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 Spiegel Online International

Browse Source
This commit is contained in:
Kovid Goyal 2012-05-15 18:35:42 +05:30
parent 8eebae3bf5
commit 4f2f8e2540
1 changed files with 22 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
recipes/spiegel_int.recipe
View File

@ -1,3 +1,4 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008-2011, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2008-2011, Darko Miletic <darko.miletic at gmail.com>'
''' '''
@ -15,6 +16,8 @@ class Spiegel_int(BasicNewsRecipe):
language = 'en_DE' language = 'en_DE'
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
auto_cleanup = True
auto_cleanup_keep = '//*[@id="spArticleTopAsset"]'
encoding = 'cp1252' encoding = 'cp1252'
publisher = 'SPIEGEL ONLINE GmbH' publisher = 'SPIEGEL ONLINE GmbH'
category = 'news, politics, Germany' category = 'news, politics, Germany'
@ -43,25 +46,25 @@ class Spiegel_int(BasicNewsRecipe):
.spPhotoGallery{font-size:x-small; color:#990000 ;} .spPhotoGallery{font-size:x-small; color:#990000 ;}
''' '''
keep_only_tags = [dict(attrs={'id':'spArticleContent'})] #keep_only_tags = [dict(attrs={'id':'spArticleContent'})]
remove_tags_after = dict(attrs={'id':'spArticleBody'}) #remove_tags_after = dict(attrs={'id':'spArticleBody'})
remove_tags = [dict(name=['meta','base','iframe','embed','object'])] #remove_tags = [dict(name=['meta','base','iframe','embed','object'])]
remove_attributes = ['clear'] #remove_attributes = ['clear']
feeds = [(u'Spiegel Online', u'http://www.spiegel.de/international/index.rss')] feeds = [(u'Spiegel Online', u'http://www.spiegel.de/international/index.rss')]
def print_version(self, url): #def print_version(self, url):
main, sep, rest = url.rpartition(',') #main, sep, rest = url.rpartition(',')
rmain, rsep, rrest = main.rpartition(',') #rmain, rsep, rrest = main.rpartition(',')
return rmain + ',druck-' + rrest + ',' + rest #return rmain + ',druck-' + rrest + ',' + rest
def preprocess_html(self, soup): #def preprocess_html(self, soup):
for item in soup.findAll(style=True): #for item in soup.findAll(style=True):
del item['style'] #del item['style']
for item in soup.findAll('a'): #for item in soup.findAll('a'):
if item.string is not None: #if item.string is not None:
str = item.string #str = item.string
item.replaceWith(str) #item.replaceWith(str)
else: #else:
str = self.tag_to_string(item) #str = self.tag_to_string(item)
item.replaceWith(str) #item.replaceWith(str)
return soup #return soup