[cnet] Update to new theplatform infrastructure (Fixes #2736)

This commit is contained in:
Philipp Hagemeister 2014-12-12 15:55:55 +01:00
parent 751536f5c8
commit 412c617d0f
2 changed files with 21 additions and 28 deletions

View file

@ -622,15 +622,13 @@ def process_ie_result(self, ie_result, download=True, extra_info={}):
ie_result['url'], ie_key=ie_result.get('ie_key'), ie_result['url'], ie_key=ie_result.get('ie_key'),
extra_info=extra_info, download=False, process=False) extra_info=extra_info, download=False, process=False)
new_result = ie_result.copy() force_properties = dict(
for f in ('_type', 'id', 'url', 'ext', 'player_url', 'formats', (k, v) for k, v in ie_result.items() if v is not None)
'entries', 'ie_key', 'duration', for f in ('_type', 'url'):
'subtitles', 'annotations', 'format', if f in force_properties:
'thumbnail', 'thumbnails'): del force_properties[f]
if f in new_result: new_result = info.copy()
del new_result[f] new_result.update(force_properties)
if f in info:
new_result[f] = info[f]
assert new_result.get('_type') != 'url_transparent' assert new_result.get('_type') != 'url_transparent'

View file

@ -15,23 +15,24 @@ class CNETIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/' _VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/'
_TEST = { _TEST = {
'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/', 'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
'md5': '041233212a0d06b179c87cbcca1577b8',
'info_dict': { 'info_dict': {
'id': '56f4ea68-bd21-4852-b08c-4de5b8354c60', 'id': '56f4ea68-bd21-4852-b08c-4de5b8354c60',
'ext': 'mp4', 'ext': 'flv',
'title': 'Hands-on with Microsoft Windows 8.1 Update', 'title': 'Hands-on with Microsoft Windows 8.1 Update',
'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.', 'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.',
'thumbnail': 're:^http://.*/flmswindows8.jpg$', 'thumbnail': 're:^http://.*/flmswindows8.jpg$',
'uploader_id': 'sarah.mitroff@cbsinteractive.com', 'uploader_id': '6085384d-619e-11e3-b231-14feb5ca9861',
'uploader': 'Sarah Mitroff', 'uploader': 'Sarah Mitroff',
},
'params': {
'skip_download': 'requires rtmpdump',
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) display_id = self._match_id(url)
display_id = mobj.group('id')
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
data_json = self._html_search_regex( data_json = self._html_search_regex(
r"<div class=\"cnetVideoPlayer\"\s+.*?data-cnet-video-options='([^']+)'", r"<div class=\"cnetVideoPlayer\"\s+.*?data-cnet-video-options='([^']+)'",
webpage, 'data json') webpage, 'data json')
@ -42,37 +43,31 @@ def _real_extract(self, url):
if not vdata: if not vdata:
raise ExtractorError('Cannot find video data') raise ExtractorError('Cannot find video data')
mpx_account = data['config']['players']['default']['mpx_account']
vid = vdata['files']['rtmp']
tp_link = 'http://link.theplatform.com/s/%s/%s' % (mpx_account, vid)
video_id = vdata['id'] video_id = vdata['id']
title = vdata.get('headline') title = vdata.get('headline')
if title is None: if title is None:
title = vdata.get('title') title = vdata.get('title')
if title is None: if title is None:
raise ExtractorError('Cannot find title!') raise ExtractorError('Cannot find title!')
description = vdata.get('dek')
thumbnail = vdata.get('image', {}).get('path') thumbnail = vdata.get('image', {}).get('path')
author = vdata.get('author') author = vdata.get('author')
if author: if author:
uploader = '%s %s' % (author['firstName'], author['lastName']) uploader = '%s %s' % (author['firstName'], author['lastName'])
uploader_id = author.get('email') uploader_id = author.get('id')
else: else:
uploader = None uploader = None
uploader_id = None uploader_id = None
formats = [{
'format_id': '%s-%s-%s' % (
f['type'], f['format'],
int_or_none(f.get('bitrate'), 1000, default='')),
'url': f['uri'],
'tbr': int_or_none(f.get('bitrate'), 1000),
} for f in vdata['files']['data']]
self._sort_formats(formats)
return { return {
'_type': 'url_transparent',
'url': tp_link,
'id': video_id, 'id': video_id,
'display_id': display_id, 'display_id': display_id,
'title': title, 'title': title,
'formats': formats,
'description': description,
'uploader': uploader, 'uploader': uploader,
'uploader_id': uploader_id, 'uploader_id': uploader_id,
'thumbnail': thumbnail, 'thumbnail': thumbnail,