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

Fix #5796 (New recipe for Honolulu Star Advertiser)

Browse Source
This commit is contained in:
Kovid Goyal 2010-06-11 12:58:37 -06:00
parent 605dbf0fab
commit 12adf2e0f4
4 changed files with 47 additions and 156 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
resources/images/news/starbulletin.png → resources/images/news/staradvertiser.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 983 B

After

Width:  |  Height:  |  Size: 983 B

96
resources/recipes/honoluluadvertiser.recipe
View File

@ -1,96 +0,0 @@
#!/usr/bin/env python
# -*- coding: cp1252 -*-
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
honoluluadvertiser.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Honoluluadvertiser(BasicNewsRecipe):
title = 'Honolulu Advertiser'
__author__ = 'Darko Miletic and Sujata Raman'
description = "Latest national and local Hawaii sports news from The Honolulu Advertiser."
publisher = 'Honolulu Advertiser'
category = 'news, Honolulu, Hawaii'
oldest_article = 2
language = 'en'
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
remove_javascript = True
cover_url = 'http://www.honoluluadvertiser.com/graphics/frontpage/frontpage.jpg'
html2lrf_options = [
'--comment' , description
, '--category' , category
, '--publisher' , publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'class':["hon_article_top","article-bodytext","hon_article_photo","storyphoto","article"]}),
dict(name='div', attrs={'id':["storycontentleft","article"]})
]
remove_tags = [dict(name=['object','link','embed']),
dict(name='div', attrs={'class':["article-tools","titleBar","invisiblespacer","articleflex-container","hon_newslist","categoryheader","columnframe","subHeadline","poster-container"]}),
dict(name='div', attrs={'align':["right"]}),
dict(name='div', attrs={'id':["pluckcomments"]}),
dict(name='td', attrs={'class':["prepsfacts"]}),
dict(name='img', attrs={'height':["1"]}),
dict(name='img', attrs={'alt':["Advertisement"]}),
dict(name='img', attrs={'src':["/gcicommonfiles/sr/graphics/common/adlabel_horz.gif","/gcicommonfiles/sr/graphics/common/icon_whatsthis.gif",]}),
]
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-size:large; color:#000000; }
.hon_article_timestamp{font-family:Arial,Helvetica,sans-serif; font-size:70%; }
.postedStoryDate{font-family:Arial,Helvetica,sans-serif; font-size:30%; }
.postedDate{font-family:Arial,Helvetica,sans-serif; font-size:30%; }
.credit{font-family:Arial,Helvetica,sans-serif; font-size:30%; }
.hon_article_top{font-family:Arial,Helvetica,sans-serif; color:#666666; font-size:30%; font-weight:bold;}
.grayBackground{font-family:Arial,Helvetica,sans-serif; color:#666666; font-size:30%;}
.hon_photocaption{font-family:Arial,Helvetica,sans-serif; font-size:30%; }
.photoCaption{font-family:Arial,Helvetica,sans-serif; font-size:30%; }
.hon_photocredit{font-family:Arial,Helvetica,sans-serif; font-size:30%; color:#666666;}
.storyphoto{font-family:Arial,Helvetica,sans-serif; font-size:30%; color:#666666;}
.article-bodytext{font-family:Arial,Helvetica,sans-serif; font-size:xx-small; }
.storycontentleft{font-family:Arial,Helvetica,sans-serif; font-size:xx-small; }
#article{font-family:Arial,Helvetica,sans-serif; font-size:xx-small; }
.contentarea{font-family:Arial,Helvetica,sans-serif; font-size:xx-small; }
.storytext{font-family:Verdana,Arial,Helvetica,sans-serif; font-size:xx-small;}
.storyHeadline{font-family:Arial,Helvetica,sans-serif; font-size:large; color:#000000; font-weight:bold;}
.source{font-family:Arial,Helvetica,sans-serif; color:#333333; font-style: italic; font-weight:bold; }
'''
feeds = [
(u'Breaking news', u'http://www.honoluluadvertiser.com/apps/pbcs.dll/section?Category=RSS01&MIME=XML' )
,(u'Local news', u'http://www.honoluluadvertiser.com/apps/pbcs.dll/section?Category=RSS02&MIME=XML' )
,(u'Sports', u'http://www.honoluluadvertiser.com/apps/pbcs.dll/section?Category=RSS03&MIME=XML' )
,(u'Island life', u'http://www.honoluluadvertiser.com/apps/pbcs.dll/section?Category=RSS05&MIME=XML' )
,(u'Entertainment', u'http://www.honoluluadvertiser.com/apps/pbcs.dll/section?Category=RSS06&MIME=XML' )
,(u'Business', u'http://www.honoluluadvertiser.com/apps/pbcs.dll/section?Category=RSS04&MIME=XML' )
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
mtag = '\n<meta http-equiv="Content-Language" content="en"/>\n'
soup.head.insert(0,mtag)
for tag in soup.findAll(name=['span','table','font']):
tag.name = 'div'
return soup
# def print_version(self, url):
# ubody, sep, rest = url.rpartition('/-1/')
# root, sep2, article_id = ubody.partition('/article/')
# return u'http://www.honoluluadvertiser.com/apps/pbcs.dll/article?AID=/' + article_id + '&template=printart'

47
resources/recipes/staradvertiser.recipe Normal file
View File

@ -0,0 +1,47 @@
__license__ = 'GPL v3'
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
'''
staradvertiser.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Starbulletin(BasicNewsRecipe):
title = 'Honolulu Star Advertiser'
__author__ = 'Darko Miletic'
description = "Latest national and local Hawaii sports news"
publisher = 'Honolulu Star-Advertiser'
category = 'news, Honolulu, Hawaii'
oldest_article = 2
max_articles_per_feed = 100
language = 'en'
no_stylesheets = True
use_embedded_content = False
encoding = 'utf8'
publication_type = 'newspaper'
extra_css = ' body{font-family: Verdana,Arial,Helvetica,sans-serif} h1,.brown,.postCredit{color: #663300} .storyDeck{font-size: 1.2em; font-weight: bold} '
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
, 'linearize_tables' : True
}
remove_tags_before = dict(attrs={'id':'storyTitle'})
remove_tags_after = dict(name='div', attrs={'class':'storytext'})
remove_tags = [
dict(name=['object','link'])
,dict(attrs={'class':'insideStoryImage'})
]
feeds = [
(u'Headlines' , u'http://www.staradvertiser.com/staradvertiser_headlines.rss' )
,(u'News' , u'http://www.staradvertiser.com/news/index.rss' )
,(u'Sports' , u'http://www.staradvertiser.com/sports/index.rss' )
,(u'Features' , u'http://www.staradvertiser.com/features/index.rss' )
,(u'Editorials', u'http://www.staradvertiser.com/editorials/index.rss' )
,(u'Business' , u'http://www.staradvertiser.com/business/index.rss' )
,(u'Travel' , u'http://www.staradvertiser.com/travel/index.rss' )
]

60
resources/recipes/starbulletin.recipe
View File

@ -1,60 +0,0 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
starbulletin.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Starbulletin(BasicNewsRecipe):
title = 'Honolulu Star-Bulletin'
__author__ = 'Darko Miletic'
description = "Latest national and local Hawaii sports news"
publisher = 'Honolulu Star-Bulletin'
category = 'news, Honolulu, Hawaii'
oldest_article = 2
max_articles_per_feed = 100
language = 'en'
no_stylesheets = True
use_embedded_content = False
encoding = 'utf8'
remove_javascript = True
cover_url = 'http://media.starbulletin.com/designimages/spacer.gif'
html2lrf_options = [
'--comment' , description
, '--category' , category
, '--publisher' , publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [ dict(name='div', attrs={'id':'storyColoumn'}) ]
remove_tags = [
dict(name=['object','link'])
,dict(name='span', attrs={'id':'printdesc'})
,dict(name='div' , attrs={'class':'lightGreyBox storyTools clearAll'})
,dict(name='div' , attrs={'id':'breadcrumbs'})
]
feeds = [
(u'Headlines', u'http://www.starbulletin.com/starbulletin_headlines.rss' )
,(u'News', u'http://www.starbulletin.com/news/index.rss' )
,(u'Sports', u'http://www.starbulletin.com/sports/index.rss' )
,(u'Features', u'http://www.starbulletin.com/features/index.rss' )
,(u'Editorials', u'http://www.starbulletin.com/editorials/index.rss' )
,(u'Business', u'http://www.starbulletin.com/business/index.rss' )
,(u'Travel', u'http://www.starbulletin.com/travel/index.rss' )
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
mtag = '\n<meta http-equiv="Content-Language" content="en"/>\n'
soup.head.insert(0,mtag)
return soup