Python把PDF表格完整转换成Excel的小白教程

1. 从 PDF 中提取“表格结构”
2. 把每一行数据收集起来
3. 修复列数不一致的问题
4. 再导出为 Excel

import pdfplumber
import pandas as pd
import os
def pdf_to_excel(pdf_path, excel_path):
    all_rows = []
    # 打开 PDF
    with pdfplumber.open(pdf_path) as pdf:
        print(f"PDF共有 {len(pdf.pages)} 页")
        # 遍历每一页
        for page_num, page in enumerate(pdf.pages, start=1):
            print(f"正在处理第 {page_num} 页...")
            tables = page.extract_tables()
            if not tables:
                continue
            for table in tables:
                for row in table:
                    # 跳过全空行
                    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(" 未提取到任何表格数据")
        return
    # 计算最大列数
    max_cols = max(len(row) for row in all_rows)
    print(f"检测到最大列数：{max_cols}")
    # 统一所有行的列数
    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)
    # 第一行作为表头
    header = normalized_rows[0]
    data = normalized_rows[1:]
    # 去除重复表头行
    clean_data = []
    for row in data:
        if row != header:
            clean_data.append(row)
    # 构建 DataFrame
    df = pd.DataFrame(clean_data, columns=header)
    # 清理空行、空列
    df = df.dropna(how='all').dropna(axis=1, how='all')
    # 导出 Excel
    df.to_excel(excel_path, index=False, engine='openpyxl')
    print("\n 转换完成")
    print(f"Excel 文件路径：{excel_path}")
    print(f"数据行数：{len(df)}")
    print(f"列数：{len(df.columns)}")
    print("列名：", list(df.columns))
    print("\n前 5 行数据预览：")
    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)

不足的补 None，多的截断

header = normalized_rows[0]

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

职位代码 | 职位名称 | ...
职位代码 | 职位名称 | ...
职位代码 | 职位名称 | ...

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