HTMLParser and weird behavior

Question

I have to extract an information from the following web page with Python 3: http://www.homefinance.nl/english/international-interest-rates/libor/libor-interest-rates-gbp.asp

The download using urllib.request seems ok, but surprisingly, when I parse the html file with my HTMLParser class the parsing seems to stop in the middle of the meta tags, without giving any rationales.

This is my code:

import urllib.request
from html.parser import HTMLParser

def downloadLIBOR():
    html_file = urllib.request.urlopen("http://www.homefinance.nl/english/international-interest-rates/libor/libor-interest-rates-gbp.asp")
    return html_file

class tmpHTMLParser(HTMLParser):

    def __init__(self):
        self._libor = "0.81625 %"
        self._stack = []
        self._properStack = []
        super().__init__()

    def handle_starttag(self, tag, attrs):
        print("starttag " + str(tag))
        print(self.get_starttag_text())
        self._stack.append(tag)

    def handle_startendtag(self, tag, attrs):
        print("startendtag")

    def unknown_decl(self, data):
        print("unknown_decl")

    def handle_endtag(self, tag):
        print("endtag " + str(tag))
        self._stack.pop()

def _buildProperStack(webpage):
    """dev tool: return the stack leading to the libor rate libor into the webpage webpage."""
    parser = tmpHTMLParser()
    parser.feed(webpage)

if __name__ == "__main__":
    webpage = downloadLIBOR()
    print("download done")
    html = str(webpage.read())
    _buildProperStack(html)
    exit(0)

Answer 1

BTW, I noticed that you forgot to do a parser.close() after the parser.feed(). It might be buffering something, and the close will force it to finish.

Answer 2

Not sure what you are actually trying to do but using BeautifulSoup for parsing HTML is much nicer and easier and less error-prone.