import codecs import pandas as pd from bs4 import BeautifulSoup from BiddingKG.dl.interface.extract import predict def test(): df = pd.read_excel("has_table_no_attach.xlsx") for index, row in df.iterrows(): if index % 100 == 0: print("Loop", index) text = row['dochtmlcon'] predict(str(index), text) if __name__ == "__main__": test()