How can I retrieve the page title of a webpage using Python?

Question

How can I retrieve the page title of a webpage (title html tag) using Python?

Answer 1

Using HTMLParser:

from urllib.request import urlopen
from html.parser import HTMLParser


class TitleParser(HTMLParser):
    def __init__(self):
        HTMLParser.__init__(self)
        self.match = False
        self.title = ''

    def handle_starttag(self, tag, attributes):
        self.match = tag == 'title'

    def handle_data(self, data):
        if self.match:
            self.title = data
            self.match = False

url = "http://example.com/"
html_string = str(urlopen(url).read())

parser = TitleParser()
parser.feed(html_string)
print(parser.title)  # prints: Example Domain