From ec95fab48256b9c1944c979f1cd940ae89e5f332 Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Thu, 12 Mar 2009 16:27:09 -0700
Subject: [PATCH] Add a no subscription needed version of the recipe for The
 Hew York Review of Books

---
 src/calibre/web/feeds/recipes/__init__.py     |  1 +
 .../recipe_new_york_review_of_books_no_sub.py | 44 +++++++++++++++++++
 2 files changed, 45 insertions(+)
 create mode 100644 src/calibre/web/feeds/recipes/recipe_new_york_review_of_books_no_sub.py

diff --git a/src/calibre/web/feeds/recipes/__init__.py b/src/calibre/web/feeds/recipes/__init__.py
index b3c3c4605b..65bb389903 100644
--- a/src/calibre/web/feeds/recipes/__init__.py
+++ b/src/calibre/web/feeds/recipes/__init__.py
@@ -34,6 +34,7 @@ recipe_modules = ['recipe_' + r for r in (
            'al_jazeera', 'winsupersite', 'borba', 'courrierinternational',
            'lamujerdemivida', 'soldiers', 'theonion', 'news_times',
            'el_universal', 'mediapart', 'wikinews_en', 'ecogeek', 'daily_mail',
+           'new_york_review_of_books_no_sub',
           )]
 
 import re, imp, inspect, time, os
diff --git a/src/calibre/web/feeds/recipes/recipe_new_york_review_of_books_no_sub.py b/src/calibre/web/feeds/recipes/recipe_new_york_review_of_books_no_sub.py
new file mode 100644
index 0000000000..d4aeba3537
--- /dev/null
+++ b/src/calibre/web/feeds/recipes/recipe_new_york_review_of_books_no_sub.py
@@ -0,0 +1,44 @@
+#!/usr/bin/env  python
+__license__   = 'GPL v3'
+__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
+__docformat__ = 'restructuredtext en'
+
+'''
+nybooks.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+from lxml import html
+from calibre.constants import preferred_encoding
+
+class NewYorkReviewOfBooks(BasicNewsRecipe):
+    
+    title = u'New York Review of Books (no subscription)'
+    description = u'Book reviews'
+    language = _('English')
+    __author__ = 'Kovid Goyal' 
+    remove_tags_before = {'id':'container'}
+    remove_tags = [{'class':['noprint', 'ad', 'footer']}, {'id':'right-content'}]
+
+    def parse_index(self):
+        root = html.fromstring(self.browser.open('http://www.nybooks.com/current-issue').read())
+        date = root.xpath('//h4[@class = "date"]')[0]
+        self.timefmt = ' ['+date.text.encode(preferred_encoding)+']'
+        articles = []
+        for tag in date.itersiblings():
+            if tag.tag == 'h4': break
+            if tag.tag == 'p':
+                if tag.get('class') == 'indented':
+                    articles[-1]['description'] += html.tostring(tag)
+                else:
+                    href = tag.xpath('descendant::a[@href]')[0].get('href')
+                    article = {
+                               'title': u''.join(tag.xpath('descendant::text()')),
+                               'date' : '',
+                               'url'  : 'http://www.nybooks.com'+href,
+                               'description': '',
+                               }
+                    articles.append(article)
+                    
+        return [('Current Issue', articles)]
+