blob: 502acc5544c3ef6f728471ce7d68d8ac5dbe53f4 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
|
#
# htmlStripper.py
#
# Sample code for stripping HTML markup tags and scripts from
# HTML source files.
#
# Copyright (c) 2006, Paul McGuire
#
from pyparsing import *
import urllib
removeText = replaceWith("")
scriptOpen,scriptClose = makeHTMLTags("script")
scriptBody = scriptOpen + SkipTo(scriptClose) + scriptClose
scriptBody.setParseAction(removeText)
anyTag,anyClose = makeHTMLTags(Word(alphas,alphanums+":_"))
anyTag.setParseAction(removeText)
anyClose.setParseAction(removeText)
htmlComment.setParseAction(removeText)
commonHTMLEntity.setParseAction(replaceHTMLEntity)
# get some HTML
targetURL = "http://wiki.python.org/moin/PythonDecoratorLibrary"
targetPage = urllib.urlopen( targetURL )
targetHTML = targetPage.read()
targetPage.close()
# first pass, strip out tags and translate entities
firstPass = (htmlComment | scriptBody | commonHTMLEntity |
anyTag | anyClose ).transformString(targetHTML)
# first pass leaves many blank lines, collapse these down
repeatedNewlines = LineEnd() + OneOrMore(LineEnd())
repeatedNewlines.setParseAction(replaceWith("\n\n"))
secondPass = repeatedNewlines.transformString(firstPass)
print secondPass
|
