some fixes and a new recipe

recipes/badania_net.recipe

@@ -1,4 +1,5 @@
 from calibre.web.feeds.news import BasicNewsRecipe
+import re
 class BadaniaNet(BasicNewsRecipe):
     title = u'badania.net'
     __author__ = 'fenuks'
@@ -6,9 +7,11 @@ class BadaniaNet(BasicNewsRecipe):
     category = 'science'
     language = 'pl'
     cover_url = 'http://badania.net/wp-content/badanianet_green_transparent.png'
+    extra_css = '.alignleft {float:left; margin-right:5px;} .alignright {float:right; margin-left:5px;}'
     oldest_article = 7
     max_articles_per_feed = 100
     no_stylesheets = True
+    preprocess_regexps = [(re.compile(r"<h4>Tekst sponsoruje</h4>", re.IGNORECASE), lambda m: ''),]
     remove_empty_feeds = True
     use_embedded_content = False
     remove_tags = [dict(attrs={'class':['omc-flex-category', 'omc-comment-count', 'omc-single-tags']})]

recipes/film_org_pl.recipe

@@ -1,5 +1,6 @@
 # vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:fdm=marker:ai
 from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import Comment
 import re
 class FilmOrgPl(BasicNewsRecipe):
     title = u'Film.org.pl'
@@ -7,14 +8,47 @@ class FilmOrgPl(BasicNewsRecipe):
     description = u"Recenzje, analizy, artykuły, rankingi - wszystko o filmie dla miłośników kina. Opisy efektów specjalnych, wersji reżyserskich, remake'ów, sequeli. No i forum filmowe. Jedne z największych w Polsce."
     category = 'film'
     language = 'pl'
-    extra_css = '.alignright {float:right; margin-left:5px;} .alignleft {float:left; margin-right:5px;}'
+    extra_css = '.alignright {float:right; margin-left:5px;} .alignleft {float:left; margin-right:5px;} .recenzja-title {font-size: 150%; margin-top: 5px; margin-bottom: 5px;}'
     cover_url = 'http://film.org.pl/wp-content/themes/KMF/images/logo_kmf10.png'
     ignore_duplicate_articles = {'title', 'url'}
     oldest_article = 7
     max_articles_per_feed = 100
     no_stylesheets = True
+    remove_javascript = True
     remove_empty_feeds = True
-    use_embedded_content = True
+    use_embedded_content = False
-    preprocess_regexps     = [(re.compile(ur'<h3>Przeczytaj także:</h3>.*', re.IGNORECASE|re.DOTALL), lambda m: '</body>'), (re.compile(ur'<div>Artykuł</div>', re.IGNORECASE), lambda m: ''), (re.compile(ur'<div>Ludzie filmu</div>', re.IGNORECASE), lambda m: '')]
+    remove_attributes = ['style']
-    remove_tags = [dict(name='img', attrs={'alt':['Ludzie filmu', u'Artykuł']})]
+    preprocess_regexps = [(re.compile(ur'<h3>Przeczytaj także:</h3>.*', re.IGNORECASE|re.DOTALL), lambda m: '</body>'), (re.compile(ur'</?center>', re.IGNORECASE|re.DOTALL), lambda m: ''), (re.compile(ur'<div>Artykuł</div>', re.IGNORECASE), lambda m: ''), (re.compile(ur'<div>Ludzie filmu</div>', re.IGNORECASE), lambda m: ''), (re.compile(ur'(<br ?/?>\s*?){2,}', re.IGNORECASE|re.DOTALL), lambda m: '')]
+    keep_only_tags = [dict(name=['h11', 'h16', 'h17']), dict(attrs={'class':'editor'})]
+    remove_tags_after = dict(id='comments')
+    remove_tags = [dict(name=['link', 'meta', 'style']), dict(name='img', attrs={'alt':['Ludzie filmu', u'Artykuł']}), dict(id='comments'), dict(attrs={'style':'border: 0pt none ; margin: 0pt; padding: 0pt;'}), dict(name='p', attrs={'class':'rating'}), dict(attrs={'layout':'button_count'})]
     feeds = [(u'Recenzje', u'http://film.org.pl/r/recenzje/feed/'), (u'Artyku\u0142', u'http://film.org.pl/a/artykul/feed/'), (u'Analiza', u'http://film.org.pl/a/analiza/feed/'), (u'Ranking', u'http://film.org.pl/a/ranking/feed/'), (u'Blog', u'http://film.org.pl/kmf/blog/feed/'), (u'Ludzie', u'http://film.org.pl/a/ludzie/feed/'), (u'Seriale', u'http://film.org.pl/a/seriale/feed/'), (u'Oceanarium', u'http://film.org.pl/a/ocenarium/feed/'), (u'VHS', u'http://film.org.pl/a/vhs-a/feed/')]
+
+    def append_page(self, soup, appendtag):
+        tag = soup.find('div', attrs={'class': 'pagelink'})
+        if tag:
+            for nexturl in tag.findAll('a'):
+                url = nexturl['href']
+                soup2 = self.index_to_soup(url)
+                pagetext = soup2.find(attrs={'class': 'editor'})
+                comments = pagetext.findAll(text=lambda text:isinstance(text, Comment))
+                for comment in comments:
+                    comment.extract()
+                pos = len(appendtag.contents)
+                appendtag.insert(pos, pagetext)
+            for r in appendtag.findAll(attrs={'class': 'pagelink'}):
+                r.extract()
+            for r in appendtag.findAll(attrs={'id': 'comments'}):
+                r.extract()
+            for r in appendtag.findAll(attrs={'style':'border: 0pt none ; margin: 0pt; padding: 0pt;'}):
+                r.extract()
+            for r in appendtag.findAll(attrs={'layout':'button_count'}):
+                r.extract()
+                
+    def preprocess_html(self, soup):
+        for c in soup.findAll('h11'):
+            c.name = 'h1'
+        self.append_page(soup, soup.body)
+        for r in soup.findAll('br'):
+            r.extract()
+        return soup

recipes/gram_pl.recipe

@@ -16,7 +16,7 @@ class Gram_pl(BasicNewsRecipe):
     #extra_css = 'h2 {font-style: italic; font-size:20px;} .picbox div {float: left;}'
     cover_url=u'http://www.gram.pl/www/01/img/grampl_zima.png'
     keep_only_tags= [dict(id='articleModule')]
-    remove_tags = [dict(attrs={'class':['breadCrump', 'dymek', 'articleFooter', 'twitter-share-button']})]
+    remove_tags = [dict(attrs={'class':['breadCrump', 'dymek', 'articleFooter', 'twitter-share-button']}), dict(name='aside')]
     feeds = [(u'Informacje', u'http://www.gram.pl/feed_news.asp'),
                         (u'Publikacje', u'http://www.gram.pl/feed_news.asp?type=articles')
                         ]

recipes/historia_pl.recipe

@@ -8,20 +8,15 @@ class Historia_org_pl(BasicNewsRecipe):
     category = 'history'
     language = 'pl'
     oldest_article = 8
+    extra_css = 'img {float: left; margin-right: 10px;} .alignleft {float: left; margin-right: 10px;}'
     remove_empty_feeds= True
     no_stylesheets = True
     use_embedded_content = True
     max_articles_per_feed = 100
     ignore_duplicate_articles = {'title', 'url'}
-
-
     feeds = [(u'Wszystkie', u'http://historia.org.pl/feed/'),
         (u'Wiadomości', u'http://historia.org.pl/Kategoria/wiadomosci/feed/'),
         (u'Publikacje', u'http://historia.org.pl/Kategoria/artykuly/feed/'),
         (u'Publicystyka', u'http://historia.org.pl/Kategoria/publicystyka/feed/'),
         (u'Recenzje', u'http://historia.org.pl/Kategoria/recenzje/feed/'),
         (u'Projekty', u'http://historia.org.pl/Kategoria/projekty/feed/'),]
-
-
-    def print_version(self, url):
-        return url + '?tmpl=component&print=1&layout=default&page='

recipes/infra_pl.recipe

@@ -6,15 +6,14 @@ class INFRA(BasicNewsRecipe):
     max_articles_per_feed = 100
     __author__ = 'fenuks'
     description = u'Serwis Informacyjny INFRA - UFO, Zjawiska Paranormalne, Duchy, Tajemnice świata.'
-    cover_url      = 'http://npn.nazwa.pl/templates/ja_teline_ii/images/logo.jpg'
+    cover_url = 'http://i.imgur.com/j7hJT.jpg'
     category = 'UFO'
     index='http://infra.org.pl'
     language = 'pl'
     max_articles_per_feed = 100
-    no_stylesheers=True
+    remove_attrs = ['style']
-    remove_tags_before=dict(name='h2', attrs={'class':'contentheading'})
+    no_stylesheets = True
-    remove_tags_after=dict(attrs={'class':'pagenav'})
+    keep_only_tags = [dict(id='ja-current-content')]
-    remove_tags=[dict(attrs={'class':'pagenav'})]
     feeds = [(u'Najnowsze wiadomo\u015bci', u'http://www.infra.org.pl/rss')]
 
     def preprocess_html(self, soup):

recipes/kdefamily_pl.recipe

@@ -1,3 +1,4 @@
+import re
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class KDEFamilyPl(BasicNewsRecipe):
@@ -9,6 +10,7 @@ class KDEFamilyPl(BasicNewsRecipe):
     cover_url = 'http://www.mykde.home.pl/kdefamily/wp-content/uploads/2012/07/logotype-e1341585198616.jpg'
     oldest_article = 7
     max_articles_per_feed = 100
+    preprocess_regexps = [(re.compile(r"Podobne wpisy.*", re.IGNORECASE|re.DOTALL), lambda m: '')]
     no_stylesheets = True
     use_embedded_content = True
     feeds = [(u'Wszystko', u'http://kdefamily.pl/feed/')]

recipes/konflikty_zbrojne.recipe

@@ -25,6 +25,7 @@ class Konflikty(BasicNewsRecipe):
         for item in soup.findAll(style=True):
             del item['style']
         for image in soup.findAll(name='a', attrs={'class':'image'}):
+            image['style'] = 'width: 210px; float: left; margin-right:5px;'
             if image.img and image.img.has_key('alt'):
                 image.name='div'
                 pos = len(image.contents)

recipes/kosmonauta_pl.recipe

@@ -8,6 +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;}'
     no_stylesheets = True
     INDEX = 'http://www.kosmonauta.net'
     oldest_article = 7
@@ -16,10 +17,13 @@ class Kosmonauta(BasicNewsRecipe):
     remove_attributes = ['style']
     max_articles_per_feed = 100
     keep_only_tags = [dict(name='div', attrs={'class':'item-page'})]
-    remove_tags = [dict(attrs={'class':['article-tools clearfix', 'cedtag', 'nav clearfix', 'jwDisqusForm']})]
+    remove_tags = [dict(attrs={'class':['article-tools clearfix', 'cedtag', 'nav clearfix', 'jwDisqusForm']}), dict(attrs={'alt':['Poprzednia strona', 'Następna strona']})]
     remove_tags_after = dict(name='div', attrs={'class':'cedtag'})
     feeds = [(u'Kosmonauta.net', u'http://www.kosmonauta.net/?format=feed&type=atom')]
     
+    def print_version(self, url):
+        return url + '?tmpl=component&print=1&layout=default&page='
+
     def preprocess_html(self, soup):
         for a in soup.findAll(name='a'):
            if a.has_key('href'):
@@ -27,4 +31,3 @@ class Kosmonauta(BasicNewsRecipe):
                if not href.startswith('http'):
                    a['href'] = self.INDEX + href
         return soup
-            

recipes/mlody_technik_pl.recipe

@@ -9,6 +9,7 @@ class Mlody_technik(BasicNewsRecipe):
     language = 'pl'
     #cover_url = 'http://science-everywhere.pl/wp-content/uploads/2011/10/mt12.jpg'
     no_stylesheets = True
+    extra_css = 'img.alignleft {float: left; margin-right: 5px;}'
     preprocess_regexps = [(re.compile(r"<h4>Podobne</h4>", re.IGNORECASE), lambda m: '')]
     oldest_article = 7
     max_articles_per_feed = 100

recipes/nauka_w_polsce.recipe

@@ -11,6 +11,8 @@ class NaukawPolsce(BasicNewsRecipe):
     max_articles_per_feed = 100
     no_stylesheets = True
     remove_empty_feeds = True
+    extra_css = '.miniaturka {float: left; margin-right: 5px; max-width: 350px;} .miniaturka-dol-strony {display: inline-block; margin: 0 15px; width: 120px;}'
+    ignore_duplicate_articles = {'title', 'url'}
     index = 'http://www.naukawpolsce.pl'
     keep_only_tags = [dict(name='div', attrs={'class':'margines wiadomosc'})]
     remove_tags = [dict(name='div', attrs={'class':'tagi'})]

recipes/niebezpiecznik.recipe

@@ -7,6 +7,8 @@ class Niebezpiecznik_pl(BasicNewsRecipe):
     category = 'hacking, IT'
     language = 'pl'
     oldest_article = 8
+    extra_css = '.entry {margin-top: 25px;}'
+    remove_attrs = ['style']
     max_articles_per_feed = 100
     no_stylesheets = True
     remove_empty_feeds = True

recipes/osworld_pl.recipe

@@ -6,6 +6,7 @@ class OSWorld(BasicNewsRecipe):
     category = 'OS, IT, open source, Linux'
     language = 'pl'
     cover_url = 'http://osworld.pl/wp-content/uploads/osworld-kwadrat-128x111.png'
+    extra_css = 'img.alignleft {float: left; margin-right: 5px;}'
     oldest_article = 7
     max_articles_per_feed = 100
     no_stylesheets = True

recipes/pc_centre_pl.recipe

@@ -11,6 +11,7 @@ class PC_Centre(BasicNewsRecipe):
     cover_url= 'http://pccentre.pl/views/images/logo.gif'
     no_stylesheets = True
     remove_empty_feeds = True
+    ignore_duplicate_articles = {'title', 'url'}
     #keep_only_tags= [dict(id='content')]
     #remove_tags=[dict(attrs={'class':['ikony r', 'list_of_content', 'dot accordion']}), dict(id='comments')]
     remove_tags=[dict(attrs={'class':'logo_print'})]

recipes/sport_pl.recipe

@@ -0,0 +1,72 @@
+#!/usr/bin/env  python
+
+__license__ = 'GPL v3'
+__copyright__ = 'teepel 2012'
+
+'''
+sport.pl
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
+class sport_pl(BasicNewsRecipe):
+    title          = 'Sport.pl'
+    __author__ = 'teepel <teepel44@gmail.com>'
+    language       = 'pl'
+    description =u'Największy portal sportowy w Polsce. Wiadomości sportowe z najważniejszych wydarzeń, relacje i wyniki meczów na żywo.'
+    masthead_url='http://press.gazeta.pl/file/mediakit/154509/c8/sportpl.jpg'
+    oldest_article = 1
+    max_articles_per_feed = 100
+    remove_javascript=True
+    no_stylesheets=True
+    remove_empty_feeds = True
+
+    keep_only_tags =[]
+    keep_only_tags.append(dict(name = 'div', attrs = {'id' : 'article'}))
+
+    remove_tags =[]
+    remove_tags.append(dict(name = 'a', attrs = {'href' : 'www.gazeta.pl'}))
+
+    feeds          = [
+                            (u'Wszystkie wiadomości', u'http://rss.gazeta.pl/pub/rss/sport.xml'),
+                            (u'Piłka nożna', u'http://www.sport.pl/pub/rss/sport/pilka_nozna.htm'),
+                            (u'F1', u'http://www.sport.pl/pub/rss/sportf1.htm'),
+                            (u'Tenis', u'http://serwisy.gazeta.pl/pub/rss/tenis.htm'),
+                            (u'Siatkówka', u'http://gazeta.pl.feedsportal.com/c/32739/f/611628/index.rss'),
+                            (u'Koszykówka', u'http://gazeta.pl.feedsportal.com/c/32739/f/611647/index.rss'),
+                            (u'Piłka ręczna', u'http://gazeta.pl.feedsportal.com/c/32739/f/611635/index.rss'),
+                            (u'Inne sporty', u'http://gazeta.pl.feedsportal.com/c/32739/f/611649/index.rss'),
+                         ]
+    def parse_feeds(self):
+        feeds = BasicNewsRecipe.parse_feeds(self)
+        for feed in feeds:
+            for article in feed.articles[:]:
+                if '[ZDJĘCIA]' in article.title:
+                    article.title = article.title.replace('[ZDJĘCIA]','')
+                elif '[WIDEO]' in article.title:
+                    article.title = article.title.replace('[WIDEO]','')
+        return feeds
+
+    def print_version(self, url):
+        if 'feedsportal' in url:
+            segment = url.split('/')
+            urlPart = segment[-2]
+            urlPart = urlPart.replace('0L0Ssport0Bpl0C','')
+            urlPart = urlPart.replace('0C10H','/')
+            urlPart = urlPart.replace('0H',',')
+            urlPart = urlPart.replace('0I','_')
+            urlPart = urlPart.replace('A','')
+            segment1 = urlPart.split('/')
+            seg1 = segment1[0]
+            seg2 = segment1[1]
+            segment2 = seg2.split(',')
+            part = segment2[0] + ',' + segment2[1]
+            return 'http://www.sport.pl/' + seg1 +  '/2029020,' + part + '.html'
+        else:
+            segment = url.split('/')
+            part2 = segment[-2]
+            part1 = segment[-1]
+            segment2 = part1.split(',')
+            part = segment2[1] + ',' + segment2[2]
+            return 'http://www.sport.pl/' + part2 + '/2029020,' + part + '.html'

recipes/tablety_pl.recipe

@@ -8,11 +8,13 @@ class Tablety_pl(BasicNewsRecipe):
     cover_url = 'http://www.tablety.pl/wp-content/themes/kolektyw/img/logo.png'
     category = 'IT'
     language = 'pl'
-    use_embedded_content=True
+    use_embedded_content = False
+    no_stylesheets = True
     oldest_article = 8
     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_after=dict(name="footer", attrs={'class':'entry-footer clearfix'})
-    #remove_tags=[dict(name='footer', attrs={'class':'entry-footer clearfix'}), dict(name='div', attrs={'class':'entry-comment-counter'})]
+    remove_tags=[dict(attrs={'class':['comments_icon', 'wp-polls', 'entry-comments']})]
     feeds = [(u'Najnowsze posty', u'http://www.tablety.pl/feed/')]

recipes/wirtualnemedia_pl.recipe

@@ -12,6 +12,7 @@ class WirtualneMedia(BasicNewsRecipe):
     description = u'Portal o mediach, reklamie, internecie, PR, telekomunikacji - nr 1 w Polsce - WirtualneMedia.pl - wiadomości z pierwszej ręki.'
     category = 'internet'
     language = 'pl'
+    ignore_duplicate_articles = {'title', 'url'}
     masthead_url= 'http://i.wp.pl/a/f/jpeg/8654/wirtualnemedia.jpeg'
     cover_url= 'http://static.wirtualnemedia.pl/img/logo_wirtualnemedia_newsletter.gif'
     remove_tags=[dict(id=['header', 'footer'])]
@@ -24,8 +25,6 @@ class WirtualneMedia(BasicNewsRecipe):
         (u'Reklama', u'http://www.wirtualnemedia.pl/rss/wm_reklama.xml'),
         (u'PR', u'http://www.wirtualnemedia.pl/rss/wm_relations.xml'),
         (u'Technologie', u'http://www.wirtualnemedia.pl/rss/wm_telekomunikacja.xml'),
-        (u'Telewizja', u'http://www.wirtualnemedia.pl/rss/wm_telewizja_rss.xml')
+        (u'Telewizja', u'http://www.wirtualnemedia.pl/rss/wm_telewizja_rss.xml')]
-        ]
-
     def print_version(self, url):
         return url.replace('artykul', 'print')