因为马上就要大四实习了，博主实在懒得在学校官网上一个个翻，直接用爬虫将所有数据都爬下来

放在表格里，这样感觉简单多了，可惜还没找到工作，so sad

总共选择了三个学校：湖南大学，中南大学，湘潭大学

三个项目代码分别如下（新手代码，惨不忍睹）：

湘潭大学：

#!/usr/bin/python3#coding=utf-8import requestsimport jsonimport loggingimport osimport xlwtbasic_url = 'http://jobs.xtu.edu.cn/index/getdaycareers?day=2018-10-'logging.basicConfig(level=logging.DEBUG,format='')workbook = xlwt.Workbook()sheet1 = workbook.add_sheet('list1')sheet1.write(0,0,'时间')sheet1.write(0,1,'地点')sheet1.write(0,2,'公司名称')sheet1.write(0,3,'专业要求')sheet1.write(0,5,'详细信息')count=1for i in range(1,32):    url = basic_url+str(i)    logging.debug('the clawer web site is:'+url)    clawertext = requests.get(url)    logging.debug(type(clawertext))    logging.debug(clawertext.json())    logging.debug(clawertext.json()['data'])    logging.debug(type(clawertext.json()['data']))        data_list = clawertext.json()['data']#the useful data     for i in data_list:        sheet1.write(count,0,i['meet_day'])        sheet1.write(count,1,i['address'])        sheet1.write(count,2,i['meet_name'])        sheet1.write(count,3,i['professionals'])        sheet1.write(count,5,'http://jobs.xtu.edu.cn/detail/career?id='+i['career_talk_id'])        count=count+1workbook.save('湘潭大学十月份招聘信息.xlsx')

中南大学：

这个最坑，花了我一个多小时

#!/usr/bin/python3#coding=utf-8import requestsimport xlwtimport jsonimport loggingimport bs4from bs4 import BeautifulSoup#初始化日志保存路劲，及格式logging.basicConfig(filename='log.txt',level=logging.DEBUG,format='%(asctime)s - %(levelname)s - %(message)s')logging.getLogger('requests').setLevel(logging.WARNING)#禁用requests的日志#初始化表格workbook = xlwt.Workbook()sheet1 = workbook.add_sheet('list')sheet1.write(0,0,'时间')sheet1.write(0,1,'地点')sheet1.write(0,2,'公司名称')sheet1.write(0,3,'职位名称')sheet1.write(0,4,'教育水平')sheet1.write(0,5,'专业要求')sheet1.write(0,6,'空缺数量')sheet1.write(0,7,'详细信息')#初始化地址json_all_url = 'http://jobsky.csu.edu.cn/Home/SearchDateAllMonth'dt1={
    'Date':'2018-09-04'}post_data = requests.post(json_all_url,data=dt1)json_data = post_data.json()logging.debug(type(json_data))'''with open('json.txt','w') as fileTxt:    for i in json_data:        fileTxt.write(str(i)+'\n')    '''basic_html_url = 'http://jobsky.csu.edu.cn/Home/ArticleDetails/'counter_all = 1for data in json_data:    company_Id=data['NewsID']    #logging.debug('the commpanyID is:'+company_Id)    html_url=basic_html_url+company_Id#html_url=basic_html_url+'13713'#static url,please delete and repaire after you have used it        html_txt = requests.get(html_url)#  logging.debug('the web site using code is:'+str(html_txt.status_code))    bs = BeautifulSoup(html_txt.text,'lxml')        #get the commpanyName        list_soup_CN = bs.find('h1',attrs={
    'class':'text-center title'})    try:            advertise_company_name=list_soup_CN.getText()        sheet1.write(counter_all,2,advertise_company_name)    except:        logging.debug("the url"+html_url+'has some problem')    #get the time and place    try:        list_soup_TP = bs.find('div',attrs={
    'id':'placeAndTime'})        advertise_time=list_soup_TP.find('p',attrs={
    'class':'text-center time'}).getText()        advertise_place=list_soup_TP.find('p',attrs={
    'class':'text-center place'}).getText()        sheet1.write(counter_all,0,advertise_time)        sheet1.write(counter_all,1,advertise_place)    except:        logging.debug("the url"+html_url+'has some problem')        try:             list_soup_demand = bs.find('table',attrs={
    'class':'table table-bordered'})        list_td = list_soup_demand.find_all('td')        counter_even = 0#use to counter ,so that we can find the number of td,and get we need data        #we can get the useful data by looking the source        for td in list_td:            if counter_even==1 :                sheet1.write(counter_all,3,td.getText())            if counter_even==3 :                sheet1.write(counter_all,4,td.getText())            if counter_even==5 :                sheet1.write(counter_all,5,td.getText())            if counter_even==7 :                sheet1.write(counter_all,6,td.getText())            counter_even =counter_even+1        sheet1.write(counter_all,7,html_url)        counter_all+=1    except:        logging.debug("the url"+html_url+'has some problem')    #保存文件    workbook.save('中南大学招聘信息.xlsx')

最后是湖南大学，不知道为什么，湖南大学招聘信息少的可怜

#!/usr/bin/python3#coding=utf-8import requestsimport jsonimport loggingimport osimport xlwtjson_url = 'https://hnu.bysjy.com.cn/module/getcareers?start_page=1&keyword=&type=inner&day=&count=15&start=1&_=1536044186160'logging.basicConfig(level=logging.DEBUG,format='')json_data = requests.get(json_url)#print(json_data.text)workbook = xlwt.Workbook()sheet1 = workbook.add_sheet('list1')sheet1.write(0,0,'时间')sheet1.write(0,1,'地点')sheet1.write(0,2,'公司名称')sheet1.write(0,3,'招聘会')sheet1.write(0,4,'专业要求')sheet1.write(0,6,'详细信息')count=1    data_list = json_data.json()['data']#the useful data for i in data_list:        sheet1.write(count,0,i['meet_day']+i['meet_time'])        sheet1.write(count,1,i['address'])        sheet1.write(count,2,i['company_name'])        sheet1.write(count,3,i['meet_name'])        sheet1.write(count,4,i['professionals'])        sheet1.write(count,5,'https://hnu.bysjy.com.cn/detail/career?id='+i['career_talk_id'])        count=count+1workbook.save('湖南大学招聘信息.xlsx')