利用python將pdf輸出為txt的實例講解

sudo pip install pdfminer;

# -*- coding: utf-8 -*-  
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 
fp = open('test.pdf', 'rb') 
#來創(chuàng)建一個pdf文檔分析器 
parser = PDFParser(fp) 
#創(chuàng)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(chuàng)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(chuàng)建一個PDF設備對象 
 # device=PDFDevice(rsrcmgr) 
 device=PDFPageAggregator(rsrcmgr,laparams=laparams) 
 # 創(chuàng)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)): 
    with open('output.txt','a') as f: 
     f.write(x.get_text().encode('utf-8')+'\n')