python爬取斗图啦表情包

表情包"/>

python爬取斗图啦表情包

自从会了python，斗图我怕过谁

不多说上代码

# -*- coding: utf-8 -*-
# @Time  : 2020/4/11 21:40
# @Author : zhao~xiujie
# @email : zxj0314@outlook
# @FileName: doutu.py.py
# @IDE: PyCharmimport requests
from lxml import etree
from urllib import request
import os
import redef parse_page(url):headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36','Referer':'.htm?ltr=','Cookie':'BAIDUID=145DFF007C12683DB04A0420F47B3EEE:FG=1','Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9'}response = requests.get(url,headers=headers)text = response.content.decode('utf-8')html = etree.HTML(text)imgs = html.xpath(r'//div[@class="page-content text-center"]//img[@class!="gif"]')for img in imgs:#获取图片名字# print(etree.tostring(img))    #打印imgimg_url = img.get('data-original')   #获取标签中的属性值alt = img.get('alt')    #获取图片中文名称alt = re.sub(r'[\?？\.。！!/]','',alt)suffix = os.path.splitext(img_url)[1]  #print(suffix)  #os模块下的url文本分割fale_name = alt + suffix    #print(fale_name) #拼接保存文件名#下载request.urlretrieve(img_url,'doutula/'+fale_name)def main():for u in range(1,1000):url = '/?page=%d' % uparse_page(url)if __name__ == '__main__':main()

获得图片信息如下

群号：992741643。
本人微信：

微信群正在维护建设阶段欢迎加入，如果添加不上可加我微信拉你进群。