Python爬取实时的贵金属行情

zzl_Kevin

已于 2024-03-26 11:31:49 修改

阅读量345

点赞数 5

分类专栏： Python爬取贵金属行情文章标签： python 开发语言爬虫网络爬虫

于 2024-03-25 16:20:24 首次发布

本文链接：https://blog.csdn.net/z1696853278/article/details/137017645

版权

Python爬取贵金属行情专栏收录该内容

4 篇文章 0 订阅

订阅专栏

本文介绍了如何使用Python的requests和BeautifulSoup库从中国工商银行新一代网上银行抓取贵金属的实时价格信息，包括名称、价格、涨跌幅等数据。

摘要由CSDN通过智能技术生成

原网址：中国工商银行新一代网上银行 (icbc.com.cn)

通过元素获取到表格对应的链接

开始，写了个字典存对应的中文名称，Python不是我的主力语言，而且很久没写了，所以写的很烂，此代码仅供学习研究，不要用于非法用途，否则后果自负

import requests
from bs4 import BeautifulSoup
import re
from datetime import datetime
# 用于发送请求的URL
url = 'https://mybank.icbc.com.cn/icbc/newperbank/perbank3/gold/futuresgold_query_out.jsp'

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,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
   'Cache-Control': 'max-age=0',
   'Connection': 'keep-alive',
   'Sec-Fetch-Dest': 'document',
   'Sec-Fetch-Mode': 'navigate',
   'Sec-Fetch-Site': 'none',
   'Sec-Fetch-User': '?1',
   'Upgrade-Insecure-Requests': '1',
   'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36 Edg/122.0.0.0',
   'sec-ch-ua': '"Chromium";v="122", "Not(A:Brand";v="24", "Microsoft Edge";v="122"',
   'sec-ch-ua-mobile': '?0',
   'sec-ch-ua-platform': '"Windows"',
   'Cookie': 'isP3bank=1; isEn_US=0; isPri=; firstZoneNo=%E5%B9%BF%E4%B8%9C_2000; arialoadData=true; ariawapChangeViewPort=true; CK_ISW_EBANKP_EBANKP-WEB-IPV6-NEW_80=bambfbmbegmbahnia-10|ZgEhV|ZgETe; sg___persistence__sugoio=%7B%22distinct_id%22%3A%20%2218e743d76de1b8-0c13ef4a74592f-4c657b58-186a00-18e743d76df2d63%22%7D'
}

gold_dict = {
    "Au(T+D)": "黄金T+D",
    "mAu(T+D)": "m黄金T+D",
    "Ag(T+D)": "白银T+D",
    "AuT+D": "黄金T+D",
    "mAuT+D": "m黄金T+D",
    "AgT+D": "白银T+D",
    "Au9999": "黄金9999",
    "Au9995": "黄金9995",
    "Au100g": "金条100g",
    "Au50g": "金条50g",
    "Ag999": "白银999",
    "AuT+N1": "黄金T+N1",
    "AuT+N2": "黄金T+N2",
    "SGiAu100g": "gi黄金100g",
    "SGiAu9999i": "i黄金9999",
    "SGiAu995i": "i黄金995",
    "Ag9999": "白银9999",
    "PT9995": "铂金9995",
    "NYAuTN06": "纽约金TN06",
    "NYAuTN12": "纽约金TN12",
}


# 发送请求并获取网页内容
response = requests.get(url)
web_content = response.text

# 使用BeautifulSoup解析网页内容
soup = BeautifulSoup(web_content, 'html.parser')

# 根据网页结构提取贵金属价格信息
# 这里假设价格信息在id为'TABLE1'的表格中
table = soup.find('table', {'id': 'resultTable'})
rows = table.find_all('tr')

# print(rows)
# 解析每一行，提取贵金属名称和价格
for i,row in enumerate(rows[1:-1]):  # 跳过表头
    cols = row.find_all('td')
    for x,col in enumerate(cols[:2]+cols[3:]):
        if x==0 :
            print("代码：" + col.text.strip())
            if col.text.strip() in gold_dict:
                print("名称："+gold_dict[col.text.strip()])
        elif x==1 :
            print("当前价：" + col.text.strip())
        elif x==2 :
            print("涨跌幅：" + col.text.strip())
        elif x==3 :
            print("成交量（手）：" + col.text.strip())
        elif x==4 :
            print("开盘价：" + col.text.strip())
        elif x==5 :
            print("昨收价：" + col.text.strip())
        elif x==6 :
            print("最高价：" + col.text.strip())
        elif x==7 :
            print("最低价：" + col.text.strip())
    print("\n")
        # print(col.text.strip())
        
time_element = soup.find('td', {'id': 'time'})
time_str = re.search(r'\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}', time_element.text).group()
# print(time_str)
update_time = datetime.strptime(time_str, '%Y-%m-%d %H:%M:%S')
formatted_time = update_time.strftime('%Y年%m月%d日 %H:%M:%S')
print("截止时间："+formatted_time)

运行结果：