Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

Improved recipe for Dilbert

Browse Source
This commit is contained in:
Kovid Goyal 2010-12-12 12:24:26 -07:00
parent 524e9f4def
commit e56e2c7f45
1 changed files with 16 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
resources/recipes/dilbert.recipe
View File

@ -3,15 +3,16 @@ __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
''' '''
http://www.dilbert.com http://www.dilbert.com
''' '''
import re
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
import re
class DosisDiarias(BasicNewsRecipe): class DilbertBig(BasicNewsRecipe):
title = 'Dilbert' title = 'Dilbert'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic and Starson17'
description = 'Dilbert' description = 'Dilbert'
oldest_article = 5 reverse_article_order = True
oldest_article = 15
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = True use_embedded_content = True
@ -29,20 +30,23 @@ class DosisDiarias(BasicNewsRecipe):
feeds = [(u'Dilbert', u'http://feeds.dilbert.com/DilbertDailyStrip' )] 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): def get_article_url(self, article):
return article.get('feedburner_origlink', None) return article.get('feedburner_origlink', None)
preprocess_regexps = [
(re.compile('strip\..*\.gif', re.DOTALL|re.IGNORECASE), lambda match: 'strip.zoom.gif')
]
def preprocess_html(self, soup): def preprocess_html(self, soup):
for tag in soup.findAll(name='a'): for tag in soup.findAll(name='a'):
if tag['href'].find('http://feedads') >= 0: if tag['href'].find('http://feedads') >= 0:
tag.extract() tag.extract()
return soup return soup
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
img {max-width:100%; min-width:100%;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''