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

Sync with trunk.

Browse Source
This commit is contained in:
John Schember 2011-08-28 09:14:56 -04:00
commit 2222ecca21
4 changed files with 93 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
recipes/hbr.recipe
View File

@ -11,9 +11,14 @@ class HBR(BasicNewsRecipe):
timefmt = ' [%B %Y]'
language = 'en'
no_stylesheets = True
recipe_disabled = ('hbr.org has started requiring the use of javascript'
' to log into their website. This is unsupported in calibre, so'
' this recipe has been disabled. If you would like to see '
' HBR supported in calibre, contact hbr.org and ask them'
' to provide a javascript free login method.')
LOGIN_URL = 'http://hbr.org/login?request_url=/'
LOGOUT_URL = 'http://hbr.org/logout?request_url=/'
LOGIN_URL = 'https://hbr.org/login?request_url=/'
LOGOUT_URL = 'https://hbr.org/logout?request_url=/'
INDEX = 'http://hbr.org/archive-toc/BR'
@ -44,7 +49,8 @@ class HBR(BasicNewsRecipe):
br['signin-form:username'] = self.username
br['signin-form:password'] = self.password
raw = br.submit().read()
if 'My Account' not in raw:
open('/t/crap.html', 'wb').write(raw)
if '>Sign out<' not in raw:
raise Exception('Failed to login, are you sure your username and password are correct?')
try:
link = br.find_link(text='Sign out')

5
recipes/hbr_blogs.recipe
View File

@ -9,6 +9,11 @@ class HBR(BasicNewsRecipe):
__author__ = 'Kovid Goyal'
language = 'en'
no_stylesheets = True
recipe_disabled = ('hbr.org has started requiring the use of javascript'
' to log into their website. This is unsupported in calibre, so'
' this recipe has been disabled. If you would like to see '
' HBR supported in calibre, contact hbr.org and ask them'
' to provide a javascript free login method.')
LOGIN_URL = 'http://hbr.org/login?request_url=/'
LOGOUT_URL = 'http://hbr.org/logout?request_url=/'

34
recipes/ntv_spor.recipe Normal file
View File

@ -0,0 +1,34 @@
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1313512459(BasicNewsRecipe):
title = u'NTVSpor'
__author__ = 'A Erdogan'
description = 'News from Turkey'
publisher = 'NTVSpor.net'
category = 'sports, Turkey'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
masthead_url = 'http://www.ntvspor.net/HTML/r/i/l.png'
language = 'tr'
extra_css ='''
body{font-family:Arial,Helvetica,sans-serif; font-size:small; align:left; color:#000000}
h1{font-size:large; color:#000000}
h2{font-size:small; color:#000000}
p{font-size:small; color:#000000}
'''
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
remove_tags = [dict(name=['embed','il','ul','iframe','object','link','base']), dict(name='div', attrs={'id':'contentPhotoGallery'}), dict(name='div', attrs={'class':'SocialMediaWrapper'}), dict(name='div', attrs={'class':'grid2'}), dict(name='div', attrs={'class':'grid8'}), dict(name='div', attrs={'id':'anonsBar'}), dict(name='div', attrs={'id':'header'})]
remove_tags_before = dict(name='h1', attrs={'style':['margin-top: 6px;']})
remove_tags_after = dict(name='div', attrs={'id':'newsBody'})
feeds = [(u'NTVSpor', u'http://www.ntvspor.net/Rss/anasayfa')]

45
recipes/ntv_tr.recipe Normal file
View File

@ -0,0 +1,45 @@
from calibre.web.feeds.news import BasicNewsRecipe
class NTVMSNBC(BasicNewsRecipe):
title = u'NTV'
__author__ = 'A Erdogan'
description = 'News from Turkey'
publisher = 'NTV'
category = 'news, politics, Turkey'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
masthead_url = 'http://www.ntvmsnbc.com/images/MSNBC/msnbc_ban.gif'
language = 'tr'
remove_tags_before = dict(name='h1')
remove_tags_after = dict(attrs={'id':'haberDetayYazi'})
extra_css ='''
body{font-family:Arial,Helvetica,sans-serif; font-size:small; align:left; color:#000000}
h1{font-size:large; color:#000000}
h2{font-size:small; color:#000000}
p{font-size:small; color:#000000}
'''
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
remove_tags = [dict(name=['embed','il','ul','iframe','object','link','base']), dict(name='div', attrs={'style':['padding: 0pt 10px 10px;']}), dict(name='div', attrs={'style':['padding: 0pt 10px 10px;']}), dict(name='div', attrs={'class':['textSmallGrey w320']}), dict(name='div', attrs={'style':['font-family:Arial; font-size:16px;font-weight:bold; font-color:#003366; margin-bottom:20px; margin-top:20px; border-bottom:solid 1px;border-color: #CCC; padding-bottom:2px;']})]
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'style':['font-family:Arial; font-size:16px;font-weight:bold; font-color:#003366; margin-bottom:20px; margin-top:20px; border-bottom:solid 1px;border-color: #CCC; padding-bottom:2px;']})
feeds = [(u'NTV', u'http://www.ntvmsnbc.com/id/3032091/device/rss/rss.xml')]
def print_version(self, url):
articleid = url.rpartition('/id/')[2]
return 'http://www.ntvmsnbc.com/id/' + articleid + '/print/1/displaymode/1098/'
def preprocess_html(self, soup):
return self.adeify_images(soup)