get_tag_and_class.py

#! /usr/bin/env python
# -*- coding: utf-8 -*-

# get_tag_and_class.rb: extract tag and class names from a HTML document.

import sys
import re

regex = re.compile('<(\w+)[^<>]*class=[\'\"]([^\'\"]+)[\'\"][^<>]*>')

result = []

line_number = 0
for line in sys.stdin:
    line_number = line_number + 1
    offset = 0
    while offset < (len(line) - 1):
        md = regex.search(line, offset)
        if md:
            result.append((line_number, md.group(1), md.group(2)))
            offset = md.end(0) + 1
        else:
            break

for t in result:
    line = "%d: %s.%s\n" % (t[0], t[1], t[2])
    sys.stdout.write(line)