'),
+ (r'http://di.com.pl/pic/photo/mini/', lambda match: 'http://di.com.pl/pic/photo/oryginal/'),
+ (r'\s*'
'''
http://www.dilbert.com
'''
+import re
from calibre.web.feeds.recipes import BasicNewsRecipe
@@ -28,6 +29,12 @@ class DosisDiarias(BasicNewsRecipe):
feeds = [(u'Dilbert', u'http://feeds.dilbert.com/DilbertDailyStrip' )]
+ preprocess_regexps = [
+ (re.compile('strip\..*\.gif', re.DOTALL|re.IGNORECASE),
+ lambda match: 'strip.zoom.gif')
+ ]
+
+
def get_article_url(self, article):
return article.get('feedburner_origlink', None)
diff --git a/resources/recipes/eclicto.recipe b/resources/recipes/eclicto.recipe
new file mode 100644
index 0000000000..a1c625b21c
--- /dev/null
+++ b/resources/recipes/eclicto.recipe
@@ -0,0 +1,49 @@
+#!/usr/bin/env python
+
+__license__ = 'GPL v3'
+__author__ = 'Mori'
+__version__ = 'v. 0.1'
+'''
+blog.eclicto.pl
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
+class BlogeClictoRecipe(BasicNewsRecipe):
+ __author__ = 'Mori'
+ language = 'pl'
+
+ title = u'Blog eClicto'
+ publisher = u'Blog eClicto'
+ description = u'Blog o e-papierze i e-bookach'
+
+ max_articles_per_feed = 100
+ cover_url = 'http://blog.eclicto.pl/wordpress/wp-content/themes/blog_eclicto/g/logo.gif'
+
+ no_stylesheets = True
+ remove_javascript = True
+ encoding = 'utf-8'
+
+ extra_css = '''
+ img{float: left; padding-right: 10px; padding-bottom: 5px;}
+ '''
+
+ feeds = [
+ (u'Blog eClicto', u'http://blog.eclicto.pl/feed/')
+ ]
+
+ remove_tags = [
+ dict(name = 'span', attrs = {'id' : 'tags'})
+ ]
+
+ remove_tags_after = [
+ dict(name = 'div', attrs = {'class' : 'post'})
+ ]
+
+ preprocess_regexps = [
+ (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
+ [
+ (r'\s*'
+'''
+eksiazki.org
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class eksiazki(BasicNewsRecipe):
+
+ title = u'eKsiazki.org'
+ desciption = u'Twoje centrum wiedzy o ePapierze i eBookach'
+ language = 'pl'
+ __author__ = u'Tomasz D\u0142ugosz'
+ no_stylesheets = True
+ remove_javascript = True
+
+ feeds = [(u'eKsiazki.org', u'http://www.eksiazki.org/feed/')]
+
+ keep_only_tags = [dict(name='div', attrs={'id':'content-body'})]
+ remove_tags = [
+ dict(name='span', attrs={'class':'nr_comm'}),
+ dict(name='div', attrs={'id':'tabsContainer'}),
+ dict(name='div', attrs={'class':'next_previous_links'})]
diff --git a/resources/recipes/houston_chronicle.recipe b/resources/recipes/houston_chronicle.recipe
index 77e35dfc0c..3ec1abbf0f 100644
--- a/resources/recipes/houston_chronicle.recipe
+++ b/resources/recipes/houston_chronicle.recipe
@@ -1,17 +1,41 @@
+#!/usr/bin/env python
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from calibre.web.feeds.news import BasicNewsRecipe
class HoustonChronicle(BasicNewsRecipe):
title = u'The Houston Chronicle'
description = 'News from Houston, Texas'
- __author__ = 'Kovid Goyal'
+ __author__ = 'Kovid Goyal and Sujata Raman'
language = 'en'
timefmt = ' [%a, %d %b, %Y]'
no_stylesheets = True
- keep_only_tags = [dict(id=['story-head', 'story'])]
- remove_tags = [dict(id=['share-module', 'resource-box',
- 'resource-box-header'])]
+ keep_only_tags = [
+ dict(id=['story-head', 'story'])
+ ]
+
+ remove_tags = [
+ dict(id=['share-module', 'resource-box',
+ 'resource-box-header'])
+ ]
+
+ extra_css = '''
+ h1{font-family :Arial,Helvetica,sans-serif; font-size:large;}
+ h2{font-family :Arial,Helvetica,sans-serif; font-size:medium; color:#666666;}
+ h3{font-family :Arial,Helvetica,sans-serif; font-size:medium; color:#000000;}
+ h4{font-family :Arial,Helvetica,sans-serif; font-size: x-small;}
+ p{font-family :Arial,Helvetica,sans-serif; font-size:x-small;}
+ #story-head h1{font-family :Arial,Helvetica,sans-serif; font-size: xx-large;}
+ #story-head h2{font-family :Arial,Helvetica,sans-serif; font-size: small; color:#000000;}
+ #story-head h3{font-family :Arial,Helvetica,sans-serif; font-size: xx-small;}
+ #story-head h4{font-family :Arial,Helvetica,sans-serif; font-size: xx-small;}
+ #story{font-family :Arial,Helvetica,sans-serif; font-size:xx-small;}
+ #Text-TextSubhed BoldCond PoynterAgateZero h3{color:#444444;font-family :Arial,Helvetica,sans-serif; font-size:small;}
+ .p260x p{font-family :Arial,Helvetica,serif; font-size:x-small;font-style:italic;}
+ .p260x h6{color:#777777;font-family :Arial,Helvetica,sans-serif; font-size:xx-small;}
+ '''
+
def parse_index(self):
soup = self.index_to_soup('http://www.chron.com/news/')
@@ -64,3 +88,6 @@ class HoustonChronicle(BasicNewsRecipe):
feeds.append((current_section, current_articles))
return feeds
+
+
+
diff --git a/resources/recipes/interia_fakty.recipe b/resources/recipes/interia_fakty.recipe
new file mode 100644
index 0000000000..cdd245fdd7
--- /dev/null
+++ b/resources/recipes/interia_fakty.recipe
@@ -0,0 +1,38 @@
+#!/usr/bin/env python
+
+__license__ = 'GPL v3'
+__copyright__ = u'2010, Tomasz Dlugosz
'
+'''
+fakty.interia.pl
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class InteriaFakty(BasicNewsRecipe):
+ title = u'Interia.pl - Fakty'
+ language = 'pl'
+ oldest_article = 7
+ __author__ = u'Tomasz D\u0142ugosz'
+ simultaneous_downloads = 2
+ no_stylesheets = True
+ remove_javascript = True
+ max_articles_per_feed = 100
+
+ feeds = [(u'Kraj', u'http://kanaly.rss.interia.pl/kraj.xml'),
+ (u'\u015awiat', u'http://kanaly.rss.interia.pl/swiat.xml'),
+ (u'Wiadomo\u015bci dnia', u'http://kanaly.rss.interia.pl/fakty.xml'),
+ (u'Przegl\u0105d prasy', u'http://kanaly.rss.interia.pl/przeglad_prasy.xml'),
+ (u'Wywiady', u'http://kanaly.rss.interia.pl/wywiady.xml'),
+ (u'Ciekawostki', u'http://kanaly.rss.interia.pl/ciekawostki.xml')]
+
+ keep_only_tags = [dict(name='div', attrs={'id':'article'})]
+
+ remove_tags = [
+ dict(name='div', attrs={'class':'box fontSizeSwitch'}),
+ dict(name='div', attrs={'class':'clear'}),
+ dict(name='div', attrs={'class':'embed embedLeft articleEmbedArticleList articleEmbedArticleListTitle'}),
+ dict(name='span', attrs={'class':'keywords'})]
+
+ extra_css = '''
+ h2 { font-size: 1.2em; }
+ '''
diff --git a/resources/recipes/interia_sport.recipe b/resources/recipes/interia_sport.recipe
new file mode 100644
index 0000000000..9c72ee28a7
--- /dev/null
+++ b/resources/recipes/interia_sport.recipe
@@ -0,0 +1,71 @@
+#!/usr/bin/env python
+
+__license__ = 'GPL v3'
+__copyright__ = u'2010, Tomasz Dlugosz '
+'''
+sport.interia.pl
+'''
+
+import re
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class InteriaSport(BasicNewsRecipe):
+ title = u'Interia.pl - Sport'
+ language = 'pl'
+ oldest_article = 7
+ __author__ = u'Tomasz D\u0142ugosz'
+ simultaneous_downloads = 3
+ no_stylesheets = True
+ remove_javascript = True
+ max_articles_per_feed = 100
+
+ feeds = [(u'Wydarzenia sportowe', u'http://kanaly.rss.interia.pl/sport.xml'),
+ (u'Pi\u0142ka no\u017cna', u'http://kanaly.rss.interia.pl/pilka_nozna.xml'),
+ (u'Siatk\xf3wka', u'http://kanaly.rss.interia.pl/siatkowka.xml'),
+ (u'Koszyk\xf3wka', u'http://kanaly.rss.interia.pl/koszykowka.xml'),
+ (u'NBA', u'http://kanaly.rss.interia.pl/nba.xml'),
+ (u'Kolarstwo', u'http://kanaly.rss.interia.pl/kolarstwo.xml'),
+ (u'\u017bu\u017cel', u'http://kanaly.rss.interia.pl/zuzel.xml'),
+ (u'Tenis', u'http://kanaly.rss.interia.pl/tenis.xml')]
+
+ keep_only_tags = [dict(name='div', attrs={'id':'article'})]
+
+ remove_tags = [dict(name='div', attrs={'class':'object gallery'})]
+
+ extra_css = '''
+ .articleDate {
+ font-size: 0.5em;
+ color: black;
+ }
+
+ .articleFoto {
+ display: block;
+ font-family: sans;
+ font-size: 0.5em;
+ text-indent: 0
+ color: black;
+ }
+
+ .articleText {
+ display: block;
+ margin-bottom: 1em;
+ margin-left: 0;
+ margin-right: 0;
+ margin-top: 1em
+ color: black;
+ }
+
+ .articleLead {
+ font-size: 1.2em;
+ }
+ '''
+
+ preprocess_regexps = [
+ (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
+ [
+ (r'
', lambda match: ''),
+ # FIXME
+ #(r'()(.*?)(
)(.*?)()', lambda match: '\1\2\4'),
+ (r'
()?(ZOBACZ|CZYTAJ) T.*?