[cnet] Add new extractor (Fixes #2679)

This commit is contained in:
Philipp Hagemeister 2014-04-03 16:21:21 +02:00
parent 968ed2a777
commit 9271bc8355
3 changed files with 75 additions and 4 deletions

View file

@ -40,6 +40,7 @@ from .clipfish import ClipfishIE
from .cliphunter import CliphunterIE from .cliphunter import CliphunterIE
from .clipsyndicate import ClipsyndicateIE from .clipsyndicate import ClipsyndicateIE
from .cmt import CMTIE from .cmt import CMTIE
from .cnet import CNETIE
from .cnn import ( from .cnn import (
CNNIE, CNNIE,
CNNBlogsIE, CNNBlogsIE,

View file

@ -0,0 +1,70 @@
# coding: utf-8
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
)
class CNETIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/'
_TEST = {
'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
'md5': '041233212a0d06b179c87cbcca1577b8',
'info_dict': {
'id': '56f4ea68-bd21-4852-b08c-4de5b8354c60',
'ext': 'mp4',
'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.',
'thumbnail': 're:^http://.*/flmswindows8.jpg$',
'uploader_id': 'sarah.mitroff@cbsinteractive.com',
'uploader': 'Sarah Mitroff',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('id')
webpage = self._download_webpage(url, display_id)
data_json = self._html_search_regex(
r"<div class=\"cnetVideoPlayer\" data-cnet-video-options='([^']+)'",
webpage, 'data json')
data = json.loads(data_json)
vdata = data['video']
video_id = vdata['id']
title = vdata['headline']
description = vdata.get('dek')
thumbnail = vdata.get('image', {}).get('path')
author = vdata.get('author')
if author:
uploader = '%s %s' % (author['firstName'], author['lastName'])
uploader_id = author.get('email')
else:
uploader = 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 {
'id': video_id,
'display_id': display_id,
'title': title,
'formats': formats,
'description': description,
'uploader': uploader,
'uploader_id': uploader_id,
'thumbnail': thumbnail,
}

View file

@ -1176,12 +1176,12 @@ class HEADRequest(compat_urllib_request.Request):
return "HEAD" return "HEAD"
def int_or_none(v, scale=1): def int_or_none(v, scale=1, default=None):
return v if v is None else (int(v) // scale) return default if v is None else (int(v) // scale)
def float_or_none(v, scale=1): def float_or_none(v, scale=1, default=None):
return v if v is None else (float(v) / scale) return default if v is None else (float(v) / scale)
def parse_duration(s): def parse_duration(s):