Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Improved recipe for The Philadelphia Inquirer

Browse Source
This commit is contained in:
Kovid Goyal 2009-11-14 19:57:09 -07:00
parent 1e6f8d72dd
commit cd242c2458
1 changed files with 51 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

71
resources/recipes/philly.recipe
View File

@ -3,50 +3,55 @@ __license__ = 'GPL v3'
'''
philly.com/inquirer/
'''
import re
from calibre.web.feeds.recipes import BasicNewsRecipe
class Philly(BasicNewsRecipe):
title = 'Philadelphia Inquirer'
__author__ = 'RadikalDissent'
__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 = '''
.byline {font-size: small; color: grey; font-style:italic; }
.lastline {font-size: small; color: grey; font-style:italic;}
.contact {font-size: small; color: grey;}
.contact p {font-size: small; color: grey;}
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;}
'''
preprocess_regexps = [(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
[
(r'<body.*<h1>', lambda match: '<body><h1>'),
(r'<font size="2" face="Arial">', lambda match: '<div class="contact"><font class="contact">'),
(r'<font face="Arial" size="2">', lambda match: '<div class="contact"><font class="contact">')
]
]
keep_only_tags = [
dict(name='h1'),
dict(name='p', attrs={'class':['byline','lastline']}),
dict(name='div', attrs={'class':'body-content'}),
dict(name='div', attrs={'class':'story-content'}),
dict(name='div', attrs={'id': 'contentinside'})
]
remove_tags = [
dict(name='hr'),
dict(name='p', attrs={'class':'buzzBadge'}),
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'
# 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'),
#('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'),
@ -54,3 +59,27 @@ class Philly(BasicNewsRecipe):
('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