en2cn/Utils/tb_data_extract.py

import pandas as pd
from pprint import pprint
from Words.Phrase_dict import en_dict_with_err_or_true_mean


path = r"G:\zwj\WL\en2cn\more_files\英译汉词汇非常见释义表.xlsx"

# df = pd.read_excel(path, sheet_name="批改错误词汇释义整理")
df = pd.read_excel(path, sheet_name="5-31")
# print(df.shape)
df = df.where(df.notnull(), "")
words = {}
for k, row in df.iterrows():
    res = {
            "err_mean": row["错误释义"] if row["错误释义"] else "",
            "true_mean": row["正确释义"] if row["正确释义"] else "",
            }
    if row["英语词汇"].strip() not in en_dict_with_err_or_true_mean:
        words[row["英语词汇"].strip()] = res
    elif en_dict_with_err_or_true_mean[row["英语词汇"].strip()] != res:
        print(row["英语词汇"].strip())
        print(res)
        print('=================================================')
pprint(words)