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 NZZ

Browse Source
This commit is contained in:
Kovid Goyal 2014-04-26 15:11:33 +05:30
parent fee9953405
commit 3ab8d26ac2
1 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
recipes/nzz_webpaper.recipe
View File

@ -2,7 +2,7 @@ import re
from calibre import strftime from calibre import strftime
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2012, Bernd Leinfelder <skoll1975 at gmail.com> ' __copyright__ = '2012-14, Bernd Leinfelder <skoll1975 at gmail.com> '
''' '''
webpaper.nzz.ch webpaper.nzz.ch
@ -35,7 +35,7 @@ class Nzz(BasicNewsRecipe):
,'publisher' : publisher ,'publisher' : publisher
} }
remove_tags = [dict(name='footer') , dict({'class' : 'fullarticle__related'})] remove_tags = [dict(name='footer') , dict({'class' : ['sharebox' , 'fullarticle__related']})]
remove_tags_before = dict(name='article') remove_tags_before = dict(name='article')
remove_tags_after= dict(name='footer') remove_tags_after= dict(name='footer')
@ -47,6 +47,7 @@ class Nzz(BasicNewsRecipe):
# print soup.prettify() # print soup.prettify()
articles = {} articles = {}
key = None
sections = [] sections = []
ans = [] ans = []
issue = soup.find("link",rel="prefetch") issue = soup.find("link",rel="prefetch")
@ -61,7 +62,7 @@ class Nzz(BasicNewsRecipe):
for art in articlesoup: for art in articlesoup:
# print art.prettify() # print art.prettify()
section=art['data-department'] section=art['data-department']
print "section is "+section # print "section is "+section
if section != lastsection: if section != lastsection:
sections.append(section) sections.append(section)
@ -71,14 +72,14 @@ class Nzz(BasicNewsRecipe):
caption = art.find("h2") caption = art.find("h2")
self.temp_files.append(PersistentTemporaryFile('_fa.html')) self.temp_files.append(PersistentTemporaryFile('_fa.html'))
self.temp_files[-1].write(art.prettify()) self.temp_files[-1].write("<html><head/><body>"+art.prettify()+"</body></html>")
self.temp_files[-1].close() self.temp_files[-1].close()
filename = self.temp_files[-1].name filename = self.temp_files[-1].name
articles[section].append( articles[section].append(
dict(title=caption.string,url='file://'+filename, date=pubdate, description='', content='')) dict(title=caption.string,url='file://'+filename, date=pubdate, description='', content=''))
ans = [(key, articles[key]) for key in sections if key in articles] ans = [(key, articles[key]) for key in sections if articles.has_key(key)]
# pprint.pprint(ans) # pprint.pprint(ans)