簡(jiǎn)介：爬取“個(gè)人簡(jiǎn)歷網(wǎng)”中的簡(jiǎn)歷模板并存儲(chǔ)到本地（http://www.gerenjianli.com/moban/index.html）
代碼：

import requests from lxml import etree import os if __name__ == '__main__':# 這是只爬取一頁(yè)數(shù)據(jù)# url = 'http://www.gerenjianli.com/moban/index.html'## headers = {# 'User-Agent':'這里放自己瀏覽器的UA就行啦'# }# # page_text = requests.get(url=url,headers=headers).text# response = requests.get(url=url, headers=headers)# # response.encoding = 'utf-8'# page_text = response.text## tree = etree.HTML(page_text)# li_list = tree.xpath('//div[@class="list_boby"]/ul[@class="prlist"]/li')# # print(li_list)## #創(chuàng)建文件夾# if not os.path.exists('./resumeLibs'):# os.mkdir('./resumeLibs')# for li in li_list:# a = li.xpath('./div/a/@href')[0]# name = li.xpath('./div/a/img/@alt')[0]# name = name.encode('iso-8859-1').decode('gbk')# download_text = requests.get(url=a,headers=headers).text# tree = etree.HTML(download_text)# download_href = tree.xpath('//div[@class="donwurl2"]/a/@href')[0]## doc_data = requests.get(url=download_href,headers=headers).content# doc_path = 'resumeLibs/' + name + '.docx'# with open(doc_path,'wb') as fp:# fp.write(doc_data)# print(name,'下載成功！')# 爬取多頁(yè)數(shù)據(jù)headers = {'User-Agent': '這里放自己瀏覽器的UA就行啦'}# 創(chuàng)建文件夾if not os.path.exists('./resumeLibs'):os.mkdir('./resumeLibs')for pagenum in range(1,4):#這里爬取了1-3頁(yè)中的簡(jiǎn)歷模板if pagenum == 1:url = 'http://www.gerenjianli.com/moban/index.html'else:url = 'http://www.gerenjianli.com/moban/index_' + str(pagenum) + '.html'# page_text = requests.get(url=url,headers=headers).textresponse = requests.get(url=url, headers=headers)# response.encoding = 'utf-8'page_text = response.texttree = etree.HTML(page_text)li_list = tree.xpath('//div[@class="list_boby"]/ul[@class="prlist"]/li')# print(li_list)for li in li_list:a = li.xpath('./div/a/@href')[0]name = li.xpath('./div/a/img/@alt')[0]name = name.encode('iso-8859-1').decode('gbk')download_text = requests.get(url=a, headers=headers).texttree = etree.HTML(download_text)download_href = tree.xpath('//div[@class="donwurl2"]/a/@href')[0]doc_data = requests.get(url=download_href, headers=headers).contentdoc_path = 'resumeLibs/' + name + '.docx'with open(doc_path, 'wb') as fp:fp.write(doc_data)print(name, '下載成功！')

總結(jié)

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

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