import requests
params={  ‘key1’:’value1’,  ‘key2’:’value2’,  ‘key3’:’value3’}html=requests.post(url,data=params)print(html.text)

import requestsurl='https://www.lagou.com'headers={   'cookie': 'xxx‘}html=requests.get(url,headers=headers)print(html.text)

def get_cookie():   # 原始網(wǎng)頁的URL,即url_start   url = 'https://www.lagou.com/jobs/list_%E6%95%B0%E6%8D%AE%E5%88%86%E6%9E%90?labelWords=&fromSearch=true&suginput='   s = requests.Session()   s.get(url, headers=headers, timeout=3)  # 請求首頁獲取cookies   cookie = s.cookies  # 為此次獲取的cookies   return cookie

import requestsimport jsonimport timeimport pandas as pd#import csv
headers = {   'origin': 'https://www.lagou.com',   'accept': 'xxxx',   'user-agent': 'xxxx',   'referer': 'xxxx'}
# 獲取cookies值def get_cookie():   # 原始網(wǎng)頁的URL,即url_start   url = 'https://www.lagou.com/jobs/list_%E6%95%B0%E6%8D%AE%E5%88%86%E6%9E%90?labelWords=&fromSearch=true&suginput='   s = requests.Session()   s.get(url, headers=headers, timeout=3)  # 請求首頁獲取cookies   cookie = s.cookies  # 為此次獲取的cookies   return cookie
# 定義獲取頁數(shù)的函數(shù)def get_page(url, params):   html = requests.post(url, data=params, headers=headers, cookies=get_cookie(), timeout=5)   # 將網(wǎng)頁的Html文件加載為json文件   json_data = json.loads(html.text)   # 解析json文件，后跟中括號為解析的路徑   total_Count = json_data['content']['positionResult']['totalCount']   page_number = int(total_Count/15) if int(total_Count/15) < 30 else 30   # 調(diào)用get_info函數(shù)，傳入url和頁數(shù)   get_info(url, page_number)
# 定義獲取招聘信息函數(shù)def get_info(url, page):   for pn in range(1, page+1):       # post請求參數(shù)       params = {           "first": "true",           "pn": str(pn),           "kd": "大數(shù)據(jù)"       }       # 獲取信息 并捕獲異常       try:           html = requests.post(url, data=params, headers=headers, cookies=get_cookie(), timeout=5)           #print(url, html.status_code)           # 將網(wǎng)頁的Html文件加載為json文件           json_data = json.loads(html.text)           # 解析json文件，后跟中括號為解析的路徑           results = json_data['content']['positionResult']['result']           df = pd.DataFrame(results)           #print(df.iloc[:,0:6])           if pn == 1:               total_df = df           else:               total_df = pd.concat([total_df,df],axis=0)           # 睡眠2秒           time.sleep(2)       except requests.exceptions.ConnectionError:           print("requests.exceptions.ConnectionError")           pass       #total_df.to_csv('招聘信息.csv', sep = ',', header = True, index = False)       total_df.to_excel('大數(shù)據(jù).xls',header=True, index=False)
# 原始網(wǎng)頁的URL#請求JSON數(shù)據(jù)的URLurl = "https://www.lagou.com/jobs/positionAjax.json?needAddtionalResult=false"params = {   "first": "true",   "pn": 1,   "kd": "大數(shù)據(jù)"}get_page(url,params)