Add recipe for the Sydney Morning Herald

src/calibre/web/feeds/recipes/__init__.py

@@ -7,7 +7,7 @@ Builtin recipes.
 recipes = [
            'newsweek', 'atlantic', 'economist', 'portfolio', 
            'nytimes', 'usatoday', 'outlook_india', 'bbc', 'greader', 'wsj',
-           'wired', 'globe_and_mail',
+           'wired', 'globe_and_mail', 'smh', 
           ]
 
 import re, imp, inspect, time

src/calibre/web/feeds/recipes/smh.py

@@ -0,0 +1,54 @@
+#!/usr/bin/env  python
+__license__   = 'GPL v3'
+__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
+__docformat__ = 'restructuredtext en'
+
+'''
+smh.com.au
+'''
+import time
+from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import BeautifulSoup
+
+
+class SMH(BasicNewsRecipe):
+    
+    title = 'Sydney Morning Herald'
+    description = 'Business News, World News and Breaking News in Australia'
+    __author__ = 'Kovid Goyal'
+    
+    def get_browser(self):
+        br = BasicNewsRecipe.get_browser()
+        br.set_handle_refresh(False)
+        return br
+    
+    def parse_index(self):
+        
+        soup = BeautifulSoup(self.browser.open('http://www.smh.com.au/text/').read())
+        
+        feeds, articles = [], []
+        feed = None
+        
+        
+        for tag in soup.findAll(['h3', 'a']):
+            if tag.name == 'h3':
+                if articles:
+                    feeds.append((feed, articles))
+                    articles = []
+                feed = self.tag_to_string(tag)
+            elif feed is not None and tag.has_key('href') and tag['href'].strip():
+                url = tag['href'].strip()
+                if url.startswith('/'):
+                    url   = 'http://www.smh.com.au' + url 
+                title = self.tag_to_string(tag)
+                articles.append({
+                                 'title': title,
+                                 'url'  : url,
+                                 'date' : time.strftime('%a, %d %b'),
+                                 'description' : '',
+                                 'content'     : '',
+                                 }) 
+                
+        return feeds
+                
+

src/calibre/web/fetch/simple.py

@@ -140,7 +140,7 @@ class RecursiveFetcher(object, LoggingInterface):
         except urllib2.URLError, err:
             if hasattr(err, 'code') and responses.has_key(err.code):
                 raise FetchError, responses[err.code]
-            if err.reason[0] == 104: # Connection reset by peer
+            if getattr(err, 'reason', [0])[0] == 104: # Connection reset by peer
                 self.log_debug('Connection reset by peer retrying in 1 second.')
                 time.sleep(1)
                 f = self.browser.open(url)