python59行代码爬取免费ppt模板

Python59行代码爬取某站中秋节ppt模板

• 网址：https://www.1ppt.com/moban/zhongqiujie/
• 用到的库：requests、re、os、lxml
• 请求方式：GET
• 项目需求：将所有页模板下载到对应的文件夹中- 一共7页，分别将对应的模板下载到对应的文件夹中
  -代码如下：

import requests
import re
import os
from lxml import etree


def path_replace(path):
    """路径分隔符转换"""
    after_path = path.replace("\\", "/")
    return after_path


def pre(o_url, agent, encoding="utf-8"):
    """预处理"""
    pre_response_data = requests.get(o_url, agent)
    pre_response_data.encoding = encoding
    pre_solve_data = etree.HTML(pre_response_data.text)
    return pre_solve_data


def create_directory(path, e_name):
    """创建文件目录"""
    if not os.path.exists(path):
        os.mkdir(path)
        print(f"{e_name}目录 创建成功！")


w_path = "F:\PycharmFiles\pachong\\first_ppt\saves\ppts\zhongqiu"
w_path = path_replace(w_path)
site = "https://www.1ppt.com/moban/zhongqiujie/"
ua_agent = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:105.0) Gecko/20100101 Firefox/105.0"}
solve_data = pre(site, ua_agent, encoding='gbk')
page_data = solve_data.xpath("//a[text()='末页']/@href")
if page_data:
    page_str = page_data[0]
    total_page = re.findall("\d+", page_str)
else:
    total_page = 1
o_url = "https://www.1ppt.com/moban/zhongqiujie/ppt_zhongqiujie_"
page_hrefs = [o_url + str(page) + ".html" for page in list(range(2, int(total_page[0]) + 1))]
page_hrefs.insert(0, "https://www.1ppt.com/moban/zhongqiujie")
for page_href in page_hrefs:
    solve_data1 = pre(page_href, ua_agent, encoding='gbk')
    file_names = solve_data1.xpath("//ul[@class='tplist']/li/a/img/@alt")
    ppt_urls = solve_data1.xpath("//ul[@class='tplist']/li/a/@href")
    dict_datas = dict(zip(file_names, ppt_urls))
    for file_name, ppt_url in dict_datas.items():
        create_directory(w_path + "/" + file_name, file_name)
        ppt_url1 = "https://www.1ppt.com"
        solve_data2 = pre(ppt_url1 + ppt_url, ua_agent)
        download_urls = solve_data2.xpath("//ul[@class='downurllist']/li/a/@href")
        solve_data3 = pre(ppt_url1 + download_urls[0], ua_agent)
        end_urls = solve_data3.xpath("//li[@class='c1']/a/@href")
        ppt_zip = requests.get(end_urls[0], ua_agent).content
        s_path = w_path + "/" + file_name + "/" + end_urls[0].split('/')[-1]
        print(s_path)
        with open(s_path, 'wb') as f:
            f.write(ppt_zip)
        print(f"{file_name}文件下载成功啦！")

运行结果展示

• 

结语

• 至此，本次爬虫项目分享结束，欢迎各位道友批评指正，也欢迎小白交流讨论，因为我也是一个正在学习的小白。最后，如果觉得对您有用，盼请各位看官点赞收藏。