calibre/recipes/consortium_news.recipe
Kovid Goyal 29cd8d64ea
Change shebangs to python from python2
Also remove a few other miscellaneous references to python2
2020-08-22 18:47:51 +05:30

78 lines
3.3 KiB
Python

#!/usr/bin/env python
##
# Title: Consortium News
##
# License: GNU General Public License v3 -
# http://www.gnu.org/copyleft/gpl.html
# Feb 2012: Initial release
__license__ = 'GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html'
'''
consortiumnews.com
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class ConsortiumNews(BasicNewsRecipe):
title = u'Consortium News'
publisher = 'Copyright © 2012 Consortiumnews. All Rights Reserved.'
language = 'en'
__author__ = 'kiavash'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
remove_javascript = True
# Flattens all the tables to make it compatible with Nook
conversion_options = {'linearize_tables': True}
remove_attributes = ['border', 'cellspacing', 'align', 'cellpadding', 'colspan',
'valign', 'vspace', 'hspace', 'alt', 'width', 'height']
# 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'<br[ ]*/>', re.IGNORECASE), lambda m: ''),
(re.compile(r'<br[ ]*clear.*/>',
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'<a.*?>'), lambda h1: ''),
(re.compile(r'</a>'), lambda h2: ''),
]
# Main article is inside this tag
keep_only_tags = [
dict(name='div', attrs={'id': lambda x: x and 'post-' in x})]
remove_tags = [
# remove 'Share this Article'
dict(name='div', attrs={'class': 'sociable'}),
dict(name='p', attrs={'class': 'tags'}), # remove 'Tags: ... '
]
feeds = [(u'Consortium News', u'http://feeds.feedburner.com/Consortiumnewscom')]