Pyquery的安装

cat /etc/redhat-release
CentOS release 6.6 (Final)

yum install gcc libffi-devel python-devel openssl-devel

curl -o libxslt-1.1.29.zip https://git.gnome.org/browse/libxslt/snapshot/libxslt-1.1.29.zip

  curl -o libxml-1.7.3.tar.gz http://xmlsoft.org/sources/old/libxml-1.7.3.tar.gz

yum instal libxslt-devel

# -*- coding:utf-8 -*-
import requests
from pyquery import PyQuery as pq

headers = {
    ‘User-Agent‘:"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.11; rv:45.0) Gecko/20100101 Firefox/45.0",
    ‘Cookie‘:"UOR=y.qq.com,widget.weibo.com,y.qq.com; SINAGLOBAL=8818090954579.496.1461652869389; ULV=1466417097935:5:3:2:4821515600800.323.1466417097929:1466410712129; SUB=_2AkMgEzhXf8NhqwJRmP0WyGPjbol3yw7EieLBAH7sJRMxHRl-yT83qnEItRAP-q6huRFAXpidMwh9ScHwNyuDMw..; SUBP=0033WrSXqPxfM72-Ws9jqgMF55529P9D9WFzaPQwqvOukuGw_aqZrYOD; YF-V5-G0=c998e7c570da2f8537944063e27af755; YF-Page-G0=ffe43932f05408fcdf32c673d8997f97"
}

s = requests.Session()
url = ‘http://weibo.com/aj/v6/comment/big?ajwvr=6&id=3995838911192732&page={}&__rnd=1468201664629‘
def save(page):
    try:
        r = s.get(url.format(page), headers=headers)
        print r.url
    except Exception, e:
        print e
        exit(0)
    v_source = pq( r.json()[‘data‘][‘html‘])
    datas = v_source(‘.list_ul .list_li‘)
    for data in datas:
        print pq(data)(‘.WB_face a img‘).attr(‘src‘)
        print pq(data)(‘.WB_from‘).text(), pq(data).find(‘.WB_text‘).text() #pq(data)(‘.WB_text‘).find(‘a‘).text(),

if __name__ == ‘__main__‘:
    for page in xrange(1,5):
        save(page)