Slate Star Codex by Ned Letcher

recipes/slate_star_codex.recipe

@@ -0,0 +1,46 @@
+#!/usr/bin/env python2
+
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
+__license__   = 'GPL v3'
+__copyright__ = '2015, Ned Letcher <ned at nedned.net>'
+
+
+"""
+calibre recipe for Slate Star Codex.
+"""
+
+
+class SlateStarCodex(BasicNewsRecipe):
+    title = u'Slate Star Codex'
+    description = 'IN A MAD WORLD, ALL BLOGGING IS PSYCHIATRY BLOGGING'
+    __author__ = 'Ned Letcher'
+    max_articles_per_feed = 20
+    language = 'en'
+    encoding = 'utf-8'
+    no_stylesheets = True
+    # alternative candidate for keep_only_tags:
+    # [{'attrs':{'class':['pjgm-posttitle', 'pjgm-postmeta', 'pjgm-postcontent']}}]
+    keep_only_tags = [dict(name='div', attrs={'class':re.compile(r'\bpost\b')})]
+    remove_tags = [dict(name='div', attrs={'class':re.compile(r'\bsharedaddy\b')})]
+   
+    def get_archived_posts(self):
+        soup = self.index_to_soup('http://slatestarcodex.com/archives/')
+        entries = soup.findAll(attrs={'class':'sya_postcontent'})
+
+        posts = []
+        for entry in entries:
+            atag = entry.find('a')
+            url = atag['href']
+            post = {
+                'title' : atag.contents[0],
+                'url' : url,
+                'date' : "-".join(url.strip('/').split('/')[-4:-1]),
+            }
+            posts.append(post)
+        return posts
+
+    def parse_index(self):
+        posts = self.get_archived_posts()
+        return [[self.title, posts]]