本文实现自动爬取拉钩网招聘信息,并将爬取结果保存在本地文本中(也可以将数据存入数据库)
使用到的Python模块包(Python3):
1.urllib.request
2.urllib.parse
3.json
简单分析:
1.在向服务器发送请求,需要传入post参数
2.搜索的职位列表信息存在一个josn文件中,可使用json模块解析
3.翻页
本文使用while True和break结合,根据json中result的值是否为空来判断当前要是否是最后一页,也可以根据json文件中pageSize和totalCount两个字段的值得出总的页面数。
完整代码:
import urllib.requestimport urllib.parseimport jsondef open_url(url,page_num,keywords):try:#设置post请求参数page_data=urllib.parse.urlencode([('pn',page_num),('kd',keywords)])#设置headerspage_headers={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0','Connection':'keep-alive','Host':'','Origin':'','Cookie':'JSESSIONID=ABAAABAABEEAAJA8F28C00A88DC4D771796BB5C6FFA2DDA; user_trace_token=0715131136-d58c1f22f6434e9992fc0b35819a572b; LGUID=0715131136-13c54b92-691c-11e7-893a-525400f775ce; index_location_city=%E5%8C%97%E4%BA%AC; _gat=1; TG-TRACK-CODE=index_search; _gid=GA1.2.496231841.1500095497; _ga=GA1.2.1592435732.1500095497; Hm_lvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1500095497; Hm_lpvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1500104021; LGSID=0715143221-5b993c04-6927-11e7-a985-5254005c3644; LGRID=0715153341-ec8dbfd2-692f-11e7-a989-5254005c3644; SEARCH_ID=d27de6042bdf4d508cf9b39616a98a0d','Accept':'application/json, text/javascript, */*; q=0.01','Content-Type':'application/x-www-form-urlencoded; charset=UTF-8','Referer':'/jobs/list_%E6%95%B0%E6%8D%AE%E6%8C%96%E6%8E%98?labelWords=&fromSearch=true&suginput=','X-Anit-Forge-Token':'None','X-Requested-With':'XMLHttpRequest'}#打开网页req=urllib.request.Request(url,headers=page_headers)content=urllib.request.urlopen(req,data=page_data.encode('utf-8')).read().decode('utf-8')return contentexcept Exception as e:print(str(e))#获取招聘职位信息def get_position(url,page_num):try:page_content=open_url(url,page_num,keywords)data=json.loads(page_content)content=data.get('content')result=[('positionId','职位ID'),('positionName','职位名称'),('salary','薪资'),('createTime','发布时间'),('workYear','工作经验'),('education','学历'),('positionLables','职位标签'),('jobNature','职位类型'),('firstType','职位大类'),('secondType','职位细类'),('positionAdvantage','职位优势'),('city','城市'),('district','行政区'),('businessZones','商圈'),('publisherId','发布人ID'),('companyId','公司ID'),('companyFullName','公司名'),('companyShortName','公司简称'),('companyLabelList','公司标签'),('companySize','公司规模'),('financeStage','融资阶段'),('industryField','企业领域'),('industryLables','企业标签')]positionResult=content.get('positionResult').get('result')if(len(positionResult)>0):for position in positionResult:with open("position.txt",'a') as fh:fh.write("---------------------------\n")for r in result:with open("position.txt",'a') as fh:fh.write(str(r[1])+":"+str(position.get(r[0]))+"\n")return len(positionResult)except Exception as e:print(str(e))#爬取拉勾网招聘职位信息if __name__=="__main__":#爬取起始页url='/jobs/positionAjax.json?city=%E5%8C%97%E4%BA%AC&needAddtionalResult=false'#设置查询的关键词keywords="数据挖掘"page_num=1while True:print("正在爬取第"+str(page_num)+"页......")result_len=get_position(url,page_num)if(result_len>0):page_num+=1else:breakprint("爬取完成")
爬取结果: