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

Here is a fault tolerant HTMLParser implementation.
You can throw pretty much anything at get_title() without it breaking, If anything unexpected happens get_title() will return None.
When Parser() downloads the page it encodes it to ASCII regardless of the charset used in the page ignoring any errors. It would be trivial to change to_ascii() to convert the data into UTF-8 or any other encoding. Just add an encoding argument and rename the function to something like to_encoding().
By default HTMLParser() will break on broken html, it will even break on trivial things like mismatched tags. To prevent this behavior I replaced HTMLParser()'s error method with a function that will ignore the errors.

#-*-coding:utf8;-*-
#qpy:3
#qpy:console

''' 
Extract the title from a web page using
the standard lib.
'''

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

def error_callback(*_, **__):
    pass

def is_string(data):
    return isinstance(data, str)

def is_bytes(data):
    return isinstance(data, bytes)

def to_ascii(data):
    if is_string(data):
        data = data.encode('ascii', errors='ignore')
    elif is_bytes(data):
        data = data.decode('ascii', errors='ignore')
    else:
        data = str(data).encode('ascii', errors='ignore')
    return data


class Parser(HTMLParser):
    def __init__(self, url):
        self.title = None
        self.rec = False
        HTMLParser.__init__(self)
        try:
            self.feed(to_ascii(urlopen(url).read()))
        except urllib.error.HTTPError:
            return
        except urllib.error.URLError:
            return
        except ValueError:
            return

        self.rec = False
        self.error = error_callback

    def handle_starttag(self, tag, attrs):
        if tag == 'title':
            self.rec = True

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

    def handle_endtag(self, tag):
        if tag == 'title':
            self.rec = False


def get_title(url):
    return Parser(url).title

print(get_title('http://www.google.com'))