python批量提取word内信息

372次阅读  |  发布于5年以前

单位收集了很多word格式的调查表,领导需要收集表单里的信息,我就把所有调查表放一个文件里,写了个python小程序把所需的信息打印出来


    #coding:utf-8

    import os
    import win32com
    from win32com.client import Dispatch, constants
    from docx import Document

    def parse_doc(f):
      """读取doc,返回姓名和行业
      """
      doc = w.Documents.Open( FileName = f )
      t = doc.Tables[0] # 根据文件中的图表选择信息
      name = t.Rows[0].Cells[1].Range.Text  
      situation = t.Rows[0].Cells[5].Range.Text
      people = t.Rows[1].Cells[1].Range.Text
      title = t.Rows[1].Cells[3].Range.Text  
      print name, situation, people,title
      doc.Close()

    def parse_docx(f):
      """读取docx,返回姓名和行业
      """
      d = Document(f)
      t = d.tables[0]
      name = t.cell(0,1).text
      situation = t.cell(0,8).text
      people = t.cell(1,2).text
      title = t.cell(1,8).text
      print name, situation, people,title


    if __name__ == "__main__":

      w = win32com.client.Dispatch('Word.Application')

      # 遍历文件
      PATH = "H:\work\\aaa" # windows文件路径
      doc_files = os.listdir(PATH)
      for doc in doc_files:
        if os.path.splitext(doc)[1] == '.docx':
          try:
            parse_docx(PATH+'\\'+doc)
          except Exception as e:
            print e
        elif os.path.splitext(doc)[1] == '.doc':
          try:
            parse_doc(PATH+'\\'+doc)
          except Exception as e:
            print e

下载安装win32com


    from win32com import client as wc
     word = wc.Dispatch('Word.Application')
     doc = word.Documents.Open('c:/test')
     doc.SaveAs('c:/test.text', 2)
     doc.Close()
     word.Quit()

这种方式产生的text文档,不能用python用普通的r方式读取,为了让python可以用r方式读取,应当写成
doc.SaveAs('c:/test', 4)
注意:系统执行完成后,会自动产生文件后缀txt(虽然没有指明后缀)。
在xp系统下面,应当,


     open(r'c:\text','r')
    wdFormatDocument = 0 wdFormatDocument97 = 0 wdFormatDocumentDefault = 16 wdFormatDOSText = 4 wdFormatDOSTextLineBreaks = 5 wdFormatEncodedText = 7 wdFormatFilteredHTML = 10 wdFormatFlatXML = 19 wdFormatFlatXMLMacroEnabled = 20 wdFormatFlatXMLTemplate = 21 wdFormatFlatXMLTemplateMacroEnabled = 22 wdFormatHTML = 8 wdFormatPDF = 17 wdFormatRTF = 6 wdFormatTemplate = 1 wdFormatTemplate97 = 1 wdFormatText = 2 wdFormatTextLineBreaks = 3 wdFormatUnicodeText = 7 wdFormatWebArchive = 9 wdFormatXML = 11 wdFormatXMLDocument = 12 wdFormatXMLDocumentMacroEnabled = 13 wdFormatXMLTemplate = 14 wdFormatXMLTemplateMacroEnabled = 15 wdFormatXPS = 18 

照着字面意思应该能对应到相应的文件格式,如果你是office 2003可能支持不了这么多格式。word文件转html有两种格式可选wdFormatHTML、wdFormatFilteredHTML(对应数字 8、10),区别是如果是wdFormatHTML格式的话,word文件里面的公式等ole对象将会存储成wmf格式,而选用 wdFormatFilteredHTML的话公式图片将存储为gif格式,而且目测可以看出用wdFormatFilteredHTML生成的HTML 明显比wdFormatHTML要干净许多。

当然你也可以用任意一种语言通过com来调用office API,比如PHP.


    from win32com import client as wc

     word = wc.Dispatch('Word.Application')

     doc = word.Documents.Open(r'c:/test1.doc')

     doc.SaveAs('c:/test1.text', 4)

     doc.Close()
     import re
     strings=open(r'c:\test1.text','r').read()
     result=re.findall('\(\s*[A-D]\s*\)|\(\xa1*[A-D]\xa1*\)|\(\s*[A-D]\s*\)|\(\xa1*[A-D]\xa1*\)',strings)
     chan=re.sub('\(\s*[A-D]\s*\)|\(\xa1*[A-D]\xa1*\)|\(\s*[A-D]\s*\)|\(\xa1*[A-D]\xa1*\)','()',strings)
     question=open(r'c:\question','a+')
     question.write(chan)
     question.close()
     answer=open(r'c:\answeronly','a+')
     for i,a in enumerate(result):
      m=re.search('[A-D]',a)
      answer.write(str(i+1)+' '+m.group()+'\n')
     answer.close()
    chan=re.sub(r'\xa3\xa8\s*[A-D]\s*\xa3\xa9','()',strings) #不要(),容易引起歧义。

Copyright© 2013-2020

All Rights Reserved 京ICP备2023019179号-8