# -*- coding: utf-8 -*- # Copyright 2015 Mike Fährmann # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License version 2 as # published by the Free Software Foundation. """Extract images from http://www.turboimagehost.com""" from .common import Extractor, Message from .. import text class TurboimagehostExtractor(Extractor): category = "turboimagehost" directory_fmt = ["{category}"] filename_fmt = "{category}_{index}_{filename}" pattern = [r"(?:https?://)?(?:www\.)?turboimagehost\.com/p/((\d+)/[^/]+\.html)"] def __init__(self, match): Extractor.__init__(self) self.part, self.index = match.groups() def items(self): page = self.request("http://www.turboimagehost.com/p/" + self.part).text data = { "category": self.category, "index": self.index, } text.extract_all(page, ( ('width' , 'var imWidth = ', ';'), ('height', 'var imHeight = ', ';'), ('url' , '