(编辑:jimmy 日期: 2024/12/30 浏览:2)
在我们人生的路途中,找工作是每个人都会经历的阶段,小编曾经也是苦苦求职大军中的一员。怀着对以后的规划和想象,我们在找工作的时候,会看一些招聘信息,然后从中挑选合适的岗位。不过招聘的岗位每个公司都有不少的需求,我们如何从中获取数据,来进行针对岗位方面的查找呢?
大致流程如下:
1.从代码中取出pid
2.根据pid拼接网址 => 得到 detail_url,使用requests.get,防止爬虫挂掉,一旦发现爬取的detail重复,就重新启动爬虫
3.根据detail_url获取网页html信息 => requests - > html,使用BeautifulSoup
若爬取太快,就等着解封
if html.status_code!=200 print('status_code if {}'.format(html.status_code))
4.根据html得到soup => soup
5.从soup中获取特定元素内容 => 岗位信息
6.保存数据到MongoDB中
代码:
# @author: limingxuan # @contect: limx2011@hotmail.com # @blog: https://www.jianshu.com/p/a5907362ba72 # @time: 2018-07-21 import requests from bs4 import BeautifulSoup import time from pymongo import MongoClient headers = { 'accept': "application/json, text/javascript, */*; q=0.01", 'accept-encoding': "gzip, deflate, br", 'accept-language': "zh-CN,zh;q=0.9,en;q=0.8", 'content-type': "application/x-www-form-urlencoded; charset=UTF-8", 'cookie': "JSESSIONID=""; __c=1530137184; sid=sem_pz_bdpc_dasou_title; __g=sem_pz_bdpc_dasou_title; __l=r=https%3A%2F%2Fwww.zhipin.com%2Fgongsi%2F5189f3fadb73e42f1HN40t8~.html&l=%2Fwww.zhipin.com%2Fgongsir%2F5189f3fadb73e42f1HN40t8~.html%3Fka%3Dcompany-jobs&g=%2Fwww.zhipin.com%2F%3Fsid%3Dsem_pz_bdpc_dasou_title; Hm_lvt_194df3105ad7148dcf2b98a91b5e727a=1531150234,1531231870,1531573701,1531741316; lastCity=101010100; toUrl=https%3A%2F%2Fwww.zhipin.com%2Fjob_detail%2F%3Fquery%3Dpython%26scity%3D101010100; Hm_lpvt_194df3105ad7148dcf2b98a91b5e727a=1531743361; __a=26651524.1530136298.1530136298.1530137184.286.2.285.199", 'origin': "https://www.zhipin.com", 'referer': "https://www.zhipin.com/job_detail/", 'user-agent': "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36" } conn = MongoClient('127.0.0.1',27017) db = conn.zhipin_jobs def init(): items = db.Python_jobs.find().sort('pid') for item in items: if 'detial' in item.keys(): #当爬虫挂掉时,跳过已爬取的页 continue detail_url = 'https://www.zhipin.com/job_detail/{}.html'.format(item['pid']) #单引号和双引号相同,str.format()新格式化方式 #第一阶段顺利打印出岗位页面的url print(detail_url) #返回的html是 Response 类的结果 html = requests.get(detail_url,headers = headers) if html.status_code != 200: print('status_code is {}'.format(html.status_code)) break #返回值soup表示一个文档的全部内容(html.praser是html解析器) soup = BeautifulSoup(html.text,'html.parser') job = soup.select('.job-sec .text') print(job) #".job-sec .job-location .location-address") item['location'] = location[0].text.strip() #工作地点 item['updated_at'] = time.strftime("%Y-%m-%d %H:%M:%S",time.localtime()) #实时爬取时间 #print(item['detail']) #print(item['location']) #print(item['updated_at']) res = save(item) #调用保存数据结构 print(res) time.sleep(40)#爬太快IP被封了24小时== #保存数据到MongoDB中 def save(item): return db.Python_jobs.update_one({'_id':item['_id']},{'$set':item}) #why item "" src="/UploadFiles/2021-04-08/202011201425152.png">