002_027 Python 从微软Word文档中抽取文本

代码如下:

#encoding=utf-8

print '中国'

#从微软Word文档中抽取文本

import fnmatch, os, sys, win32com.client

readpath=r'D:\123'

wordapp = win32com.client.gencache.EnsureDispatch("Word.Application")
try:
    for path, dirs, files in os.walk(readpath):
        for filename in files:
            if not fnmatch.fnmatch(filename, '*.docx'):continue
            doc = os.path.abspath(os.path.join(path,filename))
            print 'processing %s...' % doc
            wordapp.Documents.Open(doc)
            docastext = doc[:-4] + 'txt'
            wordapp.ActiveDocument.SaveAs(docastext,FileFormat=win32com.client.constants.wdFormatText)
            wordapp.ActiveDocument.Close()
finally:
    wordapp.Quit()
    print 'end'

f=open(r'd:\123\test.txt','r')
for line in f.readlines():
    print line.decode('gbk')
f.close()

打印结果如下：

中国
processing D:\123\test.docx...
end
I love China


我爱中国