from lxml import etree import requests import os if __name__ == "__main__" : header = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36 Edg/118.0.2088.46' } #简历网站url地址 url = "https://sc.chinaz.com/jianli/free.html" #请求响应 page_text = requests.get(url=url,headers=header).content #将网页html加载到etree对象中 tree = etree.HTML(page_text) #获取简历的a标签 host_li_list = tree.xpath('//div[@id="main"]/div/div/a') #如果jianlirar文件不存在，自动创建该文件 if not os.path.exists('./jianlirar'): os.mkdir('./jianlirar') for i in host_li_list: #获取a标签中href的地址请求响应 src = requests.get(url=i.xpath('./@href')[0],headers=header).text #加载响应后的网页文档到etree中 new_html = etree.HTML(src) #获取新网页的下载地址 new_src = new_html.xpath('//div[@class="down_wrap"]//ul/li/a/@href')[0] #请求下载地址 path = requests.get(url=new_src,headers=header).content #name_list是每一个简历完整的文件名路径 name_list = './jianlirar/'+i.xpath('./img/@alt')[0]+".rar" with open(name_list,'wb') as f : #依次将请求path写入到文件中，文件格式为rar f.write(path) print(name_list+"下载成功！")