Linux Journal and Conowego.pl by fenuks

recipes/conowego_pl.recipe

@@ -0,0 +1,38 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import BeautifulSoup
+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 !'
+    cover_url      = 'http://www.conowego.pl/fileadmin/templates/main/images/logo_top.png'
+    category       = 'IT, news'
+    language       = 'pl'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    remove_empty_feeds = True
+    use_embedded_content = False
+    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)
+
+            for r in appendtag.findAll(attrs={'class':['pages', 'paginationWrap']}):
+                r.extract()

recipes/linux_journal.recipe

@@ -0,0 +1,36 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class LinuxJournal(BasicNewsRecipe):
+    title          = u'Linux Journal'
+    __author__        = 'fenuks'
+    description   = u'The monthly magazine of the Linux community, promoting the use of Linux worldwide.'
+    cover_url      = 'http://www.linuxjournal.com/files/linuxjournal.com/ufiles/logo-lj.jpg'
+    category       = 'IT, Linux'
+    language       = 'en'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    use_embedded_content = False
+    remove_empty_feeds = True
+    keep_only_tags=[dict(id='content-inner')]
+    remove_tags_after= dict(attrs={'class':'user-signature clear-block'})
+    remove_tags=[dict(attrs={'class':['user-signature clear-block', 'breadcrumb',  'terms terms-inline']})]
+    feeds          = [(u'Front Page', u'http://feeds.feedburner.com/linuxjournalcom'), (u'News', u'http://feeds.feedburner.com/LinuxJournal-BreakingNews'), (u'Blogs', u'http://www.linuxjournal.com/blog/feed'), (u'Audio/Video', u'http://www.linuxjournal.com/taxonomy/term/28/0/feed'), (u'Community', u'http://www.linuxjournal.com/taxonomy/term/18/0/feed'), (u'Education', u'http://www.linuxjournal.com/taxonomy/term/25/0/feed'), (u'Embedded', u'http://www.linuxjournal.com/taxonomy/term/27/0/feed'), (u'Hardware', u'http://www.linuxjournal.com/taxonomy/term/23/0/feed'), (u'HOWTOs', u'http://www.linuxjournal.com/taxonomy/term/19/0/feed'), (u'International', u'http://www.linuxjournal.com/taxonomy/term/30/0/feed'), (u'Security', u'http://www.linuxjournal.com/taxonomy/term/31/0/feed'), (u'Software', u'http://www.linuxjournal.com/taxonomy/term/17/0/feed'), (u'Sysadmin', u'http://www.linuxjournal.com/taxonomy/term/21/0/feed'), (u'Webmaster', u'http://www.linuxjournal.com/taxonomy/term/24/0/feed')]
+
+    def append_page(self, soup, appendtag):
+        next = appendtag.find('li', attrs={'class':'pager-next'})
+        while next:    
+            nexturl = next.a['href']
+            appendtag.find('div', attrs={'class':'links'}).extract()
+            soup2 = self.index_to_soup('http://www.linuxjournal.com'+ nexturl)
+            pagetext = soup2.find(attrs={'class':'node-inner'}).find(attrs={'class':'content'})
+            next = appendtag.find('li', attrs={'class':'pager-next'})
+            pos = len(appendtag.contents)
+            appendtag.insert(pos, pagetext)
+        tag = appendtag.find('div', attrs={'class':'links'})
+        if tag:
+            tag.extract()
+
+    def preprocess_html(self, soup):
+        self.append_page(soup, soup.body)
+        return soup