【原创源码】【Python】使用Python爬取爱盘工具

MikoSec

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

?

01 02 03 04 05 06 07 08 09 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59

#-*- 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()

然后是打包后的exe(普通玩家玩耍)

链接：https://pan.baidu.com/s/11xc6ENUELIWaQNIJsbxojA
提取码：d3ig

百度网盘分享链接在线解析
https://www.baiduwp.com/

www.52pojie.cn

来52破52这是扛把子精神

ixsec

消灭0回复
话说 idm 下载还不错哈~~

chomosuke

工具挺好用的，但是度盘的链接好像挂了

chomosuke

大概改良了一下， 代码：

https://github.com/Maemo8086/Python_AiPan_Crawler

[Python] 纯文本查看 复制代码

?

001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050 051 052 053 054 055 056 057 058 059 060 061 062 063 064 065 066 067 068 069 070 071 072 073 074 075 076 077 078 079 080 081 082 083 084 085 086 087 088 089 090 091 092 093 094 095 096 097 098 099 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231

#!/usr/bin/python # -*- coding: utf-8 -*-   ''' MIT License   Copyright (c) 2019 Maemo8086 Copyright (c) 2019 MikoSec   Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:   The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.   THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. '''   import os import random import requests import sys import time from bs4 import BeautifulSoup from collections import deque     def download(file_url, path, filename):  # 下载函数     global headers     global download_exception       display_max = 64       if path:         if len(path) > display_max:             display_path = '...' + path[-display_max:]         else:             display_path = path     else:         display_path = '/'       if len(filename) > display_max:         display_filename = '...' + filename[-display_max:]     else:         display_filename = filename       print()     print(f'\r[Downloading] Path => {display_path}\tFile Name => {display_filename}')     sys.stdout.flush()       delay = False     if delay:         wait = round(random.uniform(0, 5), 2)         print(f'\r[Info] Waiting {wait} seconds...')         sys.stdout.flush()         time.sleep(wait)       start = time.time()  # 开始时间       if path:         if not os.path.exists(path):             os.makedirs(path)         if path[-1] != os.sep:             path += os.sep     full_path = path + filename       try:         response = requests.get(file_url, headers=headers, stream=True, timeout=30)     except:         download_exception.append((file_url, path, filename))         print(f'\r[Error] Download request for *{display_filename}* has failed.')         return       if response.status_code != 200:         response.close()         download_exception.append((file_url, path, filename))         print(f'\r[Error] Download request for *{display_filename}* has failed.\tstatus_code => {response.status_code}')         return       try:         content_size = int(response.headers['content-length'])     except:         response.close()         download_exception.append((file_url, path, filename))         print(f'\r[Error] Download request for *{display_filename}* has failed.\tMissing or invalid content-length.')         return       if content_size < 0:         response.close()         download_exception.append((file_url, path, filename))         print(f'\r[Error] Download request for *{display_filename}* has failed.\tInvalid content-length range.')         return       print('[File Size] %0.2f MB' % (content_size / 1024 ** 2))     sys.stdout.flush()       if os.path.exists(full_path):         if os.path.getsize(full_path) == content_size:  # 判断文件大小             response.close()             print('[Info] Same sized file exists, skipping...')             return         else:             print('[Warning] Overwriting existing copy.')       chunk_size = 1024     size = 0     try:         with open(full_path, 'wb', buffering=1) 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='')     except:         download_exception.append((file_url, path, filename))         if os.path.exists(full_path):             os.remove(full_path)         print(f'\r[Error] Download *{display_filename}* has failed.')         return     finally:         response.close()         end = time.time()  # 结束时间         print('\rTime elapsed: %.2fs' % (end - start))     def recursive_fetch(soup, part_url):     global url     global headers       for i in soup.find_all('td', class_='link'):  # 获取文件或目录         if i.text == 'Parent directory/':             continue           if i.text[-1] != '/':             path = part_url[len(url):]             filename = i.text             file_url = part_url + filename             download(file_url, path, filename)         else:             dir_url = part_url + i.text             print()             print(f'\r[Info] Searching under {dir_url}')               execute = True             while execute:                 wait = round(random.uniform(0, 5), 2)                 print(f'\r[Info] Waiting {wait} seconds...')                 sys.stdout.flush()                 time.sleep(wait)                   execute = False                 try:                     with requests.get(dir_url, headers=headers, timeout=30) as req:                         req.encoding = req.apparent_encoding                         soup1 = BeautifulSoup(req.text, 'lxml')                 except:                     execute = True                     print(f'\r[Error] URL request *{dir_url}* has failed, retrying...')               recursive_fetch(soup1, dir_url)     def main():     global url     global headers     global download_exception       print(         '''         Python 爱盘爬虫工具                   作者： Maemo8086，MikoSec         源码： https://github.com/Maemo8086/Python_AiPan_Crawler                   一款基于Python的吾爱破解论坛爱盘下载工具         本工具使用requests库跟bs4库         建议使用前先修改User Agent         '''     )       directory = 'AiPan'     if not os.path.exists(directory):         os.mkdir(directory)     os.chdir(directory)       try:         with requests.get(url, headers=headers, timeout=30) as req:             req.encoding = req.apparent_encoding             soup = BeautifulSoup(req.text, 'lxml')     except:         print(f'\r[Error] URL request *{url}* has failed.')         return       recursive_fetch(soup, url)       while download_exception:         print()         print(f'\r[Info] Retrying {len(download_exception)} failed downloads...')           wait = round(random.uniform(10, 30), 2)         print(f'\r[Info] Waiting {wait} seconds...')         sys.stdout.flush()         time.sleep(wait)           download_exception_copy = download_exception.copy()         download_exception.clear()         while download_exception_copy:             file_url, path, filename = download_exception_copy.pop()             file_url = file_url.strip('\\')             path = path.strip('\\')             filename = filename.strip('\\')             download(file_url, path, filename)     url = 'https://down.52pojie.cn/'  # 爱盘 URL 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'}   download_exception = deque() main()

小弟多年没写Python，请各大佬指点一下

18603867890

然后是打包后的exe(普通玩家玩耍)

链接：https://pan.baidu.com/s/11xc6ENUELIWaQNIJsbxojA
提取码：d3ig

这个链接失效了