标签：xlsx input 记录 file import pdf name
import tkinter.filedialog
import pandas as pd
import os
import pdfplumber
import tkinter
class PdfReader:
# output_file = tkinter.filedialog.asksaveasfile(title='保存到', initialfile=f"{name}.xlsx", filetypes=[("excel文件", ".xlsx")])
@staticmethod
def catch(input_file):
with pdfplumber.open(input_file) as pdf:
# 提取文件名，父目录地址
name = input_file.split('/')[-1][:-4]
path = os.path.dirname(input_file)
# 抓取pdf表格
pages = pdf.pages
writer = pd.ExcelWriter(os.path.join(path, f'{name}.xlsx'))
count = 1
for page in pages:
table = page.extract_table()
# 生成结果
df = pd.DataFrame(columns=range(len(table[0])), data=table)
df.to_excel(writer, sheet_name=f'Sheet{count}', index=None)
count += 1
writer.close()
def process(self):
input_files = tkinter.filedialog.askopenfilenames(title='选择转化文件')
for i in input_files:
try:
self.catch(input_file=i)
print(i, '转化成功')
except:
print(i, '转化失败')
if __name__ == '__main__':
PdfReader().process()
标签：xlsx,
input,
记录,
file,
import,
pdf,
name
From： https://www.cnblogs.com/AZ26/p/18216858