import requests from bs4 import beautifulsoup import pandas as pd url = "https://so.gushiwen.cn/gushi/tangshi.aspx" response = requests.get(url) soup = beautifulsoup(response.text, 'html.parser') # 提取所需数据 poems_data = [] for row in soup.find_all('tr', class_='tlist')[1:]: cols = row.find_all('td') type_ = cols.text.strip() title = cols.a.text.strip() content = cols.text.replace('\n', '').replace('\t', '') author = cols.text.strip() poems_data.append([type_, title, conte