#!/usr/bin/python
"""CommentPuller -- trivial class to extract comments from HTML pages"""

import HTMLParser
import urllib
import sys

__author__ = "Paul Bissex <pb@e-scribe.com>"
__version__ = "0.1"
__license__ = "MIT"
__usage__ = """Shell usage: CommentPuller.py <url>
Python usage: comment_list = CommentPuller('http://example.com').comments
"""

class CommentPuller(HTMLParser.HTMLParser):
    """Class for pulling comments out of HTML pages"""
    
    def __init__(self, url):
        """Set up object and fetch page HTML"""
        HTMLParser.HTMLParser.__init__(self)
        self.html = urllib.urlopen(url).read()
        self.comments = []
        self.feed(self.html)
        self.close()
        
    def handle_comment(self, data):
        """Override HTMLParser.handle_comment; collect comment strings"""
        self.comments.append(data.strip())

if __name__ == "__main__":
    try:
        url = sys.argv[1]
    except IndexError:
        print __usage__
        sys.exit()
    comment_list = CommentPuller(url).comments
    for comment in comment_list:
        print comment