calibre/recipes/philly.recipe

86 lines
3.4 KiB
Python

#!/usr/bin/env python
__license__ = 'GPL v3'
'''
philly.com/inquirer/
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
class Philly(BasicNewsRecipe):
title = 'Philadelphia Inquirer'
__author__ = 'RadikalDissent and Sujata Raman'
language = 'en'
description = 'Daily news from the Philadelphia Inquirer'
no_stylesheets = True
use_embedded_content = False
oldest_article = 1
max_articles_per_feed = 25
extra_css = '''
h1{font-family:verdana,arial,helvetica,sans-serif; font-size: large;}
h2{font-family:verdana,arial,helvetica,sans-serif; font-size: small;}
.body-content{font-family:verdana,arial,helvetica,sans-serif; font-size: small;}
.byline {font-size: small; color: #666666; font-style:italic; }
.lastline {font-size: small; color: #666666; font-style:italic;}
.contact {font-size: small; color: #666666;}
.contact p {font-size: small; color: #666666;}
#photoCaption { font-family:verdana,arial,helvetica,sans-serif; font-size:x-small;}
.photoCaption { font-family:verdana,arial,helvetica,sans-serif; font-size:x-small;}
#photoCredit{ font-family:verdana,arial,helvetica,sans-serif; font-size:x-small; color:#666666;}
.photoCredit{ font-family:verdana,arial,helvetica,sans-serif; font-size:x-small; color:#666666;}
.article_timestamp{font-size:x-small; color:#666666;}
a {font-family:verdana,arial,helvetica,sans-serif; font-size: x-small;}
'''
keep_only_tags = [
dict(name='div', attrs={'class':'story-content'}),
dict(name='div', attrs={'id': 'contentinside'})
]
remove_tags = [
dict(name='div', attrs={'class':['linkssubhead','post_balloon','relatedlist','pollquestion','b_sq']}),
dict(name='dl', attrs={'class':'relatedlist'}),
dict(name='div', attrs={'id':['photoNav','sidebar_adholder']}),
dict(name='a', attrs={'class': ['headlineonly','bl']}),
dict(name='img', attrs={'class':'img_noborder'})
]
# def print_version(self, url):
# return url + '?viewAll=y'
feeds = [
('Front Page', 'http://www.philly.com/inquirer_front_page.rss'),
('Business', 'http://www.philly.com/inq_business.rss'),
#('News', 'http://www.philly.com/inquirer/news/index.rss'),
('Nation', 'http://www.philly.com/inq_news_world_us.rss'),
('Local', 'http://www.philly.com/inquirer_local.rss'),
('Health', 'http://www.philly.com/inquirer_health_science.rss'),
('Education', 'http://www.philly.com/inquirer_education.rss'),
('Editorial and opinion', 'http://www.philly.com/inq_news_editorial.rss'),
('Sports', 'http://www.philly.com/inquirer_sports.rss')
]
def get_article_url(self, article):
ans = article.link
try:
self.log('Looking for full story link in', ans)
soup = self.index_to_soup(ans)
x = soup.find(text="View All")
if x is not None:
ans = ans + '?viewAll=y'
self.log('Found full story link', ans)
except:
pass
return ans
def postprocess_html(self, soup,first):
for tag in soup.findAll(name='div',attrs={'class':"container_ate_qandatitle"}):
tag.extract()
for tag in soup.findAll(name='br'):
tag.extract()
return soup