Kovid's 6.18 changes

.bzrignore

@@ -9,9 +9,9 @@ dist
 docs
 resources/localization
 resources/images.qrc
-resources/recipes.pickle
 resources/scripts.pickle
 resources/ebook-convert-complete.pickle
+resources/builtin_recipes.xml
 setup/installer/windows/calibre/build.log
 src/calibre/translations/.errors
 src/cssutils/.svn/

README

@@ -15,3 +15,5 @@ bzr branch lp:calibre
 To update your copy of the source code:
 bzr merge
 
+Tarballs of the source code for each release are now available \
+at http://code.google.com/p/calibre-ebook

resources/recipes/businessworldin.recipe

@@ -0,0 +1,77 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+www.businessworld.in
+'''
+
+from calibre import strftime
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class BusinessWorldMagazine(BasicNewsRecipe):
+    title                = 'Business World Magazine'
+    __author__           = 'Darko Miletic'
+    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/bw/Magazine_Current_Issue'
+    ROOT                 = 'http://www.businessworld.in'
+    use_embedded_content = False
+    encoding             = 'utf-8'
+    language             = 'en_IN'
+
+
+    conversion_options = {
+                          'comment'          : description
+                        , 'tags'             : category
+                        , 'publisher'        : publisher
+                        , 'language'         : language
+                        }
+
+    def is_in_list(self,linklist,url):
+        for litem in linklist:
+            if litem == url:
+               return True
+        return False
+    
+    
+    def parse_index(self):
+        articles = []
+        linklist = []
+        soup = self.index_to_soup(self.INDEX)
+
+        for item in soup.findAll('div', attrs={'class':'nametitle'}):
+            description = ''
+            title_prefix = ''
+            feed_link = item.find('a')
+            if feed_link and feed_link.has_key('href'):
+                url   = self.ROOT + feed_link['href']
+                if not self.is_in_list(linklist,url):
+                    title = title_prefix + self.tag_to_string(feed_link)
+                    date  = strftime(self.timefmt)
+                    articles.append({
+                                      'title'      :title
+                                     ,'date'       :date
+                                     ,'url'        :url
+                                     ,'description':description
+                                    })
+                    linklist.append(url)
+        return [(soup.head.title.string, articles)]
+
+    
+    keep_only_tags = [dict(name='div', attrs={'id':['register-panel','printwrapper']})]
+    remove_tags = [dict(name=['object','link'])]
+
+    def print_version(self, url):
+        return url.replace('/bw/','/bw/storyContent/')
+
+    def get_cover_url(self):
+        cover_url = None
+        soup = self.index_to_soup(self.INDEX)
+        cover_item = soup.find('img',attrs={'class':'toughbor'})
+        if cover_item:
+           cover_url = self.ROOT + cover_item['src']
+        return cover_url

resources/recipes/dailyreckoning.recipe

@@ -0,0 +1,47 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+dailyreckoning.com
+'''
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class dailyreckoning_us(BasicNewsRecipe):
+    title                 = 'The Daily Reckoning - US edition'
+    __author__            = 'Darko Miletic'
+    description           = 'Worldwide business and financial news and articles'
+    publisher             = 'Agora Financial, LLC.'
+    category              = 'news, business, finances, money, banking'
+    oldest_article        = 7
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    encoding              = 'utf-8'
+    language              = 'en'
+    extra_css             = ' #BlogTitle{font-size: x-large; font-weight: bold} #BlogDate{font-size: small} '
+
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+    feeds = [(u'Articles', u'http://feeds.feedburner.com/dailyreckoning?format=xml')]
+
+    keep_only_tags = [dict(name='div', attrs={'id':'Outline'})]
+    
+    remove_tags = [
+                     dict(name=['object','link','base'])
+                    ,dict(name='hr', attrs={'class':'Divider'})
+                  ]
+                  
+    remove_tags_after = dict(name='hr', attrs={'class':'Divider'})
+
+    def get_article_url(self, article):
+        return article.get('feedburner_origlink', article.get('link'))
+        
+    def print_version(self, url):
+        return url + 'print/'
+    

resources/recipes/economist.recipe

@@ -8,8 +8,7 @@ economist.com
 from calibre.web.feeds.news import BasicNewsRecipe
 from calibre.ebooks.BeautifulSoup import BeautifulSoup
 
-import mechanize, string
+import mechanize, string, urllib
-from urllib2 import quote
 
 class Economist(BasicNewsRecipe):
 
@@ -24,15 +23,26 @@ class Economist(BasicNewsRecipe):
     cover_url = 'http://www.economist.com/images/covers/currentcovereu_large.jpg'
     remove_tags = [dict(name=['script', 'noscript', 'title'])]
     remove_tags_before = dict(name=lambda tag: tag.name=='title' and tag.parent.name=='body')
+    needs_subscription = True
 
     def get_browser(self):
         br = BasicNewsRecipe.get_browser()
-        if self.username is not None and self.password is not None:
+        br.open('http://www.economist.com')
-            req = mechanize.Request('http://www.economist.com/members/members.cfm?act=exec_login', headers={'Referer':'http://www.economist.com'})
+        req = mechanize.Request(
-            data = 'logging_in=Y&returnURL=http%253A%2F%2Fwww.economist.com%2Findex.cfm&email_address=username&pword=password&x=7&y=11'
+                'http://www.economist.com/members/members.cfm?act=exec_login',
-            data = data.replace('username', quote(self.username)).replace('password', quote(self.password))
+                headers = {
-            req.add_data(data)
+                    'Referer':'http://www.economist.com/',
-            br.open(req).read()
+                    },
+                data=urllib.urlencode({
+                    'logging_in' : 'Y',
+                    'returnURL'  : '/',
+                    'email_address': self.username,
+                    'fakepword' : 'Password',
+                    'pword'     : self.password,
+                    'x'         : '0',
+                    'y'         : '0',
+                    }))
+        br.open(req).read()
         return br
 
     def parse_index(self):