python 爬取简历模板的下载地址

#!/usr/bin/env python# -*- coding:utf-8 -*-#需求：解析下载页面的链接地址http://pic.netbian.com/4kmeinv/# 对模板的首页进行解析# 每个简历模板的详情页拿到# 解析下载地址的链接importrequestsfrom lxml importetreeif__name__ == '__main__':headers = {'Us

小主早安

801人浏览 · 2020-09-16 15:38:35

小主早安 · 2020-09-16 15:38:35 发布

#!/usr/bin/env python
# -*- coding:utf-8 -*-
#需求：解析下载页面的链接地址http://pic.netbian.com/4kmeinv/
# 对模板的首页进行解析
# 每个简历模板的详情页拿到
# 解析下载地址的链接
import  requests
from lxml import  etree
if   __name__ == '__main__':
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
    }
    url = 'http://sc.chinaz.com/jianli/free.html'
    page_text = requests.get(url=url, headers=headers).text
    tree = etree.HTML(page_text)
    # a_list = tree.xpath('//div[@class="main_list jl_main"]/div[1]/a/@href')
    # print(a_list)
    # for a in a_list:
    div_list = tree.xpath('//div[@class="main_list jl_main"]/div')
    for a_list in div_list:
        #取得免费模板的详细页面的链接地址
        href_list = a_list.xpath('./a/@href')
        for detail_list_url in href_list:
            detail_text = requests.get(url=detail_list_url, headers=headers).text
            detail_tree = etree.HTML(detail_text)
            download_url=detail_tree.xpath('//div[@class="clearfix mt20 downlist"]/ul/li[1]/a/@href')
            print(download_url)