import os.path

import requests

from lxml import etree

if __name__ == '__main__':

    if not os.path.exists('./jianli'):

        os.mkdir('./jianli')

    headers = {

        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36'

    }

    # 下载前两页模板

    for i in range(1, 3):

        if i == 1:

            url = 'https://sc.chinaz.com/jianli/free.html'

        else:

            url = 'https://sc.chinaz.com/jianli/free_' + str(i) + '.html'

        page = requests.get(url=url, headers=headers)

        page.encoding = 'utf-8'

        tree = etree.HTML(page.text)

        free_jianli = tree.xpath('//div[@id="main"]/div/div')

        for free in free_jianli:

            # 获取链接

            free_url = free.xpath('./a/@href')[0]

            # 简历标题

            free_title = free.xpath('./a/img/@alt')[0]

            # 根据链接获取到对应下载页面

            free_content = requests.get(url=free_url, headers=headers).text

            free_content_tree = etree.HTML(free_content)

            # 找到下载链接

            down_path = free_content_tree.xpath('//div[@class="down_wrap"]/div[2]/ul/li[1]/a/@href')[0]

            # 下载内容的标题

            down_path_title = free_title + '.' + down_path.split('.')[-1]

            # 根据下载链接进行二进制数据下载

            down_path_content = requests.get(url=down_path, headers=headers).content

            # 存入文件中

            with open('./jianli/' + down_path_title, 'wb') as fp:

                fp.write(down_path_content)

                print(down_path_title, "下载成功")

        print("第{0}页下载成功".format(i))

    print('下载完成')