爬取新浪财经现金流量表¶

股票代码：600357 / 600358 / 600359，保存到 D:\datasets。

In [1]:
import os
import csv
import requests
from bs4 import BeautifulSoup
In [2]:
save_dir = r'D:\datasets'
os.makedirs(save_dir, exist_ok=True)
headers = {'User-Agent': 'Mozilla/5.0'}
In [3]:
def download(stockid):
    url = f'https://money.finance.sina.com.cn/corp/go.php/vFD_CashFlow/stockid/{stockid}/ctrl/part/displaytype/4.phtml'
    r = requests.get(url, headers=headers, timeout=30)
    r.encoding = 'gb2312'
    soup = BeautifulSoup(r.text, 'html.parser')
    table = soup.find('table', id='ProfitStatementNewTable0')

    rows = []
    for tr in table.find_all('tr'):
        cells = [c.get_text(strip=True) for c in tr.find_all(['td', 'th'])]
        if cells:
            rows.append(cells)

    company = rows[0][0].split('(')[0]
    path = os.path.join(save_dir, f'{company}({stockid})  现金流量表.csv')
    with open(path, 'w', newline='', encoding='utf-8-sig') as f:
        csv.writer(f).writerows(rows)
    print('保存：', path)
In [4]:
for code in ['600357', '600358', '600359']:
    download(code)

保存： D:\datasets\承德钒钛(600357)  现金流量表.csv

保存： D:\datasets\国旅联合(600358)  现金流量表.csv

保存： D:\datasets\新农开发(600359)  现金流量表.csv