import pandas as pd

file3034 = r'/root/.openclaw/workspace-xiaoyan/business_knowledge/L2单词表/30-34.xlsx'
df3034 = pd.read_excel(file3034)

print("="*60)
print("30-34.xlsx 文件结构：")
print(f"行数: {len(df3034)}")
print(f"列数: {len(df3034.columns)}")
print("\n列名:")
for i, col in enumerate(df3034.columns):
    print(f"  列{i}: {col}")

print("\n前30行内容：")
print(df3034.head(30))

print("\n尝试找出包含单词的列...")
# 检查前几列中包含字母的内容
for col_idx in range(min(5, len(df3034.columns))):
    col_data = df3034.iloc[:, col_idx].dropna()
    # 统计包含字母的单元格数
    has_letter = col_data.apply(lambda x: any(c.isalpha() for c in str(x))).sum()
    print(f"列{col_idx}: 包含字母的单元格数 = {has_letter}")