# 1.把之间案例，使用bs4,正则，xpath，进行数据提取。 # 2.爬取拉钩网上的所有python职位。 from urllib import request,parse import json,random #导入xlsxwriter 主要用于生成excel表格对象 import xlsxwriter #创建python的职位类 class python_position: def __init__(self,page,number): self.page = page self.number = number #调用创建excel对象的函数 self.create_book() self.page_chuli() print(self.page,self.number)#1 0 #创建excel对象函数 def create_book(self): #创建excel对象 self.workbook_attr = xlsxwriter.Workbook('test1.xlsx') #创建表对象,用于写入字符串 self.worksheet = self.workbook_attr.add_worksheet('test1') #处理页码数量函数 def page_chuli(self): #每次页码不一样 也就是number不一样 for page in range(1, 31): self.page = page self.user_agent() self.number += 1 self.workbook_attr.close() def user_agent(self): #浏览器列表,每次访问可以用不同的浏览器访问 user_agent_list = [ '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', 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.152 Safari/537.36', 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36', 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:58.0) Gecko/20100101 Firefox/58.0', 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36', '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', 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:31.0) Gecko/20100101 Firefox/31.0', 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36', 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36', 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.152 Safari/537.36', "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.89 Safari/537.36", "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" ] #随机选取一个浏览器访问 self.user_agent_str = random.choice(user_agent_list) #调用拉钩函数 self.lagou() def lagou(self): #职位请求地址 base_url = "https://www.lagou.com/jobs/positionAjax.json?city=%E5%8C%97%E4%BA%AC&needAddtionalResult=false&isSchoolJob=0" #判断是否是第一次访问,第二次访问data的值不一样 if self.page == 1: first = 'true' else: first = 'false' data = { 'first':first, 'pn':self.page, 'kd':'python' } print('page:',self.page) #参数拼接及转码,生成是字符串格式, 注意:长度下面的headers用的到 data = parse.urlencode(data) #一定要比较每次page不一样的时候headers的各项的细微差别 这个很重要 也是能否爬取数据的关键 #在这里Content-Length,User-Agent的值相对来说比较重要 headers = { 'Accept': 'application/json, text/javascript, */*; q=0.01', # Accept-Encoding:gzip, deflate 'Accept-Language': 'zh-CN,zh;q=0.8', 'Connection': 'keep-alive', 'Content-Length': len(data), 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', 'Cookie': 'user_trace_token=20180310205250-ccfd21f6-5b57-4e04-b90c-5e547e18d391; LGUID=20180310205255-f3afa6e4-2461-11e8-a8b5-525400f775ce; hideSliderBanner20180305WithTopBannerC=1; X_HTTP_TOKEN=673c8ae0b29d830c65e9812a6aeeb211; ab_test_random_num=0; JSESSIONID=ABAAABAAADEAAFI0BD8484557BF60A48BF2BDD6AA4C5D33; _putrc=318C0D90043747B6123F89F2B170EADC; login=true; unick=%E5%BC%A0%E6%B3%A2; showExpriedIndex=1; showExpriedCompanyHome=1; showExpriedMyPublish=1; hasDeliver=0; gate_login_token=d46c3e3008cb0364e7b47d9d261956a39273c72d679a1b0eb644e03620c100fa; TG-TRACK-CODE=index_navigation; _gid=GA1.2.1883607132.1520686376; _ga=GA1.2.2068283511.1520686375; LGSID=20180310215122-1e408aca-246a-11e8-a8ed-525400f775ce; LGRID=20180310233852-22b0d3ee-2479-11e8-a921-525400f775ce; Hm_lvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1520686378,1520689884; Hm_lpvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1520696337; SEARCH_ID=458b8d44186948ceb472c3d662f08528; index_location_city=%E5%8C%97%E4%BA%AC', 'Host': 'www.lagou.com', 'Origin': 'https://www.lagou.com', 'Referer': 'https://www.lagou.com/jobs/list_python?city=%E5%8C%97%E4%BA%AC&cl=false&fromSearch=true&labelWords=&suginput=', "User-Agent": self.user_agent_str, 'X-Anit-Forge-Code': 0, 'X-Anit-Forge-Token': 'None', 'X-Requested-With': 'XMLHttpRequest' } req = request.Request(url=base_url,data=bytes(data,encoding='utf-8'),headers=headers) response = request.urlopen(req) html = response.read() html = html.decode('utf-8') #使用json格式化,生成一个字典,然后从字典里头取值就可以,下面就是取值的过程,想要啥就可以啥 json_data = json.loads(html) # print(json_data) positionResult = json_data['content']['positionResult'] # print(positionResult) self.result_list = positionResult['result'] print(self.result_list) self.workbook() def workbook(self): for result in self.result_list: # print(len(result)) # print(len(result)) # print(result) self.worksheet1(result) self.number += 1 print(self.number) print('~~~~~~~~~~~~~~~~~~~~~haha~~~~~~~~~~~~~~~~~~~~~~~') # self.workbook_attr.close() # print(self.number) def worksheet1(self,result): # print(self.worksheet,result,self.number) keys = list(result.keys()) if self.number == 0: self.keys_list = keys for i in range(len(keys)): # 向work中添加数据 def write(self, row, col, *args): # write第一个参数是行,第二个参数是列,第三个是要写入的参数名称 print(keys[i], type(keys[i]),i) self.worksheet.write(0, i, str(keys[i])) print('~~~~~~~~~~~~~~~~~~~~0~~~~~~~~~~~~~~~~~~~~~~~~~~~~~') values = [] for k in self.keys_list: values.append(result[k]) # print(type(keys)) # values = list(result.values()) # print(type(values)) for i in range(len(values)): # 向work中添加数据 def write(self, row, col, *args): # write第一个参数是行,第二个参数是列,第三个是要写入的参数名称 print(str(values[i]),i,len(values)) self.worksheet.write(self.number+1, i, str(values[i])) print('------------------------1-------------------------------') # workbook.close() if __name__ == '__main__': lagou_python = python_position(1,0)