python爬取站长素材免费简历模板

import requests
import os

from lxml import etree

if not os.path.exists('免费简历模板'):
    os.mkdir('免费简历模板')

if __name__ == '__main__':
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'
    }
    url = 'https://sc.chinaz.com/jianli/free_%d.html'
    start = int(input("请输入起始页：").strip('\t'))
    end = int(input("请输入结束页：").strip('\t'))
    for page in range(start, end):
        if page == 1:
            new_url = 'http://sc.chinaz.com/jianli/free.html'
        else:
            new_url = format(url % page)
        page_text = requests.get(url=new_url, headers=headers).text
        tree = etree.HTML(page_text)
        li_list = tree.xpath('//div[@id="container"]/div/a/@href')
        for li in li_list:
            url_data = requests.get(url='https:'+li, headers=headers).text
            tree2 = etree.HTML(url_data)
            download_url = tree2.xpath('//*[@id="down"]/div[2]/ul/li[1]/a/@href')[0]
            download_name = tree2.xpath('//div[@class="ppt_left fl"]/div/div/h1/text()')[0]
            download_name = download_name.encode('iso-8859-1').decode('utf-8')
            download_data = requests.get(url=download_url, headers=headers).content
            with open('免费简历模板/'+download_name+'.rar', 'wb') as fp:
                fp.write(download_data)
                print(download_name, '下载完成！')