urltitle.py

from HTMLParser import HTMLParser

import requests
import re


url_regex = "(https?:\/\/[^ ]+)"

class TitleParser(HTMLParser):
    istitle = False
    def handle_starttag(self, tag, attrs):
        if tag == "title":
            self.istitle = True
    def handle_data(self, data):
        if self.istitle:
            self.title = data
            self.istitle = False

def run(data, settings):
    re_test = re.search(url_regex, data['payload'])
    if re_test:
        url = re_test.group(0)
        r = requests.get(url)
        parser = TitleParser()
        parser.feed(r.text)

        return parser.title