {
"name": "InfoQ",
"url": "http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things",
"file": "12-jan-pythonthings.mp4",
"info_dict": {
"description": "Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.",
"title": "A Few of My Favorite [Python] Things",
},
"params": {
"skip_download": True,
u'name': u'InfoQ',
u'url': u'http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things',
u'md5': u'fcaa3d995e04080dcb9465d86b5eef62',
u'info_dict': {
u'id': u'12-jan-pythonthings',
u'ext': u'mp4',
u'description': u'Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.',
u'title': u'A Few of My Favorite [Python] Things',
},
}
@ -30,26 +30,29 @@ def _real_extract(self, url):
webpage = self._download_webpage(url, video_id)
self.report_extraction(video_id)
video_title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
video_description = self._html_search_meta('description', webpage, 'description')
# The server URL is hardcoded
video_url = 'rtmpe://video.infoq.com/cfx/st/'
# Extract video URL
encoded_id = self._search_regex(r"jsclassref ?= ?'([^']*)'", webpage, 'encoded id')
real_id = compat_urllib_parse.unquote(base64.b64decode(encoded_id.encode('ascii')).decode('utf-8'))
video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id
playpath = 'mp4:' + real_id
# Extract title
video_title = self._search_regex(r'contentTitle = "(.*?)";',
webpage, 'title')
# Extract description
video_description = self._html_search_regex(r'<meta name="description" content="(.*)"(?:\s*/)?>',
webpage, 'description', fatal=False)
video_filename = video_url.split('/')[-1]
video_filename = playpath.split('/')[-1]
video_id, extension = video_filename.split('.')
return {
return [{
'id': video_id,
'url': video_url,
'title': video_title,
'ext': extension, # Extension is always(?) mp4, but seems to be flv
'description': video_description,
}
'formats': [{
'url': video_url,
'ext': extension,
'play_path': playpath,
}],
}]