Various polish news sources by fenuks

recipes/archeowiesci.recipe

@@ -0,0 +1,21 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Archeowiesci(BasicNewsRecipe):
+    title          = u'Archeowiesci'
+    __author__        = 'fenuks'
+    category       = 'archeology'
+    language       = 'pl'
+    cover_url='http://archeowiesci.pl/wp-content/uploads/2011/05/Archeowiesci2-115x115.jpg'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    auto_cleanup = True
+    remove_tags=[dict(name='span', attrs={'class':['post-ratings', 'post-ratings-loading']})]
+    feeds          = [(u'Archeowieści', u'http://archeowiesci.pl/feed/')]
+
+    def parse_feeds (self):
+      feeds = BasicNewsRecipe.parse_feeds(self)
+      for feed in feeds:
+        for article in feed.articles[:]:
+          if 'subskrypcja' in article.title:
+            feed.articles.remove(article)
+      return feeds

recipes/eioba.recipe

@@ -0,0 +1,23 @@
+# -*- coding: utf-8 -*-
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class eioba(BasicNewsRecipe):
+    title          = u'eioba'
+    __author__        = 'fenuks'
+    cover_url      = 'http://www.eioba.org/lay/logo_pl_v3.png'
+    language       = 'pl'
+    oldest_article = 7
+    remove_empty_feeds= True
+    max_articles_per_feed = 100
+    extra_css = '#ctl0_body_Topic {font-weight: bold; font-size:30px;}'
+    keep_only_tags=[dict(id=['ctl0_body_Topic', 'articleContent'])]
+    feeds          = [(u'Wszyskie kategorie', u'http://feeds.eioba.pl/eioba-pl-top'),
+	(u'Technologia', u'http://www.eioba.pl/feed/categories/1.xml'),
+	(u'Nauka', u'http://www.eioba.pl/feed/categories/12.xml'),
+	(u'Finanse', u'http://www.eioba.pl/feed/categories/7.xml'),
+	(u'Życie', u'http://www.eioba.pl/feed/categories/5.xml'),
+	(u'Zainteresowania', u'http://www.eioba.pl/feed/categories/420.xml'),
+	(u'Społeczeństwo', u'http://www.eioba.pl/feed/categories/8.xml'),
+	(u'Rozrywka', u'http://www.eioba.pl/feed/categories/10.xml'),
+	(u'Rożne', u'http://www.eioba.pl/feed/categories/9.xml')
+	]

recipes/focus_pl.recipe

@@ -0,0 +1,66 @@
+# -*- coding: utf-8 -*-
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Focus_pl(BasicNewsRecipe):
+    title          = u'Focus.pl'
+    oldest_article = 15
+    max_articles_per_feed = 100
+    __author__        = 'fenuks'
+    language       = 'pl'
+    description ='polish scientific monthly magazine'
+    category='magazine'
+    cover_url=''
+    remove_empty_feeds= True
+    no_stylesheets=True
+    remove_tags_before=dict(name='div', attrs={'class':'h2 h2f'})
+    remove_tags_after=dict(name='div', attrs={'class':'clear'})
+    feeds          = [(u'Wszystkie kategorie', u'http://focus.pl.feedsportal.com/c/32992/f/532692/index.rss'),
+	(u'Nauka', u'http://focus.pl.feedsportal.com/c/32992/f/532693/index.rss'),
+	(u'Historia', u'http://focus.pl.feedsportal.com/c/32992/f/532694/index.rss'),
+	(u'Cywilizacja', u'http://focus.pl.feedsportal.com/c/32992/f/532695/index.rss'),
+	(u'Sport', u'http://focus.pl.feedsportal.com/c/32992/f/532696/index.rss'),
+	(u'Technika', u'http://focus.pl.feedsportal.com/c/32992/f/532697/index.rss'),
+	(u'Przyroda', u'http://focus.pl.feedsportal.com/c/32992/f/532698/index.rss'),
+	(u'Technologie', u'http://focus.pl.feedsportal.com/c/32992/f/532699/index.rss'),
+	(u'Warto wiedzieć', u'http://focus.pl.feedsportal.com/c/32992/f/532700/index.rss'),
+
+
+
+]
+
+    def skip_ad_pages(self, soup):
+          tag=soup.find(name='a')
+          if tag:
+            new_soup=self.index_to_soup(tag['href']+ 'do-druku/1/', raw=True)
+            return new_soup
+
+    def append_page(self, appendtag):
+        tag=appendtag.find(name='div', attrs={'class':'arrows'})
+        if tag:
+            nexturl='http://www.focus.pl/'+tag.a['href']
+            for rem in appendtag.findAll(name='div', attrs={'class':'klik-nav'}):
+                rem.extract()
+            while nexturl:
+                 soup2=self.index_to_soup(nexturl)
+                 nexturl=None
+                 pagetext=soup2.find(name='div', attrs={'class':'txt'})
+                 tag=pagetext.find(name='div', attrs={'class':'arrows'})
+                 for r in tag.findAll(name='a'):
+                     if u'Następne' in r.string:
+                         nexturl='http://www.focus.pl/'+r['href']
+                 for rem in pagetext.findAll(name='div', attrs={'class':'klik-nav'}):
+                     rem.extract()
+                 pos = len(appendtag.contents)
+                 appendtag.insert(pos, pagetext)
+
+    def get_cover_url(self):
+        soup=self.index_to_soup('http://www.focus.pl/magazyn/')
+        tag=soup.find(name='div', attrs={'class':'clr fl'})
+        if tag:
+            self.cover_url='http://www.focus.pl/' + tag.a['href']
+            return getattr(self, 'cover_url', self.cover_url)
+
+
+    def preprocess_html(self, soup):
+         self.append_page(soup.body)
+         return soup

recipes/gazeta_wyborcza.recipe

@@ -0,0 +1,83 @@
+# -*- coding: utf-8 -*-
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Gazeta_Wyborcza(BasicNewsRecipe):
+    title          = u'Gazeta Wyborcza'
+    __author__        = 'fenuks'
+    cover_url      = 'http://bi.gazeta.pl/im/5/10285/z10285445AA.jpg'
+    language       = 'pl'
+    description ='news from gazeta.pl'
+    category='newspaper'
+    INDEX='http://wyborcza.pl'
+    remove_empty_feeds= True
+    oldest_article = 3
+    max_articles_per_feed = 100
+    remove_javascript=True
+    no_stylesheets=True
+    remove_tags_before=dict(id='k0')
+    remove_tags_after=dict(id='banP4')
+    remove_tags=[dict(name='div', attrs={'class':'rel_box'}), dict(attrs={'class':['date', 'zdjP', 'zdjM', 'pollCont', 'rel_video', 'brand', 'txt_upl']}), dict(name='div', attrs={'id':'footer'})]
+    feeds          = [(u'Kraj', u'http://rss.feedsportal.com/c/32739/f/530266/index.rss'), (u'\u015awiat', u'http://rss.feedsportal.com/c/32739/f/530270/index.rss'),
+	(u'Wyborcza.biz', u'http://wyborcza.biz/pub/rss/wyborcza_biz_wiadomosci.htm'),
+	(u'Komentarze', u'http://rss.feedsportal.com/c/32739/f/530312/index.rss'),
+	(u'Kultura', u'http://rss.gazeta.pl/pub/rss/gazetawyborcza_kultura.xml'),
+	(u'Nauka', u'http://rss.feedsportal.com/c/32739/f/530269/index.rss'), (u'Opinie', u'http://rss.gazeta.pl/pub/rss/opinie.xml'), (u'Gazeta \u015awi\u0105teczna', u'http://rss.feedsportal.com/c/32739/f/530431/index.rss'), (u'Du\u017cy Format', u'http://rss.feedsportal.com/c/32739/f/530265/index.rss'), (u'Witamy w Polsce', u'http://rss.feedsportal.com/c/32739/f/530476/index.rss'), (u'M\u0119ska Muzyka', u'http://rss.feedsportal.com/c/32739/f/530337/index.rss'), (u'Lata Lec\u0105', u'http://rss.feedsportal.com/c/32739/f/530326/index.rss'), (u'Solidarni z Tybetem', u'http://rss.feedsportal.com/c/32739/f/530461/index.rss'), (u'W pon. - \u017bakowski', u'http://rss.feedsportal.com/c/32739/f/530491/index.rss'), (u'We wt. - Kolenda-Zalewska', u'http://rss.feedsportal.com/c/32739/f/530310/index.rss'), (u'\u015aroda w \u015brod\u0119', u'http://rss.feedsportal.com/c/32739/f/530428/index.rss'), (u'W pi\u0105tek - Olejnik', u'http://rss.feedsportal.com/c/32739/f/530364/index.rss'), (u'Nekrologi', u'http://rss.feedsportal.com/c/32739/f/530358/index.rss')
+                     ]
+
+    def skip_ad_pages(self, soup):
+          tag=soup.find(name='a', attrs={'class':'btn'})
+          if tag:
+            new_soup=self.index_to_soup(tag['href'], raw=True)
+            return new_soup
+
+
+    def append_page(self, soup, appendtag):
+        loop=False
+        tag = soup.find('div', attrs={'id':'Str'})
+        if appendtag.find('div', attrs={'id':'Str'}):
+            nexturl=tag.findAll('a')
+            appendtag.find('div', attrs={'id':'Str'}).extract()
+            loop=True
+            if appendtag.find(id='source'):
+                appendtag.find(id='source').extract()
+        while loop:
+            loop=False
+            for link in nexturl:
+                if u'następne' in link.string:
+                    url= self.INDEX + link['href']
+                    soup2 = self.index_to_soup(url)
+                    pagetext = soup2.find(id='artykul')
+                    pos = len(appendtag.contents)
+                    appendtag.insert(pos, pagetext)
+                    tag = soup2.find('div', attrs={'id':'Str'})
+                    nexturl=tag.findAll('a')
+                    loop=True
+
+    def gallery_article(self, appendtag):
+        tag=appendtag.find(id='container_gal')
+        if tag:
+            nexturl=appendtag.find(id='gal_btn_next').a['href']
+            appendtag.find(id='gal_navi').extract()
+        while nexturl:
+            soup2=self.index_to_soup(nexturl)
+            pagetext=soup2.find(id='container_gal')
+            nexturl=pagetext.find(id='gal_btn_next')
+            if nexturl:
+                nexturl=nexturl.a['href']
+                pos = len(appendtag.contents)
+                appendtag.insert(pos, pagetext)
+            rem=appendtag.find(id='gal_navi')
+            if rem:
+                rem.extract()
+
+    def preprocess_html(self, soup):
+         self.append_page(soup, soup.body)
+         if soup.find(id='container_gal'):
+             self.gallery_article(soup.body)
+         return soup
+
+    def print_version(self, url):
+        if 'http://wyborcza.biz/biznes/' not in url:
+            return url
+        else:
+             return url.replace('http://wyborcza.biz/biznes/1', 'http://wyborcza.biz/biznes/2029020')

recipes/konflikty_zbrojne.recipe

@@ -0,0 +1,15 @@
+# -*- coding: utf-8 -*-
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Konflikty(BasicNewsRecipe):
+    title          = u'Konflikty Zbrojne'
+    __author__        = 'fenuks'
+    cover_url      = 'http://www.konflikty.pl/images/tapety_logo.jpg'
+    language       = 'pl'
+    description ='military news'
+    category='military, history'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    auto_cleanup = True
+
+    feeds          = [(u'Aktualności', u'http://www.konflikty.pl/rss_aktualnosci_10.xml'), (u'Artyku\u0142y', u'http://www.konflikty.pl/rss_artykuly_10.xml'), (u'Relacje', u'http://www.konflikty.pl/rss_relacje_10.xml'), (u'Recenzje', u'http://www.konflikty.pl/rss_recenzje_10.xml')]

recipes/naczytniki.recipe

@@ -0,0 +1,15 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class naczytniki(BasicNewsRecipe):
+    title          = u'naczytniki.pl'
+    __author__        = 'fenuks'
+    cover_url      = 'http://naczytniki.pl/wp-content/uploads/2010/08/logo_nc28.png'
+    language       = 'pl'
+    description ='everything about e-readers'
+    category='readers'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    remove_tags_after= dict(name='div', attrs={'class':'sociable'})
+    keep_only_tags=[dict(name='div', attrs={'class':'post'})]
+    remove_tags=[dict(name='span', attrs={'class':'comments'}), dict(name='div', attrs={'class':'sociable'})]
+    feeds          = [(u'Wpisy', u'http://naczytniki.pl/?feed=rss2')]

recipes/nowa_fantastyka.recipe

@@ -0,0 +1,47 @@
+# -*- coding: utf-8 -*-
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Nowa_Fantastyka(BasicNewsRecipe):
+    title          = u'Nowa Fantastyka'
+    oldest_article = 7
+    __author__        = 'fenuks'
+    language       = 'pl'
+    description ='site for fantasy readers'
+    category='fantasy'
+    max_articles_per_feed = 100
+    INDEX='http://www.fantastyka.pl/'
+    remove_tags_before=dict(attrs={'class':'belka1-tlo-md'})
+    #remove_tags_after=dict(name='span', attrs={'class':'naglowek-oceny'})
+    remove_tags_after=dict(name='td', attrs={'class':'belka1-bot'})
+    remove_tags=[dict(attrs={'class':'avatar2'})]
+    feeds          = []
+
+    def find_articles(self, url):
+        articles = []
+        soup=self.index_to_soup(url)
+        tag=soup.find(attrs={'class':'belka1-tlo-m'})
+        art=tag.findAll(name='a', attrs={'class':'a-box'})
+        for i in art:
+            title=i.string
+            url=self.INDEX+i['href']
+            #date=soup.find(id='footer').ul.li.string[41:-1]
+            articles.append({'title' : title,
+                   'url'   : url,
+                   'date'  : '',
+                   'description' : ''
+                    })
+        return articles
+
+    def parse_index(self):
+         feeds = []
+         feeds.append((u"Opowiadania", self.find_articles('http://www.fantastyka.pl/3.html')))
+         feeds.append((u"Publicystyka", self.find_articles('http://www.fantastyka.pl/6.html')))
+         feeds.append((u"Hype Park", self.find_articles('http://www.fantastyka.pl/9.html')))
+
+         return feeds
+
+    def get_cover_url(self):
+        soup = self.index_to_soup('http://www.fantastyka.pl/1.html')
+        cover=soup.find(name='img', attrs={'class':'okladka'})
+        self.cover_url=self.INDEX+ cover['src']
+        return getattr(self, 'cover_url', self.cover_url)