利用python爬虫进行彼岸网图库图片的抓取（bs4)

-OvO

已于 2022-11-09 20:12:27 修改

阅读量612

点赞数

文章标签： python 爬虫开发语言

于 2022-11-08 16:29:53 首次发布

本文链接：https://blog.csdn.net/levesms/article/details/127753406

版权

import requests
from bs4 import BeautifulSoup

start = input("请输入开始页数(只能从2开始):")
end = input("请输入结束页数:")
start = int(start)
end = int(end)
for sum in range(start,end):
    url = f'https://pic.netbian.com/4kmeinv/index_{sum}.html'
    domain = "https://pic.netbian.com/" 
    srcmain = "https://pic.netbian.com/" 
    headers = {
        "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36 Edg/105.0.1343.27"
    }
    resp = requests.get(url)
    resp.encoding = "gbk"
    # print(resp.text)
    main_page = BeautifulSoup(resp.text,"html.parser")
    alist = main_page.find("div",attrs={"class":"slist"}).find_all("a")
    # print(alist)
    for a in alist:
        child_href = domain + a.get('href').strip("/"