Słownik

 from html.parser import HTMLParser
 import urllib.request as urllib2
 import re
 import locale

 locale.setlocale(locale.LC_ALL, ('pl','utf8'));

 class MyHTMLParser(HTMLParser):

    #Initializing lists
    lsStartTags = list()
    lsEndTags = list()
    lsStartEndTags = list()
    lsComments = list()

    #HTML Parser Methods
    def handle_starttag(self, startTag, attrs):
        self.lsStartTags.append(startTag)

    def handle_endtag(self, endTag):
        self.lsEndTags.append(endTag)

    def handle_startendtag(self,startendTag, attrs):
        self.lsStartEndTags.append(startendTag)

    def handle_comment(self,data):
        self.lsComments.append(data)

 #creating an object of the overridden class
 parser = MyHTMLParser()

 #Opening NYTimes site using urllib2
 html_page = html_page = urllib2.urlopen("http://www.sjp.pl/dialektyka")

 #Feeding the content
 regex = re.findall('<p style="margin:.*?;?">(?:.|[żźćńółęąśŻŹĆĄŚĘŁÓŃ])*?(?<=</p>)',str(html_page.         read()));
 #regex=[regex.replace("<br />",'\n') for w in regex];
 print(regex);
 #print("Comments", parser.lsComments)