Python爬虫(使用requests) 

import requests
from lxml import etree


url = "http://avdb.la/actor/"

headers = {"User-Agent":'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.152 Safari/537.36'}

html = requests.get(url,headers = headers)

content = html.text
#content = content.encode("utf8")

selector = etree.HTML(content)

name = selector.xpath('//*[@id="waterfall"]/div/a/@title')

 

posted @ 2015-07-17 23:37  _level_  阅读(318)  评论(0)  编辑  收藏  举报