1. 從 PDF 中提取“表格結構”
2. 把每一行數(shù)據(jù)收集起來
3. 修復列數(shù)不一致的問題
4. 再導出為 Excel

import pdfplumber
import pandas as pd
import os
def pdf_to_excel(pdf_path, excel_path):
    all_rows = []
    # 打開 PDF
    with pdfplumber.open(pdf_path) as pdf:
        print(f"PDF共有 {len(pdf.pages)} 頁")
        # 遍歷每一頁
        for page_num, page in enumerate(pdf.pages, start=1):
            print(f"正在處理第 {page_num} 頁...")
            tables = page.extract_tables()
            if not tables:
                continue
            for table in tables:
                for row in table:
                    # 跳過全空行
                    if row and any(cell and cell.strip() for cell in row if isinstance(cell, str)):
                        all_rows.append(row)
    if not all_rows:
        print(" 未提取到任何表格數(shù)據(jù)")
        return
    # 計算最大列數(shù)
    max_cols = max(len(row) for row in all_rows)
    print(f"檢測到最大列數(shù)：{max_cols}")
    # 統(tǒng)一所有行的列數(shù)
    normalized_rows = []
    for row in all_rows:
        if len(row) < max_cols:
            row = row + [None] * (max_cols - len(row))
        elif len(row) > max_cols:
            row = row[:max_cols]
        normalized_rows.append(row)
    # 第一行作為表頭
    header = normalized_rows[0]
    data = normalized_rows[1:]
    # 去除重復表頭行
    clean_data = []
    for row in data:
        if row != header:
            clean_data.append(row)
    # 構建 DataFrame
    df = pd.DataFrame(clean_data, columns=header)
    # 清理空行、空列
    df = df.dropna(how='all').dropna(axis=1, how='all')
    # 導出 Excel
    df.to_excel(excel_path, index=False, engine='openpyxl')
    print("\n 轉換完成")
    print(f"Excel 文件路徑：{excel_path}")
    print(f"數(shù)據(jù)行數(shù)：{len(df)}")
    print(f"列數(shù)：{len(df.columns)}")
    print("列名：", list(df.columns))
    print("\n前 5 行數(shù)據(jù)預覽：")
    print(df.head())
if __name__ == "__main__":
    pdf_file = "Example.pdf"
    excel_file = "Result.xlsx"
    if not os.path.exists(pdf_file):
        print(f"找不到 PDF 文件：{pdf_file}")
    else:
        pdf_to_excel(pdf_file, excel_file)

import pdfplumber
import pandas as pd
import os

def pdf_to_excel(pdf_path, excel_path):

all_rows = []

with pdfplumber.open(pdf_path) as pdf:

if row and any(cell and cell.strip() for cell in row if isinstance(cell, str)):

max_cols = max(len(row) for row in all_rows)

不足的補 None，多的截斷

header = normalized_rows[0]

if row != header:
    clean_data.append(row)

職位代碼 | 職位名稱 | ...
職位代碼 | 職位名稱 | ...
職位代碼 | 職位名稱 | ...

df.to_excel(excel_path, index=False, engine='openpyxl')