煎蛋爬图过程中， find_imgs函数中，为什么b都是-1

python_xiaozhu

import urllib.request
import os
import random
def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Mobile Safari/537.36')
    '''
    proxies=['119.6.144.70:81', '111.1.36.9:80', '203.144.144.162:8080']
    proxy = random.choice(proxies)
   
    proxy_support = urllib.request.ProxyHandler({'http':proxy})
    opener = urllib.request.build_opener(proxy_support)
    #创建opener
    urllib.request.install_opener(opener)
    '''
    response = urllib.request.urlopen(req)
    html = response.read()
    return html

def get_page(url):
    html = url_open(url).decode('utf-8')
    a = html.find("current-comment-page")+23
    b = html.find(']',a)
    # 从a的起始位置
    # find后返回字符串首地址，加23刚好到数字位置
   
    return html[a:b]

def find_imgs(page_url):
    #给一个完整的链接，打开网页
    html = url_open(page_url).decode('utf-8')
   
    img_addrs = []
   
    a = html.find('img src=')
   
        
    while a!= -1:
        b = html.find('.jpg',a,a+100)
        print(b)
        if b != -1:
            img_addrs.append('http:',html[a+9:b+4])
            print('cichu',img_addrs)
        else:
            b = a+9
        a = html.find('img src=',b)
    for each in img_addrs:
        print(each)
    return img_addrs

   
    # 每一个网页不超过255
    # <img src="http://wx1.sinaimg.cn/mw600/661eb95cly1fnrzb24d2qj20u011ijt8.jpg" width="320" height="400" style="max-width: 100%; max-height: 450px;">
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_mm(folder = 'OO-XX',pages = 10):
    os.mkdir(folder)
    os.chdir(folder)

    url = 'http://jandan.net/ooxx/'

    page_num = int(get_page(url))

    for i in range(pages):
        page_num -=1
        page_url = url + "/page-" + str(page_num)+ '#comments'
        img_addrs = find_imgs(page_url)
        save_imgs(folder,img_addrs)
        
if __name__ =='__main__':
     download_mm()

sky

煎蛋反扒了

gopythoner

还不是你们爬的多了，别人加密了