爬取妹子图

Maple丶小枫

import urllib.request
import os

def url_open(url):
    req=urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3704.400 QQBrowser/10.4.3587.400')
    response = urllib.request.urlopen(url)
    html = response.read()
    return html
   

def find_imgs(url):
    html=url_open(url).decode('utf-8')
    img_addrs = []

    a = html.find('img id="curPicUrl" src=')
    while a!=-1:
        b=html.find('.jpg',a,a+255)
        if b!=-1:
            img_addrs.append(html[a+23:b+4])
        else:
            b=a+23
        a = html.find('img id="curPicUrl" src=',b)
    return img_addrs
def save_imgs(folder,img_addrs):
    for each in img_addrs:
        filename = each.split('/')[-1]
        with open(filename, 'wb') as f:
            img = url_open(each)
            f.write(img)
def download_tp(folder='sb',pages=10):
    os.mkdir(folder)
    os.chdir(folder)

    url = 'https://www.bizhizu.cn/bizhi/20167-2.html'
    url2 ='https://www.bizhizu.cn/bizhi'

    for i in range(pages):
        page_num = i
        page_url = url2 + '/20167-' + str(page_num) + '.html'
        img_addrs = find_imgs(page_url)
        save_imgs(folder,img_addrs)

if __name__ == '__main__':
    download_tp()



好像是那下载的时候除了问题  大佬求解

wongyusing

你print一下打开图片链接的状态码看下是多少？
不出什么意外的话是403

kelby

一定是返回403，至少要加一个headers吧，不然太不尊重人家了