Update various Polish recipes. And new ones for fronda and runa by Tomasz Dugosz and Mori, resp.

resources/recipes/di.recipe

@@ -15,42 +15,42 @@ class DziennikInternautowRecipe(BasicNewsRecipe):
 	language = 'pl'
 
 	title = u'Dziennik Internautow'
-	publisher = u'Dziennik Internaut\xc3\xb3w Sp. z o.o.'
-	description =u'Internet w \xc5\xbcyciu i biznesie. Porady, wywiady, interwencje, bezpiecze\xc5\x84stwo w Sieci, technologia.'
+	publisher = u'Dziennik Internaut\u00f3w Sp. z o.o.'
+	description = u'Internet w \u017cyciu i biznesie. Porady, wywiady, interwencje, bezpiecze\u0144stwo w Sieci, technologia.'
 
 	max_articles_per_feed = 100
 	oldest_article = 7
 	cover_url = 'http://di.com.pl/pic/logo_di_norm.gif'
-
+	
 	no_stylesheets = True
 	remove_javascript = True
 	encoding = 'utf-8'
-
+	
 	extra_css = '''
 		.fotodesc{font-size: 75%;}
 		.pub_data{font-size: 75%;}
 		.fotonews{clear: both; padding-top: 10px; padding-bottom: 10px;}
 		#pub_foto{font-size: 75%; float: left; padding-right: 10px;}
 	'''
-
+	
 	feeds = [
-		(u'Dziennik Internautów', u'http://feeds.feedburner.com/glowny-di')
+		(u'Dziennik Internaut\u00f3w', u'http://feeds.feedburner.com/glowny-di')
 	]
-
+	
 	keep_only_tags = [
 		dict(name = 'div', attrs = {'id' : 'pub_head'}),
 		dict(name = 'div', attrs = {'id' : 'pub_content'})
 	]
-
+	
 	remove_tags = [
 		dict(name = 'div', attrs = {'class' : 'poradniki_context'}),
 		dict(name = 'div', attrs = {'class' : 'uniBox'}),
 		dict(name = 'object', attrs = {}),
 		dict(name = 'h3', attrs = {})
 	]
-
+	
 	preprocess_regexps = [
-		(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
+		(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in 
 		[
 			(r', <a href="http://di.com.pl/komentarze,.*?</div>', lambda match: '</div>'),
 			(r'<div class="fotonews".*?">', lambda match: '<div class="fotonews">'),

resources/recipes/eclicto.recipe

@@ -1,6 +1,6 @@
 #!/usr/bin/env  python
 
-__license__ = 'GPL v3'
+__license__	= 'GPL v3'
 __author__ = 'Mori'
 __version__ = 'v. 0.1'
 '''
@@ -11,39 +11,39 @@ from calibre.web.feeds.news import BasicNewsRecipe
 import re
 
 class BlogeClictoRecipe(BasicNewsRecipe):
-    __author__ = 'Mori'
-    language = 'pl'
+	__author__ = 'Mori'
+	language = 'pl'
 
-    title = u'Blog eClicto'
-    publisher = u'Blog eClicto'
-    description = u'Blog o e-papierze i e-bookach'
+	title = u'Blog eClicto'
+	publisher = u'Blog eClicto'
+	description = u'Blog o e-papierze i e-bookach'
 
-    max_articles_per_feed = 100
-    cover_url = 'http://blog.eclicto.pl/wordpress/wp-content/themes/blog_eclicto/g/logo.gif'
-
-    no_stylesheets = True
-    remove_javascript = True
-    encoding = 'utf-8'
-
-    extra_css = '''
-        img{float: left; padding-right: 10px; padding-bottom: 5px;}
-    '''
-
-    feeds = [
-        (u'Blog eClicto', u'http://blog.eclicto.pl/feed/')
-    ]
-
-    remove_tags = [
-        dict(name = 'span', attrs = {'id' : 'tags'})
-    ]
-
-    remove_tags_after = [
-        dict(name = 'div', attrs = {'class' : 'post'})
-    ]
-
-    preprocess_regexps = [
-        (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
-        [
-            (r'\s*</', lambda match: '</'),
-        ]
-    ]
+	max_articles_per_feed = 100
+	cover_url = 'http://blog.eclicto.pl/wordpress/wp-content/themes/blog_eclicto/g/logo.gif'
+	
+	no_stylesheets = True
+	remove_javascript = True
+	encoding = 'utf-8'
+	
+	extra_css = '''
+		img{float: left; padding-right: 10px; padding-bottom: 5px;}
+	'''
+	
+	feeds = [
+		(u'Blog eClicto', u'http://blog.eclicto.pl/feed/')
+	]
+	
+	remove_tags = [
+		dict(name = 'span', attrs = {'id' : 'tags'})
+	]
+	
+	remove_tags_after = [
+		dict(name = 'div', attrs = {'class' : 'post'})
+	]
+	
+	preprocess_regexps = [
+		(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in 
+		[
+			(r'\s*</', lambda match: '</'),
+		]
+	]

resources/recipes/eksiazki.recipe

@@ -11,7 +11,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
 class eksiazki(BasicNewsRecipe):
 
     title          = u'eKsiazki.org'
-    desciption     = u'Twoje centrum wiedzy o ePapierze i eBookach'
+    description    = u'Twoje centrum wiedzy o ePapierze i eBookach'
     language = 'pl'
     __author__ = u'Tomasz D\u0142ugosz'
     no_stylesheets = True

resources/recipes/fronda.recipe

@@ -0,0 +1,34 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2010, Tomasz Dlugosz <tomek3d@gmail.com>'
+'''
+fronda.pl
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
+class Fronda(BasicNewsRecipe):
+    title          = u'Fronda.pl'
+    publisher      = u'Fronda.pl'
+    description    = u'Portal po\u015bwi\u0119cony - Infformacje'
+    language = 'pl'
+    __author__ = u'Tomasz D\u0142ugosz'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    use_embedded_content = False
+
+    feeds          = [(u'Infformacje', u'http://fronda.pl/news/feed')]
+
+    keep_only_tags = [dict(name='h1', attrs={'class':'big'}),
+                      dict(name='ul', attrs={'class':'about clear'}),
+                      dict(name='div', attrs={'class':'content'})]
+    preprocess_regexps = [
+        (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in 
+            [ (r'<a href="#" class="print">Drukuj</a>', lambda match: ''),
+              (r'<p><a href="http://fronda.pl/sklepy">.*</a></p>', lambda match: ''),
+              (r'<p><a href="http://fronda.pl/pasaz">.*</a></p>', lambda match: ''),
+              (r'<h3><strong>W.* lektury.*</a></p></div>', lambda match: '</div>'),
+              (r'<h3>Zobacz t.*?</div>', lambda match: '</div>') ]
+    ]

resources/recipes/interia_fakty.recipe

@@ -10,6 +10,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
 
 class InteriaFakty(BasicNewsRecipe):
     title          = u'Interia.pl - Fakty'
+    description    = u'Fakty ze strony interia.pl'
     language = 'pl'
     oldest_article = 7
     __author__ = u'Tomasz D\u0142ugosz'

resources/recipes/interia_sport.recipe

@@ -11,6 +11,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
 
 class InteriaSport(BasicNewsRecipe):
     title          = u'Interia.pl - Sport'
+    description    = u'Sport ze strony interia.pl'
     language = 'pl'
     oldest_article = 7
     __author__ = u'Tomasz D\u0142ugosz'
@@ -30,7 +31,8 @@ class InteriaSport(BasicNewsRecipe):
 
     keep_only_tags = [dict(name='div', attrs={'id':'article'})]
 
-    remove_tags = [dict(name='div', attrs={'class':'object gallery'})]
+    remove_tags = [dict(name='div', attrs={'class':'object gallery'}),
+                   dict(name='div', attrs={'class':'box fontSizeSwitch'})]
 
     extra_css = '''
         .articleDate {

resources/recipes/legeartis.recipe

@@ -1,6 +1,6 @@
 #!/usr/bin/env  python
 
-__license__ = 'GPL v3'
+__license__	= 'GPL v3'
 __author__ = 'Mori'
 __version__ = 'v. 0.1'
 '''
@@ -10,34 +10,34 @@ olgierd.bblog.pl
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class LegeArtisRecipe(BasicNewsRecipe):
-    __author__ = 'Mori'
-    language = 'pl'
+	__author__ = 'Mori'
+	language = 'pl'
 
-    title = u'Lege Artis'
-    publisher = u'Olgierd Rudak'
-    description = u'Wszystko, co chcieliby\xc5\x9bcie wiedzie\xc4\x87 o prawie, ale wstydzicie si\xc4\x99 zapyta\xc4\x87'
+	title = u'Lege Artis'
+	publisher = u'Olgierd Rudak'
+	description = u'Wszystko, co chcieliby\u015bcie wiedzie\u0107 o prawie, ale wstydzicie si\u0119 zapyta\u0107'
 
-    max_articles_per_feed = 100
-
-    no_stylesheets = True
-    remove_javascript = True
-
-    extra_css = '''
-        img{clear: both;}
-    '''
-
-    feeds = [
-        (u'Lege Artis', u'http://olgierd.bblog.pl/rss/rss20.xml')
-    ]
-
-    keep_only_tags = [
-        dict(name = 'div', attrs = {'class' : 'post_title'}),
-        dict(name = 'div', attrs = {'class' : 'post_date'}),
-        dict(name = 'div', attrs = {'class' : 'post_content'})
-    ]
-
-    remove_tags = [
-        dict(name = 'div', attrs = {'id' : 'bb_tools'}),
-        dict(name = 'div', attrs = {'class' : 'post_comments'}),
-        dict(name = 'object', attrs = {})
-    ]
+	max_articles_per_feed = 100
+	
+	no_stylesheets = True
+	remove_javascript = True
+	
+	extra_css = '''
+		img{clear: both;}
+	'''
+	
+	feeds = [
+		(u'Lege Artis', u'http://olgierd.bblog.pl/rss/rss20.xml')
+	]
+	
+	keep_only_tags = [
+		dict(name = 'div', attrs = {'class' : 'post_title'}),
+		dict(name = 'div', attrs = {'class' : 'post_date'}),
+		dict(name = 'div', attrs = {'class' : 'post_content'})
+	]
+	
+	remove_tags = [
+		dict(name = 'div', attrs = {'id' : 'bb_tools'}),
+		dict(name = 'div', attrs = {'class' : 'post_comments'}),
+		dict(name = 'object', attrs = {})
+	]

resources/recipes/legitymizm.recipe

@@ -10,6 +10,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
 
 class Legitymizm(BasicNewsRecipe):
     title          = u'Organizacja Monarchist\xf3w Polskich'
+    description    = u'Portal legitymistyczny'
     language = 'pl'
     oldest_article = 7
     __author__ = u'Tomasz D\u0142ugosz'

resources/recipes/michalkiewicz.recipe

@@ -12,7 +12,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
 
 class michalkiewicz(BasicNewsRecipe):
     title          = u'Stanis\u0142aw Michalkiewicz'
-    desciption     = u'Strona autorska * felietony * artyku\u0142y * komentarze'
+    description    = u'Strona autorska * felietony * artyku\u0142y * komentarze'
     __author__     = u'Tomasz D\u0142ugosz'
     language       = 'pl'
     oldest_article = 7

resources/recipes/nczas.recipe

@@ -12,7 +12,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
 
 class NCzas(BasicNewsRecipe):
     title          = u'Najwy\u017cszy Czas!'
-    desciption     = u'Najwy\u017cszy Czas!\nwydanie internetowe'
+    description    = u'Najwy\u017cszy Czas!\nwydanie internetowe'
     __author__     = u'Tomasz D\u0142ugosz'
     language       = 'pl'
     oldest_article = 7

resources/recipes/runa.recipe

@@ -0,0 +1,52 @@
+#!/usr/bin/env  python
+
+__license__ = 'GPL v3'
+__author__ = 'Mori'
+__version__ = 'v. 0.1'
+'''
+www.runa.pl/blog
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
+class FantazmatyRecipe(BasicNewsRecipe):
+	__author__ = 'Mori'
+	language = 'pl'
+
+	title = u'Fantazmaty'
+	publisher = u'Agencja Wydawnicza Runa'
+	description = u'Blog Agencji Wydawniczej Runa'
+	
+	no_stylesheets = True
+	remove_javascript = True
+	encoding = 'utf-8'
+	
+	oldest_article = 100
+	max_articles_per_feed = 100
+	
+	extra_css = '''
+		img{float: left; padding-right: 10px; padding-bottom: 5px;}
+	'''
+	
+	feeds = [
+		(u'Fantazmaty', u'http://www.runa.pl/blog/rss.xml')
+	]
+	
+	remove_tags = [
+		dict(name = 'div', attrs = {'class' : 'path'}),
+		dict(name = 'div', attrs = {'class' : 'drdot'}),
+		dict(name = 'div', attrs = {'class' : 'picture'})
+	]
+	
+	remove_tags_after = [
+		dict(name = 'div', attrs = {'class' : 'content'})
+	]
+	
+	preprocess_regexps = [
+		(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in 
+		[
+			(r'<body>.*?<div id="primary"', lambda match: '<body><div id="primary"'),
+			(r'<!--.*?-->', lambda match: '')
+		]
+	]