import re
import pandas as pd
import pdfplumber
import glob
file = glob.glob(r'./发票/*.pdf', recursive=True)
data=[]
for i in file:
with pdfplumber.open(i) as pdf:
for page in pdf.pages:
df=page.extract_table()
df=df[-1][1].split("\n")
name=df[0][4:]
code=df[1][7:]
Bank=re.findall('[\u4e00-\u9fa5]+',str(df[3][7:]))[0]
account=re.findall('\d+',str(df[3][7:]))[0]
suju=[]
suju.append(name)
suju.append(code)
suju.append(Bank)
suju.append(account)
data.append(suju)
ff=pd.DataFrame(data,columns=("名称","统一信用编号","开户行","账号"))
ff.to_excel("保存文件名称.xlsx",index=False)
