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

Update Financial Times

Browse Source 
Fixes #1286679 [Updated recipes for financial times](https://bugs.launchpad.net/calibre/+bug/1286679)
This commit is contained in:
Kovid Goyal 2014-03-02 08:32:20 +05:30
parent c91bb61d6f
commit a3fa1e9e49
2 changed files with 7 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
recipes/financial_times_uk.recipe
View File

@ -1,5 +1,5 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2010-2013, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2010-2014, Darko Miletic <darko.miletic at gmail.com>'
''' '''
www.ft.com/intl/uk-edition www.ft.com/intl/uk-edition
''' '''
@ -52,19 +52,13 @@ class FinancialTimes(BasicNewsRecipe):
return br return br
keep_only_tags = [ keep_only_tags = [
dict(name='div' , attrs={'class':['fullstory fullstoryHeader', 'ft-story-header']}) dict(name='div' , attrs={'class':['master-row editorialSection']})
,dict(name='div' , attrs={'class':'standfirst'})
,dict(name='div' , attrs={'id' :'storyContent'})
,dict(name='div' , attrs={'class':['ft-story-body','index-detail']})
,dict(name='h2' , attrs={'class':'entry-title'} )
,dict(name='span', attrs={'class':lambda x: x and 'posted-on' in x.split()} )
,dict(name='span', attrs={'class':'author_byline'} )
,dict(name='div' , attrs={'class':'entry-content'} )
] ]
remove_tags = [ remove_tags = [
dict(name='div', attrs={'id':'floating-con'}) dict(name='div', attrs={'id':'floating-con'})
,dict(name=['meta','iframe','base','object','embed','link']) ,dict(name=['meta','iframe','base','object','embed','link'])
,dict(attrs={'class':['storyTools','story-package','screen-copy','story-package separator','expandable-image']}) ,dict(attrs={'class':['storyTools','story-package','screen-copy','story-package separator','expandable-image','promobox']})
,dict(name='div', attrs={'class':lambda x: x and 'insideArticleRelatedTopics' in x.split()} )
] ]
remove_attributes = ['width','height','lang'] remove_attributes = ['width','height','lang']
@ -158,12 +152,6 @@ class FinancialTimes(BasicNewsRecipe):
item['alt'] = 'image' item['alt'] = 'image'
return soup return soup
def get_cover_url(self):
cdate = datetime.date.today()
if cdate.isoweekday() == 7:
cdate -= datetime.timedelta(days=1)
return cdate.strftime('http://specials.ft.com/vtf_pdf/%d%m%y_FRONT1_LON.pdf')
def get_obfuscated_article(self, url): def get_obfuscated_article(self, url):
count = 0 count = 0
while (count < 10): while (count < 10):

18
recipes/financial_times_us.recipe
View File

@ -52,19 +52,13 @@ class FinancialTimes(BasicNewsRecipe):
return br return br
keep_only_tags = [ keep_only_tags = [
dict(name='div' , attrs={'class':['fullstory fullstoryHeader', 'ft-story-header']}) dict(name='div' , attrs={'class':['master-row editorialSection']})
,dict(name='div' , attrs={'class':'standfirst'})
,dict(name='div' , attrs={'id' :'storyContent'})
,dict(name='div' , attrs={'class':['ft-story-body','index-detail']})
,dict(name='h2' , attrs={'class':'entry-title'} )
,dict(name='span', attrs={'class':lambda x: x and 'posted-on' in x.split()} )
,dict(name='span', attrs={'class':'author_byline'} )
,dict(name='div' , attrs={'class':'entry-content'} )
] ]
remove_tags = [ remove_tags = [
dict(name='div', attrs={'id':'floating-con'}) dict(name='div', attrs={'id':'floating-con'})
,dict(name=['meta','iframe','base','object','embed','link']) ,dict(name=['meta','iframe','base','object','embed','link'])
,dict(attrs={'class':['storyTools','story-package','screen-copy','story-package separator','expandable-image']}) ,dict(attrs={'class':['storyTools','story-package','screen-copy','story-package separator','expandable-image','promobox']})
,dict(name='div', attrs={'class':lambda x: x and 'insideArticleRelatedTopics' in x.split()} )
] ]
remove_attributes = ['width','height','lang'] remove_attributes = ['width','height','lang']
@ -158,12 +152,6 @@ class FinancialTimes(BasicNewsRecipe):
item['alt'] = 'image' item['alt'] = 'image'
return soup return soup
def get_cover_url(self):
cdate = datetime.date.today()
if cdate.isoweekday() == 7:
cdate -= datetime.timedelta(days=1)
return cdate.strftime('http://specials.ft.com/vtf_pdf/%d%m%y_FRONT1_USA.pdf')
def get_obfuscated_article(self, url): def get_obfuscated_article(self, url):
count = 0 count = 0
while (count < 10): while (count < 10):