new recipes from kalibrator project

recipes/dzial_zagraniczny.recipe

@@ -0,0 +1,29 @@
+#!/usr/bin/env  python
+
+__license__ = 'GPL v3'
+__author__ = 'teepel <teepel44@gmail.com>'
+
+'''
+dzialzagraniczny.pl
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
+class dzial_zagraniczny(BasicNewsRecipe):
+    title          = u'Dział Zagraniczny'
+    __author__ = 'teepel <teepel44@gmail.com>'
+    language       = 'pl'
+    description    = u'Polskiego czytelnika to nie interesuje'
+    INDEX = 'http://dzialzagraniczny.pl'
+    extra_css = 'img {display: block;}'
+    oldest_article = 7
+    cover_url = 'https://fbcdn-profile-a.akamaihd.net/hprofile-ak-prn1/c145.5.160.160/559442_415653975115959_2126205128_n.jpg'
+    max_articles_per_feed = 100
+    remove_empty_feeds = True
+    simultaneous_downloads = 5
+    remove_javascript = True
+    no_stylesheets = True
+    use_embedded_content = True
+    
+    feeds          = [(u'Dział zagraniczny', u'http://feeds.feedburner.com/dyndns/UOfz')]

recipes/equipped.recipe

@@ -0,0 +1,28 @@
+#!/usr/bin/env  python
+
+__license__ = 'GPL v3'
+__author__ = 'teepel <teepel44@gmail.com>, Artur Stachecki <artur.stachecki@gmail.com>'
+
+'''
+equipped.pl
+'''
+
+class equipped(AutomaticNewsRecipe):
+    title          = u'Equipped'
+    __author__ = 'teepel <teepel44@gmail.com>'
+    language       = 'pl'
+    description = u'Wiadomości z equipped.pl'
+    INDEX = 'http://equipped.pl'
+    extra_css = '.alignleft {float:left; margin-right:5px;}'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    remove_empty_feeds = True
+    simultaneous_downloads = 5
+    remove_javascript = True
+    no_stylesheets = True
+    use_embedded_content = False
+    #keep_only_tags = [dict(name='article')]
+    #remove_tags = [dict(id='disqus_thread')]
+    #remove_tags_after = [dict(id='disqus_thread')]
+
+    feeds          = [(u'Equipped', u'http://feeds.feedburner.com/Equippedpl?format=xml')]

recipes/ittechblog.recipe

@@ -0,0 +1,27 @@
+__license__ = 'GPL v3'
+__copyright__ = 'MrStefan'
+
+'''
+www.ittechblog.pl
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
+class ittechblog(BasicNewsRecipe):
+    title = u'IT techblog'
+    __author__ = 'MrStefan <mrstefaan@gmail.com>'
+    language = 'pl'
+    description =u'Na naszym blogu technologicznym znajdziesz między innymi: testy sprzętu, najnowsze startupy, technologiczne nowinki, felietony tematyczne.'
+    extra_css = '.cover > img {display:block;}'
+    remove_empty_feeds = True
+    oldest_article = 7
+    max_articles_per_feed = 100
+    remove_javascript = True
+    no_stylesheets = True
+    use_embedded_content = False
+
+    keep_only_tags =[dict(attrs={'class':'box'})]
+    remove_tags =[dict(name='aside'), dict(attrs={'class':['tags', 'counter', 'twitter-share-button']})]
+
+    feeds          = [(u'Artykuły', u'http://feeds.feedburner.com/ITTechBlog?format=xml')]

recipes/magazyn_consido.recipe

@@ -0,0 +1,88 @@
+#!/usr/bin/env python
+
+__license__ = 'GPL v3'
+
+'''
+magazynconsido.pl/
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.utils.magick import Image
+
+class magazynconsido(BasicNewsRecipe):
+    title = u'Magazyn Consido'
+    __author__ = 'Artur Stachecki <artur.stachecki@gmail.com> ,teepel <teepel44@gmail.com>'
+    language = 'pl'
+    description =u'Portal dla architektów i projektantów'
+    masthead_url='http://qualitypixels.pl/wp-content/themes/airlock/advance/inc/timthumb.php?src=http://qualitypixels.pl/wp-content/uploads/2012/01/logotyp-magazynconsido-11.png&w=455&zc=1'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    remove_javascript=True
+    no_stylesheets = True
+    use_embedded_content = False
+
+    keep_only_tags =[]
+    keep_only_tags.append(dict(name = 'h1'))
+    keep_only_tags.append(dict(name = 'p'))
+    keep_only_tags.append(dict(attrs = {'class' : 'navigation'}))
+    remove_tags =[dict(attrs = {'style' : 'font-size: x-small;' })]
+
+    remove_tags_after =[dict(attrs = {'class' : 'navigation' })]
+
+    extra_css='''       img {max-width:30%; max-height:30%; display: block; margin-left: auto; margin-right: auto;}
+                        h1 {text-align: center;}'''
+
+    def parse_index(self): #(kk)
+        soup = self.index_to_soup('http://feeds.feedburner.com/magazynconsido?format=xml')
+        feeds = []
+        articles = {}
+        sections = []
+        section = ''
+
+        for item in soup.findAll('item') :
+            section = self.tag_to_string(item.category)
+            if not articles.has_key(section) :
+                sections.append(section)
+                articles[section] = []
+            article_url = self.tag_to_string(item.guid)
+            article_title = self.tag_to_string(item.title)
+            article_date = self.tag_to_string(item.pubDate)
+            article_description = self.tag_to_string(item.description)
+            articles[section].append( { 'title' : article_title,  'url' : article_url, 'date' : article_date, 'description' : article_description })
+
+        for section in sections :
+            if section == 'Video':
+                feeds.append((section, articles[section]))
+                feeds.pop()
+            else:
+                feeds.append((section, articles[section]))
+        return feeds
+
+    def append_page(self, soup, appendtag):
+        apage = soup.find('div', attrs={'class':'wp-pagenavi'})
+        if apage is not None:
+            nexturl = soup.find('a', attrs={'class':'nextpostslink'})
+            soup2 = self.index_to_soup(nexturl['href'])
+            pagetext = soup2.findAll('p')
+            for tag in pagetext:
+                pos = len(appendtag.contents)
+                appendtag.insert(pos, tag)
+
+        while appendtag.find('div', attrs={'class': ['height: 35px;', 'post-meta', 'addthis_toolbox addthis_default_style addthis_', 'post-meta-bottom', 'block_recently_post', 'fbcomments', 'pin-it-button', 'pages', 'navigation']}) is not None:
+            appendtag.find('div', attrs={'class': ['height: 35px;', 'post-meta', 'addthis_toolbox addthis_default_style addthis_', 'post-meta-bottom', 'block_recently_post', 'fbcomments', 'pin-it-button', 'pages', 'navigation']}).replaceWith('')
+
+    def preprocess_html(self, soup): #(kk)
+        self.append_page(soup, soup.body)
+        return self.adeify_images(soup)
+
+    def postprocess_html(self, soup, first):
+        #process all the images
+        for tag in soup.findAll(lambda tag: tag.name.lower()=='img' and tag.has_key('src')):
+            iurl = tag['src']
+            img = Image()
+            img.open(iurl)
+            if img < 0:
+                raise RuntimeError('Out of memory')
+            img.type = "GrayscaleType"
+            img.save(iurl)
+        return soup

recipes/media2.recipe

@@ -0,0 +1,37 @@
+#!/usr/bin/env python
+
+__license__ = 'GPL v3'
+__copyright__ = 'teepel'
+
+'''
+media2.pl
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
+class media2_pl(BasicNewsRecipe):
+    title = u'Media2'
+    __author__ = 'teepel <teepel44@gmail.com>'
+    language = 'pl'
+    description =u'Media2.pl to jeden z najczęściej odwiedzanych serwisów dla profesjonalistów z branży medialnej, telekomunikacyjnej, public relations oraz nowych technologii.'
+    masthead_url='http://media2.pl/res/logo/www.png'
+    remove_empty_feeds= True
+    oldest_article = 1
+    max_articles_per_feed = 100
+    remove_javascript=True
+    no_stylesheets=True
+    simultaneous_downloads = 5
+
+    extra_css = '''.news-lead{font-weight: bold; }'''
+
+    keep_only_tags =[]
+    keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'news-item tpl-big'}))
+
+    remove_tags =[]
+    remove_tags.append(dict(name = 'span', attrs = {'class' : 'news-comments'}))
+    remove_tags.append(dict(name = 'div', attrs = {'class' : 'item-sidebar'}))
+    remove_tags.append(dict(name = 'div', attrs = {'class' : 'news-tags'}))
+
+
+    feeds          = [(u'Media2', u'http://feeds.feedburner.com/media2')]

recipes/mobilna.recipe

@@ -0,0 +1,27 @@
+#!/usr/bin/env python
+
+__license__ = 'GPL v3'
+__copyright__ = 'MrStefan'
+
+'''
+www.mobilna.pl
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
+class mobilna(BasicNewsRecipe):
+    title = u'Mobilna.pl'
+    __author__ = 'MrStefan <mrstefaan@gmail.com>'
+    language = 'pl'
+    description =u'twoja mobilna strona'
+    #masthead_url=''
+    remove_empty_feeds= True
+    oldest_article = 7
+    max_articles_per_feed = 100
+    remove_javascript=True
+    no_stylesheets=True
+    use_embedded_content = True
+    #keep_only_tags =[dict(attrs={'class':'Post'})]
+
+    feeds          = [(u'Artykuły', u'http://mobilna.pl/feed/')]

recipes/mojegotowanie.recipe

@@ -0,0 +1,51 @@
+#!usr/bin/env python
+
+__license__ = 'GPL v3'
+__copyright__ = 'MrStefan, teepel'
+
+'''
+www.mojegotowanie.pl
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
+class mojegotowanie(BasicNewsRecipe):
+    title = u'Moje Gotowanie'
+    __author__ = 'MrStefan <mrstefaan@gmail.com>, teepel <teepel44@gmail.com>'
+    language = 'pl'
+    description =u'Gotowanie to Twoja pasja? Uwielbiasz sałatki? Lubisz grillować? Przepisy kulinarne doskonałe na wszystkie okazje znajdziesz na www.mojegotowanie.pl.'
+    masthead_url='http://www.mojegotowanie.pl/extension/selfstart/design/self/images/top_c2.gif'
+    cover_url = 'http://www.mojegotowanie.pl/extension/selfstart/design/self/images/mgpl/mojegotowanie.gif'
+    remove_empty_feeds= True
+    oldest_article = 7
+    max_articles_per_feed = 100
+    remove_javascript=True
+    no_stylesheets=True
+
+    keep_only_tags =[]
+    keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'content'}))
+
+    feeds = [(u'Artykuły', u'http://mojegotowanie.pl/rss/feed/artykuly'),
+                 (u'Przepisy', u'http://mojegotowanie.pl/rss/feed/przepisy')]
+
+    def parse_feeds(self):
+        feeds = BasicNewsRecipe.parse_feeds(self)
+        for feed in feeds:
+            for article in feed.articles[:]:
+                if 'film' in article.title:
+                    feed.articles.remove(article)
+        return feeds
+
+    def get_article_url(self, article):
+        link = article.get('link')
+        if 'Clayout0Cset0Cprint0' in link:
+            return link
+
+    def print_version(self, url):
+        segment = url.split('/')
+        URLPart = segment[-2]
+        URLPart = URLPart.replace('0L0Smojegotowanie0Bpl0Clayout0Cset0Cprint0C', '/')
+        URLPart = URLPart.replace('0I', '_')
+        URLPart = URLPart.replace('0C', '/')
+        return 'http://www.mojegotowanie.pl/layout/set/print' + URLPart

recipes/najwyzszy_czas.recipe

@@ -0,0 +1,28 @@
+#!/usr/bin/env  python
+
+__license__ = 'GPL v3'
+__author__ = 'teepel <teepel44@gmail.com>'
+
+'''
+nczas.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
+class nczas(BasicNewsRecipe):
+    title          = u'Najwy\u017cszy Czas'
+    __author__ = 'teepel <teepel44@gmail.com>'
+    language       = 'pl'
+    description ='Wiadomości z nczas.com'
+    INDEX='http://nczas.com'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    use_embedded_content = True
+    remove_empty_feeds= True
+    simultaneous_downloads = 5
+    remove_javascript=True
+    remove_attributes = ['style']
+    no_stylesheets=True
+
+    feeds          = [(u'Najwyższy Czas', u'http://nczas.com/feed/')]

recipes/nowiny_rybnik.recipe

@@ -0,0 +1,33 @@
+#!/usr/bin/env  python
+
+__license__ = 'GPL v3'
+
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
+
+class NowinyRybnik(BasicNewsRecipe):
+    title = u'Nowiny - Rybnik'
+    __author__ = 'Artur Stachecki <artur.stachecki@gmail.com>'
+    language = 'pl'
+    description = u'Tygodnik Regionalny NOWINY. Ogłoszenia drobne, wiadomości i wydarzenia z regionu Rybnika i okolic'
+    oldest_article = 7
+    masthead_url = 'http://www.nowiny.rybnik.pl/logo/logo.jpg'
+    max_articles_per_feed = 100
+    simultaneous_downloads = 5
+    remove_javascript = True
+    no_stylesheets = True
+
+    keep_only_tags = [(dict(name='div', attrs={'id': 'drukuj'}))]
+
+    remove_tags = []
+    remove_tags.append(dict(name='div', attrs={'id': 'footer'}))
+
+    feeds = [(u'Wszystkie artykuły', u'http://www.nowiny.rybnik.pl/rss,artykuly,dzial,0,miasto,0,ile,25.xml')]
+
+    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/osw.recipe

@@ -0,0 +1,42 @@
+#!/usr/bin/env  python
+
+__license__ = 'GPL v3'
+__author__ = 'teepel <teepel44@gmail.com>'
+
+'''
+http://www.osw.waw.pl - Osrodek studiow wschodnich
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
+class OSW_Recipe(BasicNewsRecipe):
+
+    language = 'pl'
+    title          = u'Ośrodek Studiów Wschodnich'
+    __author__ = 'teepel <teepel44@gmail.com>'
+    INDEX='http://www.osw.waw.pl'
+    description = u'Ośrodek Studiów Wschodnich im. Marka Karpia. Centre for Eastern Studies.'
+    category = u'News'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    cover_url=''
+    remove_empty_feeds= True
+    no_stylesheets=True
+    remove_javascript = True
+    simultaneous_downloads = 5
+
+    keep_only_tags =[]
+    #this line should show title of the article, but it doesnt work
+    keep_only_tags.append(dict(name = 'h1', attrs = {'class' : 'print-title'}))
+    keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'print-submitted'}))
+    keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'print-content'}))
+
+    remove_tags =[]
+    remove_tags.append(dict(name = 'table', attrs = {'id' : 'attachments'}))
+    remove_tags.append(dict(name = 'div', attrs = {'class' : 'print-submitted'}))
+
+    feeds          = [(u'OSW', u'http://www.osw.waw.pl/pl/rss.xml')]
+
+    def print_version(self, url):
+        return url.replace('http://www.osw.waw.pl/pl/', 'http://www.osw.waw.pl/pl/print/')

recipes/ppe_pl.recipe

@@ -0,0 +1,41 @@
+import re
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class ppeRecipe(BasicNewsRecipe):
+    __license__ = 'GPL v3'
+    __author__ = u'Artur Stachecki <artur.stachecki@gmail.com>'
+    language = 'pl'
+    version = 1
+
+    title = u'ppe.pl'
+    category = u'News'
+    description = u'Portal o konsolach i grach wideo.'
+    cover_url=''
+    remove_empty_feeds= True
+    no_stylesheets=True
+    oldest_article = 1
+    max_articles_per_feed = 100000
+    recursions = 0
+    no_stylesheets = True
+    remove_javascript = True
+    simultaneous_downloads = 2
+
+    keep_only_tags =[]
+    keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'news-heading'}))
+    keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'tresc-poziom'}))
+
+    remove_tags =[]
+    remove_tags.append(dict(name = 'div', attrs = {'class' : 'bateria1'}))
+    remove_tags.append(dict(name = 'div', attrs = {'class' : 'bateria2'}))
+    remove_tags.append(dict(name = 'div', attrs = {'class' : 'bateria3'}))
+    remove_tags.append(dict(name = 'div', attrs = {'class' : 'news-photo'}))
+    remove_tags.append(dict(name = 'div', attrs = {'class' : 'fbl'}))
+    remove_tags.append(dict(name = 'div', attrs = {'class' : 'info'}))
+    remove_tags.append(dict(name = 'div', attrs = {'class' : 'links'}))
+
+    remove_tags.append(dict(name = 'div', attrs = {'style' : 'padding: 4px'}))
+
+    feeds          = [
+                            ('Newsy', 'feed://ppe.pl/rss/rss.xml'),
+                           ]

recipes/presseurop.recipe

@@ -0,0 +1,32 @@
+#!/usr/bin/env  python
+
+'''
+www.presseurop.eu/pl
+'''
+
+__license__ = 'GPL v3'
+__author__ = 'teepel <teepel44@gmail.com>'
+
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
+class presseurop(BasicNewsRecipe):
+    title          = u'Presseurop'
+    description = u'Najlepsze artykuły z prasy europejskiej'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    auto_cleanup = True
+
+    feeds          = [
+        (u'Polityka', u'http://www.presseurop.eu/pl/taxonomy/term/1/%2A/feed'),
+        (u'Społeczeństwo', u'http://www.presseurop.eu/pl/taxonomy/term/2/%2A/feed'),
+        (u'Gospodarka', u'http://www.presseurop.eu/pl/taxonomy/term/3/%2A/feed'),
+        (u'Kultura i debaty', u'http://www.presseurop.eu/pl/taxonomy/term/4/%2A/feed'),
+        (u'UE i Świat', u'http://www.presseurop.eu/pl/taxonomy/term/5/%2A/feed')
+        ]
+
+
+    preprocess_regexps = [
+                    (re.compile(r'\|.*</title>', re.DOTALL|re.IGNORECASE),
+    lambda match: '</title>'),
+]

recipes/res_publica.recipe

@@ -0,0 +1,34 @@
+import re
+
+from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.utils.magick import Image
+
+class ResPublicaNowaRecipe(BasicNewsRecipe):
+    __license__ = 'GPL v3'
+    __author__ = u'intromatyk <intromatyk@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/wolne_media.recipe

@@ -0,0 +1,27 @@
+#!/usr/bin/env  python
+
+__license__ = 'GPL v3'
+__author__ = 'teepel <teepel44@gmail.com>'
+
+'''
+wolnemedia.net
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
+class wolne_media(AutomaticNewsRecipe):
+    title          = u'Wolne Media'
+    __author__ = 'teepel <teepel44@gmail.com>'
+    language       = 'pl'
+    description ='Wiadomości z wolnemedia.net'
+    INDEX='http://wolnemedia.net'
+    oldest_article = 1
+    max_articles_per_feed = 100
+    remove_empty_feeds= True
+    simultaneous_downloads = 5
+    remove_javascript=True
+    no_stylesheets=True
+    auto_cleanup = True
+
+    feeds          = [(u'Wiadomości z kraju', u'http://wolnemedia.net/category/wiadomosci-z-kraju/feed/'),(u'Wiadomości ze świata', u'http://wolnemedia.net/category/wiadomosci-ze-swiata/feed/'),(u'Edukacja', u'http://wolnemedia.net/category/edukacja/feed/'),(u'Ekologia', u'http://wolnemedia.net/category/ekologia/feed/'),(u'Gospodarka', u'http://wolnemedia.net/category/gospodarka/feed/'),(u'Historia', u'http://wolnemedia.net/category/historia/feed/'),(u'Kultura', u'http://wolnemedia.net/category/kultura/feed/'),(u'Kulturoznawstwo', u'http://wolnemedia.net/category/kulturoznawstwo/feed/'),(u'Media', u'http://wolnemedia.net/category/media/feed/'),(u'Nauka', u'http://wolnemedia.net/category/nauka/feed/'),(u'Opowiadania', u'http://wolnemedia.net/category/opowiadania/feed/'),(u'Paranauka i ezoteryka', u'http://wolnemedia.net/category/ezoteryka/feed/'),(u'Polityka', u'http://wolnemedia.net/category/polityka/feed/'),(u'Prawo', u'http://wolnemedia.net/category/prawo/feed/'),(u'Publicystyka', u'http://wolnemedia.net/category/publicystyka/feed/'),(u'Reportaż', u'http://wolnemedia.net/category/reportaz/feed/'),(u'Seks', u'http://wolnemedia.net/category/seks/feed/'),(u'Społeczeństwo', u'http://wolnemedia.net/category/spoleczenstwo/feed/'),(u'Świat komputerów', u'http://wolnemedia.net/category/swiat-komputerow/feed/'),(u'Wierzenia', u'http://wolnemedia.net/category/wierzenia/feed/'),(u'Zdrowie', u'http://wolnemedia.net/category/zdrowie/feed/')]