網絡爬蟲-課時15抓取新聞評論數

網絡學習筆記

import requests
commments = requests.get('http://comment5.news.sina.com.cn/page/info?version=1&format=js&channel=gn&newsid=comos-fxvctcc8121090&group=&compress=0&ie=utf-8&oe=utf-8&page=1&page_size=20')                 

import jason
jd = json.loads(conmments.text.strip('var data='))

jd['result']['count']['total']

newsurl = 'http://news.sina.com.cn/c/nd/2016-08-20/doc-ifxvctcc8121090.shtml'
newsurl.split('/')[-1].rstrip('.shtml').lstrip('doc-i')

'fxvctcc8121090'

import re
m = re.search('doc-i(.*).shtml',newsurl )
print(m)

<_sre.SRE_Match object; span=(40, 65), match='doc-ifxvctcc8121090.shtml'>

newsid = m.group(1)
newsid

'fxvctcc8121090'