Merge branch 'master' of https://github.com/t3d/calibre

recipes/puls_biznesu.recipe

@@ -1,48 +0,0 @@
-from calibre.web.feeds.news import BasicNewsRecipe
-import re
-
-
-class PB_PL(BasicNewsRecipe):
-    title = u'Puls Biznesu'
-    __author__ = 'fenuks'
-    language = 'pl'
-    description = u'Puls Biznesu - biznes, ekonomia, giełda, inwestycje'
-    category = u'newspaper'
-    publication_type = u'newspaper'
-    encoding = 'utf-8'
-    # masthead_url = 'http://www.pb.pl/img/pb.png'
-    oldest_article = 7
-    max_articles_per_feed = 100
-    no_stylesheets = True
-    remove_empty_feeds = True
-    ignore_duplicate_articles = {'title', 'url'}
-    remove_tags_after = dict(name='div', attrs={'class': 'news_content'})
-    feeds = [
-    (u'Wszystkie', u'http://www.pb.pl/atom'),
-    (u'Puls inwestora', u'http://pulsinwestora.pb.pl/atom'),
-    (u'Puls Firmy', u'http://firma.pb.pl/atom'),
-    (u'PB Weekend', u'http://weekend.pb.pl/atom'),
-    (u'Forum MPS', u'http://forummsp.pb.pl/atom'),
-    (u'Moto', u'http://moto.pb.pl/atom'),
-    (u'Kariera i praca', u'http://kariera.pb.pl/atom'),
-
-    (u'Nieruchomości', u'http://nieruchomosci.pb.pl/atom'),
-    (u'Samorządy', u'http://samorzady.pb.pl/atom'),
-    (u'Tech', u'http://tech.pb.pl/atom'),
-    (u'Energetyka', u'http://energetyka.pb.pl/atom'),
-    (u'Retailing', u'http://retailing.pb.pl/atom'),
-    (u'Puls medycyny', u'http://pulsmedycyny.pl/atom'),
-    (u'Logistyka', u'http://logistyka.pb.pl/atom')]
-
-    def print_version(self, url):
-        article_id = re.search(r'(?P<id>\d+,\d+)', url)
-        if article_id:
-            return 'http://www.pb.pl/actionprint/' + article_id.group('id')
-        else:
-            return url
-
-    def get_cover_url(self):
-        soup = self.index_to_soup('http://archiwum.pb.pl/')
-        cover = soup.find(name='img', attrs={'class': 'cover_picture'})
-        self.cover_url = cover['src']
-        return getattr(self, 'cover_url', self.cover_url)

recipes/pure_pc.recipe

@@ -11,35 +11,10 @@ class PurePC(BasicNewsRecipe):
     description = u'Artykuły, aktualności, sprzęt, forum, chłodzenie, modding, urządzenia mobilne - wszystko w jednym miejscu.'
     category = 'IT'
     language = 'pl'
-    masthead_url = 'http://www.purepc.pl/themes/new/images/purepc.jpg'
     cover_url = 'http://www.purepc.pl/themes/new/images/purepc.jpg'
     extra_css = '.wykres_logo {float: left; margin-right: 5px;}'
     no_stylesheets = True
-    keep_only_tags = [dict(id='content')]
+
-    remove_tags_after = dict(attrs={'class': 'fivestar-widget'})
+    keep_only_tags = [dict(name='div', attrs={'class':'node page0'})]
-    remove_tags = [dict(id='navigator'), dict(
+    remove_tags = [dict(name='div', attrs={'class':'article-options'})]
-        attrs={'class': ['box-tools', 'fivestar-widget', 'PageMenuList']})]
     feeds = [(u'Wiadomo\u015bci', u'http://www.purepc.pl/node/feed')]
-
-    def append_page(self, soup, appendtag):
-        lasturl = appendtag.find(attrs={'class': 'pager-last'})
-        if lasturl:
-            regex = re.search('(.+?2C)(\d+)', lasturl.a['href'])
-            baseurl = regex.group(1).replace('?page=0%2C', '?page=1%2C')
-            baseurl = 'http://www.purepc.pl' + baseurl
-            nr = int(regex.group(2))
-            for page_nr in range(1, nr + 1):
-                soup2 = self.index_to_soup(baseurl + str(page_nr))
-                pagetext = soup2.find(attrs={'class': 'article'})
-                pos = len(appendtag.contents)
-                appendtag.insert(pos, pagetext)
-            for r in appendtag.findAll(attrs={'class': ['PageMenuList', 'pager', 'fivestar-widget']}):
-                r.extract()
-            comments = appendtag.findAll(
-                text=lambda text: isinstance(text, Comment))
-            for comment in comments:
-                comment.extract()
-
-    def preprocess_html(self, soup):
-        self.append_page(soup, soup.body)
-        return soup

recipes/racjonalista_pl.recipe

@@ -1,58 +0,0 @@
-__copyright__ = '2012, Micha\u0142 <webmaster@racjonalista.pl>'
-'''
-Racjonalista.pl
-'''
-
-from calibre.web.feeds.news import BasicNewsRecipe
-import re
-
-
-class Racjonalista(BasicNewsRecipe):
-    __author__ = u'Micha\u0142 <webmaster@racjonalista.pl>'
-    publisher = u'Fundacja Wolnej My\u015bli'
-    title = u'Racjonalista.pl'
-    description = u'Racjonalista.pl'
-    category = 'newspaper'
-    language = 'pl'
-    encoding = 'iso-8859-2'
-    oldest_article = 7
-    max_articles_per_feed = 20
-    remove_javascript = True
-    no_stylesheets = True
-    use_embedded_content = False
-    simultaneous_downloads = 2
-    timeout = 30
-    cover_url = 'http://www.racjonalista.pl/img/uimg/rac.gif'
-
-    feeds = [(u'Racjonalista.pl', u'http://www.racjonalista.pl/rss.php')]
-
-    match_regexps = [r'kk\.php']
-
-    def print_version(self, url):
-        return url.replace('/s,', '/t,')
-
-    extra_css = 'h2 {font: serif large} .cytat {text-align: right}'
-
-    remove_attributes = ['target', 'width', 'height']
-
-    preprocess_regexps = [
-        (re.compile(i[0], re.DOTALL), i[1]) for i in
-        [(r'<p[^>]*>&nbsp;</p>', lambda match: ''),
-         (r'&nbsp;', lambda match: ' '),
-         (r'<meta[^>]+>', lambda match: ''),
-         (r'<link[^>]+>', lambda match: ''),
-         (r'</?center>', lambda match: ''),
-         (r'<a href="[^"]+" rel=author><b>(?P<a>[^<]+)</b></a>',
-          lambda match: '<b>' + match.group('a') + '</b>'),
-         (r'<div align=center style="font-size:18px">(?P<t>[^<]+)</div>',
-          lambda match: '<h2>' + match.group('t') + '</h2>'),
-         (r'<table align=center width=700 border=0 cellpadding=0 cellspacing=0><tr><td width="100%" bgcolor="#edeceb" height="100%" style="font-size:12px">', lambda match: ''),  # noqa
-         (r'</td></tr><tr><td>', lambda match: ''),
-         (r'</td></tr></table></body>', lambda match: '</body>'),
-         (r'<a[^>]+><sup>(?P<p>[^<]+)</sup></a>',
-          lambda match: '<sup>' + match.group('p') + '</sup>'),
-         (r'<a name=p[^>]+>(?P<a>[^<]+)</a>', lambda match: match.group('a')),
-         (r'<a href="[^"]+" target=_blank class=linkext>Orygin[^<]+</a>',
-          lambda match: ''),
-         (r'<a href="[^"]+" class=powiazanie>Poka[^<]+</a>', lambda match: '')]
-    ]

recipes/res_publica.recipe

@@ -1,36 +0,0 @@
-#!/usr/bin/env  python2
-
-__license__ = 'GPL v3'
-
-from calibre.web.feeds.news import BasicNewsRecipe
-
-
-class ResPublicaNowaRecipe(BasicNewsRecipe):
-    __license__ = 'GPL v3'
-    __author__ = u'Artur Stachecki <artur.stachecki@gmail.com>'
-    language = 'pl'
-    version = 1
-
-    title = u'Res Publica Nowa'
-    category = u'News'
-    description = u'Portal kulturalno-społecznego kwartalnika o profilu liberalnym, wydawany przez Fundację Res Publica'
-    cover_url = ''
-    remove_empty_feeds = True
-    no_stylesheets = True
-    oldest_article = 7
-    max_articles_per_feed = 100000
-    recursions = 0
-    no_stylesheets = True
-    remove_javascript = True
-    simultaneous_downloads = 5
-
-    feeds = [
-        ('Artykuly', 'feed://publica.pl/feed'),
-    ]
-
-    def preprocess_html(self, soup):
-        for alink in soup.findAll('a'):
-            if alink.string is not None:
-                tstr = alink.string
-                alink.replaceWith(tstr)
-        return soup

recipes/rmf24_ESKN.recipe

@@ -26,13 +26,11 @@ class RMF24_ESKN(BasicNewsRecipe):
              (u'Nauka', u'http://www.rmf24.pl/nauka/feed')]
 
     keep_only_tags = [
-        dict(name='div', attrs={'class': 'box articleSingle print'})]
+        dict(name='header', attrs={'class': 'article-header'}),
+        dict(name='div', attrs={'class': 'article-container'})]
 
-    remove_tags = [
+    remove_tags = [dict(name='div', attrs={'id': 'ReklamaMobile'}),
-        dict(name='div', attrs={'class': 'toTop'}),
+        dict(name='img', attrs={'class': 'img-responsive hidden-lg hidden-md hidden-sm'})]
-        dict(name='div', attrs={'class': 'category'}),
-        dict(name='div', attrs={'class': 'REMOVE'}),
-        dict(name='div', attrs={'class': 'embed embedAd'})]
 
     extra_css = '''
         h1 { font-size: 1.2em; }
@@ -42,7 +40,6 @@ class RMF24_ESKN(BasicNewsRecipe):
         (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
         [
             (r'<h2>Zdj.cie</h2>', lambda match: ''),
-            (r'embed embed(Left|Right|Center) articleEmbed(Audio|Wideo articleEmbedVideo|ArticleFull|ArticleTitle|ArticleListTitle|AlbumHorizontal)">', lambda match: 'REMOVE">'),  # noqa
             (r'<a href="http://www.facebook.com/pages/RMF24pl/.*?>RMF24.pl</a> on Facebook</div>',
              lambda match: '</div>')
         ]

recipes/rmf24_fakty.recipe

@@ -24,14 +24,11 @@ class RMF24(BasicNewsRecipe):
              (u'\u015awiat', u'http://www.rmf24.pl/fakty/swiat/feed')]
 
     keep_only_tags = [
-        dict(name='div', attrs={'class': 'box articleSingle print'})]
+        dict(name='header', attrs={'class': 'article-header'}),
+        dict(name='div', attrs={'class': 'article-container'})]
 
-    remove_tags = [
+    remove_tags = [dict(name='div', attrs={'id': 'ReklamaMobile'}),
-        dict(name='div', attrs={'id': 'adBox625'}),
+        dict(name='img', attrs={'class': 'img-responsive hidden-lg hidden-md hidden-sm'})]
-        dict(name='div', attrs={'class': 'toTop'}),
-        dict(name='div', attrs={'class': 'category'}),
-        dict(name='div', attrs={'class': 'REMOVE'}),
-        dict(name='div', attrs={'class': 'embed embedAd'})]
 
     extra_css = '''
         h1 { font-size: 1.2em; }
@@ -40,7 +37,6 @@ class RMF24(BasicNewsRecipe):
         (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
         [
             (r'<h2>Zdj.cie</h2>', lambda match: ''),
-            (r'embed embed(Left|Right|Center) articleEmbed(Audio|Wideo articleEmbedVideo|ArticleFull|ArticleTitle|ArticleListTitle|AlbumHorizontal)">', lambda match: 'REMOVE">'),  # noqa
             (r'<a href="http://www.facebook.com/pages/RMF24pl/.*?>RMF24.pl</a> on Facebook</div>',
              lambda match: '</div>')
         ]

recipes/rmf24_opinie.recipe

@@ -19,6 +19,7 @@ class RMF24_opinie(BasicNewsRecipe):
     __author__ = u'Tomasz D\u0142ugosz'
     no_stylesheets = True
     remove_javascript = True
+    remove_empty_feeds = True
 
     feeds = [(u'Blogi', u'http://www.rmf24.pl/opinie/blogi/feed'),
              (u'Kontrwywiad',
@@ -28,16 +29,10 @@ class RMF24_opinie(BasicNewsRecipe):
              (u'Komentarze', u'http://www.rmf24.pl/opinie/komentarze/feed')]
 
     keep_only_tags = [
-        dict(name='div', attrs={'class': 'box articleSingle print'}),
+        dict(name='header', attrs={'class': 'article-header'}),
-        dict(name='div', attrs={
+        dict(name='div', attrs={'class': 'article-container'})]
-             'class': 'box articleSingle print singleCommentary'}),
-        dict(name='div', attrs={'class': 'box articleSingle print blogSingleEntry'})]
 
-    remove_tags = [
+    remove_tags = [dict(name='div', attrs={'id': 'ReklamaMobile'})]
-        dict(name='div', attrs={'class': 'toTop'}),
-        dict(name='div', attrs={'class': 'category'}),
-        dict(name='div', attrs={'class': 'REMOVE'}),
-        dict(name='div', attrs={'class': 'embed embedAd'})]
 
     extra_css = '''
         h1 { font-size: 1.2em; }

recipes/rynek_infrastruktury.recipe

@@ -17,26 +17,22 @@ class prawica_recipe(BasicNewsRecipe):
     description = u'Portal "Rynek Infrastruktury" to źródło informacji o kluczowych elementach polskiej gospodarki: drogach, kolei, lotniskach, portach, telekomunikacji, energetyce, prawie i polityce, wzmocnione eksperckimi komentarzami kluczowych analityków.'  # noqa
     remove_empty_feeds = True
     oldest_article = 1
-    max_articles_per_feed = 100
+    max_articles_per_feed = 50
     remove_javascript = True
     no_stylesheets = True
 
     feeds = [
-        (u'Drogi', u'http://www.rynekinfrastruktury.pl/rss/41'),
+        (u'Drogi', u'http://www.rynekinfrastruktury.pl/rss/drogi.xml'),
-        (u'Lotniska', u'http://www.rynekinfrastruktury.pl/rss/42'),
+        (u'Kolej', u'http://www.rynekinfrastruktury.pl/rss/kolej.xml'),
-        (u'Kolej', u'http://www.rynekinfrastruktury.pl/rss/37'),
+        (u'Energetyka', u'http://www.rynekinfrastruktury.pl/rss/energetyka.xml')
-        (u'Energetyka', u'http://www.rynekinfrastruktury.pl/rss/30'),
+        # no news in these feeds since 4 years:
-        (u'Telekomunikacja', u'http://www.rynekinfrastruktury.pl/rss/31'),
+        #(u'Porty i lotniska', u'http://www.rynekinfrastruktury.pl/rss/porty-i-lotniska.xml'),
-        (u'Porty', u'http://www.rynekinfrastruktury.pl/rss/32'),
+        #(u'Komentarze', u'http://www.rynekinfrastruktury.pl/rss/komentarze-i-felietony.xml'),
-        (u'Prawo i polityka', u'http://www.rynekinfrastruktury.pl/rss/47'),
-        (u'Komentarze', u'http://www.rynekinfrastruktury.pl/rss/38'),
     ]
 
-    keep_only_tags = []
+    keep_only_tags = [
-    keep_only_tags.append(dict(name='div', attrs={'class': 'articleContent'}))
+        dict(name='h1', attrs={'class': 'wiadTit'}),
+        dict(name='div', attrs={'class': ['wiadSzczegol', 'multimediaWiadomosci', 'wiadTresc']})
+    ]
 
-    remove_tags = []
+    remove_tags = [dict(name='span', attrs={'class': 'kom'})]
-    remove_tags.append(dict(name='span', attrs={'class': 'date'}))
-
-    def print_version(self, url):
-        return url.replace('http://www.rynekinfrastruktury.pl/artykul/', 'http://www.rynekinfrastruktury.pl/artykul/drukuj/')

recipes/rynek_kolejowy.recipe

@@ -1,40 +0,0 @@
-#!/usr/bin/env  python2
-
-__license__ = 'GPL v3'
-__author__ = 'teepel <teepel44@gmail.com>'
-
-'''
-rynek-kolejowy.pl
-'''
-
-from calibre.web.feeds.news import BasicNewsRecipe
-
-
-class rynek_kolejowy(BasicNewsRecipe):
-    title = u'Rynek Kolejowy'
-    __author__ = 'teepel <teepel44@gmail.com>'
-    language = 'pl'
-    description = u'Rynek Kolejowy - kalendarium wydarzeń branży kolejowej, konferencje, sympozja, targi kolejowe, krajowe i zagraniczne.'
-    masthead_url = 'http://p.wnp.pl/images/i/partners/rynek_kolejowy.gif'
-    remove_empty_feeds = True
-    oldest_article = 1
-    max_articles_per_feed = 100
-    remove_javascript = True
-    no_stylesheets = True
-
-    keep_only_tags = []
-    keep_only_tags.append(dict(name='div', attrs={'id': 'mainContent'}))
-
-    remove_tags = []
-    remove_tags.append(dict(name='div', attrs={'class': 'right no-print'}))
-    remove_tags.append(dict(name='div', attrs={'id': 'font-size'}))
-    remove_tags.append(dict(name='div', attrs={'class': 'no-print'}))
-
-    extra_css = '''.wiadomosc_title{ font-size: 1.4em; font-weight: bold; }'''
-
-    feeds = [(u'Wiadomości', u'http://www.rynek-kolejowy.pl/rss/rss.php')]
-
-    def print_version(self, url):
-        segment = url.split('/')
-        urlPart = segment[3]
-        return 'http://www.rynek-kolejowy.pl/drukuj.php?id=' + urlPart