Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 18:54:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update derStandard

Browse Source
This commit is contained in:
Kovid Goyal 2019-03-08 09:12:38 +05:30
parent 36136bcdb2
commit 99e8bdd227
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 12 additions and 43 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

55
recipes/der_standard.recipe
View File

@ -7,11 +7,15 @@ __copyright__ = '2009, Gerhard Aigner <gerhard.aigner at gmail.com>'
''' http://www.derstandard.at - Austrian Newspaper '''
import re
import random
from calibre.web.feeds.news import BasicNewsRecipe
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
class DerStandardRecipe(BasicNewsRecipe):
title = u'derStandard'
__author__ = 'Gerhard Aigner and Sujata Raman and Marcel Jira and Peter Reschenhofer'
@ -32,8 +36,8 @@ class DerStandardRecipe(BasicNewsRecipe):
feeds = [
(u'Newsroom', u'http://derStandard.at/?page=rss&ressort=Seite1'),
(u'Inland', u'http://derstandard.at/?page=rss&ressort=InnenPolitik'),
(u'International', u'http://derstandard.at/?page=rss&ressort=InternationalPolitik'),
(u'International', u'http://derstandard.at/?page=rss&ressort=International'),
(u'Inland', u'http://derstandard.at/?page=rss&ressort=Inland'),
(u'Wirtschaft', u'http://derStandard.at/?page=rss&ressort=Wirtschaft'),
(u'Web', u'http://derStandard.at/?page=rss&ressort=Web'),
(u'Sport', u'http://derStandard.at/?page=rss&ressort=Sport'),
@ -47,16 +51,16 @@ class DerStandardRecipe(BasicNewsRecipe):
(u'Lifestyle', u'http://derStandard.at/?page=rss&ressort=Lifestyle'),
(u'Reisen', u'http://derStandard.at/?page=rss&ressort=Reisen'),
(u'Familie', u'http://derstandard.at/?page=rss&ressort=Familie'),
(u'Greenlife', u'http://derStandard.at/?page=rss&ressort=Greenlife'),
(u'Meinung', u'http://derStandard.at/?page=rss&ressort=Meinung'),
(u'User', u'http://derStandard.at/?page=rss&ressort=User'),
(u'Karriere', u'http://derStandard.at/?page=rss&ressort=Karriere'),
(u'Immobilien', u'http://derstandard.at/?page=rss&ressort=Immobilien'),
(u'Automobil', u'http://derstandard.at/?page=rss&ressort=Automobil'),
(u'dieStandard', u'http://dieStandard.at/?page=rss&ressort=diestandard'),
(u'daStandard', u'http://daStandard.at/?page=rss&ressort=dastandard')
(u'dieStandard', u'http://derStandard.at/?page=rss&ressort=diestandard'),
]
keep_only_tags = [
dict(name='div', attrs={'class': re.compile('^artikel')})
classes('article-header article-body'),
]
remove_tags = [
@ -70,38 +74,3 @@ class DerStandardRecipe(BasicNewsRecipe):
]
remove_attributes = ['width', 'height']
preprocess_regexps = [
(re.compile(r'\[[\d]*\]', re.DOTALL |
re.IGNORECASE), lambda match: ''),
(re.compile(r'bgcolor="#\w{3,6}"',
re.DOTALL | re.IGNORECASE), lambda match: '')
]
filter_regexps = [r'/r[1-9]*']
def get_article_url(self, article):
matchObj = re.search(re.compile(
r'/r' + '[1-9]*', flags=0), article.link, flags=0)
if matchObj:
return None
return article.link
def preprocess_html(self, soup):
if soup.find('div', {'class': re.compile('^artikel')}) is None:
self.abort_article()
for t in soup.findAll(['ul', 'li']):
t.name = 'div'
return soup
def get_cover_url(self):
base_url = 'https://epaper.derstandard.at/'
url = base_url + 'shelf.act?s=' + str(random.random() * 10000)
soup = self.index_to_soup(url)
img = soup.find(
'img', {'class': re.compile('^thumbnailBig'), 'src': True})
if img and img['src']:
cover_url = base_url + img['src']
return cover_url