如何批量下载免费的课件

最新推荐文章于 2024-12-08 13:03:45 发布

原创最新推荐文章于 2024-12-08 13:03:45 发布 · 726 阅读

CC 4.0 BY-SA版权

文章标签：

#   本文仅供学习参考。
#   https://www.ypppt.com/article/2018/4692.html 点击图片链接
#   https://www.ypppt.com/p/d.php?aid=4692  点击下载链接
#   https://down.ypppt.com/uploads/soft/180301/1-1P301092632.zip  下载地址
#   提示证书错误

#加载模块
import requests
#去除运行的警告
import urllib3
#正则表达式
import re

urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
#初始化变量 
page = 1
#循环下载
while True:
#第一页和第二页链接不一样
        if page == 1:
            url = 'https://www.ypppts.com/moban/'
        else:
            url = f'https://www.ypppts.com/moban/list-{page}.html'


        print(page)
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.6261.95 Safari/537.36'
        }
        res = requests.get(url, headers=headers)
        res.encoding = 'utf-8'
#找到id和名字
        ppt_list = re.findall('<a href="/article/.*?/(.*?).html" class="p-title" target="_blank">(.*?)</a>', res.text)

        for pptlist in ppt_list:
            pptid = pptlist[0]
            pptname = pptlist[1]
#合成网址
            url = 'https://www.ypppt.com/p/d.php?aid=' + pptid
            res = requests.get(url, headers=headers, verify=False)
#找到下载网址
            down_url = re.findall('<a href="(.*?)">下载地址1</a>',res.text)[-1]
            downres =requests.get(down_url, headers=headers, verify=False)
            if 'pan.baidu' in down_url:
                 continue
            open(f'PPT模板/{pptname}.{down_url.split(".")[-1]}','wb').write(downres.content)
        page += 1