# HG changeset patch
# User Jeff Hammel <k0scist@gmail.com>
# Date 1457382124 28800
# Node ID cb1b91c6bcebe615093e1733229d4af921b6d2c9
# Parent  489204193cd7c19132044bb859c4910f757bf36f
example program for HTML -> text conversion using only HTMLParser

diff -r 489204193cd7 -r cb1b91c6bceb python/html2text.py
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/python/html2text.py	Mon Mar 07 12:22:04 2016 -0800
@@ -0,0 +1,52 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+"""
+convert HTML to text using only HTMLParser
+"""
+
+# imports
+import argparse
+import sys
+from HTMLParser import HTMLParser
+
+class HTML2Text(HTMLParser):
+
+    def __init__(self):
+        HTMLParser.__init__(self)
+        self.in_body = False
+        self.text = []
+
+    def handle_starttag(self, tag, attrs):
+        if tag == 'body':
+            self.in_body = True
+
+    def handle_data(self, data):
+        if self.in_body:
+            data = data.strip()
+            if data:
+                self.text.append(data)
+
+    def __str__(self):
+        return '\n'.join(self.text)
+
+def main(args=sys.argv[1:]):
+
+    # parse command line
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument('input', nargs='?',
+                        type=argparse.FileType('r'), default=sys.stdin,
+                        help='input file, or read from stdin if ommitted')
+    options = parser.parse_args(args)
+
+    # parse HTML
+    html = options.input.read()
+    html_parser = HTML2Text()
+    html_parser.feed(html)
+    html_parser.close()
+
+    # output it
+    print (html_parser)
+
+if __name__ == '__main__':
+    main()