使用Python爬取NSE 52周新高数据表遇阻，求技术支持

方法一：直接下载CSV文件（最便捷） #

NSE提供了直接获取数据的API接口，无需爬取页面，直接请求即可拿到CSV格式数据：

import requests

# 52周新高数据接口
url_high = "https://www.nseindia.com/api/52-week-high-low?index=equities"
# 52周新低数据接口
url_low = "https://www.nseindia.com/api/52-week-high-low?index=equities&type=low"

# 添加请求头，避免被拦截
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36'
}

# 下载并保存新高数据
response_high = requests.get(url_high, headers=headers)
with open('nse_52week_high.csv', 'wb') as f:
    f.write(response_high.content)

# 下载并保存新低数据
response_low = requests.get(url_low, headers=headers)
with open('nse_52week_low.csv', 'wb') as f:
    f.write(response_low.content)

方法二：用Selenium+BeautifulSoup爬取页面表格 #

如果需要从页面爬取表格，需等待页面动态加载完成后再解析，修正后的代码如下：

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from bs4 import BeautifulSoup
import pandas as pd

# 初始化Chrome浏览器（需确保ChromeDriver与Chrome版本匹配）
driver = webdriver.Chrome()
driver.get("https://www.nseindia.com/market-data/52-week-high-low")

# 等待表格加载完成（最多等待10秒）
wait = WebDriverWait(driver, 10)
wait.until(EC.presence_of_element_located((By.CLASS_NAME, 'equity-table')))

# 解析页面源码中的表格
soup = BeautifulSoup(driver.page_source, 'html.parser')
table = soup.find('table', class_='equity-table')

# 转换为DataFrame并输出
df = pd.read_html(str(table))[0]
print(df.head())

# 保存为CSV文件
df.to_csv('nse_52week_table.csv', index=False)

# 关闭浏览器
driver.quit()

注意事项 #

• 确保ChromeDriver版本与本地Chrome浏览器版本一致，否则会启动失败
• 可添加--headless=new参数启用无头模式，避免弹出浏览器窗口：

  from selenium.webdriver.chrome.options import Options
  options = Options()
  options.add_argument('--headless=new')
  driver = webdriver.Chrome(options=options)
  

内容的提问来源于stack exchange，提问作者Jaya Vamshi