python讀取PDF文件內容

import os
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfpage import PDFPage
from pdfminer.pdfpage import PDFTextExtractionNotAllowed
from pdfminer.pdfinterp import PDFResourceManager
from pdfminer.pdfinterp import PDFPageInterpreter
from pdfminer.pdfdevice import PDFDevice
from pdfminer.layout import *
from pdfminer.converter import PDFPageAggregator


import os
import pdb

#inputFile = r'D:\用戶目錄\桌面\340xxxxxxxxxxxxxxxxxx0.pdf'


def decode_text(s):
    """
    Decodes a PDFDocEncoding string to Unicode.
    Adds py3 compatability to pdfminer's version.
    """
    if type(s) == bytes and s.startswith(b'\xfe\xff'):
        return six.text_type(s[2:], 'utf-16be', 'ignore')
    else:
        ords = (ord(c) if type(c) == str else c for c in s)
        return ''.join(PDFDocEncoding[o] for o in ords)



def get_msgs(inputFile):
    msgs = []
    fp = open(inputFile, 'rb')
    #來創建一個pdf文檔分析器
    parser = PDFParser(fp)  
    #創建一個PDF文檔對象存儲文檔結構
    document = PDFDocument(parser)
    # 檢查文件是否允許文本提取
    if not document.is_extractable:
        raise PDFTextExtractionNotAllowed
    else:
        # 創建一個PDF資源管理器對象來存儲共賞資源
        rsrcmgr=PDFResourceManager()
        # 設定參數進行分析
        laparams=LAParams()
        # 創建一個PDF設備對象
        # device=PDFDevice(rsrcmgr)
        device=PDFPageAggregator(rsrcmgr,laparams=laparams)
        # 創建一個PDF解釋器對象
        interpreter=PDFPageInterpreter(rsrcmgr,device)
     
        # 處理每一頁
        for page in PDFPage.create_pages(document):
     
            interpreter.process_page(page)
     
            # 接受該頁面的LTPage對象
            layout=device.get_result()
     
            for x in layout:
                
                if(isinstance(x,LTTextBoxHorizontal)):
                    #print(x.get_text().strip())
                    
                    msgs.append(x.get_text().strip())
                    
        return msgs
                   


    #print(msgs[5][5:]+ '\t' + msgs[4][4:])
    


if __name__ == "__main__":
    names = os.listdir('.')
    for i in names:
        if os.path.splitext(i)[-1] == '.pdf':
            #print(i)
            msg = get_msgs(i)
            #print(msg)
            ms = msg[5][5:]+ '\t' + msg[4][4:]
            with open('學生信息表.txt','a') as f:
                f.write(ms+'\n')