106 lines
3.5 KiB
Python
106 lines
3.5 KiB
Python
# -*- coding: utf-8 -*-
|
|
|
|
# Copyright(C) 2012-2014 Laurent Bachelier
|
|
#
|
|
# This file is part of weboob.
|
|
#
|
|
# weboob is free software: you can redistribute it and/or modify
|
|
# it under the terms of the GNU Affero General Public License as published by
|
|
# the Free Software Foundation, either version 3 of the License, or
|
|
# (at your option) any later version.
|
|
#
|
|
# weboob 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 Affero General Public License for more details.
|
|
#
|
|
# You should have received a copy of the GNU Affero General Public License
|
|
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
|
|
|
|
|
|
class Profile(object):
|
|
"""
|
|
A profile represents the way Browser should act.
|
|
Usually it is to mimic a real browser.
|
|
"""
|
|
|
|
def setup_session(self, session):
|
|
"""
|
|
Change default headers, set up hooks, etc.
|
|
|
|
Warning: Do not enable lzma, bzip or bzip2, sdch encodings
|
|
as python-requests does not support it yet.
|
|
Supported as of 2.2: gzip, deflate, compress.
|
|
In doubt, do not change the default Accept-Encoding header
|
|
of python-requests.
|
|
"""
|
|
raise NotImplementedError()
|
|
|
|
|
|
class Weboob(Profile):
|
|
"""
|
|
It's us!
|
|
Recommended for Weboob-friendly websites only.
|
|
"""
|
|
|
|
def __init__(self, version):
|
|
self.version = version
|
|
|
|
def setup_session(self, session):
|
|
session.headers['User-Agent'] = 'weboob/%s' % self.version
|
|
|
|
|
|
class Firefox(Profile):
|
|
"""
|
|
Try to mimic a specific version of Firefox.
|
|
Ideally, it should follow the current ESR Firefox:
|
|
https://www.mozilla.org/en-US/firefox/organizations/all.html
|
|
Do not change the Firefox version without checking the Gecko one!
|
|
"""
|
|
|
|
def setup_session(self, session):
|
|
"""
|
|
Set up headers for a standard Firefox request
|
|
(except for DNT which isn't on by default but is a good idea).
|
|
|
|
The goal is to be unidentifiable.
|
|
"""
|
|
# Replace all base requests headers
|
|
# https://developer.mozilla.org/en/Gecko_user_agent_string_reference
|
|
# https://bugzilla.mozilla.org/show_bug.cgi?id=572650
|
|
session.headers = {
|
|
'Accept-Language': 'en-us,en;q=0.5',
|
|
'Accept-Encoding': 'gzip, deflate',
|
|
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
|
|
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Firefox/31.0',
|
|
'DNT': '1'}
|
|
|
|
|
|
class Wget(Profile):
|
|
"""
|
|
Common alternative user agent.
|
|
Some websites will give you a version with less JavaScript.
|
|
Some others could ban you (after all, wget is not a real browser).
|
|
"""
|
|
def __init__(self, version='1.11.4'):
|
|
self.version = version
|
|
|
|
def setup_session(self, session):
|
|
# Don't remove base headers, if websites want to block fake browsers,
|
|
# they will probably block any wget user agent anyway.
|
|
session.headers.update({
|
|
'Accept': '*/*',
|
|
'User-Agent': 'Wget/%s' % self.version})
|
|
|
|
|
|
class Android(Profile):
|
|
"""
|
|
An android profile for mobile websites
|
|
"""
|
|
|
|
def setup_session(self, session):
|
|
"""
|
|
Set up user agent.
|
|
"""
|
|
session.headers.update({
|
|
'User-Agent': 'Mozilla/5.0 (Linux; U; Android 2.1; en-us; Nexus One Build/ERD62) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17'})
|