Python爬虫-ppt全站爬取

Python爬虫-ppt全站爬取

import re
import requests
wz = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36'}

page = 1
# 1.请求ppt模板的总页面 https://www.ypppt.com/moban/  找到很多个下载页面的网址
while True:
    if page == 1:
        url1 = 'https://www.ypppt.com/moban/'
    else:
        url1 = f'https://www.ypppt.com/moban/list-{page}.html'
    res = requests.get(url1, headers=wz)
    res.encoding = 'utf-8'  # python最常用最常用的编码 万国码！

    aids = re.findall('<a href="/article/.*?/(.*?).html" class="p-title"', res.text)
    if not aids:
        break
    titles = re.findall('class="p-title" target="_blank">(.*?)</a>', res.text)

    for i in range(len(aids)):
        url2 = 'https://www.ypppt.com/p/d.php?aid=' + aids[i]   # 每一个编号aids[i]
        res = requests.get(url2, headers=wz)                    # 请求这个链接 找到下载地址
        download_url = re.findall('<li><a href="(.*?)">下载地址1</a></li>', res.text)
        res = requests.get(download_url[-1], headers=wz)        # 请求下载的链接 保存在文件中
        open(f'PPT模板/{titles[i]}.zip', 'wb').write(res.content)       # 每一个标题titles[i]
        print(f'已经下载{titles[i]}.zip~~~')
    page += 1















# url2 = 'https://www.ypppt.com/p/d.php?aid=' + aid


# 2.请求下载页面的网址 https://www.ypppt.com/p/d.php?aid=6157 找到下载地址
# 3.https://down.ypppt.com/uploads/soft/200617/1-20061H34358.zip 下载文件