Various new and updated Polish news sources

recipes/archeowiesci.recipe

@@ -1,7 +1,7 @@
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Archeowiesci(BasicNewsRecipe):
-    title          = u'Archeowiesci'
+    title          = u'Archeowieści'
     __author__        = 'fenuks'
     category       = 'archeology'
     language       = 'pl'

recipes/bachormagazyn.recipe

@@ -0,0 +1,43 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+__license__   = 'GPL v3'
+__copyright__   = u'Łukasz Grąbczewski 2013'
+__version__   = '1.0'
+
+'''
+bachormagazyn.pl
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class bachormagazyn(BasicNewsRecipe):
+	__author__ = u'Łukasz Grączewski'
+	title = u'Bachor Magazyn'
+	description = u'Alternatywny magazyn o alternatywach rodzicielstwa'
+	language = 'pl'
+	publisher = 'Bachor Mag.'
+	publication_type = 'magazine'
+	masthead_url = 'http://bachormagazyn.pl/wp-content/uploads/2011/10/bachor_header1.gif'
+	no_stylesheets = True
+	remove_javascript = True
+	use_embedded_content = False
+	remove_empty_feeds = True
+	
+	oldest_article = 32 #monthly +1
+	max_articles_per_feed = 100
+
+	feeds = [
+			(u'Bezradnik dla nieudacznych rodziców', u'http://bachormagazyn.pl/feed/')
+			]
+
+	keep_only_tags = []
+	keep_only_tags.append(dict(name = 'div', attrs = {'id' : 'content'}))
+
+	remove_tags = []
+	remove_tags.append(dict(attrs = {'id' : 'nav-above'}))
+	remove_tags.append(dict(attrs = {'id' : 'nav-below'}))
+	remove_tags.append(dict(attrs = {'id' : 'comments'}))
+	remove_tags.append(dict(attrs = {'class' : 'entry-info'}))
+	remove_tags.append(dict(attrs = {'class' : 'comments-link'}))
+	remove_tags.append(dict(attrs = {'class' : 'sharedaddy sd-sharing-enabled'}))

recipes/frazpc.recipe

@@ -18,6 +18,7 @@ class FrazPC(BasicNewsRecipe):
     max_articles_per_feed = 100
     use_embedded_content = False
     no_stylesheets = True
+    remove_empty_feeds = True
     cover_url='http://www.frazpc.pl/images/logo.png'
     feeds          = [
         (u'Aktualno\u015bci', u'http://www.frazpc.pl/feed/aktualnosci'),

recipes/kopalniawiedzy.recipe

@@ -16,6 +16,7 @@ class KopalniaWiedzy(BasicNewsRecipe):
     max_articles_per_feed = 100
     INDEX          = u'http://kopalniawiedzy.pl/'
     remove_javascript     = True
+    remove_empty_feeds = True
     no_stylesheets        = True
 
     remove_tags    = [{'name':'p', 'attrs': {'class': 'keywords'}}, {'name':'div', 'attrs': {'class':'sexy-bookmarks sexy-bookmarks-bg-caring'}}, {'name':'div', 'attrs': {'class':'article-time-and-cat'}}, {'name':'p', 'attrs': {'class':'tags'}}]

recipes/kurier_galicyjski.recipe

@@ -3,7 +3,7 @@ from calibre.ebooks.BeautifulSoup import BeautifulSoup as bs
 class KurierGalicyjski(BasicNewsRecipe):
     title          = u'Kurier Galicyjski'
     __author__        = 'fenuks'
-    #description   = u''
+    description   = u'Kurier Galicyjski - największa gazeta dla Polaków na Ukrainie. Bieżące wydarzenia z życia polskiej mniejszości, historia, kultura, polityka, reportaże.'
     category       = 'news'
     language       = 'pl'
     cover_url = 'http://www.duszki.pl/Kurier_galicyjski_bis2_small.gif'

recipes/kurier_szczecinski.recipe

@@ -3,7 +3,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
 class KurierSzczecinski(BasicNewsRecipe):
     title          = u'Kurier Szczeci\u0144ski'
     __author__        = 'fenuks'
-    description   = u'24Kurier jest portalem Kuriera Szczecińskiego. Zawiera aktualności ze Szczecina oraz wiadomości regionalne z  województwa zachodniopomorskiego. '
+    description   = u'24Kurier jest portalem Kuriera Szczecińskiego. Zawiera aktualności ze Szczecina oraz wiadomości regionalne z  województwa zachodniopomorskiego.'
     category       = 'newspaper'
     #publication_type = ''
     language       = 'pl'

recipes/niebezpiecznik.recipe

@@ -3,7 +3,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
 class Niebezpiecznik_pl(BasicNewsRecipe):
     title          = u'Niebezpiecznik.pl'
     __author__        = 'fenuks'
-    description   = 'Niebezpiecznik.pl'
+    description   = u'Niebezpiecznik.pl – o bezpieczeństwie i nie...'
     category       = 'hacking, IT'
     language       = 'pl'
     oldest_article = 8

recipes/nowy_obywatel.recipe

@@ -0,0 +1,42 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+__license__   = 'GPL v3'
+__copyright__   = u'Łukasz Grąbczewski 2013'
+__version__   = '1.0'
+
+'''
+nowyobywatel.pl
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class nowyobywatel(BasicNewsRecipe):
+	__author__ = u'Łukasz Grączewski'
+	title = u'Nowy Obywatel'
+	description = u'Pismo na rzecz sprawiedliwości społecznej'
+	language = 'pl'
+	publisher = 'Stowarzyszenie „Obywatele Obywatelom”'
+	publication_type = 'magazine'
+	masthead_url = 'http://lewicowo.pl/wp-content/uploads/2011/11/nowy-obywatel1.png'
+	no_stylesheets = True
+	remove_javascript = True
+	use_embedded_content = True
+	remove_empty_feeds = True
+	
+	oldest_article = 32 #monthly +1
+	max_articles_per_feed = 100
+	simultaneous_downloads = 20
+
+	feeds = [
+			(u'Aktualności', u'http://nowyobywatel.pl/category/aktualnosci/feed/'),
+			(u'Opinie', u'http://nowyobywatel.pl/category/opinie/feed/'),
+			(u'Nasze rozmowy', u'http://nowyobywatel.pl/category/nasze-rozmowy/feed/'),
+			(u'Inspiracje', u'http://nowyobywatel.pl/category/inspiracje/feed/')
+			]
+	
+
+	remove_tags = []
+	remove_tags.append(dict(attrs = {'class' : 'post-date'}))
+	remove_tags.append(dict(attrs = {'class' : 'printfriendly'}))
+	remove_tags.append(dict(attrs = {'class' : 'social4i'}))

recipes/swiat_obrazu.recipe

@@ -1,7 +1,7 @@
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Swiat_Obrazu(BasicNewsRecipe):
-    title          = u'Swiat Obrazu'
+    title          = u'Świat Obrazu'
     __author__        = 'fenuks'
     description   = u'Internetowy Dziennik o Fotografii i Wideo www.SwiatObrazu.pl to źródło informacji o technice fotografii i wideo, o sprzęcie najbardziej znanych i uznanych firm: Canon, Nikon, Sony, Hasselblad i wielu innych. Znajdziecie tu programy do obróbki zdjęć, forum foto i forum wideo i galerie zdjęć. Codziennie najświeższe informacje: aktualności, testy, poradniki, wywiady, felietony. Swiatobrazu.pl stale organizuje konkursy oraz warsztaty fotograficzne i wideo.'
     category       = 'photography'

recipes/swiatkindle.recipe

@@ -19,6 +19,7 @@ class swiatczytnikow(BasicNewsRecipe):
 
     feeds       = [(u'Świat Czytników - wpisy', u'http://swiatczytnikow.pl/feed')]
 
-    remove_tags = [dict(name = 'ul', attrs = {'class' : 'similar-posts'})]
+    remove_tags = [dict(name = 'ul', attrs = {'class' : 'similar-posts'}),
+        dict(name = 'div', attrs = {'class' : 'feedflare'})]
 
     preprocess_regexps = [(re.compile(u'<h3>Czytaj dalej:</h3>'), lambda match: '')]

recipes/telepolis_pl.recipe

@@ -16,11 +16,31 @@ class telepolis(BasicNewsRecipe):
     use_embedded_content = False
 
     feeds = [
-        (u'Wiadomości', u'http://www.telepolis.pl/rss/news.php')#,
-        #(u'Artykuły', u'http://www.telepolis.pl/rss/artykuly.php')
+        (u'Wiadomości', u'http://www.telepolis.pl/rss,2,5,0.html')
     ]
 
     keep_only_tags = [
         dict(name='div', attrs={'class':'flol w510'}),
+        dict(name='div', attrs={'class':'main_tresc'}),
         dict(name='div', attrs={'class':'main_tresc_news'})
     ]
+
+    def append_page(self, soup, appendtag):
+        chpage= appendtag.find(attrs={'class':'str'})
+        if chpage:
+            for page in chpage.findAll('a'):
+                if page.renderContents() == 'Następna ›':
+                    break
+                soup2 = self.index_to_soup(page['href'])
+                pagetext = soup2.find(attrs={'class':'main_tresc'})
+                pos = len(appendtag.contents)
+                appendtag.insert(pos, pagetext)
+            for r in appendtag.findAll(attrs={'class':'str'}):
+                r.extract()
+
+    def preprocess_html(self, soup):
+        self.append_page(soup, soup.body)
+        for image in soup.findAll('img'):
+            if 'm.jpg' in image['src']:
+                image['src'] = image['src'].replace('m.jpg', '.jpg')
+        return soup

recipes/zycie_warszawy.recipe

@@ -3,12 +3,13 @@
 
 __license__   = 'GPL v3'
 __copyright__   = u'Łukasz Grąbczewski 2012-2013'
-__version__   = '1.1'
+__version__   = '1.2'
 
 '''
 zw.com.pl
 '''
 
+import re
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class zyciewarszawy(BasicNewsRecipe):
@@ -17,12 +18,14 @@ class zyciewarszawy(BasicNewsRecipe):
 	description = u'Wiadomości z Warszawy'
 	language = 'pl'
 	publisher = 'Presspublica'
-	publication_type = 'newspapper'
+	publication_type = 'newspaper'
 	masthead_url = 'http://www.zw.com.pl/static/img/logo_zw.gif'
 	no_stylesheets = True
 	remove_javascript = True
+	use_embedded_content = False
+	remove_empty_feeds = True
 
-	oldest_article = 1 #daily news only
+	oldest_article = 1.5 #last 36h
 	max_articles_per_feed = 100
 
 	feeds = [(u'Najnowsze', u'http://www.zw.com.pl/rss/1.html')]
@@ -31,15 +34,15 @@ class zyciewarszawy(BasicNewsRecipe):
 	keep_only_tags.append(dict(name = 'div', attrs = {'id' : 'storyp'}))
 
 	remove_tags = []
-	remove_tags.append(dict(name = 'div', attrs = {'class' : 'authordate'}))
-	remove_tags.append(dict(name = 'div', attrs = {'class' : 'author'}))
-	'''remove_tags.append(dict(name = 'div', attrs = {'class' : 'seealso'}))'''
-	remove_tags.append(dict(name = 'div', attrs = {'class' : 'more'}))
-	remove_tags.append(dict(name = 'div', attrs = {'class' : 'clr'}))
-	remove_tags.append(dict(name = 'div', attrs = {'id' : 'adk_0'}))
-	remove_tags.append(dict(name = 'div', attrs = {'id' : 'adsense_0'}))
-	remove_tags.append(dict(name = 'div', attrs = {'id' : 'share_bottom'}))
-	remove_tags.append(dict(name = 'div', attrs = {'id' : 'copyright_law'}))
+	remove_tags.append(dict(attrs = {'class' : 'author'}))
+	remove_tags.append(dict(attrs = {'class' : 'more'}))
+	remove_tags.append(dict(attrs = {'class' : 'clr'}))
+	remove_tags.append(dict(attrs = {'id' : 'adk_0'}))
+	remove_tags.append(dict(attrs = {'id' : 'adsense_0'}))
+	remove_tags.append(dict(attrs = {'id' : 'share_bottom'}))
+	remove_tags.append(dict(attrs = {'id' : 'copyright_law'}))
+
+	preprocess_regexps = [(re.compile(r',3.jpg'), lambda m: ',2.jpg')]
 
 	def print_version(self, url):
 		url += "?print=tak"