[Python]HTML转换为TXT的脚本

舒畅

1 from formatter import AbstractFormatter, NullWriter
2 from htmllib import HTMLParser
3
4 def _(str, in_encoder="gbk", out_encoder="utf8"):
5 return unicode(str, in_encoder).encode(out_encoder)
6 7
8 class myWriter(NullWriter):
9 def __init__(self): 10 NullWriter.__init__(self)
11 self._bodyText = []
12
13 def send_flowing_data(self, str):
14 self._bodyText.append(str)
15
16 def _get_bodyText(self):
17 return '/n'.join(self._bodyText)
18
19 bodyText = property(_get_bodyText, None, None, 'plain text from body')
20
21 class myHTMLParser(HTMLParser):
22 def do_meta(self, attrs):
23 self.metas = attrs
24
25 def convertFile(filename):
26 mywriter = myWriter()
27 absformatter = AbstractFormatter(mywriter)
28 parser = myHTMLParser(absformatter)
29 parser.feed(open(filename).read())
30 return ( _(parser.title), parser.formatter.writer.bodyText )
31 32 import os 33 import os.path
34
35 OUTPUTDIR = "./txt" 36 INPUTDIR = "."
37 if __name__ == "__main__": 38 if not os.path.exists(OUTPUTDIR):
39 os.mkdir(OUTPUTDIR)
40
41 for file in os.listdir(INPUTDIR):
42 if file[-4:] == '.htm':
43 print "Coverting", file,
44 outfilename, text = convertFile(file)
45 outfilename = outfilename + '.txt'
46 outfullname = os.path.join(OUTPUTDIR, outfilename) 47 open(outfullname, "wt").write(text)
48 print "Done!"
49