I used autopep8 on some files and did carefully check the changes. I ignored E501,E302,E231,E225,E222,E221,E241,E203 in my search, and at least E501 on any autopep8 run. Other style fixes not related to PEP8: * Only use new-style classes. I don't think the usage of old-style classes was voluntary. Old-style classes are removed in Python 3. * Convert an if/else to a one-liner in mediawiki, change docstring style change to a comment something that wasn't really appropriate for a docstring. * Unneeded first if condition in meteofrance
128 lines
3.8 KiB
Python
128 lines
3.8 KiB
Python
# -*- coding: utf-8 -*-
|
|
|
|
# Copyright(C) 2010-2011 Noé Rubinstein
|
|
#
|
|
# 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/>.
|
|
|
|
from __future__ import with_statement
|
|
|
|
import re
|
|
|
|
from weboob.capabilities.gallery import ICapGallery, BaseGallery, BaseImage
|
|
from weboob.tools.backend import BaseBackend
|
|
from weboob.tools.browser import BaseBrowser, BasePage
|
|
from weboob.tools.test import BackendTest
|
|
|
|
__all__ = ['GenericComicReaderBackend']
|
|
|
|
|
|
class DisplayPage(BasePage):
|
|
def get_page(self, gallery):
|
|
src = self.document.xpath(self.browser.params['img_src_xpath'])[0]
|
|
|
|
return BaseImage(src,
|
|
gallery=gallery,
|
|
url=src)
|
|
|
|
def page_list(self):
|
|
return self.document.xpath(self.browser.params['page_list_xpath'])
|
|
|
|
|
|
class GenericComicReaderBrowser(BaseBrowser):
|
|
def __init__(self, browser_params, *args, **kwargs):
|
|
self.params = browser_params
|
|
BaseBrowser.__init__(self, *args, **kwargs)
|
|
|
|
def iter_gallery_images(self, gallery):
|
|
self.location(gallery.url)
|
|
assert self.is_on_page(DisplayPage)
|
|
|
|
for p in self.page.page_list():
|
|
if 'page_to_location' in self.params:
|
|
self.location(self.params['page_to_location'] % p)
|
|
else:
|
|
self.location(p)
|
|
|
|
assert self.is_on_page(DisplayPage)
|
|
yield self.page.get_page(gallery)
|
|
|
|
def fill_image(self, image, fields):
|
|
if 'data' in fields:
|
|
image.data = self.readurl(image.url)
|
|
|
|
|
|
class GenericComicReaderBackend(BaseBackend, ICapGallery):
|
|
NAME = 'genericcomicreader'
|
|
MAINTAINER = 'Noé Rubinstein'
|
|
EMAIL = 'noe.rubinstein@gmail.com'
|
|
VERSION = '0.b'
|
|
DESCRIPTION = 'Generic comic reader backend; subclasses implement specific sites'
|
|
LICENSE = 'AGPLv3+'
|
|
BROWSER = GenericComicReaderBrowser
|
|
|
|
BROWSER_PARAMS = {}
|
|
ID_REGEXP = None
|
|
URL_REGEXP = None
|
|
ID_TO_URL = None
|
|
PAGES = {}
|
|
|
|
def create_default_browser(self):
|
|
b = self.create_browser(self.BROWSER_PARAMS)
|
|
b.PAGES = self.PAGES
|
|
try:
|
|
b.DOMAIN = self.DOMAIN
|
|
except AttributeError:
|
|
pass
|
|
return b
|
|
|
|
def iter_gallery_images(self, gallery):
|
|
with self.browser:
|
|
return self.browser.iter_gallery_images(gallery)
|
|
|
|
def get_gallery(self, _id):
|
|
match = re.match(r'^%s$' % self.URL_REGEXP, _id)
|
|
if match:
|
|
_id = match.group(1)
|
|
else:
|
|
match = re.match(r'^%s$' % self.ID_REGEXP, _id)
|
|
if match:
|
|
_id = match.group(0)
|
|
else:
|
|
return None
|
|
|
|
gallery = BaseGallery(_id, url=(self.ID_TO_URL % _id))
|
|
with self.browser:
|
|
return gallery
|
|
|
|
def fill_gallery(self, gallery, fields):
|
|
gallery.title = gallery.id
|
|
|
|
def fill_image(self, image, fields):
|
|
with self.browser:
|
|
self.browser.fill_image(image, fields)
|
|
|
|
OBJECTS = {
|
|
BaseGallery: fill_gallery,
|
|
BaseImage: fill_image}
|
|
|
|
|
|
class GenericComicReaderTest(BackendTest):
|
|
def _test_download(self, _id):
|
|
g = self.backend.get_gallery(_id)
|
|
it = self.backend.iter_gallery_images(g)
|
|
it.next()
|
|
img = it.next()
|
|
self.backend.fillobj(img, ('url', 'data'))
|