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

recipes/bash_org_pl.recipe

@@ -1,51 +0,0 @@
-from calibre.web.feeds.news import BasicNewsRecipe
-
-
-class Bash_org_pl(BasicNewsRecipe):
-    title = u'Bash.org.pl'
-    __author__ = 'fenuks'
-    description = 'Bash.org.pl - zabawne cytaty z IRC'
-    category = 'funny quotations, humour'
-    language = 'pl'
-    cover_url = u'http://userlogos.org/files/logos/dzikiosiol/none_0.png'
-    max_articles_per_feed = 50
-    no_stylesheets = True
-    keep_only_tags = [dict(name='a', attrs={'class': 'qid click'}),
-                      dict(name='div', attrs={'class': 'quote post-content post-body'})]
-
-    def latest_articles(self):
-        articles = []
-        soup = self.index_to_soup(u'http://bash.org.pl/latest/')
-        tags = soup.findAll('a', attrs={'class': 'qid click'})
-        for a in tags:
-            title = a.string
-            url = 'http://bash.org.pl' + a['href']
-            articles.append({'title': title,
-                             'url': url,
-                             'date': '',
-                             'description': ''
-                             })
-        return articles
-
-    def random_articles(self):
-        articles = []
-        for i in range(self.max_articles_per_feed):
-            soup = self.index_to_soup(u'http://bash.org.pl/random/')
-            url = soup.find('a', attrs={'class': 'qid click'})
-            title = ''
-            url = 'http://bash.org.pl/random/'
-            articles.append({'title': title,
-                             'url': url,
-                             'date': '',
-                             'description': ''
-                             })
-        return articles
-
-    def populate_article_metadata(self, article, soup, first):
-        article.title = soup.find(attrs={'class': 'qid click'}).string
-
-    def parse_index(self):
-        feeds = []
-        feeds.append((u"Najnowsze", self.latest_articles()))
-        feeds.append((u"Losowe", self.random_articles()))
-        return feeds

recipes/conowego_pl.recipe

@@ -1,56 +0,0 @@
-from calibre.web.feeds.news import BasicNewsRecipe
-from calibre.ebooks.BeautifulSoup import BeautifulSoup, Comment
-
-
-class CoNowegoPl(BasicNewsRecipe):
-    title = u'conowego.pl'
-    __author__ = 'fenuks'
-    description = u'Nowy wortal technologiczny oraz gazeta internetowa. Testy najnowszych produktów, fachowe porady i recenzje. U nas znajdziesz wszystko o elektronice użytkowej !'  # noqa
-    category = 'IT, news'
-    language = 'pl'
-    oldest_article = 7
-    max_articles_per_feed = 100
-    INDEX = 'http://www.conowego.pl/'
-    extra_css = '.news-single-img {float:left; margin-right:5px;}'
-    no_stylesheets = True
-    remove_empty_feeds = True
-    use_embedded_content = False
-    ignore_duplicate_articles = {'title', 'url'}
-    keep_only_tags = [
-        dict(name='div', attrs={'class': 'news_list single_view'})]
-    remove_tags = [
-        dict(name='div', attrs={'class': ['ni_bottom', 'ni_rank', 'ni_date']})]
-    feeds = [(u'Aktualno\u015bci', u'http://www.conowego.pl/rss/aktualnosci-5/?type=100'), (u'Gaming', u'http://www.conowego.pl/rss/gaming-6/?type=100'),
-             (u'Porady', u'http://www.conowego.pl/rss/porady-3/?type=100'), (u'Testy', u'http://www.conowego.pl/rss/testy-2/?type=100')]
-
-    def preprocess_html(self, soup):
-        for i in soup.findAll('img'):
-            i.parent.insert(0, BeautifulSoup('<br />'))
-            i.insert(len(i), BeautifulSoup('<br />'))
-        self.append_page(soup, soup.body)
-        return soup
-
-    def append_page(self, soup, appendtag):
-        tag = appendtag.find('div', attrs={'class': 'pages'})
-        if tag:
-            nexturls = tag.findAll('a')
-            for nexturl in nexturls[:-1]:
-                soup2 = self.index_to_soup(
-                    'http://www.conowego.pl/' + nexturl['href'])
-                pagetext = soup2.find(attrs={'class': 'ni_content'})
-                pos = len(appendtag.contents)
-                appendtag.insert(pos, pagetext)
-
-            comments = appendtag.findAll(
-                text=lambda text: isinstance(text, Comment))
-            for comment in comments:
-                comment.extract()
-            for r in appendtag.findAll(attrs={'class': ['pages', 'paginationWrap']}):
-                r.extract()
-
-    def get_cover_url(self):
-        soup = self.index_to_soup('http://www.conowego.pl/magazyn/')
-        tag = soup.find(attrs={'class': 'ms_left'})
-        if tag:
-            self.cover_url = self.INDEX + tag.find('img')['src']
-        return getattr(self, 'cover_url', self.cover_url)

recipes/czas_gentlemanow.recipe

@@ -9,7 +9,7 @@ class CzasGentlemanow(BasicNewsRecipe):
     description = u'Historia mężczyzn z dala od wielkiej polityki'
     category = 'blog'
     language = 'pl'
-    cover_url = 'http://czasgentlemanow.pl/wp-content/uploads/2012/10/logo-Czas-Gentlemanow1.jpg'
+    cover_url = 'https://czasgentlemanow.pl/wp-content/uploads/2012/10/logo-Czas-Gentlemanow1.jpg'
     ignore_duplicate_articles = {'title', 'url'}
     oldest_article = 7
     max_articles_per_feed = 100
@@ -17,18 +17,10 @@ class CzasGentlemanow(BasicNewsRecipe):
     .wp-caption-text {text-align: left;} img.aligncenter {display: block; margin-left: auto; margin-right: auto;} .alignleft {float: left; margin-right:5px;}'
     no_stylesheets = True
     remove_empty_feeds = True
-    preprocess_regexps = [
-        (re.compile(u'<h3>Może Cię też zainteresować:</h3>'), lambda m: '')]
     use_embedded_content = False
-    keep_only_tags = [dict(name='div', attrs={'class': 'content'})]
-    remove_tags = [dict(attrs={'class': 'meta_comments'}), dict(
-        id=['comments', 'related_posts_thumbnails', 'respond'])]
-    remove_tags_after = dict(id='comments')
+    keep_only_tags = [dict(name='div', attrs={'class': 'post-wrapper'})]
+    remove_tags = [dict(attrs={'class': ['awac-wrapper', 'post-bottom', 'comment', 'seperate']})]
     feeds = [
-    (u'M\u0119ski \u015awiat', u'http://czasgentlemanow.pl/category/meski-swiat/feed/'),
-    (u'Styl', u'http://czasgentlemanow.pl/category/styl/feed/'),
-    (u'Vademecum Gentlemana', u'http://czasgentlemanow.pl/category/vademecum/feed/'),
-
-    (u'Dom i rodzina', u'http://czasgentlemanow.pl/category/dom-i-rodzina/feed/'),
-    (u'Honor', u'http://czasgentlemanow.pl/category/honor/feed/'),
-    (u'Gad\u017cety Gentlemana', u'http://czasgentlemanow.pl/category/gadzety-gentlemana/feed/')]
+    (u'Charakter', u'https://czasgentlemanow.pl/category/charakter/feed/'),
+    (u'Wizerunek', u'https://czasgentlemanow.pl/category/wizerunek/feed/'),
+    (u'Relacje międzyludzkie', u'https://czasgentlemanow.pl/category/relacje-miedzyludzkie/feed/')]

recipes/myapple_pl.recipe

@@ -6,7 +6,6 @@ class MyAppleRecipe(BasicNewsRecipe):
     __license__ = 'GPL v3'
     __author__ = u'Artur Stachecki <artur.stachecki@gmail.com>'
     language = 'pl'
-    version = 1
 
     title = u'MyApple.pl'
     category = u'News'
@@ -22,16 +21,10 @@ class MyAppleRecipe(BasicNewsRecipe):
     remove_javascript = True
     simultaneous_downloads = 3
 
-    keep_only_tags = []
-    keep_only_tags.append(dict(name='div', attrs={'id': 'article_content'}))
+    keep_only_tags = [dict(name='article')]
 
-    remove_tags = []
-    remove_tags.append(
-        dict(name='div', attrs={'class': 'article_author_date_comment_container'}))
-    remove_tags.append(dict(name='div', attrs={'class': 'fullwidth'}))
-    remove_tags.append(dict(name='div', attrs={'class': 'cmslinks'}))
-    remove_tags.append(dict(name='div', attrs={'class': 'googleads-468'}))
-    remove_tags.append(dict(name='div', attrs={'id': 'comments'}))
+    remove_tags = [dict(name='a', attrs={'class': 'twitter-follow-button'}),
+                   dict(name='ul', attrs={'class': 'list-inline text-muted small mb-0 mt-1'})]
 
     extra_css = '''
                     body {font-family: verdana, arial, helvetica, geneva, sans-serif ;}
@@ -39,7 +32,7 @@ class MyAppleRecipe(BasicNewsRecipe):
                     '''
 
     feeds = [
-        ('News', 'feed://myapple.pl/external.php?do=rss&type=newcontent&sectionid=1&days=120&count=10'),
+        ('Wpisy', 'https://myapple.pl/posts.atom'),
     ]
 
     def preprocess_html(self, soup):

recipes/samcik_blox.recipe

@@ -1,27 +0,0 @@
-#!/usr/bin/env  python2
-
-__license__ = 'GPL v3'
-__author__ = 'teepel <teepel44@gmail.com>'
-
-'''
-samcik.blox.pl
-'''
-
-from calibre.web.feeds.news import BasicNewsRecipe
-
-
-class samcik(BasicNewsRecipe):
-    title = u'Maciej Samcik Blog'
-    __author__ = 'teepel <teepel44@gmail.com>'
-    language = 'pl'
-    description = u'Blog Macieja Samcika, długoletniego dziennikarza ekonomicznego Gazety Wyborczej . O finansach małych i dużych. Mnóstwo ciekawostek na temat pieniędzy.'  # noqa
-    oldest_article = 7
-    max_articles_per_feed = 100
-    remove_javascript = True
-    no_stylesheets = True
-    simultaneous_downloads = 3
-
-    remove_tags = []
-    remove_tags.append(dict(name='table', attrs={'border': '0'}))
-
-    feeds = [(u'Wpisy', u'http://samcik.blox.pl/rss2')]