python爬取表情包

从斗图啦网站爬取表情包

import requests

from lxml import etree

import time

for i in range(1,6):

        url ='https://www.doutula.com/article/list/?page={}'.format(i)

        headers = {'Referer':'https://www.doutula.com/',

                          'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.111 Safari/537.36'}

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

        html = etree.HTML(resp.text)

        srcs = html.xpath('//img/@data-original')

        for src in srcs :

                filename = src.split('/')[-1]

                img = requests.get(src,headers=headers)

                with open('imgs/'+filename,'wb')as file:

                        file.write(img.content)

                print(src,filename)

新东西是Referer,wb,'imgs/'+filename,img.content, srcs = html.xpath('//img/@data-original'),  filename = src.split('/')[-1]