Update to new pyparsing and Python features

git-svn-id: svn://svn.code.sf.net/p/pyparsing/code/trunk@417 9bf210a0-9d2d-494c-87cf-cfb32e7dff7b

1 files changed, 7 insertions, 14 deletions

diff --git a/src/examples/htmlStripper.py b/src/examples/htmlStripper.py
index 0b0f459..1d7a0f0 100644
--- a/src/examples/htmlStripper.py
+++ b/src/examples/htmlStripper.py
@@ -4,32 +4,25 @@
 #  Sample code for stripping HTML markup tags and scripts from 

 #  HTML source files.

 #

-# Copyright (c) 2006, Paul McGuire

+# Copyright (c) 2006, 2016, Paul McGuire

 #

-from pyparsing import *

+from contextlib import closing

 import urllib.request, urllib.parse, urllib.error

+from pyparsing import (makeHTMLTags, SkipTo, commonHTMLEntity, replaceHTMLEntity, 

+    htmlComment, anyOpenTag, anyCloseTag, LineEnd, OneOrMore, replaceWith)

 

-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.request.urlopen( targetURL )

-targetHTML = targetPage.read()

-targetPage.close()

+with closing(urllib.request.urlopen( targetURL )) as targetPage:

+    targetHTML = targetPage.read().decode("UTF-8")

 

 # first pass, strip out tags and translate entities

 firstPass = (htmlComment | scriptBody | commonHTMLEntity | 

-             anyTag | anyClose ).transformString(targetHTML)

+             anyOpenTag | anyCloseTag ).suppress().transformString(targetHTML)

 

 # first pass leaves many blank lines, collapse these down

 repeatedNewlines = LineEnd() + OneOrMore(LineEnd())