diff --git a/recipes/common_dreams.recipe b/recipes/common_dreams.recipe index 5443b5890b..62edfe8684 100644 --- a/recipes/common_dreams.recipe +++ b/recipes/common_dreams.recipe @@ -1,38 +1,89 @@ +#!/usr/bin/env python +## +## Title: Common Dreams +## +## License: GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html +# Feb 2012: Cleaned up the output to have only the main article + +__license__ = 'GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html' +''' +commondreams.org +''' + +import re from calibre.web.feeds.news import BasicNewsRecipe class CommonDreams(BasicNewsRecipe): # Identify the recipe title = u'Common Dreams' - description = u'Progressive news and views' + description = u'Breaking News & Views for the Progressive Community.' + cover_url = 'https://s3.amazonaws.com/s3.commondreams.org/images/common-dreams.png' __author__ = u'XanthanGum' language = 'en' - # Format the text - - extra_css = ''' - body{font-family:verdana,arial,helvetica,geneva,sans-serif ;} - h1{font-size: xx-large;} - h2{font-size: large;} - ''' - - # Pick no article older than seven days and limit the number of articles per feed to 100 - oldest_article = 7 max_articles_per_feed = 100 - # Remove everything before the article + no_stylesheets = True + remove_javascript = True + + # Flattens all the tables to make it compatible with Nook + conversion_options = {'linearize_tables' : True} - remove_tags_before = dict(name = 'div', attrs = {'id':'node-header'}) + remove_attributes = [ 'border', 'cellspacing', 'align', 'cellpadding', 'colspan', + 'valign', 'vspace', 'hspace', 'alt', 'width', 'height' ] - # Remove everything after the article + # Specify extra CSS - overrides ALL other CSS (IE. Added last). + extra_css = 'body { font-family: verdana, helvetica, sans-serif; } \ + .introduction, .first { font-weight: bold; } \ + .cross-head { font-weight: bold; font-size: 125%; } \ + .cap, .caption { display: block; font-size: 80%; font-style: italic; } \ + .cap, .caption, .caption img, .caption span { display: block; margin: 5px auto; } \ + .byl, .byd, .byline img, .byline-name, .byline-title, .author-name, .author-position, \ + .correspondent-portrait img, .byline-lead-in, .name, .bbc-role { display: block; \ + font-size: 80%; font-style: italic; margin: 1px auto; } \ + .story-date, .published { font-size: 80%; } \ + table { width: 100%; } \ + td img { display: block; margin: 5px auto; } \ + ul { padding-top: 10px; } \ + ol { padding-top: 10px; } \ + li { padding-top: 5px; padding-bottom: 5px; } \ + h1 { font-size: 175%; font-weight: bold; } \ + h2 { font-size: 150%; font-weight: bold; } \ + h3 { font-size: 125%; font-weight: bold; } \ + h4, h5, h6 { font-size: 100%; font-weight: bold; }' + + # Remove the line breaks and float left/right and picture width/height. + preprocess_regexps = [(re.compile(r'', re.IGNORECASE), lambda m: ''), + (re.compile(r'', re.IGNORECASE), lambda m: ''), + (re.compile(r'float:.*?'), lambda m: ''), + (re.compile(r'width:.*?px'), lambda m: ''), + (re.compile(r'height:.*?px'), lambda m: ''), + (re.compile(r''), lambda m: ''), + (re.compile(r''), lambda m: ''), + ] - remove_tags_after = dict(name = 'div', attrs = {'class':'copyright-info'}) + # Main article is inside this tag + keep_only_tags = [ + dict(name='div', attrs={'id':lambda x: x and 'node-' in x}), + ] + + remove_tags = [ + dict(name='div', attrs={'class':'node-links clear-block'}), # remove Share options + ] + + # Identify the news feeds - feeds = [(u'Headlines', u'http://www.commondreams.org/feed/headlines_rss'), - (u'Further News Articles', u'http://www.commondreams.org/feed/further_rss'), - (u'Views', u'http://www.commondreams.org/feed/views_rss'), - (u'Progressive Newswire', u'http://www.commondreams.org/feed/newswire_rss')] + feeds = [(u'Headlines', u'https://www.commondreams.org/feed/headlines_rss'), + (u'Further News Articles', u'https://www.commondreams.org/feed/further_rss'), + (u'Views', u'https://www.commondreams.org/feed/views_rss'), + (u'Progressive Newswire', u'https://www.commondreams.org/feed/newswire_rss')] + + + def print_version(self, url): + url = url + '?print' + return url \ No newline at end of file