111 lines
5 KiB
Python
111 lines
5 KiB
Python
# -*- 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
|