1. 程式人生 > >根據搜尋內容爬取拉鉤網和招聘網的職位招聘資訊

根據搜尋內容爬取拉鉤網和招聘網的職位招聘資訊

程式碼:

import requests
import time
import random

ip_list = ['117.135.132.107', '121.8.98.196',  '194.116.198.212']

#http請求頭資訊
headers={
'Accept':'application/json, text/javascript, */*; q=0.01',
'Accept-Encoding':'gzip, deflate, br',
'Accept-Language':'zh-CN,zh;q=0.8',
'Connection':'keep-alive',
'Content-Length':'25',
'Content-Type':'application/x-www-form-urlencoded; charset=UTF-8',
'Cookie':'user_trace_token=20170214020222-9151732d-f216-11e6-acb5-525400f775ce; LGUID=20170214020222-91517b06-f216-11e6-acb5-525400f775ce; JSESSIONID=ABAAABAAAGFABEF53B117A40684BFB6190FCDFF136B2AE8; _putrc=ECA3D429446342E9; login=true; unick=yz; showExpriedIndex=1; showExpriedCompanyHome=1; showExpriedMyPublish=1; hasDeliver=0; PRE_UTM=; PRE_HOST=; PRE_SITE=; PRE_LAND=https%3A%2F%2Fwww.lagou.com%2F; TG-TRACK-CODE=index_navigation; Hm_lvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1494688520,1494690499,1496044502,1496048593; Hm_lpvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1496061497; _gid=GA1.2.2090691601.1496061497; _gat=1; _ga=GA1.2.1759377285.1487008943; LGSID=20170529203716-8c254049-446b-11e7-947e-5254005c3644; LGRID=20170529203828-b6fc4c8e-446b-11e7-ba7f-525400f775ce; SEARCH_ID=13c3482b5ddc4bb7bfda721bbe6d71c7; index_location_city=%E6%9D%AD%E5%B7%9E',
'Host':'www.lagou.com',
'Origin':'https://www.lagou.com',
'Referer':'https://www.lagou.com/jobs/list_Python?',
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36',
'X-Anit-Forge-Code':'0',
'X-Anit-Forge-Token':'None',
'X-Requested-With':'XMLHttpRequest'
}

def get_json(url,page,lange_name):
    #構造一個framdata資料
    FramData = {'firts':'true','pn':page,'kd':lange_name}
    #採用request是post方法,返回requests<200>,訪問成功
    JsonDatas = requests.post(url,FramData,headers=headers,proxies={'http': 'http://' + random.choice(ip_list)}).json()
    #獲取字典資料
    #JsonDatas = jsonData.json()
    return  JsonDatas

def parser_json(page,JsonDatas):#JsonDatas資料庫型別是字典
    #total = int(JsonDatas['content']['positionResult']['totalCount'])
    companyInfos = []
    #獲取招聘資訊的公司,列表型別
    companyInfo = JsonDatas['content']['positionResult']['result']
    #對每一個公司遍歷
    print("正在解析{0}頁招聘資訊".format(page))
    for company in companyInfo:
        #定義一個列表,暫時儲存一個公司資訊
        comInfo = []
        #公司所在城市
        if company['district'] is not None:
            city =  company['city'] + '-' + company['district']
        else:
            city = company['city']
        #print(city)
        comInfo.append(city)
        # 職位名稱
        positionName = company['positionName']
        #print(positionName)
        comInfo.append(positionName)
        #獲取公司名稱
        companyFullName = company['companyFullName']+ '(' + company['companyShortName'] + ')'
        #print(companyFullName)
        comInfo.append(companyFullName)
        #要求學歷
        education = company['education']
        #print(education)
        comInfo.append(education)
        #職位型別
        jobNature = company['jobNature']
        #print(jobNature)
        comInfo.append(jobNature)
        #職位待遇
        positionAdvantages = company['positionAdvantage']
        positionAdvantage = positionAdvantages.replace(',',';').replace(',',';')
        #print(positionAdvantage)
        comInfo.append(positionAdvantage)
        #工資
        salary = company['salary']
        #print(salary)
        comInfo.append(salary)
        #經驗要求
        workYear = company['workYear']
        comInfo.append(workYear)
        #分佈時間
        time = company['createTime']
        comInfo.append(time)
        #將每個公司的資訊加入companyInfos中
        companyInfos.append(comInfo)
    print("第{0}頁解析完成".format(page))
    return companyInfos
def writeCSV(page,fw,companyInfos):
    for companyInfo in companyInfos:
        #print(companyInfo)
        fw.write(",".join(companyInfo)+'\n')
    print("第{0}頁資料寫入完畢".format(page))
    
def main():
    path = 'F:'  # 檔案儲存路徑
    start_page = 1
    end_page = 20 #預設
    lange_name = input("請輸入要所有的職位:")
    city = input("請輸入工作地點:")
    #建立檔案
    fw = open(path + '\lagou_' + lange_name + '.csv', 'a+')
    #構造url連結
    start_url = 'https://www.lagou.com/jobs/positionAjax.json?px=default&city='
    end_url = '&needAddtionalResult=false&isSchoolJob=0'
    url=start_url + city + end_url
    page = start_page
    row = ['工作地點','職位名稱', '公司名稱', '要求學歷', '工作性質', '工作福利', '薪水', '工作經驗要求','釋出時間']
    fw.write(",".join(row) + '\n')
    while page < end_page:
        time.sleep(12)
        print("正在抓取第{0}頁招聘資料資訊".format(page))
        #獲取json資料
        JsonDatas = get_json(url,page,lange_name)
        #對獲取的資料進行解析
        companyInfos = parser_json(page,JsonDatas)
        #將資訊寫入CSV檔案中
        writeCSV(page,fw,companyInfos)
        page = page+1
    print("所有資料寫入完畢")

if __name__ == '__main__':
    main()