编程语言
首页 > 编程语言> > python——提取pdf(将pdf文件转成txt)

python——提取pdf(将pdf文件转成txt)

作者:互联网

# -*- 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
# # os.chdir(r'F:\test')
# fp = open('s.pdf', 'rb')
# #来创建一个pdf文档分析器
# parser = PDFParser(fp)  
# #创建一个PDF文档对象存储文档结构
# document = PDFDocument(parser)
# # 检查文件是否允许文本提取
# if not document.is_extractable:
#     raise PDFTextExtractionNotAllowed
# else:
#     # 创建一个PDF资源管理器对象来存储共赏资源
#     rsrcmgr=PDFResourceManager()
#     # 设定参数进行分析
#     laparams=LAParams()
#     # 创建一个PDF设备对象
#     # device=PDFDevice(rsrcmgr)
#     device=PDFPageAggregator(rsrcmgr,laparams=laparams)
#     # 创建一个PDF解释器对象
#     interpreter=PDFPageInterpreter(rsrcmgr,device)
#     # 处理每一页
#     for page in PDFPage.create_pages(document):
#         interpreter.process_page(page)
#         # 接受该页面的LTPage对象
#         layout=device.get_result()
#         for x in layout:
#             if(isinstance(x,LTTextBoxHorizontal)):
#                 with open('h.txt','w') as f:
#                     f.write(str(x.get_text().encode('utf-8'))+"\n")
# print("process done")

#_*_coding:utf-8_*_
 
from pdfminer.pdfparser import  PDFParser
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfpage import PDFPage
from pdfminer.pdfdevice import PDFDevice
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import LTTextBoxHorizontal,LAParams
from pdfminer.pdfpage import PDFTextExtractionNotAllowed
 
 
def parse(Path,Save_name):
    
    parser = PDFParser(Path)
    document = PDFDocument(parser)
  
 
    if not document.is_extractable:
        raise PDFTextExtractionNotAllowed
    else:
        rsrcmgr = PDFResourceManager()
        laparams = LAParams()
        device = PDFPageAggregator(rsrcmgr,laparams=laparams)
        interpreter = PDFPageInterpreter(rsrcmgr,device)
 
        for page in PDFPage.create_pages(document):
            interpreter.process_page(page)
            layout = device.get_result()
            for x in layout:
                if(isinstance(x,LTTextBoxHorizontal)):
                    with open('%s'%(Save_name),'a') as f:
                        # results = x.get_text().encode('gbk')
                        results = x.get_text()
                        f.write(results)
 
if __name__ == '__main__':
    Path = open('s.pdf','rb')
    parse(Path,'1.txt')

 

标签:layout,laparams,python,rsrcmgr,pdfminer,device,pdf,import,txt
来源: https://www.cnblogs.com/shunguo/p/14533230.html