爬取手机型号数据

import requests
import os
import time
import pandas as pd

# url = 'http://model.super202.cn/' # 网站门户地址
url = 'http://model.super202.cn/getJixingData.html' # 动态公共链接



headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.0.0 Safari/537.36'
}


def craw_table(page,limit):
    params = {
        'page': page,
        'limit':limit
    }

    resp = requests.get(url,headers = headers,params = params)
    resp.encoding = 'utf-8'
    data = resp.json()["data"]
    df = pd.DataFrame(data)
    df = df[['id', 'pinpai', 'name', 'wangluo', 'jixing']]
    return df

df_list  = []

for page in range(1,11):
    print("正在爬取第%s页"%page)
    df = craw_table(page,50)
    '''合并多个dateframe'''
    df_list.append(df)
    time.sleep(1)
data = pd.concat(df_list)
print(data.tail())
os.chdir(r'C:\Users\DELL\Desktop')
data.to_csv('手机型号对照表.csv',encoding='utf-8-sig') # ,encoding='utf-8-sig'

# 查看尾页
print(data.tail())

# df = craw_table(2015,10)

# df_list  = []
# for page in range(1,11):
#     print("爬取第%s页："%page)
#     df = craw_table(page)
#     '''合并多个dateframe'''
#     df_list.append(df)
#
# if __name__ == '__main__':
#     os.chdir(r'C:\Users\DELL\Desktop')
#     data = pd.concat(df_list)
#     data.to_excel('手机型号对照表.xlsx',index  =False)

resp.json() 后：