【原创源码】【Python】使用Python爬取爱盘工具

本文来源吾爱破解论坛

刚装的Windows准备学逆向，装点工具。由于本人比较懒，不想一个一个工具去找然后再下载，虽然可以装吾爱的虚拟机，但是操作起来没物理机舒服(然而窝还是装了)。
正好爱盘这里有不少工具。所以enmmmm
Python Start
Wirte Code
Start Python Code.
Get Tools.

因为爱盘几个大字写着不允许多线程下载(如果我理解无误的话)。就没有写多线程enmmm
爱盘限制多线程下载访问，请使用单线程进行下载访问，多并发会被禁止访问。

需要安装的库文件:
requests -- HTTP请求库
bs4 -- 解析库

下面是源码qwq(码农玩家玩耍)

[Python] 纯文本查看 复制代码

#-*- coding: utf-8 -*-
import os
import time

import requests

from bs4 import BeautifulSoup

def download(downurl, path, filename): # 下载函数
    start = time.time() # 开始时间
    
    if not os.path.exists(path):
        os.makedirs(path)
    if path[-1] != os.sep:
        path += os.sep
    file = path+filename
    size = 0
    
    response = requests.get(downurl, stream=True)
    if response.status_code != 200:
        print(f"[Erroe] url => {url}\tstatus_code => {response.status_code}")
        return
      
    chunk_size = 1024
    content_size = int(response.headers["content-length"])
    
    print("[File Size]: %0.2f MB" % (content_size / chunk_size / 1024))
    with open(file, "wb") as f:
        for data in response.iter_content(chunk_size):
            f.write(data)
            size += len(data)
            print("\r[Downloading]: %s>%.2f%%" % ("="*int(size*50/content_size), float(size/content_size*100)), end="")
    
    end = time.time() # 结束时间
    print("Using Time: %.2fs"%(end-start))

def main():
    url = "https://down.52pojie.cn/Tools/" # 爱盘Tools URL
    if not os.path.exists("Tools"):
        os.mkdir("Tools")
    os.chdir("Tools")
    headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77me/77.0.3865.120 Safari/537.36"}
    req = requests.get(url, headers=headers)
    soup = BeautifulSoup(req.text,'lxml')
    for i in soup.find_all("td", class_="link")[1:]: # 获取目录
        tooldir = i.text
        dir_url = url+tooldir
        print(dir_url) # 目录URL
        req = requests.get(dir_url)
        req.encoding = "utf-8"
        soup1 = BeautifulSoup(req.text,'lxml')
        for j in soup1.find_all("td", class_="link")[1:]: # 获取文件
            path = tooldir
            filename = j.text
            downurl = dir_url+filename
            print(f"[Downloading] Path => {path}\tFileName => {filename}")
            download(downurl, path, filename)

main()