用python抓取智联招聘信息并存入excel
tags:python 智联招聘导出excel
引言：前一阵子是人们俗称的金三银四，跳槽的小朋友很多，我觉得每个人都应该给自己做一下规划，根据自己的进步作出调整。建议不要看到身边的人涨了工资就盲目的心动。一般来说跳槽后要熟悉新的环境会浪费不少时间，如果现在的工作在氛围和自身进步上还可以接受，其他比如待遇方面可以和公司协调解决。
本文参考了yaoyefengchen的博客：文章链接，并进行了地域搜索优化和将存储方式由cvs改成大家常用的excel。下面进入正文
先说一下大概流程：
在智联职位搜索页面上选好自己的搜索条件后，发现链接地址为：
http://sou.zhaopin.com/jobs/searchresult.ashx?jl=北京&kw=php高级工程师&sm=0&re=2006&isfilter=1&p=1&sf=10001&st=15000
分析链接中的参数如下（过滤条件可以选择不写），并构造出请求的数据，header的设置只要可以访问网页即可。
paras = {
'jl': city, # 搜索城市
'kw': keyword, # 搜索关键词
'isadv': 0, # 是否打开更详细搜索选项
'isfilter': 1, # 是否对结果过滤
'p': page, # 页数
're': region # region的缩写，地区，2005代表海淀
}
# sf=10001&st=15000这两个是我筛选的工资区间，如果有这个需求可以自己添加参数。
url = 'https://sou.zhaopin.com/jobs/searchresult.ashx?' + urlencode(paras)yaoyefengchen用的是正则匹配出职位，薪资，公司等信息，并没有提供具体地域（比如海淀还是朝阳）对应的region。我后来是用的xpath提取出了北京的各个地域组成字典，直接输入地区的汉字就可以了。如下：
# 取搜索页面得到地域的对应数字 比如海淀对应2005
def parseHtmlToGetRegion(regionAddress):
url = 'http://sou.zhaopin.com/jobs/searchresult.ashx?jl=北京&sm=0&isfilter=1&p=1&re=2006'
# 获取代理ip地址 只取前五页
html= getHtml(url)
regionId = html.xpath('/html/body/div[3]/div[3]/div[1]/div[4]/div[1]/div[2]/a/@href')
region = html.xpath('/html/body/div[3]/div[3]/div[1]/div[4]/div[1]/div[2]/a/text()')
#解析一下region中的编号去掉无效内容
regionList = {}
for i,regionHref in enumerate(regionId):
if i==0:
continue
regionList[region[i]] = regionId[i][-4::]
return regionList.get(regionAddress)另外，cvs格式在用一些工具比如excel打开的时候经常出现乱码，需要转化或者下载一些专用的软件。我觉得很不方便，所以直接存成了excel格式，不得不说，在存数据到excel文件这方面，python简直比php容易太多了。
# 存入excle
def write_xls_file(filename, headers, jobs):
table = xlwt.Workbook(encoding='utf8')
table_page = table.add_sheet('jobs')
for i,header in enumerate(headers):
table_page.write(0,i,header)
for j,items in enumerate(jobs,start = 1):
for q,item in items.items():
table_page.write(j, q, item)
table.save(filename)
完整代码如下，可以直接使用。别忘了保存文章最下面的user_agents.py文件
#-*- coding: utf-8 -*-
'''
Created on 2018-05-7
@author: Vinter_he
'''
import re
import requests
import xlwt
from tqdm import tqdm
from urllib.parse import urlencode
from requests.exceptions import RequestException
from lxml import etree
import user_agents
import random
import datetime
def get_one_page(city, keyword, region, page):
'''
获取网页html内容并返回
'''
paras = {
'jl': city, # 搜索城市
'kw': keyword, # 搜索关键词
'isadv': 0, # 是否打开更详细搜索选项
'isfilter': 1, # 是否对结果过滤
'p': page, # 页数
're': region # region的缩写，地区，2005代表海淀
}
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36',
'Host': 'sou.zhaopin.com',
'Referer': 'https://www.zhaopin.com/',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate, br',
'Accept-Language': 'zh-CN,zh;q=0.9'
}
url = 'https://sou.zhaopin.com/jobs/searchresult.ashx?' + urlencode(paras)
try:
# 获取网页内容，返回html数据
response = requests.get(url, headers=headers)
# 通过状态码判断是否获取成功
if response.status_code == 200:
return response.text
return None
except RequestException as e:
return None
def parse_one_page(html):
'''
解析HTML代码，提取有用信息并返回
'''
# 正则表达式进行解析
pattern = re.compile('<a style=.*? target="_blank">(.*?)</a>.*?' # 匹配职位信息
'<td class="gsmc"><a href="(.*?)" target="_blank">(.*?)</a>.*?' # 匹配公司网址和公司名称
'<td class="zwyx">(.*?)</td>', re.S) # 匹配月薪
# 匹配所有符合条件的内容
items = re.findall(pattern, html)
for item in items:
job_name = item[0]
job_name = job_name.replace('<b>', '')
job_name = job_name.replace('</b>', '')
yield {
0: job_name,
1: item[1],
2: item[2],
3: item[3]
}
# 存入excle
def write_xls_file(filename, headers, jobs):
table = xlwt.Workbook(encoding='utf8')
table_page = table.add_sheet('jobs')
for i,header in enumerate(headers):
table_page.write(0,i,header)
for j,items in enumerate(jobs,start = 1):
for q,item in items.items():
table_page.write(j, q, item)
table.save(filename)
def main(city, keyword, region, pages):
'''
主函数
'''
filename = '智联_' +datetime.date.today().strftime('%Y-%m-%d')+ city + '_' + keyword + '.xls'
headers = ['job', 'website', 'company', 'salary']
jobs = []
for i in tqdm(range(pages)):
'''
获取该页中所有职位信息，写入xls文件
'''
region = parseHtmlToGetRegion(region)
html = get_one_page(city, keyword, region, i)
items = parse_one_page(html)
for item in items:
jobs.append(item)
write_xls_file(filename, headers, jobs)
def getHtml(url):
response = requests.get(url=url, headers={'User-Agent':random.choice(user_agents.user_agents)}, timeout=10).text
html = etree.HTML(response)
return html
# 取搜索页面得到地域的对应数字 比如海淀对应2005
def parseHtmlToGetRegion(regionAddress):
url = 'http://sou.zhaopin.com/jobs/searchresult.ashx?jl=北京&sm=0&isfilter=1&p=1&re=2006'
# 获取代理ip地址 只取前五页
html= getHtml(url)
regionId = html.xpath('/html/body/div[3]/div[3]/div[1]/div[4]/div[1]/div[2]/a/@href')
region = html.xpath('/html/body/div[3]/div[3]/div[1]/div[4]/div[1]/div[2]/a/text()')
#解析一下region中的编号去掉无效内容
regionList = {}
for i,regionHref in enumerate(regionId):
if i==0:
continue
regionList[region[i]] = regionId[i][-4::]
return regionList.get(regionAddress)
if __name__ == '__main__':
main('北京', 'php工程师', '朝阳', 10)
下面是和以前一样的user_agents.py文件 这个文件以后就不给了大家可以自己保存一下备用
#!/usr/bin/python
# -*- coding:utf-8 -*-
'''
Created on 2018-04-27
@author: Vinter_he
'''
user_agents = [
'Mozilla/5.0 (Windows; U; Windows NT 5.1; it; rv:1.8.1.11) Gecko/20071127 Firefox/2.0.0.11',
'Opera/9.25 (Windows NT 5.1; U; en)',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)',
'Mozilla/5.0 (compatible; Konqueror/3.5; Linux) KHTML/3.5.5 (like Gecko) (Kubuntu)',
'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.0.12) Gecko/20070731 Ubuntu/dapper-security Firefox/1.5.0.12',
'Lynx/2.8.5rel.1 libwww-FM/2.14 SSL-MM/1.4.1 GNUTLS/1.2.9'
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1",
"Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6",
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6",
"Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1",
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5",
"Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
"Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3",
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24",
"Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24"
]