一个简单的表情包爬取程序

最新推荐文章于 2024-04-13 00:01:27 发布

原创最新推荐文章于 2024-04-13 00:01:27 发布 · 545 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#python #爬虫

爬虫专栏收录该内容

1 篇文章

订阅专栏

一个简单的表情包爬取程序

图源网站斗图吧

工具requests库

正则表达式切割

import requests
from lxml import etree
from urllib import request
import os
import re

def main():
    for x in range(1,101):
        url = "http://www.doutula.com/photo/list/?page=%d" %x
        parse_page(url)

def parse_page(url):
    headers = {
        "User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.26 Safari/537.36 Core/1.63.5478.400 QQBrowser/10.1.1550.400"

    }
    response = requests.get(url,headers = headers)
    text = response.text
    what = etree.HTML(text)
    imgs = what.xpath("//body//img")
    for img in imgs:
        img_url = img.get("data-original")
        alt = img.get("alt")
        alt = re.sub(r'[\?？.，。!！]','',alt)
        suffixs = os.path.splitext(img_url)[1]
        suffix = suffixs.split('!')[0]
        filename = alt +suffix
        request.urlretrieve(img_url,"image/"+filename)



if __name__ == '__main__':
    main()