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

recipes/ekundelek_pl.recipe

@@ -1,19 +0,0 @@
-#!/usr/bin/env python2
-
-__license__ = 'GPL v3'
-__copyright__ = u'2012, Artur Stachecki <artur.stachecki@gmail.com>'
-
-from calibre.web.feeds.news import BasicNewsRecipe
-
-
-class swiatczytnikow(BasicNewsRecipe):
-    title = u'eKundelek'
-    description = u'Najsympatyczniejszy blog o e-czytnikach Kindle'
-    language = 'pl'
-    __author__ = u'Artur Stachecki'
-    oldest_article = 7
-    max_articles_per_feed = 100
-    remove_empty_feeds = True
-    remove_tags = [dict(name='div', attrs={'class': 'feedflare'})]
-
-    feeds = [(u'Wpisy', u'http://feeds.feedburner.com/Ekundelekpl?format=xml')]

recipes/eso_pl.recipe

@@ -12,7 +12,7 @@ class ESO(BasicNewsRecipe):
     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'
+    cover_url = 'https://www.eso.org/public/archives/logos/medium/eso-logo-black-outline.jpg'
     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']})]
@@ -21,6 +21,9 @@ class ESO(BasicNewsRecipe):
     (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/')]
 
+    keep_only_tags = [
+        dict(name='div',attrs={'class':'col-md-9 left-column'})]
+
     def preprocess_html(self, soup):
         for a in soup.findAll('a', href=True):
             if a['href'].startswith('/'):

recipes/gry_online_pl.recipe

@@ -18,7 +18,7 @@ class GryOnlinePl(BasicNewsRecipe):
     keep_only_tags = [dict(name='div', attrs={'class': [
                            'gc660', 'gc660 S013', 'news_endpage_tit', 'news_container', 'news']})]
     remove_tags = [
-        dict({'class': ['nav-social', 'add-info', 'smlb', 'lista lista3 lista-gry', 'S013po', 'S013-npb', 'zm_gfx_cnt_bottom', 'ocen-txt', 'wiecej-txt', 'wiecej-txt2', 'twitter-share-button']})]  # noqa
+        dict({'class': ['nav-social', 'add-info', 'smlb', 'lista lista3 lista-gry', 'S013po', 'S013-npb', 'zm_gfx_cnt_bottom', 'ocen-txt', 'wiecej-txt', 'wiecej-txt2', 'social-for-old-news', 'social-for-old-rec']})]  # noqa
     feeds = [
         (u'Newsy', 'http://www.gry-online.pl/rss/news.xml'),
         ('Teksty', u'http://www.gry-online.pl/rss/teksty.xml')]

recipes/tvn24.recipe

@@ -9,29 +9,31 @@ class tvn24(BasicNewsRecipe):
     description = u'Sport, Biznes, Gospodarka, Informacje, Wiadomości Zawsze aktualne wiadomości z Polski i ze świata'
     category = 'news'
     language = 'pl'
-    cover_url = 'http://www.qzdrowiu.pl/Upload/KnowQZdrowiu_PressOffice/TVN24_logo_575702b7-edce-4b6f-a41b-4395f9456f96_ff6d6ccf-528a-4b94-9e61-2fed727aba35.png'  # noqa
+    cover_url = 'http://ncplus.pl/~/media/n/npl/kanaly/logo%20na%20strony%20kanalow/tvn24-630.png'  # noqa
     extra_css = 'ul {list-style: none; padding: 0; margin: 0;} li {float: left;margin: 0 0.15em;}'
     remove_empty_feeds = True
     remove_javascript = True
     no_stylesheets = True
     keep_only_tags = [
-        #       dict(name='h1', attrs={'class':'size38 mt20 pb20'}),
+        dict(name='article',attrs={'class':'mb20'})
-        dict(name='div', attrs={'class': 'mainContainer'}),
-        #       dict(name='p'),
-        #       dict(attrs={'class':['size18 mt10 mb15', 'bold topicSize1', 'fromUsers content', 'textArticleDefault']})
     ]
     remove_tags = [
-        dict(attrs={'class': ['commentsInfo', 'textSize', 'related newsNews align-right', 'box', 'watchMaterial text', 'related galleryGallery align-center', 'advert block-alignment-right', 'userActions', 'socialBookmarks', 'im yourArticle fl', 'dynamicButton addComment fl', 'innerArticleModule onRight cols externalContent', 'thumbsGallery', 'relatedObject customBlockquote align-right', 'lead', 'mainRightColumn', 'articleDateContainer borderGreyBottom', 'socialMediaContainer onRight loaded', 'quizContent', 'twitter', 'facebook', 'googlePlus', 'share', 'voteResult', 'reportTitleBar bgBlue_v4 mb15', 'innerVideoModule center']}),  # noqa
+        dict(attrs={'class': ['commentsInfo', 'textSize', 'related newsNews align-right', 'box', 'watchMaterial text', 'related galleryGallery align-center', 'advert block-alignment-right', 'userActions', 'socialBookmarks', 'im yourArticle fl', 'dynamicButton addComment fl', 'thumbsGallery', 'relatedObject customBlockquote align-right', 'lead', 'mainRightColumn', 'articleDateContainer borderGreyBottom', 'socialMediaContainer onRight loaded', 'quizContent', 'twitter', 'facebook', 'googlePlus', 'share', 'voteResult', 'reportTitleBar bgBlue_v4 mb15', 'innerVideoModule center']}),  # noqa
-        dict(name='article', attrs={'class': [
+        dict(name='aside'),
-             'singleArtPhotoCenter', 'singleArtPhotoRight', 'singleArtPhotoLeft']}),
+        dict(name='figure'),
         dict(name='section', attrs={
-             'id': ['forum', 'innerArticle', 'quiz toCenter', 'mb20']}),
+             'id': ['forum', 'innerArticle', 'quiz toCenter', 'mb20']})
-        dict(name='div', attrs={
-             'class': 'socialMediaContainer big p20 mb20 borderGrey  loaded'})
     ]
     remove_tags_after = [dict(name='li', attrs={'class': 'share'})]
     feeds = [(u'Najnowsze', u'http://www.tvn24.pl/najnowsze.xml'), ]
 
+    def get_article_url(self, article):
+        link = article.get('link')
+        # following websites are linked in aforementioned feeds, but have different layout not compatible with this recipe
+        banned = ['tvnwarszawa.pl','tvnmeteo.pl','szklokontaktowe.tvn24.pl','tvn24bis.pl']
+        if not any(x in link for x in banned):
+            return link
+
     def preprocess_html(self, soup):
         for alink in soup.findAll('a'):
             if alink.string is not None: