Fix New Journal of Physics

recipes/njp.recipe

@@ -1,14 +1,25 @@
 #!/usr/bin/env  python
 # -*- coding: utf-8 -*-
 
-__license__     = 'GPL v3'
+##
+## Title:        New Journal of Physics
+## License:      GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html
+## Copyright:    Chema Cort\xe9s
+##
+## Written:      Jan 2011
+## Last Edited:  Jan 2012 - by Kiavash
+##
+
+__license__   = 'GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html'
 __copyright__   = u'Chema Cort\xe9s - 2011-01-05'
-__version__     = 'v0.01'
+__version__     = 'v0.5.0'
-__date__        = '2011-01-05'
+__date__        = '2012-01-13'
+
 '''
 njp.org
 '''
 
+import re	# Import the regular expressions module.
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class NewJournalOfPhysics(BasicNewsRecipe):
@@ -18,15 +29,61 @@ class NewJournalOfPhysics(BasicNewsRecipe):
     publisher      = u'IOP (Institute of Physics)'
     category       = 'physics, journal, science'
     language       = 'en'
-
+    
-    oldest_article = 30
-    max_articles_per_feed = 100
-
-    keep_only_tags = [dict(id=['fulltextContainer'])]
-    no_stylesheets=True
-    use_embedded_content=False
-
     feeds          = [(u'Latest Papers', u'http://iopscience.iop.org/1367-2630/?rss=1')]
+    
+    cover_url      = 'http://images.iop.org/journals_icons/Info/1367-2630/cover.gif'
+    
+    oldest_article = 7
+    max_articles_per_feed = 30
+    timeout = 30
+    
+    no_stylesheets = True
+    use_embedded_content = False
+    remove_javascript = True
+    remove_empty_feeds = True
+    asciiize = True	# Converts all none ascii characters to their ascii equivalents
+    
+    keep_only_tags = [
+                        dict(id=['articleEvoContainer']),
+                     ]
+    
+    remove_tags    = [
+                        dict(name='div', attrs={'class':'affiliations'}), # Removes Shoow Affiliations
+                        dict(name='div', attrs={'class':'abst-icon-links'}), # Removes Tags and PDF export
+                        dict(name='p', attrs={'class':'studyimage'}),	# remove Studay image
+                        dict(name='a', attrs={'class':'icon powerpoint'}),	# remove Export to PowerPoint Slide
+                        dict(name='a', attrs={'title':'CrossRef'}),	# remove CrossRef icon
+                        dict(name='a', attrs={'title':'PubMed'}),	# remove PubMed icon
+                        dict(name='a', attrs={'e4f5426941':'true'}),	# remove cross ref image
+                        dict(name='img', attrs={'src':''}),	# remove empty image
+                        dict(name='a', attrs={'class':'closeChap'}),	# remove 'Close'
+                        dict(name='ul', attrs={'class':'breadcrumbs'}),	# remove Top breadcrumbs
+                     ]
+    
+    extra_css = 'body { font-family: verdana, helvetica, sans-serif; } \
+                 .introduction, .first { font-weight: bold; } \
+                 .cross-head { font-weight: bold; font-size: 125%; } \
+                 .cap, .caption { display: block; font-size: 80%; font-style: italic; } \
+                 .cap, .caption, .caption img, .caption span { display: block; margin: 5px auto; } \
+                 .byl, .byd, .byline img, .byline-name, .byline-title, .author-name, .author-position, \
+                    .correspondent-portrait img, .byline-lead-in, .name, .bbc-role { display: block; \
+                    font-size: 80%; font-style: italic; margin: 1px auto; } \
+                 .story-date, .published { font-size: 80%; } \
+                 table { width: 100%; } \
+                 td img { display: block; margin: 5px auto; } \
+                 ul { padding-top: 10px; } \
+                 ol { padding-top: 10px; } \
+                 li { padding-top: 5px; padding-bottom: 5px; } \
+                 h1 { font-size: 175%; font-weight: bold; } \
+                 h2 { font-size: 150%; font-weight: bold; } \
+                 h3 { font-size: 125%; font-weight: bold; } \
+                 h4, h5, h6 { font-size: 100%; font-weight: bold; }'
+    
+    # Remove the line breaks.
+    preprocess_regexps     = [(re.compile(r'<br[ ]*/>', re.IGNORECASE), lambda m: ''),
+                              (re.compile(r'<br[ ]*clear.*/>', re.IGNORECASE), lambda m: ''),
+                              ]
 
     def print_version(self, url):
-        return url+"/fulltext"
+        return url+"/article"