python读取pdf内容

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import pdfplumber
import time
from tqdm import tqdm
import pandas as pd

def get_balance_table(file):
    # 获取合并资产负债表内容
    start = 0
    ret=[]
    with pdfplumber.open(file) as pdf:      
        for page in pdf.pages:
            try:
                text = page.extract_text()
                if '合并资产负债表' in text and '编制单位' in text:
                    start = 1
                if start:
                    table = page.extract_table({
                        "vertical_strategy": "lines", 
                        "horizontal_strategy": "lines",
                        "explicit_vertical_lines": [],
                        "explicit_horizontal_lines": [],
                        "snap_tolerance": 3,
                        "join_tolerance": 3,
                        "edge_min_length": 3,
                        "min_words_vertical": 3,
                        "min_words_horizontal": 1,
                        "keep_blank_chars": False,
                        "text_tolerance": 3,
                        "text_x_tolerance": None,
                        "text_y_tolerance": None,
                        "intersection_tolerance": 1,
                        "intersection_x_tolerance": None,
                        "intersection_y_tolerance": None,
                    })
                    ret.extend(table)
                if '负债和所有者权益总计' in text and '所有者权益合计' in text:
                    break
            except Exception as e:
                print(e)
    return ret
    
if __name__ == "__main__":
    start_time = time.time()
    print("time start:%s"%(time.strftime("%Y-%m-%d %H:%M:%S",time.localtime(start_time))))
    data = get_balance_table("1.pdf")
    df = pd.DataFrame(data)
    df=df[df.iloc[:,0].notnull()]
    df.to_excel("1.xlsx")
    end_time = time.time()
    print("time end:%s"%(time.strftime("%Y-%m-%d %H:%M:%S",time.localtime(end_time))))
    print("take: %s S"%(int(end_time-start_time)))