糗事百科实例
import requests
from lxml import etree
page=1 #爬取第一页
base_url=‘https://www.qiushibaike.com/8hr/page/%d/’%page #请求地址
headers={‘User-Agent’: ‘Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.80 Safari/537.36’} #user-agent
try:
response=requests.get(base_url,headers=headers)
resHtml=response.text #响应的内容
html=etree.HTML(resHtml) #转化为树形结构
li_list=html.xpath('//li[@class="item typs_video"]')
for li in li_list:
name=li.xpath('./div/div/a/img/@alt') #用户名
content=li.xpath('./div/a/text()') #内容
zan=li.xpath('./div/div/div/span[position()=1]/text()') #点赞
pinlun=li.xpath('./div/div/div/span[last()-1]/text()') #评论次数
lianjie=li.xpath('./a/img/@src') #链接
print('用户名:',name[0],'点赞:',zan[0],'评论:',pinlun[0])
print('内容:',content[0])
print(lianjie[0])
print('============================================================')
except Exception as e:
print(e)