[已解决]【求助】煎蛋爬妹子图403如何解决

二农戏猪`

import urllib.request
import os
import base64
import re

def get_page(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent:', 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36')
    response = urllib.request.urlopen(url)
    html = response.read().decode('utf-8')

    a = r'<span class="current-comment-page">[(\d+)]</span>'
   
    page_list = re.findall(a,html)

    print(page_list)
   
   
def base_num(page_num):
    pass

def find_pic_url(page_url):
    pass

def save_pic(folder, pic_url):
    pass

def download_mm(folder = 'mm', pages = 10):
    #创建一个文件夹
    os.mkdir(folder)
    os.chdir(folder)

    url = 'http://jandan.net/ooxx'
    #获取页码
    page_num = int(get_page(url))

    for i in range(pages):
        page_num -=i
        #base64加密
        base_num(page_num)
        #获取页码地址
        page_url = url + str(base_num) + '#comments'
        #获取图片具体地址并保存成列表
        pic_url = find_pic_url(page_url)
        save_pic(folder, pic_url)

        
if __name__ == '__main__':
    download_mm()
这个是代码 ，测试第一个的时候直接403，大佬教我怎么解决

最佳答案

月排行榜 / 总排行榜

Twilight6

2020-8-10 16:56:12

把 response = urllib.request.urlopen(url) 改成 response = urllib.request.urlopen(req)

以及 header 里面的 User-Agent 字符串里的冒号去掉

def get_page(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent',
                   'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36')
    response = urllib.request.urlopen(req)
    html = response.read().decode('utf-8')

    a = r'<span class="current-comment-page">[(\d+)]</span>'

    page_list = re.findall(a, html)

    print(page_list)

跳转到最佳答案楼层

Twilight6

把 response = urllib.request.urlopen(url) 改成 response = urllib.request.urlopen(req)

以及 header 里面的 User-Agent 字符串里的冒号去掉

def get_page(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent',
                   'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36')
    response = urllib.request.urlopen(req)
    html = response.read().decode('utf-8')

    a = r'<span class="current-comment-page">[(\d+)]</span>'

    page_list = re.findall(a, html)

    print(page_list)

suchocolate

论坛里好多人都是这个问题，明明建了req，最后还是没调用，以哪里的代码做的模板？

二农戏猪`

Twilight6 发表于 2020-8-10 16:56
把 response = urllib.request.urlopen(url) 改成 response = urllib.request.urlopen(req)

以及 he ...

我的正则表达式没问题吧，为什么还是报错