4grab/htmlparser.py

######################################################################
# Copyright 2009, 2010 ryuslash
#
# This file is part of 4grab.
#
# 4grab is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# 4grab is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with 4grab.  If not, see <http://www.gnu.org/licenses/>.
######################################################################

import sgmllib
import re

class MyParser(sgmllib.SGMLParser):
    def __init__(self, verbose=0):
        sgmllib.SGMLParser.__init__(self, verbose)
        
        self.hyperlinks = []
        self.url_reg = re.compile('res/\d+\Z')
        self.prev = ""
        
    def parse(self, s):
        self.feed(s)
        self.close()

    def start_a(self, attributes):
        for name, value in attributes:
            if name == "href":
                if self.url_reg.search(value) != None:
                    if self.prev != value:
                        self.hyperlinks.append(value)
                        self.prev = value
    
    def get_hyperlinks(self):
        return self.hyperlinks

class MySubParser(MyParser):
    def __init__(self, verbose=0):
        MyParser.__init__(self, verbose)
        self.url_reg = re.compile('/src/\d+\.\w{3,4}\Z')