求助，根据小甲鱼编写的煎蛋网爬虫总是显示未定义html

saberkor

import urllib.request
import os



def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3672.400 QQBrowser/10.4.3448.400')
    response = urllib.request.urlopen(req)
    html = response.read()
    #print(url)
    #测试

    return html

def get_page(url):
    html = url_open(url).decode('utf-8')
    #req = urllib.request.Request(url)
    #req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3672.400 QQBrowser/10.4.3448.400')
    #response = urllib.request.urlopen(url)
    #html = response.read().decode('utf-8'),1,2,3式打包定义为一个函数可以直接引用，4式不可以定义为一个函数因为用decode改变了格式，会使图片显示不出来，所以得后面定义

    a = html.find('current-comment-page') + 23
    b = html.find(']',a)


    return html[a:b]
   

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

    a = html.find('img src=')

    while a!= -1:
        
        b = html.find('.jpg',a,a+360)
        if b != -1:
            img_addrs.append(html[a+9:b+4])
        else:
            b = a + 9

        a = html.find('img src=',b)

    #for each in img_addrs:
       #print(each)查看
        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_mm(folder='ooxx',pages=10):
    os.mkdir(folder)
    os.chdir(folder)


    url = "http://jiandan.net/ooxx/"
    page_num = int(get_page(url))

    for i in range(pages):
        page_num -= i
        page_url = url + 'page-' + str(page_num) + '#comments'
        img_addrs = find_imgs(page_url)
        save_imgs(folder,img_addrs)


if __name__== '__main__':
    download_mm()
结果显示：
Traceback (most recent call last):
  File "D:\软件\python37\程序\煎蛋网.py", line 76, in <module>
    download_mm()
  File "D:\软件\python37\程序\煎蛋网.py", line 71, in download_mm
    img_addrs = find_imgs(page_url)
  File "D:\软件\python37\程序\煎蛋网.py", line 35, in find_imgs
    a = html.find('img src=')
NameError: name 'html' is not defined

°蓝鲤歌蓝

换个网站测试，这个网站好像挂了，就算没挂，它现在的反爬虫手段和以前的也基本不一样了。

saberkor

°蓝鲤歌蓝 发表于 2019-4-26 23:36
换个网站测试，这个网站好像挂了，就算没挂，它现在的反爬虫手段和以前的也基本不一样了。

好的，谢谢啦

风丶少

def find_imgs(url):
    hrml = url_open(url).decode('utf-8')
    img_addrs = []
这里html写成了hrml,报错的地方就是这里