当前位置：首页 > article >正文

python解析网页上的json数据落地到EXCEL

article 2024/12/24 11:38:30

安装必要的库

import requests
import pandas as pd
import os
import sys
import io
import urllib3
import json

测试数据

网页上的数据结构如下

{
    "success": true,
    "code": "CIFM_0000",
    "encode": null,
    "message": "ok",
    "url": null,
    "total": 3,
    "items": [
        {
            "summaryDate": "20240611",
            "summaryType": "naturalDay",
            "workday": true,
            "newCustNum": 1,
            "haveCustNum": 1691627,
            "newAccountNum": 2,
            "haveAccountNum": 1692934,
            "totalShare": 4947657341.69,
            "netCash": -3523387.25,
            "yield": 0.01386
        },
        {
            "summaryDate": "20240612",
            "summaryType": "naturalDay",
            "workday": true,
            "newCustNum": 5,
            "haveCustNum": 1672766,
            "newAccountNum": 5,
            "haveAccountNum": 1674071,
            "totalShare": 4927109080.29,
            "netCash": -20735233.55,
            "yield": 0.01387
        },
        {
            "summaryDate": "20240613",
            "summaryType": "naturalDay",
            "workday": true,
            "newCustNum": 4,
            "haveCustNum": 1662839,
            "newAccountNum": 5,
            "haveAccountNum": 1664146,
            "totalShare": 4927405885.59,
            "netCash": 110659.8,
            "yield": 0.01389
        }
    ],
    "data": null,
    "info": null
}

详细逻辑代码

import requests
import pandas as pd
import os
import sys
import io
import urllib3
import json

urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')

url = "https://ip/ma/web/trade/dailySummary?startDate={pi_startdate}&endDate={pi_enddate}"
headers = {
    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
    "Accept-Language": "zh-CN,zh;q=0.9",
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36 Edg/119.0.0.0",
}

def save_data(data, columns, excel_path, sheet_name):
    df = pd.DataFrame(data, columns=columns)
    if not os.path.exists(excel_path):
        df.to_excel(excel_path, sheet_name=sheet_name, index=False)
    else:
        with pd.ExcelWriter(excel_path, engine='openpyxl', mode='a') as writer:
            df.to_excel(writer, sheet_name=sheet_name, index=False)

def json2list(response_text):
    # 把json数据转化为python用的类型
    json_dict = json.loads(response_text)
    src_total = json_dict["total"]
    print("src_total: {}".format(src_total))
    items = json_dict["items"]
    excel_columns = ['summaryDate',
                     'summaryType',
                     'workday',
                     'newCustNum',
                     'haveCustNum',
                     'newAccountNum',
                     'haveAccountNum',
                     'totalShare',
                     'netCash',
                     'yield'
                     ]
    excel_data = []
    # 使用XPath定位元素并打印内容
    for item in items:
        excel_row_data = []
        for column_index in range(len(excel_columns)):
            data = str(item[excel_columns[column_index]])
            if excel_columns[column_index] == 'workday':
                data = str(0 if data == "False" else 1)
            excel_row_data.append(data)
        excel_data.append(excel_row_data)
    trg_total = len(excel_data)
    # 稽核
    print("trg_total: {}".format(trg_total))
    vn_biasval = trg_total - src_total
    if vn_biasval != 0:
        print("This audit-rule is not passed,diff: {}".format(vn_biasval))
        exit(-1)
    else:
        print("This audit-rule is passed,diff: {}".format(vn_biasval))
    return excel_columns, excel_data


if __name__ == '__main__':
    try:
        excel_path = "C:/xxx/temp/ylb_dailySummary_{pi_startdate}_{pi_enddate}.xlsx"
        sheet_name = 'result_data'
        pi_startdate = 20240611
        pi_enddate = 20240613
        excel_path = excel_path.format(pi_startdate=pi_startdate, pi_enddate=pi_enddate)
        url = url.format(pi_startdate=pi_startdate, pi_enddate=pi_enddate)
        print("url:{}".format(url))
        print("excel_path:{}".format(excel_path))
        response_text = requests.get(url, headers=headers, timeout=(21, 300), verify=False).content.decode("utf8")
        excel_columns, excel_data = json2list(response_text)
        print("=================excel_columns=======================")
        print(excel_columns)
        print("=================excel_data==========================")
        for x in excel_data:
            print(x)
        print("=====================================================")
        # 文件存在，则删除
        if os.path.exists(excel_path):
            os.remove(excel_path)
        # 保存文件
        save_data(excel_data, excel_columns, excel_path, sheet_name)
        print("save_data is end.")
    except Exception as e:
        print("[ERROR]：" + str(e))
        exit(-1)

代码解析

请求头
构造请求头

urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')

url = "https://ip/ma/web/trade/dailySummary?startDate={pi_startdate}&endDate={pi_enddate}"
headers = {
    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
    "Accept-Language": "zh-CN,zh;q=0.9",
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36 Edg/119.0.0.0",
}

数据保存到excel
如果excel已经存在，那么则会将数据追加到excel中

def save_data(data, columns, excel_path, sheet_name):
    df = pd.DataFrame(data, columns=columns)
    if not os.path.exists(excel_path):
        df.to_excel(excel_path, sheet_name=sheet_name, index=False)
    else:
        with pd.ExcelWriter(excel_path, engine='openpyxl', mode='a') as writer:
            df.to_excel(writer, sheet_name=sheet_name, index=False)

解析json数据获取字段名称以及对应的数据list列表

def json2list(response_text):
    # 把json数据转化为python用的类型
    json_dict = json.loads(response_text)
    src_total = json_dict["total"]
    print("src_total: {}".format(src_total))
    items = json_dict["items"]
    excel_columns = ['summaryDate',
                     'summaryType',
                     'workday',
                     'newCustNum',
                     'haveCustNum',
                     'newAccountNum',
                     'haveAccountNum',
                     'totalShare',
                     'netCash',
                     'yield'
                     ]
    excel_data = []
    # 使用XPath定位元素并打印内容
    for item in items:
        excel_row_data = []
        for column_index in range(len(excel_columns)):
            data = str(item[excel_columns[column_index]])
            if excel_columns[column_index] == 'workday':
                data = str(0 if data == "False" else 1)
            excel_row_data.append(data)
        excel_data.append(excel_row_data)
    trg_total = len(excel_data)
    # 稽核
    print("trg_total: {}".format(trg_total))
    vn_biasval = trg_total - src_total
    if vn_biasval != 0:
        print("This audit-rule is not passed,diff: {}".format(vn_biasval))
        exit(-1)
    else:
        print("This audit-rule is passed,diff: {}".format(vn_biasval))
    return excel_columns, excel_data