From 492ee08a55fba6f1300295e328fbca60479a8dca Mon Sep 17 00:00:00 2001
From: Joey Erskine <erskinejoey@gmail.com>
Date: Mon, 24 Jun 2013 14:04:12 -0500
Subject: [PATCH] fixes #76 adds tablespoon spider

---
 .../openrecipes/spiders/tablespoon_spider.py  | 56 +++++++++++++++++++
 1 file changed, 56 insertions(+)
 create mode 100644 scrapy_proj/openrecipes/spiders/tablespoon_spider.py

diff --git a/scrapy_proj/openrecipes/spiders/tablespoon_spider.py b/scrapy_proj/openrecipes/spiders/tablespoon_spider.py
new file mode 100644
index 0000000..b36779e
--- /dev/null
+++ b/scrapy_proj/openrecipes/spiders/tablespoon_spider.py
@@ -0,0 +1,56 @@
+from scrapy.contrib.spiders import CrawlSpider, Rule
+from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
+from scrapy.selector import HtmlXPathSelector
+from openrecipes.items import RecipeItem, RecipeItemLoader
+
+
+class TablespoonMixin(object):
+    source = 'tablespoon'
+
+    def parse_item(self, response):
+
+        hxs = HtmlXPathSelector(response)
+
+        base_path = '//*[@class="recipe-area hrecipe"]'
+
+        recipes_scopes = hxs.select(base_path)
+
+        name_path = '//*[@class="fn"]/text()'
+        description_path = '//*[@class="summary"]/text()'
+        image_path = '//*[@class="photo"]/@src'
+        recipeYield_path = '//*[@class="servings"]/text()'
+
+        recipes = []
+
+        for r_scope in recipes_scopes:
+            il = RecipeItemLoader(item=RecipeItem())
+
+            il.add_value('source', self.source)
+
+            il.add_value('name', r_scope.select(name_path).extract())
+            il.add_value('image', r_scope.select(image_path).extract())
+            il.add_value('url', response.url)
+            il.add_value('description', r_scope.select(description_path).extract())
+            il.add_value('recipeYield', r_scope.select(recipeYield_path).extract())
+
+            recipes.append(il.load_item())
+
+        return recipes
+
+
+class TablespooncrawlSpider(CrawlSpider, TablespoonMixin):
+
+    name = "tablespoon.com"
+
+    allowed_domains = ["tablespoon.com"]
+
+    start_urls = [
+        "http://www.tablespoon.com/search/#&page_type=",
+    ]
+
+    rules = (
+        Rule(SgmlLinkExtractor(allow=('/search/#&page_type=&sort=&page=\d+'))),
+
+        Rule(SgmlLinkExtractor(allow=('/recipes/\[a-z]+/\d+/')),
+             callback='parse_item'),
+    )