/usr/share/pyshared/weboob/tools/capabilities/gallery/genericcomicreader.py is in python-weboob-core 0.g-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 | # -*- 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/>.
import re
from weboob.capabilities.gallery import ICapGallery, BaseGallery, BaseImage
from weboob.tools.backend import BaseBackend
from weboob.tools.browser import BaseBrowser, BasePage
__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 = u'Noé Rubinstein'
EMAIL = 'noe.rubinstein@gmail.com'
VERSION = '0.g'
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}
|