# Configuration file for feed reader.

# Mandatory for all feeds: name [section name], url.
# dir is also mandatory but typically inherited from the defaults.

# page_start and page_end will drop anything before and after those patterns
# (the patterns themselves will be kept). Normal Python re syntax.

# If a URL matching single_page_pat is found in the story page and
# can be loaded, it will be subsituted for the normal story page.

# skip_pat can include multiple patterns -- separate with newlines/indents.

# XXX to fix:
# - font size in linuxplanet
# - included box in word-a-day

[DEFAULT]
# Defaults for all feeds: may be overridden for specific feeds.
dir = ~/feeds/
verbose = True
skip_images = true
levels = 2
ascii = false
logfile = ~/feedme.out
formats = none
save_days = 5

[A Word A Day]
url = http://wordsmith.org/awad/rss1.xml
page_start = <td width="400" valign="top">
page_end = <p class="rightbox">
skip_pat = style=".*?"
  Follow us on.*?</div>

[Slate]
url = http://www.slate.com/rss
page_start = <div id="article_top">
page_end = <div id="comments_button"
single_page_pat = http://www.slate.com/id/[0-9]+/pagenum/all/
# Slate has some really bizarro patterns they put in stories!
# Like <a href="http://online.wsj.com/article_email/SB10001424052748704828104576021481410635432-lMyQjAxMTAwMDEwODExNDgyWj.html" target="_blank" xmlns:tools="XslTools"><span style="color:#000080;">estimated</span></a>
skip_pat = <div id="toolbox".*?</div></div>
  <iframe.*?</iframe>
  <style.*?</style>
  style *= *".*?"
  color: *".*?"
  <div id="tool_cntr">.*?class="recommend_closer">CLOSE</a></div>
  <div class="large_article_photo".*?</div>

[Linux Planet]
url = http://www.linuxplanet.com/rss
#page_start = <!--**** begin content ****-->
page_start = <!--content_start 1-->
page_end = <!--**** end content ****-->
skip_pat = <FONT .*?SIZE=.*?>

[The Register]
url = http://www.theregister.co.uk/headlines.atom
page_start = <div id="article">
page_end = <div id="related-stories">
page_start = <div id="body">

[BBC News Science]
url = http://newsrss.bbc.co.uk/rss/newsonline_world_edition/science/nature/rss.xml
page_start = <a name="startcontent">
  <span class="story-date"> 
  <div class="emp-decription" id="meta-information">
  <h1 class="story-header">
  <p class="introduction"
  <h1 class="story-header">
page_end = <div class="share-body-bottom">
  </div><!-- / story-body -->
  <h3>Bookmark with:</h3>
skip_pat = <h2 class="quote">.*?End Quote</span>
  <div id="page-bookmark-links-head".*?</script>
  <div class="story-feature narrow">.*?</div> *<p id="story_continues_1">

#[World News Australia]
#url = http://www.sbs.com.au/news/rss/Section/Top%20Stories
#page_start = <div class="teaser row">
#page_end = <div class="links_comments

#[BBC World News]
#url = http://newsrss.bbc.co.uk/rss/newsonline_world_edition/front_page/rss.xml
#page_start = <h1 class="story-header">
#page_end = <!-- / story-body -->
#skip_pat = <a class="hidden".*?</a>
##skip_pat = <div class="article-nav".*?</div>
##encoding = iso8859-15
#verbose = True

[Knight Science]
url = http://ksjtracker.mit.edu/feed/
page_start = <div class="post"
page_end = <div id="sidebar">
skip_pat = <cite>.*?</cite>

[Grammar Girl]
url = http://grammar.quickanddirtytips.com/PodcastsRSS.ashx?podcast=grammar
page_start = <div class="article-text">
page_end = <!-- end .article-text -->

[Nutrition Diva]
url = http://nutritiondiva.quickanddirtytips.com/PodcastsRSS.ashx?podcast=nutritiondiva
page_start = <div class="article-text">
page_end = <!-- end .article-text -->

[House Call Doc]
url = http://housecalldoctor.quickanddirtytips.com/PodcastsRSS.ashx?podcast=housecalldoctor
page_start = <div class="article-text">
page_end = <!-- end .article-text -->

[Math Dude]
url = http://www.quickanddirtytips.com/xml/mathdude.xml
page_start = <div class="article-text">
page_end = <!-- end .article-text -->

[Slashdot]
url = http://rss.slashdot.org/Slashdot/slashdot
levels = 2
page_start = <div id="text-
page_end = <div class="article-foot

[World Wide Words]
url = http://www.worldwidewords.org/rss/newsletter.xml
#levels = 1

[Jon Carroll]
url = http://feeds.sfgate.com/sfgate/rss/feeds/jcarroll
page_start = <div id="bodytext_bottom"
#page_start = <div id="articlecontent">
page_end = </div><!--/articlecontent -->

[Merc local news]
url = http://feeds.mercurynews.com/mngi/rss/CustomRssServlet/568/200748.xml
page_start = <div id="articleBody"
page_end = <div class="articleOptions">
skip_pat = <div id="photoviewer".*?</div></div>
  <div id="caption".*?</div>
  <span class="articleEmbeddedViewerBox">.*?<span fd-type="start" fd-id="default"></span>

[LA Times World]
url = http://www.latimes.com/news/nationworld/world/rss2.0.xml
page_start = <div id="story-body-text">
page_end = <div class="google-ad-story-bottom">

[David Lazarus]
url = http://feeds.latimes.com/ConsumerConfidential
page_start = <div id="story-body">
page_end = <div class="sphereTools">
single_page_pat = http://www.latimes.com/.*full.column

[Wired Science]
url = http://www.wired.com/wiredscience/feed/
page_start = <div class="entry">
page_end = <div class="entryExtra">

[NASW]
url = http://www.nasw.org/articles.xml
page_start = <div class="content-body">
page_end = <div class="links">

[Xtra]
url = ~/feeds/xtraurls.rss
nocache = true

#[Ubuntu Weekly News]
#url = http://feeds2.feedburner.com/ubuntu-news
#levels = 2

[Five chapters]
url = http://www.fivechapters.com/feed/atom/
page_start = <div id="content"
page_end = <div id="sidebar"