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 #3487 (Recipe standard.at defect)

Browse Source
This commit is contained in:
Kovid Goyal 2009-09-17 08:42:52 -06:00
parent 2f5325e387
commit 9e95f7e7f6
1 changed files with 31 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
src/calibre/web/feeds/recipes/recipe_der_standard.py
View File

@ -10,8 +10,8 @@ from calibre.web.feeds.news import BasicNewsRecipe
class DerStandardRecipe(BasicNewsRecipe): class DerStandardRecipe(BasicNewsRecipe):
title = u'derStandard' title = u'derStandard'
__author__ = 'Gerhard Aigner' __author__ = 'Gerhard Aigner and Sujata Raman'
description = u'Nachrichten aus Österreich' description = u'Nachrichten aus ??sterreich'
publisher ='derStandard.at' publisher ='derStandard.at'
category = 'news, politics, nachrichten, Austria' category = 'news, politics, nachrichten, Austria'
use_embedded_content = False use_embedded_content = False
@ -21,18 +21,16 @@ class DerStandardRecipe(BasicNewsRecipe):
encoding = 'utf-8' encoding = 'utf-8'
language = 'de' language = 'de'
recursions = 0
oldest_article = 1 oldest_article = 1
max_articles_per_feed = 100 max_articles_per_feed = 100
html2lrf_options = [
'--comment' , description
, '--category' , category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
extra_css = '''
.artikelBody{font-family:Arial,Helvetica,sans-serif;}
.artikelLeft{font-family:Arial,Helvetica,sans-serif;font-size:x-small;}
h4{color:#404450;font-size:x-small;}
h6{color:#404450; font-size:x-small;}
'''
feeds = [(u'International', u'http://derstandard.at/?page=rss&ressort=internationalpolitik'), feeds = [(u'International', u'http://derstandard.at/?page=rss&ressort=internationalpolitik'),
(u'Inland', u'http://derstandard.at/?page=rss&ressort=innenpolitik'), (u'Inland', u'http://derstandard.at/?page=rss&ressort=innenpolitik'),
(u'Wirtschaft', u'http://derstandard.at/?page=rss&ressort=investor'), (u'Wirtschaft', u'http://derstandard.at/?page=rss&ressort=investor'),
@ -43,22 +41,33 @@ class DerStandardRecipe(BasicNewsRecipe):
(u'Kultur', u'http://derstandard.at/?page=rss&ressort=kultur'), (u'Kultur', u'http://derstandard.at/?page=rss&ressort=kultur'),
(u'Wissenschaft', u'http://derstandard.at/?page=rss&ressort=wissenschaft'), (u'Wissenschaft', u'http://derstandard.at/?page=rss&ressort=wissenschaft'),
(u'Gesundheit', u'http://derstandard.at/?page=rss&ressort=gesundheit'), (u'Gesundheit', u'http://derstandard.at/?page=rss&ressort=gesundheit'),
(u'Bildung', u'http://derstandard.at/?page=rss&ressort=subildung')] (u'Bildung', u'http://derstandard.at/?page=rss&ressort=subildung')
remove_tags = [dict(name='div'), dict(name='a'), dict(name='link'), dict(name='meta'), ]
dict(name='form',attrs={'name':'sitesearch'}), dict(name='hr')]
keep_only_tags = [
dict(name='div', attrs={'class':["artikel","artikelLeft","artikelBody"]}) ,
]
remove_tags = [
dict(name='link'), dict(name='meta'),dict(name='iframe'),dict(name='style'),
dict(name='form',attrs={'name':'sitesearch'}), dict(name='hr'),
dict(name='div', attrs={'class':["diashow"]})]
preprocess_regexps = [ preprocess_regexps = [
(re.compile(r'\[[\d]*\]', re.DOTALL|re.IGNORECASE), lambda match: ''), (re.compile(r'\[[\d]*\]', re.DOTALL|re.IGNORECASE), lambda match: ''),
(re.compile(r'bgcolor="#\w{3,6}"', re.DOTALL|re.IGNORECASE), lambda match: '') (re.compile(r'bgcolor="#\w{3,6}"', re.DOTALL|re.IGNORECASE), lambda match: '')
] ]
def print_version(self, url): filter_regexps = [r'/r[1-9]*']
return url.replace('?id=', 'txt/?id=')
#def print_version(self, url):
# return url.replace('?id=', 'txt/?id=')
def get_article_url(self, article): def get_article_url(self, article):
'''if the article links to a index page (ressort) or a picture gallery '''if the article links to a index page (ressort) or a picture gallery
(ansichtssache), don't add it''' (ansichtssache), don't add it'''
if (article.link.count('ressort') > 0 or article.title.lower().count('ansichtssache') > 0): if ( article.link.count('ressort') > 0 or article.title.lower().count('ansichtssache') > 0 ):
return None return None
return article.link return article.link
def preprocess_html(self, soup): def preprocess_html(self, soup):
@ -66,4 +75,7 @@ class DerStandardRecipe(BasicNewsRecipe):
soup.html['lang'] = self.lang soup.html['lang'] = self.lang
mtag = '<meta http-equiv="Content-Type" content="text/html; charset=' + self.encoding + '">' mtag = '<meta http-equiv="Content-Type" content="text/html; charset=' + self.encoding + '">'
soup.head.insert(0,mtag) soup.head.insert(0,mtag)
for t in soup.findAll(['ul', 'li']):
t.name = 'div'
return soup return soup