From 383e16cff2aba5c7a998c3dce0ee6727bd5c8ae7 Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Wed, 20 Jan 2016 14:59:39 +0530
Subject: [PATCH] Update Business World Magazine

Fixes #1534463 [Business World Indian Recipe not working](https://bugs.launchpad.net/calibre/+bug/1534463)
---
 recipes/businessworldin.recipe | 73 ++++++++--------------------------
 1 file changed, 16 insertions(+), 57 deletions(-)

diff --git a/recipes/businessworldin.recipe b/recipes/businessworldin.recipe
index cb5f443e9f..02f58f6757 100644
--- a/recipes/businessworldin.recipe
+++ b/recipes/businessworldin.recipe
@@ -4,73 +4,32 @@ __copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
 www.businessworld.in
 '''
 
-import re
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class BusinessWorldMagazine(BasicNewsRecipe):
     title                = 'Business World Magazine'
     __author__           = 'Kovid Goyal'
     description          = 'News from India'
-    publisher            = 'ABP Pvt Ltd Publication'
     category             = 'news, politics, finances, India, Asia'
-    delay                = 1
     no_stylesheets       = True
-    INDEX                = 'http://www.businessworld.in/businessworld/magazine_latest_issue.php'
-    ROOT                 = 'http://www.businessworld.in'
     encoding             = 'utf-8'
     language             = 'en_IN'
-    auto_cleanup = True
-
-    def parse_index(self):
-        br = self.browser
-        br.open(self.ROOT)
-        raw = br.open(br.click_link(text_regex=re.compile('Current.*Issue',
-            re.I))).read()
-        soup = self.index_to_soup(raw)
-        mc = soup.find(attrs={'class':'mag_cover'})
-        if mc is not None:
-            img = mc.find('img', src=True)
-            if img is not None:
-                self.cover_url = img['src']
-
-        feeds = []
-        current_section = None
-        articles = []
-        for tag in soup.findAll(['h3', 'h2']):
-            inner_a = tag.find('a')
-            if tag.name == 'h3' and inner_a is not None:
-                continue
-            if tag.name == 'h2' and (inner_a is None or current_section is
-                    None):
-                continue
-
-            if tag.name == 'h3':
-                if current_section is not None and articles:
-                    feeds.append((current_section, articles))
-                current_section = self.tag_to_string(tag)
-                self.log('Found section:', current_section)
-                articles = []
-            elif tag.name == 'h2':
-                url = inner_a.get('href', None)
-                if url is None: continue
-                if url.startswith('/'): url = self.ROOT + url
-                title = self.tag_to_string(inner_a)
-                h1 = tag.findPreviousSibling('h1')
-                if h1 is not None:
-                    title = self.tag_to_string(h1) + title
-                self.log('\tFound article:', title)
-                articles.append({'title':title, 'url':url, 'date':'',
-                    'description':''})
-
-        if current_section and articles:
-            feeds.append((current_section, articles))
-
-        return feeds
-
-
-
-
-
+    oldest_article       = 2
 
+    keep_only_tags = [
+        dict(attrs={'class':['main-article']}),
+    ]
+    remove_tags = [
+        dict(id='video_n_ad_div'),
+        dict(attrs={'class':['meta-tools', 'social-article']}),
+    ]
+    remove_tags_after = dict(attrs={'class':'social-article'})
 
+    feeds = ['http://www.businessworld.in/rss/all-article.xml']
 
+    def preprocess_html(self, soup):
+        for img in soup.findAll('img', attrs={'data-original':True}):
+            img['src'] = img['data-original']
+        for ins in soup.findAll(attrs={'class':'adsbygoogle'}):
+            ins.parent.extract()
+        return soup