简单爬虫问题，爬取图片出现HTTP Error 403: Forbidden

qq1046764742

import urllib.request
import urllib.error
import re

def read_url(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/69.0.3497.100 Safari/537.36")
    req.add_header("Referer","https://www.ilemiss.net")
    '''

    header = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.75 Safari/537.36","Referer":"https://www.ilemiss.net"}
    req = urllib.request.Request(url,headers=header)
    date = urllib.request.urlopen(req).read().decode("utf-8","ignore")
    return date


def download_picture(url):
    date = read_url(url)
    last = re.findall(r'<a href="\d{4}_(\d{2}).html">尾页',date)[0]
    name = re.findall(r'<a href="(\d{4})_\d{2}.html">尾页',date)[0]
    fist = re.search(r'https://pic.ilemiss.net/\d{4}/1\.jpg',date).group()

    for i in range(1,int(last)+1):
        scr = fist.split("1.jpg")[0]
        pic_name = name+str(i)+".jpg"
        urllib.request.urlretrieve(scr,pic_name)


for i in range(2,10):
    url = "https://www.ilemiss.net/sexy/index_"+str(i)+".html"
    date = read_url(url)
    pic_list = re.findall(r'class="imbtxt"><p><a href="(.*?\.html)" ',date)
    for each in pic_list:
        print(each)
        try:
            download_picture(each)
        except Exception as e:
            print(e)
        

qq1046764742

求各位大神帮忙解决，谢谢

qq1046764742

自己顶

彩虹七号

可能被反爬了，设置代理试一试

qq1046764742

代理IP吗，也不行啊

qq1046764742

这个应该和代理没什么关系，因为网页爬取没有问题，只是图片无法下载

qq1046764742

？

qq1046764742

竟然无人回答，是太简单了吗

snaker

修改一下代码，可以爬，但是服务器有反爬

1. 
   
2. import urllib.request
   
3. import urllib.error
   
4. import re
   
5. 
   
6. def read_url(url):
   
7. 
   
8.     '''
   
9.     req = urllib.request.Request(url)
   
10.     req.add_header("User-Agent","Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36")
    
11.     req.add_header("Referer","https://www.ilemiss.net")
    
12.     '''
    
13. 
    
14.     header = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.75 Safari/537.36","Referer":"https://www.ilemiss.net"}
    
15.     req = urllib.request.Request(url,headers=header)
    
16.     date = urllib.request.urlopen(req).read().decode("utf-8","ignore")
    
17.     return date
    
18. 
    
19. 
    
20. def download_picture(url):
    
21.     date = read_url(url)
    
22.     last = re.findall(r'<a href="\d{4}_(\d{2}).html">尾页',date)[0]
    
23.     name = re.findall(r'<a href="(\d{4})_\d{2}.html">尾页',date)[0]
    
24.     fist = re.search(r'http://img.qincns.com/\d{4}/1\.jpg',date).group()                #修改
    
25.     for i in range(1,int(last)+1):
    
26.         scr = fist.split("1.jpg")[0]
    
27. 
    
28.         pic_url = scr+str(i)+".jpg"         #修改
    
29.         pic_name = name+"-"+str(i)+".jpg"       #修改
    
30.         urllib.request.urlretrieve(pic_url,pic_name)        #修改
    
31. 
    
32. 
    
33. for i in range(2,10):
    
34.     url = "https://www.ilemiss.net/sexy/index_"+str(i)+".html"
    
35.     date = read_url(url)
    
36.     pic_list = re.findall(r'class="imbtxt"><p><a href="(.*?\.html)" ',date)
    
37.     for each in pic_list:
    
38.         print(each)
    
39.         try:
    
40.             download_picture(each)
    
41.         except Exception as e:
    
42.             print(e)
    
43. 
    

复制代码

                               
登录/注册后可看大图

superfishme

解决了吗