new backend allrecipes

modules/allrecipes/__init__.py

@@ -0,0 +1,22 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2013 Julien Veyssier
+#
+# 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 .backend import AllrecipesBackend
+
+__all__ = ['AllrecipesBackend']

modules/allrecipes/backend.py

@@ -0,0 +1,62 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2013 Julien Veyssier
+#
+# 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 weboob.capabilities.recipe import ICapRecipe, Recipe
+from weboob.tools.backend import BaseBackend
+
+from .browser import AllrecipesBrowser
+
+__all__ = ['AllrecipesBackend']
+
+
+class AllrecipesBackend(BaseBackend, ICapRecipe):
+    NAME = 'allrecipes'
+    MAINTAINER = u'Julien Veyssier'
+    EMAIL = 'julien.veyssier@aiur.fr'
+    VERSION = '0.g'
+    DESCRIPTION = u'Allrecipes English recipe website'
+    LICENSE = 'AGPLv3+'
+    BROWSER = AllrecipesBrowser
+
+    def create_default_browser(self):
+        return self.create_browser()
+
+    def get_recipe(self, id):
+        return self.browser.get_recipe(id)
+
+    def iter_recipes(self, pattern):
+        return self.browser.iter_recipes(pattern.encode('utf-8'))
+
+    def fill_recipe(self, recipe, fields):
+        if 'nb_person' in fields or 'instructions' in fields:
+            rec = self.get_recipe(recipe.id)
+            recipe.picture_url = rec.picture_url
+            recipe.instructions = rec.instructions
+            recipe.ingredients = rec.ingredients
+            recipe.comments = rec.comments
+            recipe.author = rec.author
+            recipe.nb_person = rec.nb_person
+            recipe.cooking_time = rec.cooking_time
+            recipe.preparation_time = rec.preparation_time
+
+        return recipe
+
+    OBJECTS = {
+        Recipe: fill_recipe,
+    }

modules/allrecipes/browser.py

@@ -0,0 +1,51 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2013 Julien Veyssier
+#
+# 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 weboob.tools.browser import BaseBrowser, BrowserHTTPNotFound
+
+from .pages import RecipePage, ResultsPage, FourOFourPage
+
+
+__all__ = ['AllrecipesBrowser']
+
+
+class AllrecipesBrowser(BaseBrowser):
+    DOMAIN = 'allrecipes.com'
+    PROTOCOL = 'http'
+    ENCODING = 'utf-8'
+    USER_AGENT = BaseBrowser.USER_AGENTS['wget']
+    PAGES = {
+        'http://allrecipes.com/search/default.aspx\?qt=k&wt=.*&rt=r&origin=.*': ResultsPage,
+        'http://allrecipes.com/Recipe/.*/Detail.aspx': RecipePage,
+        'http://allrecipes.com/404.aspx.*': FourOFourPage
+    }
+
+    def iter_recipes(self, pattern):
+        self.location('http://allrecipes.com/search/default.aspx?qt=k&wt=%s&rt=r&origin=Home%%20Page' % (pattern))
+        assert self.is_on_page(ResultsPage)
+        return self.page.iter_recipes()
+
+    def get_recipe(self, id):
+        try:
+            self.location('http://allrecipes.com/Recipe/%s/Detail.aspx' % id)
+        except BrowserHTTPNotFound:
+            return
+        if self.is_on_page(RecipePage):
+            return self.page.get_recipe(id)

modules/allrecipes/pages.py

@@ -0,0 +1,115 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2013 Julien Veyssier
+#
+# 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 weboob.capabilities.recipe import Recipe, Comment
+from weboob.capabilities.base import NotAvailable, NotLoaded
+from weboob.tools.browser import BasePage
+
+
+__all__ = ['RecipePage', 'ResultsPage', 'FourOFourPage']
+
+
+class FourOFourPage(BasePage):
+    pass
+
+
+class ResultsPage(BasePage):
+    """ Page which contains results as a list of recipies
+    """
+    def iter_recipes(self):
+        for div in self.parser.select(self.document.getroot(), 'div.recipe-info'):
+            thumbnail_url = NotAvailable
+            short_description = NotAvailable
+            imgs = self.parser.select(div.getparent(), 'img')
+            if len(imgs) > 0:
+                url = unicode(imgs[0].attrib.get('src', ''))
+                if url.startswith('http://'):
+                    thumbnail_url = url
+
+            link = self.parser.select(div, 'a.title', 1)
+            title = unicode(link.text)
+            id = unicode(link.attrib.get('href', '').split('/')[2])
+
+            recipe = Recipe(id, title)
+            recipe.thumbnail_url = thumbnail_url
+            recipe.short_description = short_description
+            recipe.instructions = NotLoaded
+            recipe.ingredients = NotLoaded
+            recipe.nb_person = NotLoaded
+            recipe.cooking_time = NotLoaded
+            recipe.preparation_time = NotLoaded
+            recipe.author = NotLoaded
+            yield recipe
+
+
+class RecipePage(BasePage):
+    """ Page which contains a recipe
+    """
+    def get_recipe(self, id):
+        title = NotAvailable
+        preparation_time = NotAvailable
+        cooking_time = NotAvailable
+        author = NotAvailable
+        nb_person = NotAvailable
+        ingredients = NotAvailable
+        picture_url = NotAvailable
+        instructions = NotAvailable
+        comments = []
+
+        title = unicode(self.parser.select(self.document.getroot(), 'h1#itemTitle', 1).text)
+        imgillu = self.parser.select(self.document.getroot(), 'img#imgPhoto')
+        if len(imgillu) > 0:
+            picture_url = unicode(imgillu[0].attrib.get('src', ''))
+
+        ingredients = []
+        l_ing = self.parser.select(self.document.getroot(), 'li#liIngredient')
+        for ing in l_ing:
+            ingtxt = unicode(ing.text_content().strip())
+            if ingtxt != '':
+                ingredients.append(ingtxt)
+
+        instructions = u''
+        l_divinst = self.parser.select(self.document.getroot(), 'div.directLeft li')
+        num_instr = 1
+        for inst in l_divinst:
+            instructions += '%s: %s\n' % (num_instr, inst.text_content())
+	    num_instr += 1
+
+        emprep = self.parser.select(self.document.getroot(), 'span#prepMinsSpan em')
+        if len(emprep) > 0:
+            preparation_time = int(emprep[0].text)
+        emcooktime = self.parser.select(self.document.getroot(), 'span#cookMinsSpan em')
+        if len(emcooktime) > 0:
+            cooking_time = int(emcooktime[0].text)
+        l_nbpers = self.parser.select(self.document.getroot(), 'span#lblYield[itemprop=recipeYield]')
+        if len(l_nbpers) > 0:
+            nb_person = int(l_nbpers[0].text.split()[0])
+
+        recipe = Recipe(id, title)
+        recipe.preparation_time = preparation_time
+        recipe.cooking_time = cooking_time
+        recipe.nb_person = nb_person
+        recipe.ingredients = ingredients
+        recipe.instructions = instructions
+        recipe.picture_url = picture_url
+        recipe.comments = comments
+        recipe.author = author
+        recipe.thumbnail_url = NotLoaded
+        return recipe

modules/allrecipes/test.py

@@ -0,0 +1,32 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2013 Julien Veyssier
+#
+# 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 weboob.tools.test import BackendTest
+
+
+class AllrecipesTest(BackendTest):
+    BACKEND = 'allrecipes'
+
+    def test_recipe(self):
+        recipes = self.backend.iter_recipes('french fries')
+        for recipe in recipes:
+            full_recipe = self.backend.get_recipe(recipe.id)
+            assert full_recipe.instructions
+            assert full_recipe.ingredients
+            assert full_recipe.title