Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-08-07 09:01:38 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update NZZ

Browse Source
This commit is contained in:
Kovid Goyal 2013-12-18 09:47:45 +05:30
parent d51a0be334
commit 480cc884fe
2 changed files with 37 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
recipes/nzz_ger.recipe
View File

@ -1,4 +1,3 @@
__license__ = 'GPL v3'
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>, 2012 Bernd Leinfelder <skoll1975@gmail.com>'
@ -41,7 +40,6 @@ class Nzz(BasicNewsRecipe):
,'publisher' : publisher
}
remove_attributes=['width','height','lang']
remove_tags_before = dict(id='main')
remove_tags_after = dict(id='articleBodyText')

56
recipes/nzz_webpaper.recipe
View File

@ -1,3 +1,4 @@
import re
from calibre import strftime
__license__ = 'GPL v3'
@ -7,6 +8,7 @@ __copyright__ = '2012, Bernd Leinfelder <skoll1975 at gmail.com> '
webpaper.nzz.ch
'''
from calibre.ptempfile import PersistentTemporaryFile
from calibre.web.feeds.recipes import BasicNewsRecipe
class Nzz(BasicNewsRecipe):
@ -23,6 +25,7 @@ class Nzz(BasicNewsRecipe):
encoding = 'utf-8'
use_embedded_content = False
language = 'de'
temp_files = []
extra_css = 'h1 {font: sans-serif large;}\n.byline {font:monospace;}'
conversion_options = {
@ -32,7 +35,7 @@ class Nzz(BasicNewsRecipe):
,'publisher' : publisher
}
remove_tags = [dict(name='footer')]
remove_tags = [dict(name='footer') , dict({'class' : 'fullarticle__related'})]
remove_tags_before = dict(name='article')
remove_tags_after= dict(name='footer')
@ -41,47 +44,52 @@ class Nzz(BasicNewsRecipe):
baseref = 'https://webpaper.nzz.ch'
soup = self.index_to_soup(baseref)
# print soup.prettify()
articles = {}
sections = []
ans = []
issue = soup.find("link",rel="prefetch")
issuelist = soup.find(id="issueSelectorList")
soup = self.index_to_soup(baseref+issue['href'])
# print soup.prettify()
section = ""
lastsection = ""
pubdate = strftime('%a, %d %b')
feeds = issuelist.findAll("a")
for f in feeds:
section = f.string
sectionref = baseref + f['href']
articlesoup = soup.findAll("article",{"class" : re.compile(".*fullarticle[ \"].*")})
for art in articlesoup:
# print art.prettify()
section=art['data-department']
print "section is "+section
ans.append(section)
if section != lastsection:
sections.append(section)
articles[section]=[]
lastsection=section
articlesoup = self.index_to_soup(sectionref)
caption = art.find("h2")
articlesoup = articlesoup.findAll('article','article')
for a in articlesoup:
artlink = a.find('a')
self.temp_files.append(PersistentTemporaryFile('_fa.html'))
self.temp_files[-1].write(art.prettify())
self.temp_files[-1].close()
filename = self.temp_files[-1].name
arthref = baseref + artlink['href']
arthead = a.find('h2')
artcaption = arthead.string
articles[section].append(
dict(title=caption.string,url='file://'+filename, date=pubdate, description='', content=''))
pubdate = strftime('%a, %d %b')
ans = [(key, articles[key]) for key in sections if key in articles]
if not artcaption is None:
if not articles.has_key(section):
articles[section] = []
articles[section].append(
dict(title=artcaption, url=arthref, date=pubdate, description='', content=''))
# pprint.pprint(ans)
ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
return ans
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
if self.username is not None and self.password is not None:
br.open('https://cas.nzz.ch/cas/login')
br.open('https://webpaper.nzz.ch/login')
br.select_form(nr=0)
br['username'] = self.username
br['password'] = self.password
br.submit()
return br