Fixed recipes for The LA Times and Budget Fashionista

installer/osx/py2app/main.py

@@ -272,6 +272,9 @@ class Py2App(object):
         for f in glob.glob('src/calibre/plugins/*.so'):
             shutil.copy2(f, dest)
             self.fix_dependencies_in_lib(join(dest, basename(f)))
+            if 'podofo' in f:
+                self.change_dep('libpodofo.0.6.99.dylib',
+                self.FID+'/'+'libpodofo.0.6.99.dylib', join(dest, basename(f)))
 
 
     @flush
@@ -374,7 +377,7 @@ class Py2App(object):
 
     @flush
     def add_misc_libraries(self):
-        for x in ('usb', 'unrar'):
+        for x in ('usb', 'unrar', 'readline.6.0'):
             print '\nAdding', x
             x = 'lib%s.dylib'%x
             shutil.copy2(join(SW, 'lib', x), self.frameworks_dir)

src/calibre/gui2/convert/txt_output.py

@@ -6,7 +6,7 @@ __docformat__ = 'restructuredtext en'
 
 from calibre.gui2.convert.txt_output_ui import Ui_Form
 from calibre.gui2.convert import Widget
-from calibre.ebooks.txt.writer import TxtNewlines
+from calibre.ebooks.txt.newlines import TxtNewlines
 from calibre.gui2.widgets import BasicComboModel
 
 newline_model = None

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

@@ -1,7 +1,7 @@
 #!/usr/bin/env  python
 
 __license__   = 'GPL v3'
-__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
 '''
 latimes.com
 '''
@@ -17,13 +17,19 @@ class LATimes(BasicNewsRecipe):
     language              = _('English')
     no_stylesheets        = True
     use_embedded_content  = False
+    encoding              = 'utf-8'
+    lang                  = 'en-US'
 
-    keep_only_tags    = [ dict(name='div', attrs={'id':'center'   }) ]
-    remove_tags_after = [ dict(name='div', attrs={'id':'socialnet'}) ]
-    remove_tags       = [
-                           dict(name='div' , attrs={'id':'wrapper_vid'    })
-                          ,dict(name='div' , attrs={'id':'article_related'})
-                          ,dict(name='div' , attrs={'id':'socialnet'      })
-                        ]
+    conversion_options = {
+          'comment'          : description
+        , 'language'         : lang
+    }
+    
+    keep_only_tags    = [dict(name='div', attrs={'class':'story'   })]
+    remove_tags_after = [dict(name='div', attrs={'id':'story-body' })]
+    remove_tags       = [dict(name='div', attrs={'class':['thumbnail','articlerail','tools']})]
 
     feeds          = [(u'News', u'http://feeds.latimes.com/latimes/news')]
+    
+    def get_article_url(self, article):
+        return article.get('feedburner_origlink')

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

@@ -6,9 +6,7 @@ __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
 www.thebudgetfashionista.com
 '''
 
-import re
 from calibre.web.feeds.recipes import BasicNewsRecipe
-from calibre.ebooks.BeautifulSoup import Tag
 
 class TheBudgetFashionista(BasicNewsRecipe):
     title                  = 'The Budget Fashionista'
@@ -24,40 +22,22 @@ class TheBudgetFashionista(BasicNewsRecipe):
     lang                   = 'en-US'
     language               = _('English')
 
-    preprocess_regexps = [(re.compile(r"</head>{0,1}", re.DOTALL|re.IGNORECASE),lambda match: '')]
+    conversion_options = {
+          'comment'          : description
+        , 'tags'             : category
+        , 'publisher'        : publisher
+        , 'language'         : lang
+    }
 
-    html2lrf_options = [
-                          '--comment', description
-                        , '--category', category
-                        , '--publisher', publisher
-                        ]
-
-    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
-
-    keep_only_tags = [dict(name='div', attrs={'id':'singlepost'})]
-    remove_tags_after = dict(name='div', attrs={'id':'postnav'})
-    remove_tags = [
-                     dict(name=['object','link','script','iframe','form'])
-                    ,dict(name='div', attrs={'id':'postnav'})
-                  ]
+    keep_only_tags = [dict(name='div', attrs={'class':'columnLeft'})]
+    remove_tags_after = dict(name='div', attrs={'class':'postDetails'})
+    remove_tags = [dict(name=['object','link','script','iframe','form','login-button'])]
 
     feeds = [(u'Articles', u'http://www.thebudgetfashionista.com/feeds/atom/')]
 
     def preprocess_html(self, soup):
-        for item in soup.findAll(style=True):
-            del item['style']
-        return soup
+        for it in soup.findAll('img'):
+            if it.parent.name == 'a':
+               it.parent.name = 'div'
+        return soup;
 
-    def postprocess_html(self, soup, x):
-        body = soup.find('body')
-        post = soup.find('div', attrs={'id':'singlepost'})
-        if post and body:
-          post.extract()
-          body.extract()
-          soup.html.append(body)
-          body.insert(1,post)
-        mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
-        mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
-        soup.head.insert(0,mlang)
-        soup.head.insert(1,mcharset)
-        return self.adeify_images(soup)