Updated recipes for The Straits Times and MSDN Magazine

This commit is contained in:
Kovid Goyal 2009-10-07 17:27:38 -06:00
parent 4267c8f85d
commit 64f0769b08
2 changed files with 93 additions and 119 deletions

View File

@ -1,62 +1,43 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
msdn.microsoft.com/en-us/magazine
'''
from calibre.web.feeds.news import BasicNewsRecipe
class MSDNMagazine_en(BasicNewsRecipe):
title = 'MSDN Magazine'
__author__ = 'Darko Miletic'
description = 'The Microsoft Journal for Developers'
publisher = 'Microsoft Press'
category = 'news, IT, Microsoft, programming, windows'
oldest_article = 31
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
remove_javascript = True
current_issue = 'http://msdn.microsoft.com/en-us/magazine/default.aspx'
language = 'en'
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
feeds = [(u'Articles', u'http://msdn.microsoft.com/en-us/magazine/rss/default.aspx?z=z&iss=1')]
keep_only_tags = [dict(name='div', attrs={'class':'topic'})]
remove_tags = [
dict(name=['object','link','base','table'])
,dict(name='div', attrs={'class':'MTPS_CollapsibleRegion'})
]
def get_cover_url(self):
cover_url = None
soup = self.index_to_soup(self.current_issue)
link_item = soup.find('span',attrs={'class':'ContentsImageSpacer'})
if link_item:
imgt = link_item.find('img')
if imgt:
cover_url = imgt['src']
return cover_url
def preprocess_html(self, soup):
for item in soup.findAll('div',attrs={'class':['FeatureSmallHead','ColumnTypeSubTitle']}):
item.name="h2"
for item in soup.findAll('div',attrs={'class':['FeatureHeadline','ColumnTypeTitle']}):
item.name="h1"
for item in soup.findAll('div',attrs={'class':'ArticleTypeTitle'}):
item.name="h3"
return soup
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
msdn.microsoft.com/en-us/magazine
'''
from calibre.web.feeds.news import BasicNewsRecipe
class MSDNMagazine_en(BasicNewsRecipe):
title = 'MSDN Magazine'
__author__ = 'Darko Miletic'
description = 'The Microsoft Journal for Developers'
publisher = 'Microsoft Press'
category = 'news, IT, Microsoft, programming, windows'
oldest_article = 31
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
language = 'en'
feeds = [(u'Articles', u'http://msdn.microsoft.com/en-us/magazine/rss/default.aspx?z=z&iss=1')]
keep_only_tags = [dict(name='div', attrs={'class':'navpage'})]
remove_tags = [
dict(name=['object','link','base','table'])
,dict(name='div', attrs={'class':'MTPS_CollapsibleRegion'})
]
remove_tags_after = dict(name='div', attrs={'class':'navpage'})
def preprocess_html(self, soup):
for item in soup.findAll('div',attrs={'class':['FeatureSmallHead','ColumnTypeSubTitle']}):
item.name="h2"
for item in soup.findAll('div',attrs={'class':['FeatureHeadline','ColumnTypeTitle']}):
item.name="h1"
for item in soup.findAll('div',attrs={'class':'ArticleTypeTitle'}):
item.name="h3"
return soup

View File

@ -1,57 +1,50 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
www.straitstimes.com
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
class StraitsTimes(BasicNewsRecipe):
title = 'The Straits Times'
__author__ = 'Darko Miletic'
description = 'Singapore newspaper'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
publisher = 'Singapore Press Holdings Ltd.'
category = 'news, politics, singapore, asia'
language = 'en'
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
, '--ignore-tables'
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True'
remove_tags = [
dict(name=['object','link'])
,dict(name='table', attrs={'width':'980'})
,dict(name='td' , attrs={'class':'padlrt10'})
]
feeds = [
(u'Singapore' , u'http://www.straitstimes.com/STI/STIFILES/rss/break_singapore.xml' )
,(u'SE Asia' , u'http://www.straitstimes.com/STI/STIFILES/rss/break_sea.xml' )
,(u'Money' , u'http://www.straitstimes.com/STI/STIFILES/rss/break_money.xml' )
,(u'Sport' , u'http://www.straitstimes.com/STI/STIFILES/rss/break_sport.xml' )
,(u'World' , u'http://www.straitstimes.com/STI/STIFILES/rss/break_world.xml' )
,(u'Tech & Science' , u'http://www.straitstimes.com/STI/STIFILES/rss/break_tech.xml' )
,(u'Lifestyle' , u'http://www.straitstimes.com/STI/STIFILES/rss/break_lifestyle.xml' )
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup
def print_version(self, url):
return url.replace('http://www.straitstimes.com','http://www.straitstimes.com/print')
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
www.straitstimes.com
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
class StraitsTimes(BasicNewsRecipe):
title = 'The Straits Times'
__author__ = 'Darko Miletic'
description = 'Singapore newspaper'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
publisher = 'Singapore Press Holdings Ltd.'
category = 'news, politics, singapore, asia'
language = 'en'
extra_css = ' .top_headline{font-size: x-large; font-weight: bold} '
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
}
remove_tags = [dict(name=['object','link','map'])]
keep_only_tags = [dict(name='div', attrs={'class':['top_headline','story_text']})]
feeds = [
(u'Singapore' , u'http://www.straitstimes.com/STI/STIFILES/rss/break_singapore.xml' )
,(u'SE Asia' , u'http://www.straitstimes.com/STI/STIFILES/rss/break_sea.xml' )
,(u'Money' , u'http://www.straitstimes.com/STI/STIFILES/rss/break_money.xml' )
,(u'Sport' , u'http://www.straitstimes.com/STI/STIFILES/rss/break_sport.xml' )
,(u'World' , u'http://www.straitstimes.com/STI/STIFILES/rss/break_world.xml' )
,(u'Tech & Science' , u'http://www.straitstimes.com/STI/STIFILES/rss/break_tech.xml' )
,(u'Lifestyle' , u'http://www.straitstimes.com/STI/STIFILES/rss/break_lifestyle.xml' )
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup