new backend cuisineaz for cookboob, not finished
This commit is contained in:
parent
31a3cf589b
commit
88971d96f9
7 changed files with 303 additions and 2 deletions
|
|
@ -46,7 +46,7 @@ class SevenFiftyGramsBackend(BaseBackend, ICapRecipe):
|
|||
return self.browser.iter_recipes(pattern.encode('utf-8'))
|
||||
|
||||
def fill_recipe(self, recipe, fields):
|
||||
if 'thumbnail_url' in fields or 'instructions' in 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
|
||||
|
|
|
|||
22
modules/cuisineaz/__init__.py
Normal file
22
modules/cuisineaz/__init__.py
Normal file
|
|
@ -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 CuisineazBackend
|
||||
|
||||
__all__ = ['CuisineazBackend']
|
||||
63
modules/cuisineaz/backend.py
Normal file
63
modules/cuisineaz/backend.py
Normal file
|
|
@ -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 CuisineazBrowser
|
||||
|
||||
from urllib import quote_plus
|
||||
|
||||
__all__ = ['CuisineazBackend']
|
||||
|
||||
|
||||
class CuisineazBackend(BaseBackend, ICapRecipe):
|
||||
NAME = 'cuisineaz'
|
||||
MAINTAINER = u'Julien Veyssier'
|
||||
EMAIL = 'julien.veyssier@aiur.fr'
|
||||
VERSION = '0.f'
|
||||
DESCRIPTION = 'Cuisine AZ recipe website'
|
||||
LICENSE = 'AGPLv3+'
|
||||
BROWSER = CuisineazBrowser
|
||||
|
||||
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.nb_person = rec.nb_person
|
||||
recipe.cooking_time = rec.cooking_time
|
||||
recipe.preparation_time = rec.preparation_time
|
||||
|
||||
return recipe
|
||||
|
||||
OBJECTS = {
|
||||
Recipe:fill_recipe,
|
||||
}
|
||||
46
modules/cuisineaz/browser.py
Normal file
46
modules/cuisineaz/browser.py
Normal file
|
|
@ -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__ = ['CuisineazBrowser']
|
||||
|
||||
class CuisineazBrowser(BaseBrowser):
|
||||
DOMAIN = 'www.cuisineaz.com'
|
||||
PROTOCOL = 'http'
|
||||
ENCODING = 'utf-8'
|
||||
USER_AGENT = BaseBrowser.USER_AGENTS['wget']
|
||||
PAGES = {
|
||||
'http://www.cuisineaz.com/recettes/recherche_v2.aspx\?recherche=.*': ResultsPage,
|
||||
'http://www.cuisineaz.com/recettes/.*[0-9]*.aspx': RecipePage,
|
||||
}
|
||||
|
||||
def iter_recipes(self, pattern):
|
||||
self.location('http://www.cuisineaz.com/recettes/recherche_v2.aspx?recherche=%s' % (pattern.replace(' ','-')))
|
||||
assert self.is_on_page(ResultsPage)
|
||||
return self.page.iter_recipes()
|
||||
|
||||
def get_recipe(self, id):
|
||||
self.location('http://www.cuisineaz.com/recettes/%s.aspx' % id)
|
||||
assert self.is_on_page(RecipePage)
|
||||
return self.page.get_recipe(id)
|
||||
137
modules/cuisineaz/pages.py
Normal file
137
modules/cuisineaz/pages.py
Normal file
|
|
@ -0,0 +1,137 @@
|
|||
# -*- 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.rechRecette'):
|
||||
thumbnail_url = NotAvailable
|
||||
short_description = NotAvailable
|
||||
imgs = self.parser.select(div,'img.photo')
|
||||
if len(imgs) > 0:
|
||||
thumbnail_url = unicode(imgs[0].attrib.get('src',''))
|
||||
|
||||
link = self.parser.select(div,'a.rechRecetTitle',1)
|
||||
title = unicode(link.text)
|
||||
id = unicode(link.attrib.get('href','').split('/')[-1].replace('.aspx',''))
|
||||
|
||||
|
||||
short_description = u''
|
||||
ldivprix = self.parser.select(div,'div.prix')
|
||||
if len(ldivprix) > 0:
|
||||
divprix = ldivprix[0]
|
||||
nbprixneg = 0
|
||||
spanprix = self.parser.select(divprix,'span')
|
||||
if len(spanprix) > 0:
|
||||
nbprixneg = unicode(spanprix[0].text).count(u'€')
|
||||
nbprixtot = unicode(divprix.text_content()).count(u'€')
|
||||
short_description += u'Cost: %s/%s ; '%(nbprixtot - nbprixneg, nbprixtot)
|
||||
|
||||
short_description += unicode(' '.join(self.parser.select(div,'div.rechResume',1).text_content().split()).strip()).replace(u'€','')
|
||||
short_description += u' '
|
||||
short_description += unicode(' '.join(self.parser.select(div,'div.rechIngredients',1).text_content().split()).strip())
|
||||
|
||||
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(),'head > title',1).text.split(' - ')[1])
|
||||
main = self.parser.select(self.document.getroot(),'div.recette_description',1)
|
||||
|
||||
rec_infos = self.parser.select(self.document.getroot(),'div.recette_infos div.infos_column strong')
|
||||
for info_title in rec_infos:
|
||||
if u'Temps de préparation' in unicode(info_title.text):
|
||||
if info_title.tail.strip() != '':
|
||||
preparation_time = int(info_title.tail.split()[0])
|
||||
if 'h' in info_title.tail:
|
||||
preparation_time = 60*preparation_time
|
||||
if 'Temps de cuisson' in info_title.text:
|
||||
if info_title.tail.strip() != '':
|
||||
cooking_time = int(info_title.tail.split()[0])
|
||||
if 'h' in info_title.tail:
|
||||
cooking_time = 60*cooking_time
|
||||
if 'Nombre de personnes' in info_title.text:
|
||||
if info_title.tail.strip() != '':
|
||||
nb_person = int(info_title.tail)
|
||||
|
||||
ingredients = []
|
||||
p_ing = self.parser.select(main,'div.data.top.left > div.content p')
|
||||
for ing in p_ing:
|
||||
ingtxt = unicode(ing.text_content().strip())
|
||||
if ingtxt != '':
|
||||
ingredients.append(ingtxt)
|
||||
|
||||
lines_instr = self.parser.select(main,'div.data.top.right div.content li')
|
||||
if len(lines_instr) > 0:
|
||||
instructions = u''
|
||||
for line in lines_instr:
|
||||
inst = ' '.join(line.text_content().strip().split())
|
||||
instructions += '%s\n'% inst
|
||||
instructions = instructions.strip('\n')
|
||||
|
||||
imgillu = self.parser.select(self.document.getroot(),'div.resume_recette_illustree img.photo')
|
||||
if len(imgillu) > 0:
|
||||
picture_url = unicode(imgillu[0].attrib.get('src',''))
|
||||
|
||||
for divcom in self.parser.select(self.document.getroot(),'div.comment-outer'):
|
||||
comtxt = unicode(' '.join(divcom.text_content().strip().split()))
|
||||
if u'| Répondre' in comtxt:
|
||||
comtxt = comtxt.strip('0123456789').replace(u' | Répondre','')
|
||||
comments.append(comtxt)
|
||||
|
||||
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
|
||||
33
modules/cuisineaz/test.py
Normal file
33
modules/cuisineaz/test.py
Normal file
|
|
@ -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 CuisineazTest(BackendTest):
|
||||
BACKEND = 'cuisineaz'
|
||||
|
||||
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
|
||||
|
||||
|
|
@ -46,7 +46,7 @@ class MarmitonBackend(BaseBackend, ICapRecipe):
|
|||
return self.browser.iter_recipes(quote_plus(pattern.encode('utf-8')))
|
||||
|
||||
def fill_recipe(self, recipe, fields):
|
||||
if 'thumbnail_url' in fields or 'instructions' in 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
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue