[已解决]为啥以用了user-agent 之后还是报403 啊求老铁们帮助

lychee007 · 发表于 2018-3-19 10:44:11

马上注册，结交更多好友，享用更多功能^_^

您需要登录才可以下载或查看，没有账号？立即注册

x

以下是源码：

import urllib.request
import os

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')
response = urllib.request.urlopen(url)
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)

return html[a:b]

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

a = html.find('img src=')

while a != -1 :
      b = html.find('.jpg',a,a+255)
      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)

def save_imgs(folder,img_addrs):
for each in img_addrs:
      fliename = each.split('/')[-1]
      with open(fliename,'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://jandan.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()

如下图是报错：

这是报错