python_读取 doc,docx,pdf

Posted 2020-09-07

#!/usr/bin/env python
# -*- coding: utf-8 -*-
import docx

from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from cStringIO import StringIO

from win32com import client
import sys
reload(sys)
sys.setdefaultencoding(‘gb2312‘)

def readDocx(docxPath):
    fullText = []
    doc = docx.Document(docxPath)
    paras = doc.paragraphs
    for p in paras:
        fullText.append(p.text.strip())
    return ‘\n‘.join(fullText)
def readPdf(pdfPath):
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    codec = ‘utf-8‘
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
    fp = file(pdfPath, ‘rb‘)
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    password = ""
    maxpages = 0
    caching = True
    pagenos=set()
    for page in PDFPage.get_pages(fp, pagenos, maxpages=maxpages, password=password,caching=caching, check_extractable=True):
        interpreter.process_page(page)
    fp.close()
    device.close()
    str = retstr.getvalue()
    retstr.close()
    return str
def readDoc(docPath):
    fullText = []
    word = client.Dispatch(‘Word.Application‘)    
    # 打开一个已存在的文件
    doc = word.Documents.Open(docPath)
    #print doc.Content
    #print text
    doc.SaveAs(‘c:/temp.txt‘, 2)
    # 关闭
    doc.Close()
    word.Quit()
    f=open(r‘c:/temp.txt‘,‘r‘)  
    for line in f.readlines(): 
        #f len(line)!=line.count(‘\n‘):
        fullText.append(line.decode(‘gbk‘).strip())
    f.close()
    return ‘\n‘.join(fullText)
if __name__ == ‘__main__‘:
    #docxValue=readDocx(‘d:/1.docx‘)
    #print docxValue
    #pdfValue = readPdf(‘d:/3.pdf‘)
    #print pdfValue
    docValue = readDoc(‘d:/2.doc‘)
    print docValue