Various Polish news sources by fenuks

recipes/badania_net.recipe

@@ -0,0 +1,17 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+class BadaniaNet(BasicNewsRecipe):
+    title          = u'badania.net'
+    __author__ = 'fenuks'
+    description   = u'chcesz wiedzieć więcej?'
+    category       = 'science'
+    language       = 'pl'
+    cover_url = 'http://badania.net/wp-content/badanianet_green_transparent.png'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    remove_empty_feeds = True
+    use_embedded_content = False
+    remove_tags = [dict(attrs={'class':['omc-flex-category', 'omc-comment-count', 'omc-single-tags']})]
+    remove_tags_after = dict(attrs={'class':'omc-single-tags'})
+    keep_only_tags = [dict(id='omc-full-article')]
+    feeds          = [(u'Psychologia', u'http://badania.net/category/psychologia/feed/'), (u'Technologie', u'http://badania.net/category/technologie/feed/'), (u'Biologia', u'http://badania.net/category/biologia/feed/'), (u'Chemia', u'http://badania.net/category/chemia/feed/'), (u'Zdrowie', u'http://badania.net/category/zdrowie/'), (u'Seks', u'http://badania.net/category/psychologia-ewolucyjna-tematyka-seks/feed/')]

recipes/eso_pl.recipe

@@ -0,0 +1,23 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class ESO(BasicNewsRecipe):
+    title          = u'ESO PL'
+    __author__        = 'fenuks'
+    description   = u'ESO, Europejskie Obserwatorium Południowe, buduje i obsługuje najbardziej zaawansowane naziemne teleskopy astronomiczne na świecie'
+    category       = 'astronomy'
+    language       = 'pl'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    remove_empty_feeds = True
+    use_embedded_content = False
+    cover_url = 'https://twimg0-a.akamaihd.net/profile_images/1922519424/eso-twitter-logo.png'
+    keep_only_tags = [dict(attrs={'class':'subcl'})]
+    remove_tags = [dict(id='lang_row'), dict(attrs={'class':['pr_typeid', 'pr_news_feature_link', 'outreach_usage', 'hidden']})]
+    feeds          = [(u'Wiadomo\u015bci', u'http://www.eso.org/public/poland/news/feed/'), (u'Og\u0142oszenia', u'http://www.eso.org/public/poland/announcements/feed/'), (u'Zdj\u0119cie tygodnia', u'http://www.eso.org/public/poland/images/potw/feed/')]
+
+    def preprocess_html(self, soup):
+        for a in soup.findAll('a', href=True):
+            if a['href'].startswith('/'):
+                a['href'] = 'http://www.eso.org' + a['href']
+        return soup

recipes/kdefamily_pl.recipe

@@ -0,0 +1,14 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class KDEFamilyPl(BasicNewsRecipe):
+    title          = u'KDEFamily.pl'
+    __author__        = 'fenuks'
+    description   = u'KDE w Polsce'
+    category       = 'open source, KDE'
+    language       = 'pl'
+    cover_url = 'http://www.mykde.home.pl/kdefamily/wp-content/uploads/2012/07/logotype-e1341585198616.jpg'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    use_embedded_content = True
+    feeds          = [(u'Wszystko', u'http://kdefamily.pl/feed/')]

recipes/kurier_galicyjski.recipe

@@ -0,0 +1,56 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import BeautifulSoup as bs
+class KurierGalicyjski(BasicNewsRecipe):
+    title          = u'Kurier Galicyjski'
+    __author__        = 'fenuks'
+    #description   = u''
+    category       = 'news'
+    language       = 'pl'
+    cover_url = 'http://www.duszki.pl/Kurier_galicyjski_bis2_small.gif'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    remove_empty_feeds = True
+    no_stylesheets = True
+    keep_only_tags = [dict(attrs={'class':'item-page'})]
+    remove_tags = [dict(attrs={'class':'pagenav'}), dict(attrs={'style':'border-top-width: thin; border-top-style: dashed; border-top-color: #CCC; border-bottom-width: thin; border-bottom-style: dashed; border-bottom-color: #CCC; padding-top:5px; padding-bottom:5px; text-align:right; margin-top:10px; height:20px;'})]
+    feeds          = [(u'Wydarzenia', u'http://kuriergalicyjski.com/index.php/wydarzenia?format=feed&type=atom'), (u'Publicystyka', u'http://kuriergalicyjski.com/index.php/niezwykle-historie?format=feed&type=atom'), (u'Reporta\u017ce', u'http://kuriergalicyjski.com/index.php/report?format=feed&type=atom'), (u'Rozmowy Kuriera', u'http://kuriergalicyjski.com/index.php/kuriera?format=feed&type=atom'), (u'Przegl\u0105d prasy', u'http://kuriergalicyjski.com/index.php/2012-01-05-14-08-55?format=feed&type=atom'), (u'Kultura', u'http://kuriergalicyjski.com/index.php/2011-12-02-14-26-39?format=feed&type=atom'), (u'Zabytki', u'http://kuriergalicyjski.com/index.php/2011-12-02-14-27-32?format=feed&type=atom'), (u'Polska-Ukraina', u'http://kuriergalicyjski.com/index.php/pol-ua?format=feed&type=atom'), (u'Polacy i Ukrai\u0144cy', u'http://kuriergalicyjski.com/index.php/polacy-i-ukr?format=feed&type=atom'), (u'Niezwyk\u0142e historie', u'http://kuriergalicyjski.com/index.php/niezwykle-historie?format=feed&type=atom'), (u'Polemiki', u'http://kuriergalicyjski.com/index.php/polemiki?format=feed&type=atom')]
+
+    def append_page(self, soup, appendtag):
+        pager = soup.find(id='article-index')
+        if pager:
+            pager = pager.findAll('a')[1:]
+        if pager:
+            for a in pager:
+                nexturl = 'http://www.kuriergalicyjski.com' + a['href']
+                soup2 = self.index_to_soup(nexturl)
+                pagetext = soup2.find(attrs={'class':'item-page'})
+                if pagetext.h2:
+                    pagetext.h2.extract()
+                r = pagetext.find(attrs={'class':'article-info'})
+                if r:
+                    r.extract()
+                pos = len(appendtag.contents)
+                appendtag.insert(pos, pagetext)
+                pos = len(appendtag.contents)
+            for r in appendtag.findAll(id='article-index'):
+                r.extract()
+            for r in appendtag.findAll(attrs={'class':'pagenavcounter'}):
+                r.extract()
+            for r in appendtag.findAll(attrs={'class':'pagination'}):
+                r.extract()
+            for r in appendtag.findAll(attrs={'class':'pagenav'}):
+                r.extract()
+            for r in appendtag.findAll(attrs={'style':'border-top-width: thin; border-top-style: dashed; border-top-color: #CCC; border-bottom-width: thin; border-bottom-style: dashed; border-bottom-color: #CCC; padding-top:5px; padding-bottom:5px; text-align:right; margin-top:10px; height:20px;'}):
+                r.extract()
+
+    def preprocess_html(self, soup):
+        self.append_page(soup, soup.body)
+        for r in soup.findAll(style=True):
+            del r['style']
+        for img in soup.findAll(attrs={'class':'easy_img_caption smartresize'}):
+            img.insert(len(img.contents)-1, bs('<br />'))
+            img.insert(len(img.contents), bs('<br /><br />'))
+        for a in soup.findAll('a', href=True):
+            if a['href'].startswith('/'):
+                a['href'] = 'http://kuriergalicyjski.com' + a['href']
+        return soup

recipes/nauka_w_polsce.recipe

@@ -0,0 +1,47 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+class NaukawPolsce(BasicNewsRecipe):
+    title          = u'Nauka w Polsce'
+    __author__        = 'fenuks'
+    description   = u'Serwis Nauka w Polsce ma za zadanie popularyzację polskiej nauki. Można na nim znaleźć wiadomości takie jak:  osiągnięcia polskich naukowców, wydarzenia na polskich uczelniach, osiągnięcia studentów, konkursy dla badaczy, staże i stypendia naukowe, wydarzenia w polskiej nauce, kalendarium wydarzeń w nauce, materiały wideo o nauce.'
+    category       = 'science'
+    language       = 'pl'
+    cover_url = 'http://www.naukawpolsce.pap.pl/Themes/Pap/images/logo-pl.gif'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    remove_empty_feeds = True
+    index = 'http://www.naukawpolsce.pl'
+    keep_only_tags = [dict(name='div', attrs={'class':'margines wiadomosc'})]
+    remove_tags = [dict(name='div', attrs={'class':'tagi'})]
+
+    def find_articles(self, url):
+        articles = []
+        soup=self.index_to_soup(url)
+        for i in soup.findAll(name='div', attrs={'class':'aktualnosci-margines lista-depesz information-content'}):
+            title = i.h1.a.string
+            url = self.index + i.h1.a['href']
+            date = '' #i.span.string
+            articles.append({'title' : title,
+                   'url'   : url,
+                   'date'  : date,
+                   'description' : ''
+                    })
+        return articles
+
+    def parse_index(self):
+         feeds = []
+         feeds.append((u"Historia i kultura", self.find_articles('http://www.naukawpolsce.pl/historia-i-kultura/')))
+         feeds.append((u"Kosmos", self.find_articles('http://www.naukawpolsce.pl/kosmos/')))
+         feeds.append((u"Przyroda", self.find_articles('http://www.naukawpolsce.pl/przyroda/')))
+         feeds.append((u"Społeczeństwo", self.find_articles('http://www.naukawpolsce.pl/spoleczenstwo/')))
+         feeds.append((u"Technologie", self.find_articles('http://www.naukawpolsce.pl/technologie/')))
+         feeds.append((u"Uczelnie", self.find_articles('http://www.naukawpolsce.pl/uczelnie/')))
+         feeds.append((u"Nauki medyczne", self.find_articles('http://www.naukawpolsce.pl/zdrowie/')))
+
+         return feeds
+
+    def preprocess_html(self, soup):
+        for p in soup.findAll(name='p', text=re.compile(' ')):
+            p.extract()
+        return soup

recipes/osworld_pl.recipe

@@ -0,0 +1,33 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+class OSWorld(BasicNewsRecipe):
+    title          = u'OSWorld.pl'
+    __author__        = 'fenuks'
+    description   = u'OSWorld.pl to serwis internetowy, dzięki któremu poznasz czym naprawdę jest Open Source. Serwis poświęcony jest wolnemu oprogramowaniu jak linux mint, centos czy ubunty. Znajdziecie u nasz artykuły, unity oraz informacje o certyfikatach CACert. OSWorld to mały świat wielkich systemów!'
+    category       = 'OS, IT, open source, Linux'
+    language       = 'pl'
+    cover_url = 'http://osworld.pl/wp-content/uploads/osworld-kwadrat-128x111.png'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    remove_empty_feeds = True
+    use_embedded_content = False
+    keep_only_tags = [dict(id=['dzial', 'posts'])]
+    remove_tags = [dict(attrs={'class':'post-comments'})]
+    remove_tags_after = dict(attrs={'class':'entry clr'})
+    feeds          = [(u'Artyku\u0142y', u'http://osworld.pl/category/artykuly/feed/'), (u'Nowe wersje', u'http://osworld.pl/category/nowe-wersje/feed/')]
+
+    def append_page(self, soup, appendtag):
+        tag = appendtag.find(attrs={'id':'paginacja'})
+        if tag:
+            for nexturl in tag.findAll('a'):
+                soup2 = self.index_to_soup(nexturl['href'])
+                pagetext = soup2.find(attrs={'class':'entry clr'})
+                pos = len(appendtag.contents)
+                appendtag.insert(pos, pagetext)
+            for r in appendtag.findAll(attrs={'id':'paginacja'}):
+                r.extract()
+
+
+    def preprocess_html(self, soup):
+         self.append_page(soup, soup.body)
+         return soup

recipes/ubuntu_pomoc_org.recipe

@@ -0,0 +1,22 @@
+import re
+from calibre.web.feeds.news import BasicNewsRecipe
+class UbuntuPomoc(BasicNewsRecipe):
+    title          = u'Ubuntu-pomoc.org'
+    __author__        = 'fenuks'
+    description   = u'Strona poświęcona systemowi Ubuntu Linux. Znajdziesz tutaj przydatne i sprawdzone poradniki oraz sposoby rozwiązywania wielu popularnych problemów. Ten blog rozwiąże każdy Twój problem - jeśli nie teraz, to wkrótce! :)'
+    category       = 'Linux, Ubuntu, open source'
+    language       = 'pl'
+    cover_url = 'http://www.ubuntu-pomoc.org/grafika/ubuntupomoc.png'
+    preprocess_regexps = [(re.compile(r'<div class="ciekawostka">.+', re.IGNORECASE|re.DOTALL), lambda m: '')]
+    oldest_article = 7
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    remove_javascript = True
+    remove_empty_feeds = True
+    use_embedded_content = False
+    remove_attrs = ['style']
+    keep_only_tags = [dict(attrs={'class':'post'})]
+    remove_tags_after = dict(attrs={'class':'underEntry'})
+    remove_tags = [dict(attrs={'class':['underPostTitle', 'yarpp-related', 'underEntry', 'social', 'tags', 'commentlist', 'youtube_sc']}), dict(id=['wp_rp_first', 'commentReply'])]
+    feeds          = [(u'Ca\u0142o\u015b\u0107', u'http://feeds.feedburner.com/Ubuntu-Pomoc'),
+                     (u'Gry', u'http://feeds.feedburner.com/GryUbuntu-pomoc')]

recipes/wprost_rss.recipe

@@ -0,0 +1,71 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2010, matek09, matek09@gmail.com'
+__copyright__ = 'Modified 2011,  Mariusz Wolek <mariusz_dot_wolek @ gmail dot com>'
+__copyright__ = 'Modified 2012,  Artur Stachecki <artur.stachecki@gmail.com>'
+
+
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
+class Wprost(BasicNewsRecipe):
+    title = u'Wprost (RSS)'
+    __author__ = 'matek09'
+    description = 'Weekly magazine'
+    encoding = 'ISO-8859-2'
+    no_stylesheets = True
+    language = 'pl'
+    remove_javascript = True
+    recursions = 0
+    use_embedded_content = False
+    remove_empty_feeds = True
+    remove_tags_before = dict(dict(name = 'div', attrs = {'id' : 'print-layer'}))
+    remove_tags_after = dict(dict(name = 'div', attrs = {'id' : 'print-layer'}))
+    '''
+    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}
+
+    feeds = [(u'Tylko u nas', u'http://www.wprost.pl/rss/rss_wprostextra.php'),
+	(u'Wydarzenia', u'http://www.wprost.pl/rss/rss.php'),
+	(u'Komentarze', u'http://www.wprost.pl/rss/rss_komentarze.php'),
+	(u'Wydarzenia: Kraj', u'http://www.wprost.pl/rss/rss_kraj.php'),
+	(u'Komentarze: Kraj', u'http://www.wprost.pl/rss/rss_komentarze_kraj.php'),
+	(u'Wydarzenia: Świat', u'http://www.wprost.pl/rss/rss_swiat.php'),
+	(u'Komentarze: Świat', u'http://www.wprost.pl/rss/rss_komentarze_swiat.php'),
+	(u'Wydarzenia: Gospodarka', u'http://www.wprost.pl/rss/rss_gospodarka.php'),
+	(u'Komentarze: Gospodarka', u'http://www.wprost.pl/rss/rss_komentarze_gospodarka.php'),
+	(u'Wydarzenia: Życie', u'http://www.wprost.pl/rss/rss_zycie.php'),
+	(u'Komentarze: Życie', u'http://www.wprost.pl/rss/rss_komentarze_zycie.php'),
+	(u'Wydarzenia: Sport', u'http://www.wprost.pl/rss/rss_sport.php'),
+	(u'Komentarze: Sport', u'http://www.wprost.pl/rss/rss_komentarze_sport.php'),
+	(u'Przegląd prasy', u'http://www.wprost.pl/rss/rss_prasa.php')
+	]
+
+    def get_cover_url(self):
+        soup = self.index_to_soup('http://www.wprost.pl/tygodnik')
+        cover = soup.find(attrs={'class':'wprost-cover'})
+        if cover:
+            self.cover_url = cover['src']
+        return getattr(self, 'cover_url', self.cover_url)