import urllib2
import urllib
from lxml import etree
def tieba_spider(fullurl):
headers = {
"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36"
}
request = urllib2.Request(fullurl,headers = headers)
html = urllib2.urlopen(request).read()
获取a标签的href属性啊，也就是链接
内容全部来源于网络收集，如有侵权，请联系网站删除：QQ：24596024