Merge pull request #12 from RyanNoelk/dev

Dev to master

README.md

@@ -5,7 +5,7 @@
 A simple web scraping tool for recipe sites I use in a project of mine that makes sense to live as
 a separate package.
 
-    pip install git+git://github.com/RyanNoelk/[email protected].3
+    pip install git+git://github.com/RyanNoelk/[email protected].5
 
 then:
 
@@ -34,16 +34,6 @@ If you are programmer PRs with fixes are warmly welcomed and acknowledged with a
 ### Scrapers available for:
 
 - [http://allrecipes.com/](http://allrecipes.com/)
-- [http://bonappetit.com/](http://bonappetit.com/)
-- [http://cookstr.com/](http://cookstr.com/)
-- [http://epicurious.com/](http://epicurious.com/)
-- [http://finedininglovers.com/](https://www.finedininglovers.com/)
-- [http://foodrepublic.com/](http://foodrepublic.com)
-- [http://jamieoliver.com/](http://www.jamieoliver.com/)
-- [http://mybakingaddiction.com/](http://mybakingaddiction.com/)
-- [http://simplyrecipes.com/](http://www.simplyrecipes.com)
-- [http://steamykitchen.com/](http://steamykitchen.com/)
-- [http://tastykitchen.com/](http://tastykitchen.com/)
-- [http://thevintagemixer.com/](http://www.thevintagemixer.com/)
-- [http://twopeasandtheirpod.com/](http://twopeasandtheirpod.com/)
-- [http://whatsgabycooking.com/](http://whatsgabycooking.com/)
+- [http://budgetbytes.com/](http://budgetbytes.com/)
+- [http://pamperedchef.com/](http://pamperedchef.com/)
+- [http://tasteofhome.com/](http://tasteofhome.com/)

recipe_scrapers/__init__.py

@@ -1,10 +1,12 @@
 #!/usr/bin/env python
 # encoding: utf-8
 import re
+import datetime
 
 from .allrecipes import AllRecipes
 from .bonappetit import BonAppetit
 from .budgetbytes import BudgetBytes
+from .budgetbytesv2 import BudgetBytesv2
 from .cookstr import Cookstr
 from .epicurious import Epicurious
 from .finedininglovers import FineDiningLovers
@@ -23,6 +25,7 @@
     AllRecipes.host(): AllRecipes,
     # BonAppetit.host(): BonAppetit,
     BudgetBytes.host(): BudgetBytes,
+    BudgetBytesv2.host(): BudgetBytesv2,
     # Cookstr.host(): Cookstr,
     # Epicurious.host(): Epicurious,
     # FineDiningLovers.host(): FineDiningLovers,
@@ -55,9 +58,21 @@ def url_path_to_dict(path):
     return url_dict
 
 
+def get_version(url_dict):
+    if url_dict['host'] == 'budgetbytes.com':
+        path = url_dict.get('path').split('/')
+        current_time = datetime.datetime.strptime(path[1] + '-' + path[2], '%Y-%m')
+        compare_time = datetime.datetime.strptime('2017-04', '%Y-%m')
+        if current_time > compare_time:
+            return url_dict['host'] + '-v2'
+    return url_dict['host']
+
+
 def scrap_me(url_path):
     url_path = url_path.replace('://www.', '://')
-    return SCRAPERS[url_path_to_dict(url_path)['host']](url_path)
+    url_dict = url_path_to_dict(url_path)
+    url_dict['host'] = get_version(url_dict)
+    return SCRAPERS[url_dict['host']](url_path)
 
 
 __all__ = ['scrap_me']

recipe_scrapers/budgetbytes.py

@@ -57,7 +57,7 @@ def instructions(self):
         ]
 
     def description(self):
-        li = self.soup.find('div', {'class': 'entry-content'}).findAll('p')
+        li = self.soup.find('article', {'class': 'post'}).findAll('p')
         return li[0].get_text()
 
     def image(self):

recipe_scrapers/budgetbytesv2.py

@@ -0,0 +1,82 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+from fractions import Fraction
+from ._abstract import AbstractScraper
+from ._utils import normalize_string
+
+
+class BudgetBytesv2(AbstractScraper):
+
+    @classmethod
+    def host(self):
+        return 'budgetbytes.com-v2'
+
+    def title(self):
+        return self.soup.find('h1').get_text()
+
+    def total_time(self):
+        return {
+            'prep-time': self.soup.find(
+                'span',
+                {'class': 'wprm-recipe-prep_time-minutes'}
+            ).get_text(),
+            'cook-time': self.soup.find(
+                'span',
+                {'class': 'wprm-recipe-cook_time-minutes'}
+            ).get_text()
+        }
+
+    def servings(self):
+        return self.soup.find('span', {'itemprop': 'recipeYield'}).get_text().split(' ', 1)[0]
+
+    def ingredients(self):
+        ingredients_html = self.soup.findAll('li', {'class': 'wprm-recipe-ingredient'})
+        ingredients = []
+
+        for ingredient in ingredients_html:
+            try:
+                ingredient_dict = {
+                    'quantity': round(float(sum(Fraction(s) for s in ingredient.find(
+                        'span',
+                        {'class': 'wprm-recipe-ingredient-amount'}
+                    ).get_text().split())), 3),
+                    'measurement': ingredient.find(
+                        'span',
+                        {'class': 'wprm-recipe-ingredient-unit'}
+                    ).get_text(),
+                    'title': ingredient.find(
+                        'span',
+                        {'class': 'wprm-recipe-ingredient-name'}
+                    ).get_text()
+                }
+            except AttributeError:
+                ingredient_dict = {
+                    'title': ingredient.find(
+                        'span',
+                        {'class': 'wprm-recipe-ingredient-name'}
+                    ).get_text()
+                }
+            except:
+                ingredient_dict = {
+                    'title': ingredient
+                }
+
+            ingredients.append(ingredient_dict)
+
+        return ingredients
+
+    def instructions(self):
+        instructions_html = self.soup.findAll('li', {'class': 'wprm-recipe-instruction'})
+
+        return [
+            normalize_string(instruction.get_text())
+            for instruction in instructions_html
+        ]
+
+    def description(self):
+        li = self.soup.find('article', {'class': 'post'}).findAll('p')
+        return li[0].get_text()
+
+    def image(self):
+        return self.soup.find('img', {'class': 'alignnone'})["src"]