Source code for libka.qtwebkit_releases_html_parser

# -*- coding: utf-8 -*-
# pylint: disable=line-too-long
# kate: space-indent on; indent-width 4; replace-tabs on; indent-mode python; remove-trailing-space modified;
# vim: expandtab ts=4
# pylint: enable=line-too-long

############################################################################
#   Copyright © 2018 José Manuel Santamaría Lema <panfaust@gmail.com>      #
#                                                                          #
#   This program is free software; you can redistribute it and/or modify   #
#   it under the terms of the GNU General Public License as published by   #
#   the Free Software Foundation; either version 2 of the License, or      #
#   (at your option) any later version.                                    #
############################################################################

"""Module providing the QtWebKitReleasesHTMLParser class."""

import re
from html.parser import HTMLParser
import urllib3
import certifi

from debian.debian_support import Version




class QtWebKitReleasesHTMLParser(HTMLParser): #pylint: disable=abstract-method
    """
    Class to parse the HTML of the webkit releases and find out the latest
    upstream release.
    """

    def __init__(self):
        super(QtWebKitReleasesHTMLParser, self).__init__()
        self._latest_version = Version("0")



    def parse_releases_url(self):
        """
        Parses QtWebkit releases url.
        """
        releases_url = "https://github.com/annulen/webkit/releases/"
        #Get the update excuses web page
        http = urllib3.PoolManager(cert_reqs='CERT_REQUIRED', ca_certs=certifi.where())
        response = http.request("GET", releases_url)
        html_str = response.data.decode('utf-8')
        self.feed(html_str)




    def handle_starttag(self, tag, attrs):
        """
        Process all HTML tags, detect links which may point to `*.tar.xz` source code releases.
        """
        if (tag == "a") and (attrs[0][0] == "href"):
            rel_url = attrs[0][1]
            if rel_url.startswith("/annulen/webkit/releases/download/qtwebkit-tp"):
                #Discard this kind of links
                return
            if rel_url.startswith("/annulen/webkit/releases/download/qtwebkit-"):
                version_found = rel_url.split('/')[-1].split('qtwebkit-')[1].split('.tar.xz')[0]
                version_found = re.sub(r'\-', r'~', version_found)
                try:
                    version_found = Version(version_found)
                except ValueError:
                    return
                if version_found > self._latest_version:
                    self._latest_version = version_found




    def get_latest_version(self):
        """
        Returns the latest QtWebkit version after parsing the HTML releases page
        """
        return self._latest_version