Python对pdf中的关键字过滤（pdfminer3k或pdfminer使用）

Z时代
2024-01-10
分类：综合

python

最近在实习，老板一下子发给了我120份研报，然而很多都是没用的。聪明的大脑一定要想办法让电脑帮助自己完成简单的工作！

下面是Python筛选含有“”丙烯“”关键字的程序，由于文件的保密性只能贴出代码。

注意：

pip install pdfminer3k而不是pdfminer
导入的时候名字是pdfminer，原因我才是python版本的问题

# -*- coding: utf-8 -*-
"""
Created on Fri May 10 16:54:16 2019
@author: didi.lv
"""
import os
from io import StringIO
import shutil
# 注意：一定要pip install pdfminer3k 而不是pdfminer
from pdfminer.pdfinterp import PDFResourceManager, process_pdf
from pdfminer.converter import TextConverter
from pdfminer.layout import  LAParams
# 读取pdf的函数，返回内容
def readPdf(pdf_file):
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    laparams = LAParams()
    device = TextConverter(rsrcmgr=rsrcmgr, outfp=retstr, laparams=laparams)
    process_pdf(rsrcmgr=rsrcmgr, device=device, fp=pdf_file)
    device.close()
    content = retstr.getvalue()
    retstr.close()
    return content
def file_name(file_dir):   
    names = []
    for root, dirs, files in os.walk(file_dir):
        names.append(files)
    return files
if __name__ == '__main__':
    file_dir = r'C:\\Users\didi.lv\Desktop\filenames'
    file_names_str = str(file_name(file_dir))
    name_ = file_names_str.split('.pdf\', ')
# 简单的check下这个代码的细节，需要理解
    name_temp1 = name_[0]
    name_[0] = name_temp1[1:]
    name_temp2 = name_[-1]
    name_[-1] = name_temp2[0:-6] 
    i = 0
    for name_check in name_[48:]:
        print('--------------------------------------------------------')
        i += 1
        print(i)
        name_check = name_check[1:]
        name_check += '.pdf'
        name_check_open = r'C:\\Users\didi.lv\Desktop\filenames' + '\\' + name_check
        pdf_file = open(name_check_open, 'rb')
        content = readPdf(pdf_file)
        if '丙烯' in content:
        # 注意这里是从原始位置filenames1复制到目标位置filenames2
            file_origin = r'C:\\Users\didi.lv\Desktop\filenames1' + '\\' + name_check
            file_target = r'C:\\Users\didi.lv\Desktop\filenames2' + '\\' + name_check
            shutil.copyfile(file_origin,file_target)
            print('copy No. %d file' %i)