爬取智联招聘(面向对象)

有待完善

import re
import requests
import os
import xlwt
import codecs

class Item(object):
    zhiwei = None
    gongzi = None
    gongzuodidian = None
    gongsimingcheng = None

class getPosition(object):
    def __init__(self):
        self.urlBase = 'http://sou.zhaopin.com/jobs/searchresult.ashx?jl=%E5%85%A8%E5%9B%BD&kw=%E6%95%B0%E6%8D%AE%E5%88%86%E6%9E%90%E5%B8%88&sm=0&isfilter=0&fl=489&isadv=0&sg=aae5284f62664af8b14611bda6d68315&p=1'
        self.urls = []
        self.items = []
        self.getUrls(2)
        # self.getHTML(self.urls)
        self.spider(self.urls)
        self.save(self.items)

    def getHTML(self,url):
        kv = {'user-agent':'Mozilla/5.0'}
        r = requests.get(url,headers = kv)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text

    def getUrls(self,pages):
        urlHead = 'http://sou.zhaopin.com/jobs/searchresult.ashx?jl=%E5%85%A8%E5%9B%BD&kw=%E6%95%B0%E6%8D%AE%E5%88%86%E6%9E%90%E5%B8%88&sm=0&isfilter=0&fl=489&isadv=0&sg=aae5284f62664af8b14611bda6d68315&p='
        for i in range(1,pages+1):
            url = urlHead + str(i)
            self.urls.append(url)

    def spider(self,urls):
        pat1 = '<b>(.*?)</b>'
        pat3 = '<td class="zwyx">(.*?)</td>'
        pat4 = '<td class="gzdd">(.*?)</td>'
        pat5 = 'target="_blank">(.*?)<'
        item = Item()
        for url in urls:
            html = self.getHTML(url)
            item.zhiwei = re.compile(pat1).findall(html)
            item.gongzi = re.compile(pat3).findall(html)
            item.gongzuodidian = re.compile(pat4).findall(html)
            item.gongsimingcheng = re.compile(pat5).findall(html)
        self.items.append(item)
        print(len(item.zhiwei))
        print(len(item.gongzi))

    def save(self,items):
        fileName = '1a.txt'.encode('GBK')
        tplt = "{0:^10}\t{1:<10}\t{2:^10}\t{3:^10}"
        with codecs.open(fileName,'w','utf-8') as f:
            for item in items:
                # f.write(tplt.format(item.zhiwei,item.gongzi,item.gongzuodidian,item.gongsimingcheng))
                # f.write("%s \t %s \t %s \t %s \r\n" % (' '.join(item.zhiwei),item.gongzi,item.gongzuodidian,item.gongsimingcheng))
                for i in range(59):
                    print(tplt.format(item.zhiwei[i],item.gongzi[i],item.gongzuodidian[i],item.gongsimingcheng[i]))
                    # print(item.zhiwei[i])
                    # print(item.gongzi[i])



if __name__ == '__main__':
    p = getPosition()