diff options
| author | Cengiz Kaygusuz <cngkaygusuz@gmail.com> | 2017-11-20 20:46:39 -0500 |
|---|---|---|
| committer | Cengiz Kaygusuz <cngkaygusuz@gmail.com> | 2017-11-20 20:46:39 -0500 |
| commit | 27e183a78c8062ed7c2bbb91655a5e56cd697bba (patch) | |
| tree | 88fd355a0cc6da4c130582e092d702836596cbb2 /examples/htmlStripper.py | |
| parent | 4ba589cf13588e90992e23deb5a9784340efd2cc (diff) | |
| download | pyparsing-git-27e183a78c8062ed7c2bbb91655a5e56cd697bba.tar.gz | |
Move src to root
Diffstat (limited to 'examples/htmlStripper.py')
| -rw-r--r-- | examples/htmlStripper.py | 32 |
1 files changed, 32 insertions, 0 deletions
diff --git a/examples/htmlStripper.py b/examples/htmlStripper.py new file mode 100644 index 0000000..1d7a0f0 --- /dev/null +++ b/examples/htmlStripper.py @@ -0,0 +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 = "http://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)
\ No newline at end of file |