简单爬取百度贴吧图片

import urllib.request
import urllib
from lxml import  etree
import requests
url="https://tieba.baidu.com/f?kw=%E6%A1%8C%E9%9D%A2&ie=utf-8&pn=50"
headers={ 'User-Agent':'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'}


response=requests.get(url,headers)
html=etree.HTML(response.text)

img=html.xpath('//*[@class="threadlist_media j_threadlist_media clearfix"]/li/a/img')

x=1
for i in range(len(img)):#用xpath返回的img是一个包含字典的列表
           data=img[i].attrib#返回标签的href和class，text返回文本，tag返回标签名
           j=data['data-original']#根据输出的字典获取所需链接
           x=x+1
           urllib.request.urlretrieve(j,"C:\\Users\\lenovo\\Desktop\\%s.jpg"% x)#将文件下载到本地，加后缀表明格式
   

 

转载于:https://www.cnblogs.com/persistence-ok/p/11440495.html