Fixed dict structure in makeHTMLTags expressions, and added tag_body attribute to the generated start expression giving easy access to a SkipTo(closeTag) that will parse the tag's body text; some code cleanup and removed duplication among examples

1 files changed, 32 insertions, 32 deletions

diff --git a/examples/htmlStripper.py b/examples/htmlStripper.py
index c3dbcf1..18f3395 100644
--- a/examples/htmlStripper.py
+++ b/examples/htmlStripper.py
@@ -1,32 +1,32 @@
-#

-# htmlStripper.py

-#

-#  Sample code for stripping HTML markup tags and scripts from

-#  HTML source files.

-#

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

-#

-from contextlib import closing

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

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

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

-

-scriptOpen,scriptClose = makeHTMLTags("script")

-scriptBody = scriptOpen + SkipTo(scriptClose) + scriptClose

-commonHTMLEntity.setParseAction(replaceHTMLEntity)

-

-# get some HTML

-targetURL = "https://wiki.python.org/moin/PythonDecoratorLibrary"

-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 |

-             anyOpenTag | anyCloseTag ).suppress().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)

+#
+# htmlStripper.py
+#
+#  Sample code for stripping HTML markup tags and scripts from
+#  HTML source files.
+#
+# Copyright (c) 2006, 2016, Paul McGuire
+#
+from contextlib import closing
+import urllib.request, urllib.parse, urllib.error
+from pyparsing import (makeHTMLTags, commonHTMLEntity, replaceHTMLEntity,
+    htmlComment, anyOpenTag, anyCloseTag, LineEnd, OneOrMore, replaceWith)
+
+scriptOpen, scriptClose = makeHTMLTags("script")
+scriptBody = scriptOpen + scriptOpen.tag_body + scriptClose
+commonHTMLEntity.setParseAction(replaceHTMLEntity)
+
+# get some HTML
+targetURL = "https://wiki.python.org/moin/PythonDecoratorLibrary"
+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 |
+             anyOpenTag | anyCloseTag ).suppress().transformString(targetHTML)
+
+# first pass leaves many blank lines, collapse these down
+repeatedNewlines = LineEnd()*(2,)
+repeatedNewlines.setParseAction(replaceWith("\n\n"))
+secondPass = repeatedNewlines.transformString(firstPass)
+
+print(secondPass)