import requests from lxml import etree import os # 分頁： if __name__ == "__main__":if not os.path.exists('./jianli'):os.mkdir('./jianli')for pageName in range(1, 4):if pageName == 1:url = 'https://sc.chinaz.com/jianli/free.html'print('正在爬取網(wǎng)站第1頁內(nèi)容')else:url = format('https://sc.chinaz.com/jianli/free_%d.html' % pageName)print('正在爬取網(wǎng)站第%d頁內(nèi)容' % pageName)# 1.爬取網(wǎng)頁信息 https://sc.chinaz.com/jianli/free.htmlheaders = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36'}# 爬取到頁面源碼數(shù)據(jù)url = 'https://sc.chinaz.com/jianli/free.html'page_text = requests.get(url=url,headers=headers).text# 2.數(shù)據(jù)解析tree = etree.HTML(page_text)jl_href= tree.xpath('//div[@id="container"]/div/a/@href')# 拿到每個簡歷的urlfor jl in jl_href:one_url = 'https:' + jl# print(one_url)# 3.拿到每個簡歷的下載地址one_page_taxt = requests.get(url=one_url,headers=headers).textone_tree = etree.HTML(one_page_taxt)one_adress = one_tree.xpath('//div[@id="down"]/div[2]/ul/li[1]/a/@href')[0]# print(one_adress)# 4.持久化存儲# 拿到每個簡歷的名字jl_name = one_tree.xpath('//*[@class="bgwhite"]/div[1]/h1/text()')[0] + '.rar'jl_name = jl_name.encode('iso-8859-1').decode('utf-8')# print(jl_name)download = requests.get(url=one_adress, headers=headers).contentadress_path = './jianli/' + jl_namewith open(adress_path, 'wb') as fp:fp.write(download)print(jl_name, '下載成功！！！')print('over')

總結(jié)

以上是生活随笔為你收集整理的爬虫：python爬取简历模板的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。