Python爬虫练习-Xpath解析批量爬取PPT

批量爬取PPT，分页爬取

import os
import requests
from lxml import etree

if __name__ == '__main__':
    # UA伪装
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.70 Safari/537.36'
    }
    # 指定url
    url = 'https://sc.chinaz.com/ppt/free_%d.html'
    # 分页爬取
    for pageNum in range(1, 3):
        new_url = format(url % pageNum)
        if pageNum == 1:
            new_url = 'https://sc.chinaz.com/ppt/free.html'
        # 发起请求
        response = requests.get(url=new_url, headers=headers)
        # 手动设置响应数据的编码格式
        response.encoding = 'utf-8'
        page_text = response.text
        # xpath解析标签
        tree = etree.HTML(page_text)
        ppt_list = tree.xpath('//div[@]/div[5]/div')
        # 判断文件夹
        if not os.path.exists('./ppt'):
            os.mkdir('./ppt')
        for div in ppt_list:
            # 获取ppt的url
            data_url = 'https://sc.chinaz.com/' + div.xpath('.//div[2]/a/@href')[0]
            # 获取名称
            ppt_name = div.xpath('./div[2]/a/text()')[0] + '.rar'
            # 通用处理中文乱码的解决方案
            # ppt_name = ppt_name.encode('iso-8859-1').decode('gbk')
            # 发起请求
            page_text = requests.get(url=data_url, headers=headers).text
            # 解析下载url
            a_terr = etree.HTML(page_text)
            # 处理异常
            try:
                a_page_text = a_terr.xpath('//div[@]/a/@href')[0]
            except IndexError:
                continue
            # 发起请求
            rar_href = requests.get(url=a_page_text, headers=headers).content
            # 路径
            ppt_path = 'ppt/' + ppt_name
            # 保存
            with open(ppt_path, 'wb') as fp:
                fp.write(rar_href)
                print(ppt_name, '--下载成功--')