Merge from trunk

recipes/automatiseringgids.recipe

@@ -0,0 +1,39 @@
+import re
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class autogids(BasicNewsRecipe):
+    title = u'Automatiseringgids IT'
+    oldest_article = 7
+    __author__     = 'DrMerry'
+    description    = 'IT-nieuws van Automatiseringgids'
+    language       = 'nl'
+    publisher              = 'AutomatiseringGids'
+    category               = 'Nieuws, IT, Nederlandstalig'
+    simultaneous_downloads = 5
+    #delay          = 1
+    timefmt        = ' [%A, %d %B, %Y]'
+    #timefmt        = ''
+    no_stylesheets = True
+    remove_javascript = True
+    remove_empty_feeds = True
+    publication_type = 'newspaper'
+    encoding              = 'utf-8'
+    cover_url    = 'http://www.automatiseringgids.nl/siteimg/header_logo.gif'
+    keep_only_tags = [dict(id=['content'])]
+    extra_css = '.artikelheader {font-size:0.8em; color: #666;} .artikelintro {font-weight:bold} div.imgArticle {float: right; margin: 0 0em 1em 1em; display: block; position: relative; } \
+        h2 { margin: 0 0 0.5em; min-height: 30px; font-size: 1.5em; letter-spacing: -0.2px; margin: 0 0 0.5em; color: black; font-weight: bold; line-height: 1.2em; padding: 4px 3px 0; }'
+
+
+
+    remove_tags = [dict(name='div', attrs={'id':['loginbox','reactiecollapsible','reactiebox']}),
+        dict(name='div', attrs={'class':['column_a','column_c','bannerfullsize','reactieheader','reactiecollapsible','formulier','artikel_headeroptions']}),
+        dict(name='ul', attrs={'class':['highlightlist']}),
+        dict(name='input', attrs={'type':['button']}),
+        dict(name='div', attrs={'style':['display:block; width:428px; height:30px; float:left;']}),
+    ]
+    preprocess_regexps = [
+        (re.compile(r'(<h3>Reacties</h3>|<h2>Zie ook:</h2>|<div style=".*</div>|<a[^>]*>|</a>)', re.DOTALL|re.IGNORECASE),
+        lambda match: ''),
+    ]
+
+    feeds          = [(u'Actueel', u'http://www.automatiseringgids.nl/rss.aspx')]

recipes/computer_active.recipe

@@ -1,9 +1,9 @@
 #!/usr/bin/env  python
 __license__     = 'GPL v3'
 __author__      = 'DrMerry Based on v1.01 by Lorenzo Vigentini'
-__copyright__   = 'For version 1.02: DrMerry'
+__copyright__   = 'For version 1.02, 1.03: DrMerry'
-__version__     = 'v1.02'
+__version__     = 'v1.03'
-__date__        = '08, July 2011'
+__date__        = '11, July 2011'
 __description__ = 'Computeractive publishes new downloads, reviews, news stories, step-by-step guides and answers to PC problems every day. Original version (c): 2009, Lorenzo Vigentini <l.vigentini at gmail.com>'
 
 '''
@@ -11,9 +11,10 @@ http://www.computeractive.co.uk/
 '''
 
 from calibre.web.feeds.news import BasicNewsRecipe
+import re
 
 class computeractive(BasicNewsRecipe):
-    __author__    = 'Lorenzo Vigentini'
+    __author__      = 'DrMerry'
     description   = 'Computeractive publishes new downloads, reviews, news stories, step-by-step guides and answers to PC problems every day.'
     cover_url     = 'http://images.pcworld.com/images/common/header/header-logo.gif'
 
@@ -31,6 +32,8 @@ class computeractive(BasicNewsRecipe):
 
     remove_javascript     = True
     no_stylesheets        = True
+    remove_empty_feeds   = True
+    remove_tags_after = dict(name='div', attrs={'class':'article_tags_block'})
 
     keep_only_tags     = [
                             dict(name='div', attrs={'id':'container_left'})
@@ -42,13 +45,14 @@ class computeractive(BasicNewsRecipe):
                             dict(name='a', attrs={'class':'largerImage'})
                         ]
 
+    preprocess_regexps = [
+        (re.compile(r'(<a [^>]*>|</a>)', re.DOTALL|re.IGNORECASE),
+        lambda match: ''),
+    ]
+
     feeds          = [
                        (u'General content', u'http://feeds.computeractive.co.uk/rss/latest/computeractive/all'),
                        (u'News', u'http://feeds.computeractive.co.uk/rss/latest/computeractive/news'),
-                       (u'Downloads', u'http://feeds.computeractive.co.uk/rss/latest/computeractive/downloads'),
-                       (u'Hardware', u'http://feeds.computeractive.co.uk/rss/latest/computeractive/hardware'),
-                       (u'Software', u'http://feeds.computeractive.co.uk/rss/latest/computeractive/software'),
-                       (u'Competitions', u'http://www.v3.co.uk/feeds/rss20/personal-technology/competitions')
                      ]
 
 

recipes/geek_poke.recipe

@@ -0,0 +1,35 @@
+#!/usr/bin/python
+
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
+class AdvancedUserRecipe1307556816(BasicNewsRecipe):
+    title          = u'Geek and Poke'
+    __author__     = u'DrMerry'
+    description    = u'Geek and Poke Cartoons'
+    oldest_article = 31
+    max_articles_per_feed = 100
+    language       = u'en'
+    simultaneous_downloads = 5
+    #delay          = 1
+    timefmt        = ' [%A, %d %B, %Y]'
+    summary_length = -1
+    no_stylesheets = True
+    cover_url = 'http://geekandpoke.typepad.com/aboutcoders.jpeg'
+    remove_javascript = True
+    remove_empty_feeds = True
+    publication_type = 'blog'
+
+    preprocess_regexps = [ (re.compile(r'(<p>&nbsp;</p>|<iframe.*</iframe>|<a[^>]*>Tweet</a>|<a[^>]*>|</a>)', re.DOTALL|re.IGNORECASE),lambda match: ''),
+                                          (re.compile(r'(&nbsp;|  )', re.DOTALL|re.IGNORECASE),lambda match: ' '),
+                                          (re.compile(r'<br( /)?>(<br( /)?>)+', re.DOTALL|re.IGNORECASE),lambda match: '<br>')
+                                         ]
+
+    extra_css = 'body, h3, p, h2, h1, div, span{margin:0px} h2.date-header {font-size: 0.7em; color:#eee;} h3.entry-header{font-size: 1.0em} div.entry-body{font-size: 0.9em}'
+
+
+    remove_tags_before = dict(name='h2', attrs={'class':'date-header'})
+    remove_tags_after = dict(name='div', attrs={'class':'entry-body'})
+
+
+    feeds          = [(u'Geek and Poke', u'http://feeds.feedburner.com/GeekAndPoke?format=xml')]