智联招聘（保存Excel文件）

#coding:utf-8
#__author__='wang'

#python内置模块
import re,urllib2
from random import choice

#Python第三方模块
import xlwt

#定义智联招聘爬虫类
class ZLZP(object):
    """
     work_name:用于接收岗位名称
     like_citys：用于接收意向城市
    """
    def __init__(self,work_name,like_citys):
        self.work_name = work_name
        self.like_citys = like_citys
        self.total_page_num = 0

        city_string = ''
        for city in self.like_citys:
            # 最后一个城市后面不需要添加%2B，在URL中表示+
            if city == self.like_citys[-1]:
                city_string += city
            else:
                city_string += city
                city_string += '%2B'

        self.base_url = 'http://sou.zhaopin.com/jobs/searchresult.ashx?' 
+ 'jl=' + city_string + '&kw=' + self.work_name
        user_agent_list =["Mozilla/5.0 (Windows NT 6.1; WOW64)
 AppleWebKit/537.36 (KHTML, like Gecko)",
    "Mozilla/5.0 (Windows NT 5.1; U; en; rv:1.8.1) Gecko/20061208 
Firefox/2.0.0 Opera 9.50",
    "Opera/8.0 (Windows NT 5.1; U; en)",
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; en) Opera 9.50",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 
(KHTML, like Gecko) ",
    "Chrome/39.0.2171.95 Safari/537.36 OPR/26.0.1656.60"]
        self.headers = {'User-Agent':choice(user_agent_list)}

    #定义获取HTML源代码的函数
    def get_page_code(self,pageNum):
        #根据pageNum的值，拼接某一页的绝对地址
        absulote_url = self.base_url + '&p=' +str(pageNum)
        request = urllib2.Request(absulote_url,headers=self.headers)
        try:
            response = urllib2.urlopen(request)
        except Exception,e:
            print '获取第{}页数据失败，原因是：{}'.format(pageNum,e)
            return None
        else:
            print '获取第{}页数据成功！'.format(pageNum)
            html = response.read()
            return html

    #定义获取网页总职位数的函数，根据职位是计算一共有多少页
    def get_total_position(self,html):
        pattern = re.compile(r'<span class="search_yx_tj">.*?<em>(.*?)
</em>',re.S)
        number = int(re.search(pattern,html).group(1))
        if number:
            #计算总页数
            if number%60 == 0:
                #每一个展示60个数据刚好将总职位数显示完
                self.total_page_num = number/60
            else:
                #剩余数据个数不够60个需要单独增加一页
                self.total_page_num = number/60 +1
                #
        else:
            print '获取总职位的正则有问题'
            return
    #定义获取职位信息发的函数
    def get_all_data(self,html):
        pattern = re.compile(r'<table.*?class="newlist">.*?<td 
class="zwmc.*?<a.*?>(.*?)</a>.*?<td.*?class="fk_lv.*?<span>(.*?)
</span>.*?<td class="gsmc.*?_blank">(.*?)</a>.*?<td class="zwyx">
(.*?)</td>.*?<td class="gzdd">(.*?)</td>',re.S)
        results = re.findall(pattern,html)
        data_list= []
        for result in results:
            remove_element = re.compile(r'<.*?>',re.S)
            #过滤职位描述和公司名称
            zwmc = re.sub(remove_element,'',result[0])
            gsmc = re.sub(remove_element,'',result[2])
            data_list.append((zwmc,result[1],gsmc,result[3],result[4]))
        return data_list
        #定义创建Excel表的函数
    def open_excel_file(self):
        #创建工作表的对象
        workbook = xlwt.Workbook(encoding= 'utf-8')
        #设置表头
        sheet = workbook.add_sheet('Python职位表')
        #第一个参数表示行号，第二个参数表示列数
        sheet.write(0,0,'职位名称')
        sheet.write(0,1,'反馈率')
        sheet.write(0,2,'公司名称')
        sheet.write(0,3,'职位月薪')
        sheet.write(0,4,'工作地点')
        return sheet,workbook

    #定义开始爬虫的函数
    def stsrt_spider(self):
        #1.获取首页源代码
        html = self.get_page_code(1)
        if html ==  None:
            print '首页源代获取失败'
            return
        #2.提取总职位数，获取总页数
        self.get_total_position(html)
        #3.开始根据总页数循环写入数据
        sheet, workbook =self.open_excel_file()
        #记录当前行号
        recode_row = 1
        for x in xrange(1,self.total_page_num+1):
            html = self.get_page_code(x)
            if html == None:
                #跳过本页写入数据
                continue
            results_list = self.get_all_data(html)
            for zwmc,fk_lv,gsmc,zwyx,gzdd in results_list:
                #通过sheet对象按照行号和列好写入Excel表中
                sheet.write(recode_row, 0,zwmc)
                sheet.write(recode_row, 1, fk_lv)
                sheet.write(recode_row, 2, gsmc)
                sheet.write(recode_row, 3, zwyx)
                sheet.write(recode_row, 4, gzdd)
                recode_row += 1

        #通过workbook对象，将Excel数据保存到本地
        workbook.save(u'Python职业介绍.xls')

if __name__ == '__main__':
    # zlzp = ZLZP('python',['郑州','杭州'])
    # html = zlzp.get_page_code(1)
    # zlzp.get_total_position(html)
    # zlzp.get_all_data(html)
    workname = raw_input('请输入搜索职位')
    citys=[]
    while True:
        city_name = raw_input('请输入意向城市（Q退出输入）：')
        if city_name =='Q':
            break
        citys.append(city_name)
    zlzp = ZLZP(workname,citys)
    zlzp.stsrt_spider()