python pdfplumber库批量提取pdf表格数据转换为excel

pip install pdfplumber

import pdfplumber
import pandas as pd

pdf = pdfplumber.open("/Users/wangwangyuqing/Desktop/1.pdf")
pages = pdf.pages

if len(pages) > 1:
    tables = []
    for each in pages:
        table = each.extract_table()
        tables.extend(table)
else:
    tables = each.extract_table()
data = pd.DataFrame(tables[1:], columns=tables[0])
data
data.to_excel("/Users/wangwangyuqing/Desktop/1.xlsx", index=False)

import os
import glob
path = r'/Users/wangwangyuqing/Desktop/pdf文件'
for f in glob.glob(os.path.join(path, "*.pdf")):
    res = save_pdf_to_excel(f)
    print(res)
def save_pdf_to_excel(path):
    #     print('文件名为：',path.split('/')[-1].split('.')[0] + '.xlsx')
    pdf = pdfplumber.open(path)
    pages = pdf.pages
    if len(pages) > 1:
        tables = []
        for each in pages:
            table = each.extract_table()
            tables.extend(table)
    else:
        tables = each.extract_table()
    data = pd.DataFrame(tables[1:], columns=tables[0])
    file_name = path.split('/')[-1].split('.')[0] + '.xlsx'
    data.to_excel("/Users/wangwangyuqing/Desktop/data/{}".format(file_name), index=False)
    return '保存成功！'