diff --git a/qutebrowser/browser/adblock.py b/qutebrowser/browser/adblock.py index d43efa6ee..b08e69032 100644 --- a/qutebrowser/browser/adblock.py +++ b/qutebrowser/browser/adblock.py @@ -32,6 +32,34 @@ from qutebrowser.utils import objreg, standarddir, log, message from qutebrowser.commands import cmdutils +def guess_zip_filename(zf): + """Guess which file to use inside a zip file. + + Args: + zf: A ZipFile instance. + """ + files = zf.namelist() + if len(files) == 1: + return files[0] + else: + for e in files: + if posixpath.splitext(e)[0].lower() == 'hosts': + return e + raise FileNotFoundError("No hosts file found in zip") + +def get_fileobj(byte_io): + """Get an usable file object to read the hosts file from.""" + byte_io.seek(0) # rewind downloaded file + if zipfile.is_zipfile(byte_io): + byte_io.seek(0) # rewind what zipfile.is_zipfile did + zf = zipfile.ZipFile(byte_io) + filename = guess_zip_filename(zf) + byte_io = zf.open(filename, mode='r') + else: + byte_io.seek(0) # rewind what zipfile.is_zipfile did + return io.TextIOWrapper(byte_io, encoding='utf-8') + + class FakeDownload: """A download stub to use on_download_finished with local files.""" @@ -103,33 +131,6 @@ class HostBlocker: download.finished.connect( functools.partial(self.on_download_finished, download)) - def _guess_zip_filename(self, zf): - """Guess which file to use inside a zip file. - - Args: - zf: A ZipFile instance. - """ - files = zf.namelist() - if len(files) == 1: - return files[0] - else: - for e in files: - if posixpath.splitext(e)[0].lower() == 'hosts': - return e - raise FileNotFoundError("No hosts file found in zip") - - def _get_fileobj(self, byte_io): - """Get an usable file object to read the hosts file from.""" - byte_io.seek(0) # rewind downloaded file - if zipfile.is_zipfile(byte_io): - byte_io.seek(0) # rewind what zipfile.is_zipfile did - zf = zipfile.ZipFile(byte_io) - filename = self._guess_zip_filename(zf) - byte_io = zf.open(filename, mode='r') - else: - byte_io.seek(0) # rewind what zipfile.is_zipfile did - return io.TextIOWrapper(byte_io, encoding='utf-8') - def _merge_file(self, byte_io): """Read and merge host files. @@ -142,7 +143,7 @@ class HostBlocker: error_count = 0 line_count = 0 try: - f = self._get_fileobj(byte_io) + f = get_fileobj(byte_io) except (FileNotFoundError, UnicodeDecodeError, zipfile.BadZipFile, zipfile.LargeZipFile) as e: message.error('last-focused', "adblock: Error while reading {}: " diff --git a/qutebrowser/config/configdata.py b/qutebrowser/config/configdata.py index aa92b8ea3..a2f851908 100644 --- a/qutebrowser/config/configdata.py +++ b/qutebrowser/config/configdata.py @@ -125,7 +125,7 @@ DATA = collections.OrderedDict([ "Whether to wrap finding text to the top when arriving at the end."), ('startpage', - SettingValue(typ.List(), 'http://www.duckduckgo.com'), + SettingValue(typ.List(), 'https://www.duckduckgo.com'), "The default page(s) to open at the start, separated by commas."), ('auto-search', diff --git a/scripts/hostblock_blame.py b/scripts/hostblock_blame.py new file mode 100644 index 000000000..49a46aa84 --- /dev/null +++ b/scripts/hostblock_blame.py @@ -0,0 +1,66 @@ +#!/usr/bin/env python3 +# vim: ft=python fileencoding=utf-8 sts=4 sw=4 et: + +# Copyright 2014 Florian Bruhin (The Compiler) +# +# This file is part of qutebrowser. +# +# qutebrowser 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 3 of the License, or +# (at your option) any later version. +# +# qutebrowser is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with qutebrowser. If not, see . + +# pylint: disable=broad-except + +"""Check by which hostblock list a host was blocked.""" + +import sys +import io +import os +import os.path +import configparser +import urllib.request + +from PyQt5.QtCore import QStandardPaths + +sys.path.insert(0, os.path.join(os.path.dirname(__file__), os.pardir)) +from qutebrowser.browser import adblock + + +def main(): + """Check by which hostblock list a host was blocked.""" + if len(sys.argv) != 2: + print("Usage: {} ".format(sys.argv[0]), file=sys.stderr) + sys.exit(1) + confdir = QStandardPaths.writableLocation(QStandardPaths.ConfigLocation) + confdir = confdir.replace('/', os.sep) + if confdir.split(os.sep)[-1] != 'qutebrowser': + confdir = os.path.join(confdir, 'qutebrowser') + confpath = os.path.join(confdir, 'qutebrowser.conf') + parser = configparser.ConfigParser() + print("config path: {}".format(confpath)) + successful = parser.read(confpath, encoding='utf-8') + if not successful: + raise IOError("configparser did not read files successfully!") + lists = parser['content']['host-block-lists'] + for url in lists.split(','): + print("checking {}...".format(url)) + raw_file = urllib.request.urlopen(url) + byte_io = io.BytesIO(raw_file.read()) + f = adblock.get_fileobj(byte_io) + for line in f: + if sys.argv[1] in line: + print("FOUND {} in {}:".format(sys.argv[1], url)) + print(" " + line.rstrip()) + + +if __name__ == '__main__': + main()