new backend 750g for cookboob, get_recipe NYI

modules/750g/__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 SevenFiftyGramsBackend
+
+__all__ = ['SevenFiftyGramsBackend']

modules/750g/backend.py

@@ -0,0 +1,63 @@
+# -*- 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 SevenFiftyGramsBrowser
+
+from urllib import quote_plus
+
+__all__ = ['SevenFiftyGramsBackend']
+
+
+class SevenFiftyGramsBackend(BaseBackend, ICapRecipe):
+    NAME = '750g'
+    MAINTAINER = u'Julien Veyssier'
+    EMAIL = 'julien.veyssier@aiur.fr'
+    VERSION = '0.f'
+    DESCRIPTION = '750g recipe website'
+    LICENSE = 'AGPLv3+'
+    BROWSER = SevenFiftyGramsBrowser
+
+    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 'thumbnail_url' 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.nb_person        = rec.nb_person
+            recipe.cooking_time     = rec.cooking_time
+            recipe.preparation_time = rec.preparation_time
+
+        return recipe
+
+    OBJECTS = {
+            Recipe:fill_recipe,
+            }

modules/750g/browser.py

@@ -0,0 +1,46 @@
+# -*- 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
+
+from .pages import RecipePage, ResultsPage
+
+
+__all__ = ['SevenFiftyGramsBrowser']
+
+class SevenFiftyGramsBrowser(BaseBrowser):
+    DOMAIN = 'www.750g.com'
+    PROTOCOL = 'http'
+    ENCODING = 'utf-8'
+    USER_AGENT = BaseBrowser.USER_AGENTS['wget']
+    PAGES = {
+        'http://www.750g.com/recettes_.*.htm': ResultsPage,
+        'http://www.750g.com/.*r[0-9]*.htm': RecipePage,
+        }
+
+    def iter_recipes(self, pattern):
+        self.location('http://www.750g.com/recettes_%s.htm' % (pattern.replace(' ','_')))
+        assert self.is_on_page(ResultsPage)
+        return self.page.iter_recipes()
+
+    def get_recipe(self, id):
+        self.location('http://www.750g.com/%s.htm' % id)
+        assert self.is_on_page(RecipePage)
+        return self.page.get_recipe(id)

modules/750g/pages.py

@@ -0,0 +1,111 @@
+# -*- 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
+from weboob.capabilities.base import NotAvailable, NotLoaded
+from weboob.tools.browser import BasePage
+
+
+__all__ = ['RecipePage', 'ResultsPage']
+
+
+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.recette_description > div.data'):
+            links = self.parser.select(div,'div.info > p.title > a.fn')
+            if len(links) > 0:
+                link = links[0]
+                title = unicode(link.text)
+                id = unicode(link.attrib.get('href','').strip('/').replace('.htm','htm'))
+                thumbnail_url = NotAvailable
+                short_description = NotAvailable
+
+                imgs = self.parser.select(div,'img.recipe-image')
+                if len(imgs) > 0:
+                    thumbnail_url = unicode(imgs[0].attrib.get('src',''))
+                short_description =  unicode(' '.join(self.parser.select(div,'div.infos_column',1).text_content().split()).strip())
+                imgs_cost = self.parser.select(div,'div.infos_column img')
+                cost_tot = len(imgs_cost)
+                cost_on = 0
+                for img in imgs_cost:
+                    if img.attrib.get('src','').endswith('euro_on.png'):
+                        cost_on += 1
+                short_description += u' %s/%s'%(cost_on,cost_tot)
+
+                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
+                yield recipe
+                    
+
+
+class RecipePage(BasePage):
+    """ Page which contains a recipe
+    """
+    def get_recipe(self, id):
+        title = NotAvailable
+        preparation_time = NotAvailable
+        cooking_time = NotAvailable
+        nb_person = NotAvailable
+        ingredients = NotAvailable
+        picture_url = NotAvailable
+        instructions = NotAvailable
+        comments = []
+
+        title = unicode(self.parser.select(self.document.getroot(),'h1.m_title',1).text_content().strip())
+        main = self.parser.select(self.document.getroot(),'div.m_content_recette_main',1)
+        preparation_time = int(self.parser.select(main,'p.m_content_recette_info span.preptime',1).text_content())
+        cooking_time = int(self.parser.select(main,'p.m_content_recette_info span.cooktime',1).text_content())
+        ing_header_line = self.parser.select(main,'p.m_content_recette_ingredients span',1).text_content()
+        if '(pour' in ing_header_line and ')' in ing_header_line:
+            nb_person = int(ing_header_line.split('pour ')[-1].split('personnes)')[0].split()[0])
+        ingredients = self.parser.select(main,'p.m_content_recette_ingredients',1).text_content().strip().split('- ')
+        ingredients=ingredients[1:]
+        rinstructions = self.parser.select(main,'div.m_content_recette_todo',1).text_content().strip()
+        instructions = u''
+        for line in rinstructions.split('\n'):
+            instructions += '%s\n'%line.strip()
+        instructions = instructions.strip('\n')
+        imgillu = self.parser.select(self.document.getroot(),'a.m_content_recette_illu img')
+        if len(imgillu) > 0:
+            picture_url = unicode(imgillu[0].attrib.get('src',''))
+        for divcom in self.parser.select(self.document.getroot(),'div.m_commentaire_row'):
+            note = self.parser.select(divcom,'div.m_commentaire_note span',1).text.strip()
+            user = self.parser.select(divcom,'div.m_commentaire_content span',1).text.strip()
+            content = self.parser.select(divcom,'div.m_commentaire_content p',1).text.strip()
+            comments.append(u'user: %s, note: %s, comment: %s'%(user,note,content))
+
+        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.thumbnail_url = NotLoaded
+        return recipe

modules/750g/test.py

@@ -0,0 +1,33 @@
+# -*- 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 SevenFiftyGramsTest(BackendTest):
+    BACKEND = '750g'
+
+    def test_recipe(self):
+        recipes = self.backend.iter_recipes('fondue')
+        for recipe in recipes:
+            full_recipe = self.backend.get_recipe(recipe.id)
+            assert full_recipe.instructions
+            assert full_recipe.ingredients
+            assert full_recipe.title
+            assert full_recipe.preparation_time
+

modules/marmiton/pages.py

@@ -38,7 +38,7 @@ class ResultsPage(BasePage):
                 short_description = NotAvailable
                 imgs = self.parser.select(tds[0],'img')
                 if len(imgs) > 0:
-                    thumbnail_url = unicode(imgs[0].attrib('src',''))
+                    thumbnail_url = unicode(imgs[0].attrib.get('src',''))
                 link = self.parser.select(tds[1],'div.m_search_titre_recette a',1)
                 title = unicode(link.text)
                 id = link.attrib.get('href','').replace('.aspx','').replace('/recettes/recette_','')