用Python爬取各大高校并可视化帮弟弟选大学,弟弟直呼牛X(数据可视化)

一、获取url

打开中国教育在线网，按 F12，顶部选择NetWork，选择XHR

刷新页面，观察url，通过对Reponse的分析找到真正的url为：https://api.eol.cn/gkcx/api/

数据存储在Json中。

再点击Headers，查看请求参数

请求方式为POST

二、发送请求

拿到url，我们就可以利用requests模拟浏览器发送请求，拿到返回的Json数据。代码如下：

# 导入包
import numpy as np
import pandas as pd
import requests
import json
from fake_useragent import UserAgent
import time
# 获取一页
def get_one_page(page_num):
 # 获取URL
 url = 'https://api.eol.cn/gkcx/api/'
 # 构造headers
 headers = {
  'User-Agent': UserAgent().random,
  'Origin': 'https://gkcx.eol.cn',
  'Referer': 'https://gkcx.eol.cn/school/search?province=&schoolflag=&recomschprop=',
 }
 # 构造data
 data = {
  'access_token': "",
  'admissions': "",
  'central': "",
  'department': "",
  'dual_class': "",
  'f211': "",
  'f985': "",
  'is_dual_class': "",
  'keyword': "",
  'page': page_num,
  'province_id': "",
  'request_type': 1,
  'school_type': "",
  'size': 20,
  'sort': "view_total",
  'type': "",
  'uri': "apigkcx/api/school/hotlists",
 }
 # 发起请求
 try:
  response = requests.post(url=url, data=data, headers=headers)
 except Exception as e:
  print(e) 
  time.sleep(3) 
  response = requests.post(url=url, data=data, headers=headers)

三、解析json数据

根据Response返回的Json格式，解析出我们想要的内容，代码如下：

# 解析获取数据
 school_data = json.loads(response.text)['data']['item']
 # 学校名
 school_name = [i.get('name') for i in school_data]
 # 隶属部门
 belong = [i.get('belong') for i in school_data]
 # 高校层次
 dual_class_name = [i.get('dual_class_name') for i in school_data]
 # 是否985
 f985 = [i.get('f985') for i in school_data]
 # 是否211
 f211 = [i.get('f211') for i in school_data]
 # 办学类型
 level_name = [i.get('level_name') for i in school_data]
 # 院校类型
 type_name = [i.get('type_name') for i in school_data]
 # 是否公办
 nature_name = [i.get('nature_name') for i in school_data]
 # 人气值
 view_total = [i.get('view_total') for i in school_data]
 # 省份
 province_name = [i.get('province_name') for i in school_data]
 # 城市
 city_name = [i.get('city_name') for i in school_data]
 # 区域
 county_name = [i.get('county_name') for i in school_data]
 
 # 保存数据
 df_one = pd.DataFrame({
  'school_name': school_name,
  'belong': belong,
  'dual_class_name': dual_class_name,
  'f985': f985,
  'f211': f211,
  'level_name': level_name,
  'type_name': type_name,
  'nature_name': nature_name,
  'view_total': view_total,
  'province_name': province_name,
  'city_name': city_name,
  'county_name': county_name,
 })
 return df_one

四、存入Excel

先将数据存入Pandas，用于做数据分析，再写入Excel存储。

# 获取多页
def get_all_page(all_page_num):
 # 存储表
 df_all = pd.DataFrame()
 # 循环页数
 for i in range(all_page_num):
  # 打印进度
  print(f'正在获取第{i + 1}页的高校信息')
  # 调用函数
  df_one = get_one_page(page_num=i+1)
  # 追加
  df_all = df_all.append(df_one, ignore_index=True)
  # 休眠
  time.sleep(np.random.uniform(2))
 return df_all

# 运行函数
df_school = get_all_page(all_page_num=143)
# 读出数据
df_school.to_excel('./data/全国高校数据.xlsx', index=False)