Various new and updated Polish news sources

recipes/benchmark_pl.recipe

@@ -14,6 +14,7 @@ class BenchmarkPl(BasicNewsRecipe):
     max_articles_per_feed = 100
     extra_css = 'ul {list-style-type: none;}'
     no_stylesheets = True
+    use_embedded_content = False
     #remove_attributes = ['style']
     preprocess_regexps = [(re.compile(ur'<h3><span style="font-size: small;">&nbsp;Zobacz poprzednie <a href="http://www.benchmark.pl/news/zestawienie/grupa_id/135">Opinie dnia:</a></span>.*</body>', re.DOTALL|re.IGNORECASE), lambda match: '</body>'), (re.compile(ur'Więcej o .*?</ul>', re.DOTALL|re.IGNORECASE), lambda match: '')]
 

recipes/cdrinfo_pl.recipe

@@ -23,8 +23,8 @@ class cdrinfo(BasicNewsRecipe):
     preprocess_regexps = [(re.compile(u'<p[^>]*?>Uprzejmie prosimy o przestrzeganie netykiety.+?www\.gravatar\.com</a>\.</p>', re.DOTALL), lambda match: '')]
     ignore_duplicate_articles = {'title', 'url'}
 
-    keep_only_tags = [dict(name='input', attrs={'name':'ref'}), dict(id='text')]
+    keep_only_tags = [dict(name='input', attrs={'name':'ref'}), dict(id=['text', 'text2'])]
-    remove_tags = [dict(attrs={'class':['navigation', 'sociable']}), dict(name='hr'), dict(id='respond')]
+    remove_tags = [dict(attrs={'class':['navigation', 'sociable', 'last6news']}), dict(name='hr'), dict(id='respond')]
     remove_tags_after = dict(id='artnawigacja')
     feeds = [(u'Wiadomości', 'http://feeds.feedburner.com/cdrinfo'), (u'Recenzje', 'http://www.cdrinfo.pl/rss/rss_recenzje.php'),
             (u'Konsole', 'http://konsole.cdrinfo.pl/rss/rss_konsole_news.xml'),

recipes/computerworld_pl.recipe

@@ -13,10 +13,11 @@ class Computerworld_pl(BasicNewsRecipe):
     oldest_article = 7
     max_articles_per_feed = 100
     remove_attributes = ['style',]
+    use_embedded_content = False
     preprocess_regexps = [(re.compile(u'Zobacz również:', re.IGNORECASE), lambda m: ''), (re.compile(ur'[*]+reklama[*]+', re.IGNORECASE), lambda m: ''),]
-    keep_only_tags = [dict(id=['szpaltaL', 's2011'])]
+    keep_only_tags = [dict(id=['article-default-body'])]
-    remove_tags_after = dict(name='div', attrs={'class':'tresc'})
+    remove_tags = [dict(attrs={'class':['share_tools nocontent', 'rec']}), dict(id=['topComment', 'bottom_tools'])]
-    remove_tags = [dict(attrs={'class':['nnav', 'rMobi', 'tagi', 'rec']}), dict(name='a', attrs={'target':'_blank'})]
+
     feeds          = [(u'Wiadomo\u015bci', u'http://rssout.idg.pl/cw/news_iso.xml')]
 
     def skip_ad_pages(self, soup):

recipes/dobreprogamy.recipe

@@ -18,8 +18,8 @@ class Dobreprogramy_pl(BasicNewsRecipe):
     max_articles_per_feed = 100
     remove_attrs = ['style', 'width', 'height']
     preprocess_regexps = [(re.compile(ur'<div id="\S+360pmp4">Twoja przeglądarka nie obsługuje Flasha i HTML5 lub wyłączono obsługę JavaScript...</div>'), lambda match: '') ]
-    keep_only_tags=[dict(attrs={'class':['news', 'entry single']})]
+    keep_only_tags = [dict(attrs={'class':['entry single']}), dict(id='phContent_divArticle')]
-    remove_tags = [dict(attrs={'class':['newsOptions', 'noPrint', 'komentarze', 'tags  font-heading-master']}), dict(id='komentarze'), dict(name='iframe')]
+    remove_tags = [dict(attrs={'class':['newsOptions', 'noPrint', 'komentarze', 'tags  font-heading-master', 'social nested-grid  grid-margin-px15-top clearfix no-mobile', 'page-info text-h4 font-heading grid-margin-px15-top color-annotation clearfix']}), dict(id='komentarze'), dict(name='iframe')]
     #remove_tags = [dict(name='div', attrs={'class':['komentarze', 'block', 'portalInfo', 'menuBar', 'topBar']})]
     feeds = [(u'Aktualności', 'http://feeds.feedburner.com/dobreprogramy/Aktualnosci'),
                  ('Blogi', 'http://feeds.feedburner.com/dobreprogramy/BlogCzytelnikow')]

recipes/forsal.recipe

@@ -9,6 +9,7 @@ class ForsalPL(BasicNewsRecipe):
     oldest_article = 7
     max_articles_per_feed = 100
     use_embedded_content = False
+    remove_empty_feeds = True
     ignore_duplicate_articles = {'title', 'url'}
     cover_url = 'http://www.bizneswnieruchomosciach.pl/wp-content/uploads/2010/07/logo_forsal.jpg'
     no_stylesheets = True

recipes/infra_pl.recipe

@@ -11,6 +11,7 @@ class INFRA(BasicNewsRecipe):
     index='http://infra.org.pl'
     language = 'pl'
     max_articles_per_feed = 100
+    remove_empty_feeds = True
     remove_attrs = ['style']
     no_stylesheets = True
     keep_only_tags = [dict(id='ja-current-content')]

recipes/kdefamily_pl.recipe

@@ -13,5 +13,8 @@ class KDEFamilyPl(BasicNewsRecipe):
     preprocess_regexps = [(re.compile(r"Podobne wpisy.*", re.IGNORECASE|re.DOTALL), lambda m: '')]
     no_stylesheets = True
     remove_empty_feeds = True
-    use_embedded_content = True
+    use_embedded_content = False
+    keep_only_tags = [dict(attrs={'class':'blog-post'})]
+    remove_tags = [dict(attrs={'class':['blog-bottom', 'ratings hreview-aggregate']})]
+
     feeds = [(u'Wszystko', u'http://kdefamily.pl/feed/')]

recipes/kosmonauta_pl.recipe

@@ -8,7 +8,7 @@ class Kosmonauta(BasicNewsRecipe):
     category = 'astronomy'
     language = 'pl'
     cover_url = 'http://bi.gazeta.pl/im/4/10393/z10393414X,Kosmonauta-net.jpg'
-    extra_css = '.thumbnail {float:left;margin-right:5px;}'
+    extra_css = '.thumb-left {float:left; margin-right:5px;} .calibre_navbar {clear: both;}'
     no_stylesheets = True
     INDEX = 'http://www.kosmonauta.net'
     oldest_article = 7

recipes/lomza.recipe

@@ -1,7 +1,7 @@
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Lomza(BasicNewsRecipe):
-    title          = u'4Lomza'
+    title          = u'4Łomza'
     __author__        = 'fenuks'
     description   = u'Regionalny portal. Najświeższe informacje z regionu, kulturalne, sportowe. Ogłoszenia, baza biznesu, forum.'
     cover_url      = 'http://www.4lomza.pl/i/logo4lomza_m.jpg'

recipes/national_geographic_pl.recipe

@@ -10,7 +10,7 @@ class recipeMagic(BasicNewsRecipe):
     title                  = 'National Geographic PL'
     __author__             = 'Marcin Urban 2011'
     __modified_by__        = 'fenuks'
-    description            = 'legenda wśród magazynów z historią sięgającą 120 lat'
+    description            = u'Legenda wśród magazynów z historią sięgającą 120 lat'
     #cover_url                 = 'http://www.guj.pl/var/guj/storage/images/media/nasze_magazyny/national_geographic/logo/ng_logo/2606-1-pol-PL/ng_logo.jpg'
     oldest_article         = 7
     max_articles_per_feed  = 100
@@ -21,6 +21,7 @@ class recipeMagic(BasicNewsRecipe):
     publisher              = 'G+J Gruner+Jahr Polska'
     category               = 'news, PL,'
     language               = 'pl'
+    remove_empty_feeds = True
     publication_type       = 'newsportal'
     extra_css              = ''' body {font-family: verdana, arial, helvetica, geneva, sans-serif ;}
                         h1{text-align: center;}
@@ -47,14 +48,16 @@ class recipeMagic(BasicNewsRecipe):
 
     def find_articles(self, url):
         articles = []
-        soup=self.index_to_soup(url)
+        soup = self.index_to_soup(url)
-        tag=soup.find(attrs={'class':'arl'})
+        tag = soup.find(attrs={'class':'arl'})
-        art=tag.ul.findAll('li')
+        if not tag:
+            return articles
+        art = tag.ul.findAll('li')
         for i in art:
-            title=i.a['title']
+            title = i.a['title']
-            url=i.a['href']
+            url = i.a['href']
             #date=soup.find(id='footer').ul.li.string[41:-1]
-            desc=i.div.p.string
+            desc = i.div.p.string
             articles.append({'title' : title,
                    'url'   : url,
                    'date'  : '',

recipes/odkrywcy_pl.recipe

@@ -0,0 +1,102 @@
+__license__ = 'GPL v3'
+import re
+import datetime
+from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import Comment
+
+class Odkrywcy(BasicNewsRecipe):
+    title          = u'Odkrywcy.pl'
+    __author__        = 'fenuks'
+    description   = u''
+    #publication_type = ''
+    language       = 'pl'
+    #encoding = ''
+    extra_css = 'img {display: block;}'
+    cover_url = ''
+    #masthead_url = ''
+    INDEX = 'http://odkrywcy.pl'
+    use_embedded_content = False
+    oldest_article = 7
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    remove_empty_feeds = True
+    remove_javascript = True
+    remove_attributes = ['style', 'font']
+    ignore_duplicate_articles = {'title', 'url'}
+
+    keep_only_tags = [dict(attrs={'class':'content'})]
+    remove_tags = [dict(name='a', attrs={'href':['#opOpinie', '#opinie']}), dict(attrs={'class':['fr', 'clra', 'close', 'wpsocial-fbFanpageBox', 'tagi', 'test']}), dict(id=['rekSrd05', 'moreTopNews']), dict(name='img', attrs={'class':'zr'}), dict(name='img', attrs={'alt':u'Następne'})]
+    remove_tags_after = dict(id='aTxt')
+    #remove_tags_before = dict()
+    feeds = [(u'', '')]
+    
+    def find_articles(self, url):
+        articles = []
+        soup = self.index_to_soup(url)
+        for i in soup.findAll(attrs={'class':'katZj clra'}):
+            tmp = i.find('small')
+            datestring = re.search('dodano: (\d{4}-\d{2}-\d{2})', tmp.string).group(1)
+            d = datetime.datetime.strptime(datestring, "%Y-%m-%d").date()
+            if (datetime.datetime.now().date() - d).days > self.oldest_article:
+                continue
+            tmp = i.find('a')
+            title = tmp.string
+            url = self.INDEX + tmp['href']
+            articles.append({'title' : title,
+                   'url'   : url,
+                   'date'  : '',
+                   'description' : ''
+                    })
+        return articles
+
+    def parse_index(self):
+         feeds = []
+         feeds.append((u'Człowiek', self.find_articles('http://odkrywcy.pl/kat,111396,name,Czlowiek,kategoria.html')))
+         feeds.append((u'Technologie', self.find_articles('http://odkrywcy.pl/kat,111398,name,Technologie,kategoria.html')))
+         feeds.append((u'Ekologia', self.find_articles('http://odkrywcy.pl/kat,111400,name,Ekologia,kategoria.html')))
+         feeds.append((u'Kosmos', self.find_articles('http://odkrywcy.pl/kat,111402,name,Kosmos,kategoria.html')))
+         feeds.append((u'Cywilizacja', self.find_articles('http://odkrywcy.pl/kat,111404,name,Cywilizacja,kategoria.html')))
+         feeds.append((u'Przyroda', self.find_articles('http://odkrywcy.pl/kat,111406,name,Przyroda,kategoria.html')))
+         feeds.append((u'Fizyka i chemia', self.find_articles('http://odkrywcy.pl/kat,111408,name,Fizyka,kategoria.html')))
+         feeds.append((u'Historia', self.find_articles('http://odkrywcy.pl/kat,122994,name,Historia,kategoria.html')))
+         feeds.append((u'Media', self.find_articles('http://odkrywcy.pl/kat,116794,name,Media,media.html')))
+
+         return feeds
+         
+    def append_page(self, soup, appendtag):
+        tag = soup.find('a', attrs={'class': 'btnNext'})
+        urls = []
+        while tag is not None:
+            if tag['href'] in urls:
+                break
+            urls.append(tag['href'])
+            soup2 = self.index_to_soup(self.INDEX + tag['href'])
+            tag = soup2.find(name='a', attrs={'class': 'btnNext'})
+            pagetext = soup2.findAll(attrs={'class':'content'})
+            for container in pagetext:
+                header = container.find(name='h1')
+                if header:
+                    header.extract()
+                for comment in container.findAll(text=lambda text:isinstance(text, Comment)):
+                    comment.extract()
+            for container in pagetext:
+                pos = len(appendtag.contents)
+                appendtag.insert(pos, container)
+        for r in appendtag.findAll(attrs={'class':'galStr'}):
+            r.extract()
+        for r in appendtag.findAll(attrs={'alt':'Następne'}):
+            r.extract()
+        for r in appendtag.findAll(attrs={'alt':'Poprzednie'}):
+            r.extract()
+        for r in appendtag.findAll(attrs={'class':'clra'}):
+            r.extract()
+        for r in appendtag.findAll(attrs={'class':'close'}):
+            r.extract()
+        for r in appendtag.findAll(attrs={'class':'tagi'}):
+            r.extract()
+        for r in appendtag.findAll(attrs={'id':'moreTopNews'}):
+            r.extract()
+
+    def preprocess_html(self, soup):
+        self.append_page(soup, soup.body)
+        return soup

recipes/polter_pl.recipe

@@ -2,7 +2,7 @@ __license__ = 'GPL v3'
 import re
 from calibre.web.feeds.news import BasicNewsRecipe
 
-class Poltergeist(BasicNewsRecipe):
+class Polter(BasicNewsRecipe):
     title          = u'Polter.pl'
     __author__        = 'fenuks'
     description   = u'Największy polski serwis poświęcony ogólno pojętej fantastyce - grom fabularnym (RPG), książkom, filmowi, komiksowi, grom planszowym, karcianym i bitewnym.'
@@ -10,23 +10,21 @@ class Poltergeist(BasicNewsRecipe):
     #publication_type = ''
     language       = 'pl'
     #encoding = ''
-    extra_css = '.image, .floatright {float: right; margin-left: 10px;} .floatleft {float: left; margin-right: 10px;}'
+    extra_css = '.image, .floatright {float: right; margin-left: 10px;} .floatleft {float: left; margin-right: 10px;} .calibre_navbar {clear: both;} .p_title {font-weight: bold;} .p_image {margin-left: auto; margin-right: auto; display: block;} .italic {font-style: italic;}'
     cover_url = 'http://static.polter.pl/sub/promo/bpromo2524.jpg'
     #masthead_url = ''
     use_embedded_content = False
     oldest_article = 7
-    preprocess_regexps = [(re.compile(ur'<div[^>]*?id="pol_lista"[^>]*?>.*</body>', re.DOTALL|re.IGNORECASE), lambda match: '</body>'), (re.compile(ur'<a[^>]*?>wersja do druku</a>', re.DOTALL|re.IGNORECASE), lambda match: '')]
     max_articles_per_feed = 100
     no_stylesheets = True
     remove_empty_feeds = True
     remove_javascript = True
-    remove_attributes = ['style', 'font']
+    remove_attributes = ['font', 'fieldset', 'onclick']
     ignore_duplicate_articles = {'title', 'url'}
 
     keep_only_tags = [dict(attrs={'class':'boxcontent'})]
-    remove_tags = [dict(attrs={'class':'fb-like'}), dict(attrs={'alt':'Wersja do druku'}), dict(id='pol_liczba'), dict(attrs={'scr':'http://static.polter.pl/tplimg/buttons/ceneo_140_40.gif'})]
+    remove_tags = [dict(id='komentarze')]
-    remove_tags_after = dict(attrs={'class':'fb-like'})
+    remove_tags_after = dict(id='komentarze')
-    #remove_tags_before = dict()
 
     feeds = [(u'Wieści', 'http://polter.pl/wiesci,rss.html'), (u'RPG', 'http://rpg.polter.pl/wiesci,rss.html'), (u'Książki', 'http://ksiazki.polter.pl/wiesci,rss.html'), (u'Film', 'http://film.polter.pl/wiesci,rss.html'), (u'Komiks', 'http://komiks.polter.pl/wiesci,rss.html'), (u'Gry bitewne', 'http://bitewniaki.polter.pl/wiesci,rss.html'), (u'Gry karciane', 'http://karcianki.polter.pl/wiesci,rss.html'), (u'Gry planszowe', 'http://planszowki.polter.pl/wiesci,rss.html'), (u'Gry PC', 'http://gry.polter.pl/wiesci,rss.html'), (u'Gry konsolowe', 'http://konsole.polter.pl/wiesci,rss.html'), (u'Konwenty', 'http://konwenty.polter.pl/wiesci,rss.html'), (u'Blogi', 'http://polter.pl/blogi,rss.html')]
 
@@ -35,9 +33,24 @@ class Poltergeist(BasicNewsRecipe):
             s['class'] = 'floatleft'
         for s in soup.findAll(attrs={'style':re.compile('float: ?right')}):
             s['class'] = 'floatright'
+        for s in soup.findAll(style=True):
+            if 'bold;' in s['style']:
+                if s.get('class', ''):
+                    s['class'] = s['class'] + ' p_title'
+                else:
+                    s['class'] = 'p_title'
+            if 'italic;' in s['style']:
+                if s.get('class', ''):
+                    s['class'] = s['class'] + ' italic'
+                else:
+                    s['class'] = 'italic'
+            del s['style']
+
         tag = soup.find(id='twoja_ocena')
         if tag:
             tag.parent.extract()
         for tag in soup.findAll(id='lista_chce_ile'):
             tag.parent.parent.extract()
+        for r in soup.findAll(name='a', href=re.compile(r'^http://www.ceneo.pl/')):
+            r.extract()
         return soup

recipes/tablety_pl.recipe

@@ -14,7 +14,5 @@ class Tablety_pl(BasicNewsRecipe):
     max_articles_per_feed = 100
     preprocess_regexps = [(re.compile(ur'<p><strong>Przeczytaj także.*?</a></strong></p>', re.DOTALL), lambda match: ''), (re.compile(ur'<p><strong>Przeczytaj koniecznie.*?</a></strong></p>', re.DOTALL), lambda match: '')]
     keep_only_tags = [dict(id='news_block')]
-    #remove_tags_before=dict(name="h1", attrs={'class':'entry-title'})
+    remove_tags=[dict(attrs={'class':['comments_icon', 'wp-polls', 'entry-comments', 'wp-polls-loading', 'ts-fab-wrapper', 'entry-footer']})]
-    #remove_tags_after=dict(name="footer", attrs={'class':'entry-footer clearfix'})
-    remove_tags=[dict(attrs={'class':['comments_icon', 'wp-polls', 'entry-comments']})]
     feeds = [(u'Najnowsze posty', u'http://www.tablety.pl/feed/')]

recipes/wprost_rss.recipe

@@ -16,33 +16,11 @@ class Wprost(BasicNewsRecipe):
     no_stylesheets = True
     language = 'pl'
     remove_javascript = True
-    recursions = 0
     use_embedded_content = False
     ignore_duplicate_articles = {'title', 'url'}
     remove_empty_feeds = True
-    remove_tags_before = dict(dict(name = 'div', attrs = {'id' : 'print-layer'}))
+    keep_only_tags = [dict(attrs={'class':'art-area'})]
-    remove_tags_after = dict(dict(name = 'div', attrs = {'id' : 'print-layer'}))
+    remove_tags = [dict(attrs={'class':'add300x250'})]
-    '''
-    keep_only_tags =[]
-    keep_only_tags.append(dict(name = 'table', attrs = {'id' : 'title-table'}))
-    keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'div-header'}))
-    keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'div-content'}))
-    keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'def element-autor'}))
-    '''
-
-    preprocess_regexps = [(re.compile(r'style="display: none;"'), lambda match: ''),
-        (re.compile(r'display: block;'), lambda match: ''),
-        (re.compile(r'\<td\>\<tr\>\<\/table\>'), lambda match: ''),
-        (re.compile(r'\<table .*?\>'), lambda match: ''),
-        (re.compile(r'\<tr>'), lambda match: ''),
-        (re.compile(r'\<td .*?\>'), lambda match: ''),
-        (re.compile(r'\<div id="footer"\>.*?\</footer\>'), lambda match: '')]
-
-    remove_tags =[]
-    remove_tags.append(dict(name = 'div', attrs = {'class' : 'def element-date'}))
-    remove_tags.append(dict(name = 'div', attrs = {'class' : 'def silver'}))
-    remove_tags.append(dict(name = 'div', attrs = {'id' : 'content-main-column-right'}))
-
 
     extra_css = '''.div-header {font-size: x-small; font-weight: bold}'''
     #h2 {font-size: x-large; font-weight: bold}

recipes/zaufana_trzecia_strona.recipe

@@ -13,6 +13,7 @@ class ZTS(BasicNewsRecipe):
     max_articles_per_feed = 100
     no_stylesheets = True
     remove_empty_feeds = True
+    use_embedded_content = False
     keep_only_tags = [dict(name='div', attrs={'class':'post postcontent'})]
     remove_tags = [dict(name='div', attrs={'class':'dolna-ramka'})]
     feeds          = [(u'Strona g\u0142\xf3wna', u'http://feeds.feedburner.com/ZaufanaTrzeciaStronaGlowna'), (u'Drobiazgi', u'http://feeds.feedburner.com/ZaufanaTrzeciaStronaDrobiazgi')]

recipes/znadplanszy_pl.recipe

@@ -0,0 +1,27 @@
+__license__ = 'GPL v3'
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class ZnadPlanszy(BasicNewsRecipe):
+    title          = u'ZnadPlanszy.pl'
+    __author__        = 'fenuks'
+    description   = u''
+    #publication_type = ''
+    language       = 'pl'
+    #encoding = ''
+    #extra_css = ''
+    cover_url = 'http://znadplanszy.pl/wp-content/uploads/2013/05/logo-znadplanszy.png'
+    #masthead_url = ''
+    use_embedded_content = False
+    oldest_article = 14
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    remove_empty_feeds = True
+    remove_javascript = True
+    remove_attributes = ['style', 'font']
+    ignore_duplicate_articles = {'title', 'url'}
+
+    #keep_only_tags = [dict()]
+    remove_tags = [dict(attrs={'class':'rounded-container'})]
+    remove_tags_after = dict(attrs={'id':'dotEPUBcontent'})
+    remove_tags_before = dict(attrs={'class':'content units nine alpha'})
+    feeds = [(u'Wszystkie', 'http://znadplanszy.pl/full-feed/posts/')]