First commit

master
pictuga 2013-02-25 15:50:32 +01:00
commit 51fe6ce81b
3 changed files with 85 additions and 0 deletions

20
liferea.css 100644
View File

@ -0,0 +1,20 @@
img
{
max-width: 80%;
height: auto;
}
.bbx_container, /*TT*/
.share-help, /*BBC*/
div.video_container iframe, /*LM*/
.story-info, .story-share.bluelinks, .story-content img:last-child, .pager /*CI*/
{
display: none;
}
h2.txt15_140, /*LM*/
h2.chapo /*FranceInfo*/
{
font-size: 1em;
font-weight: normal;
}

51
morss 100755
View File

@ -0,0 +1,51 @@
#! /usr/bin/env python2.7
import sys
from lxml import etree
import urllib2
if len(sys.argv) < 2:
print "argument please"
sys.exit(1)
debug = (len(sys.argv) == 3)
node = sys.argv[1]
xml = sys.stdin.read()
rss = etree.fromstring(xml)
items = rss.xpath('//item')
#comment below to keep too-long feeds (like BBC)
del items[30:]
for item in items:
title = item.findtext('title')
link = item.findtext('link')
desc = item.xpath('description')[0]
if debug:
print title
print link
try:
data = urllib2.urlopen(link).read()
html = etree.HTML(data)
match = html.xpath(node)
if len(match):
text = etree.tostring(match[0])
if debug:
print text
desc.text = text
else:
if debug:
print "no match"
except urllib2.HTTPError, error:
if debug:
print "error"
if len(sys.argv) == 2:
print etree.tostring(rss)

14
rules 100644
View File

@ -0,0 +1,14 @@
LeMonde
//*[contains(@class,'article') or contains(@id,'content')]
TehranTimes
//div[@class='article-indent']
BBC
//h1/..
FranceInfo
//h2[@class='chapo']/..
Courrier International
//div[@class='story-content']