from html_table_parser import HTMLTableParser def tableParse(value): p = HTMLTableParser() p.feed(value) print(p.tables)
import pandas as pd def framParse(value): soup=BeautifulSoup(value, 'html.parser') tables = soup.select('table') print(tables) df_list = [] for table in tables: print(pd.read_html(table.prettify())) df_list.append(pd.concat(pd.read_html(table.prettify()))) df = pd.concat(df_list) df.to_excel('vscode快捷键大全.xlsx')
以上两种方式均可以解析标准表格