Python爬取东方财富股票数据

   今天给你们带来了通过selenium获取东方财富股票数据实例，用于学习。 

1.基本完整实例：

from selenium import webdriverfrom bs4 import BeautifulSoup# 创建Chrome浏览器驱动对象driver = webdriver.Chrome()# 构建URLurl = 'http://quote.eastmoney.com/center/gridlist.html#hs_a_board'# 发起GET请求driver.get(url)# 等待页面加载完成driver.implicitly_wait(10)# 解析响应内容soup = BeautifulSoup(driver.page_source, 'html.parser')# 获取股票信息表格table = soup.select('.table_wrapper-table tbody')# 遍历每行数据for row in table[0].find_all('tr'): # 获取每列数据    columns = row.find_all('td') # 提取所需的股票信息 stock_name = columns[1].text h_share_code = columns[2].text hkd_price = columns[3].text change_percent = columns[4].text hk_stock_bar = columns[5].text a_share_code = columns[6].text rmb_price = columns[7].text a_change_percent = columns[8].text a_stock_bar = columns[9].text price_ratio = columns[10].text premium_percent = columns[11].text
# 打印股票信息 print('股票名称:', stock_name) print('H股代码:', h_share_code) print('最新价(HKD):', hkd_price) print('涨跌幅:', change_percent) print('港股吧:', hk_stock_bar) print('A股代码:', a_share_code) print('最新价(RMB):', rmb_price) print('涨跌幅(A股):', a_change_percent) print('A股吧:', a_stock_bar) print('比价（A/H）:', price_ratio) print('溢价（A/H）%:', premium_percent)    print('---------------------------------------')# 关闭浏览器driver.quit()

输出：---------------------------------------股票名称: 300538H股代码: 同益股份最新价(HKD): 股吧 资金流 数据涨跌幅: 23.01港股吧: 12.79%A股代码: 2.61最新价(RMB): 42.09万涨跌幅(A股): 9.55亿A股吧: 25.34%比价（A/H）: 24.48溢价（A/H）%: 19.31---------------------------------------

2.获取股票信息，跳页，保存到csv里：

import csvfrom selenium import webdriverfrom selenium.webdriver.chrome.options import Optionsfrom selenium.webdriver.common.by import Byfrom selenium.webdriver.support.ui import WebDriverWaitfrom selenium.webdriver.support import expected_conditions as ECfrom bs4 import BeautifulSoup
# 创建Chrome浏览器驱动选项对象chrome_options = Options()chrome_options.add_argument('--headless')chrome_options.add_argument('--disable-gpu')
# 创建Chrome浏览器驱动对象driver = webdriver.Chrome(options=chrome_options)
# 构建URLurl = 'http://quote.eastmoney.com/center/gridlist.html#hs_a_board'
# 发起GET请求driver.get(url)
# 等待页面加载完成wait = WebDriverWait(driver, 10)wait.until(EC.visibility_of_element_located((By.CSS_SELECTOR, '.table_wrapper-table')))
# 创建CSV文件csv_file = open('股票数据.csv', 'w', newline='', encoding='utf-8-sig')writer = csv.writer(csv_file)# 写入表头信息writer.writerow([ '股票名称', '沪股通代码', '港币价格', '涨跌幅', '港股通卖出价', 'A股代码', '人民币价格', '涨跌幅(A股)', 'A股卖出价', '价格比', '溢价率'])
while True: # 解析响应内容 soup = BeautifulSoup(driver.page_source, 'html.parser')
# 获取股票信息表格 table = soup.select('.table_wrapper-table tbody')
# 遍历每行数据 for row in table[0].find_all('tr'): # 获取每列数据 columns = row.find_all('td')
# 提取所需的股票信息 stock_name = columns[1].text h_share_code = columns[2].text hkd_price = columns[3].text change_percent = columns[4].text hk_stock_bar = columns[5].text a_share_code = columns[6].text rmb_price = columns[7].text a_change_percent = columns[8].text a_stock_bar = columns[9].text price_ratio = columns[10].text premium_percent = columns[11].text
# 写入CSV文件 writer.writerow([ stock_name, h_share_code, hkd_price, change_percent, hk_stock_bar, a_share_code, rmb_price, a_change_percent, a_stock_bar, price_ratio, premium_percent ])
# 查找下一页按钮 next_button = driver.find_element(By.CSS_SELECTOR, '.paginate_button.next')
# 判断下一页按钮是否可点击，如果不可点击，则表示已经是最后一页 if 'disabled' in next_button.get_attribute('class'): break
# 点击下一页按钮 next_button.click()
# 等待页面加载完成 wait.until(EC.visibility_of_element_located((By.CSS_SELECTOR, '.table_wrapper-table')))
# 关闭CSV文件csv_file.close()
# 关闭浏览器driver.quit()