Village Voice by Barty

recipes/villagevoice.recipe

@@ -0,0 +1,46 @@
+#!/usr/bin/env  python
+
+import re
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class VillageVoice(BasicNewsRecipe):
+
+    title        = 'Village Voice'
+    feeds        = [
+        ("Complete Issue", "http://villagevoice.com/syndication/issue"),
+        ("News", "http://villagevoice.com/syndication/section/news"),
+        ("Music", "http://villagevoice.com/syndication/section/music"),
+        ("Movies", "http://villagevoice.com/syndication/section/film"),
+        #("Restaurants", "http://villagevoice.com/syndication/section/dining"),
+        #("Music Events", "http://villagevoice.com/syndication/events?type=music"),
+        #("Calendar Events", "http://villagevoice.com/syndication/events"),
+        #("Promotional Events", "http://villagevoice.com/syndication/promoEvents"),
+        #("Restaurant Guide", "http://villagevoice.com/syndication/restaurants/search")
+        ]
+
+    auto_cleanup          = True
+    max_articles_per_feed = 50
+    masthead_url          = "http://assets.villagevoice.com/img/citylogo.png"
+    language = 'en'
+    __author__ = 'Barty'
+
+    seen_urls = []
+
+    # village voice breaks the article up into multiple pages, so
+    # parse page and grab the print url
+
+    url_regex = re.compile(r'\/content\/printVersion\/\d+',re.I)
+
+    def print_version(self, url):
+        if url in self.seen_urls:
+            return None
+        self.seen_urls.append( url)
+        soup = self.index_to_soup(url)
+        atag = soup.find('a',attrs={'href':self.url_regex})
+        if atag is None:
+            self.log('Warning: no print url found for '+url)
+        else:
+            m = self.url_regex.search(atag['href'])
+            if m:
+                url = 'http://www.villagevoice.com'+m.group(0)
+        return url