Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 10:44:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

Implement #2690 (Various Belgian recipes)

Browse Source
This commit is contained in:
Kovid Goyal 2009-06-23 11:03:55 -07:00
parent 521890f655
commit e311bc02a8
8 changed files with 261 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
src/calibre/gui2/images/news/gva_be.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 621 B

BIN
src/calibre/gui2/images/news/hln.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 295 B

BIN
src/calibre/gui2/images/news/tijd.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 381 B

1
src/calibre/web/feeds/recipes/__init__.py
View File

@ -50,6 +50,7 @@ recipe_modules = ['recipe_' + r for r in (
'marca', 'kellog_faculty', 'kellog_insight',
'theeconomictimes_india', '7dias', 'buenosaireseconomico',
'diagonales', 'miradasalsur', 'newsweek_argentina', 'veintitres',
'gva_be', 'hln', 'tijd', 'degentenaar',
)]
import re, imp, inspect, time, os

75
src/calibre/web/feeds/recipes/recipe_degentenaar.py Normal file
View File

@ -0,0 +1,75 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
www.nieuwsblad.be
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class DeGentenaarOnline(BasicNewsRecipe):
title = 'De Gentenaar Online'
__author__ = 'Darko Miletic'
description = 'News from Belgium in Dutch'
publisher = 'De Gentenaar'
category = 'news, politics, Belgium'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
language = _('Dutch')
lang = 'nl-BE'
direction = 'ltr'
html2lrf_options = [
'--comment' , description
, '--category' , category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\noverride_css=" p {text-indent: 0cm; margin-top: 0em; margin-bottom: 0.5em} "'
keep_only_tags = [dict(name='span', attrs={'id':['lblArticleTitle','lblArticleIntroduction','lblArticleMainText']})]
remove_tags = [dict(name=['embed','object'])]
feeds = [
(u'Snelnieuws' , u'http://feeds.nieuwsblad.be/nieuws/snelnieuws' )
,(u'Binnenland' , u'http://feeds.nieuwsblad.be/nieuws/binnenland' )
,(u'Buitenland' , u'http://feeds.nieuwsblad.be/nieuwsblad/buitenland' )
,(u'Economie' , u'http://feeds.nieuwsblad.be/economie/home' )
,(u'Economie' , u'http://feeds.nieuwsblad.be/economie/home' )
,(u'Algemeen' , u'http://feeds.nieuwsblad.be/life/algemeen' )
,(u'Film' , u'http://feeds.nieuwsblad.be/life/film' )
,(u'Boek' , u'http://feeds.nieuwsblad.be/life/boeken' )
,(u'Muziek' , u'http://feeds.nieuwsblad.be/life/muziek' )
,(u'Podium' , u'http://feeds.nieuwsblad.be/life/podium' )
,(u'TV & radio' , u'http://feeds.nieuwsblad.be/life/tv' )
]
def print_version(self, url):
return url.replace('/Detail.aspx?articleid','/PrintArticle.aspx?ArticleID')
def get_article_url(self, article):
return article.get('guid', None)
def preprocess_html(self, soup):
del soup.body['onload']
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll('span'):
item.name='div'
if item.has_key('id') and item['id'] == 'lblArticleTitle':
item.name='h3'
soup.html['lang'] = self.lang
soup.html['dir' ] = self.direction
mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
soup.head.insert(0,mlang)
soup.head.insert(1,mcharset)
return soup

63
src/calibre/web/feeds/recipes/recipe_gva_be.py Normal file
View File

@ -0,0 +1,63 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
www.gva.be
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class GazetvanAntwerpen(BasicNewsRecipe):
title = 'Gazet van Antwerpen'
__author__ = 'Darko Miletic'
description = 'News from Belgium in Dutch'
publisher = 'Gazet van Antwerpen'
category = 'news, politics, Belgium'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
language = _('Dutch')
lang = 'nl-BE'
direction = 'ltr'
html2lrf_options = [
'--comment' , description
, '--category' , category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\noverride_css=" p {text-indent: 0cm; margin-top: 0em; margin-bottom: 0.5em} "'
keep_only_tags = [dict(name='div', attrs={'id':'article'})]
remove_tags = [
dict(name=['embed','object'])
, dict (name='div',attrs={'class':['note NotePortrait','note']})
]
remove_tags_after = dict(name='span', attrs={'class':'author'})
feeds = [
(u'Overzicht & Blikvanger', u'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/overview/overzicht' )
,(u'Stad & Regio' , u'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/stadenregio' )
,(u'Economie' , u'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/economie' )
,(u'Binnenland' , u'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/binnenland' )
,(u'Buitenland' , u'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/buitenland' )
,(u'Media & Cultur' , u'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/mediaencultuur')
,(u'Wetenschap' , u'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/mediaencultuur')
,(u'Sport' , u'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/sport' )
]
def preprocess_html(self, soup):
del soup.body['onload']
for item in soup.findAll(style=True):
del item['style']
soup.html['lang'] = self.lang
soup.html['dir' ] = self.direction
mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
soup.head.insert(0,mlang)
soup.head.insert(1,mcharset)
return soup

52
src/calibre/web/feeds/recipes/recipe_hln.py Normal file
View File

@ -0,0 +1,52 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
www.hln.be
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class HLN_be(BasicNewsRecipe):
title = 'Het Belang Van Limburg'
__author__ = 'Darko Miletic'
description = 'News from Belgium in Dutch'
publisher = 'Het Belang Van Limburg'
category = 'news, politics, Belgium'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
language = _('Dutch')
lang = 'nl-BE'
direction = 'ltr'
html2lrf_options = [
'--comment' , description
, '--category' , category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\noverride_css=" p {text-indent: 0cm; margin-top: 0em; margin-bottom: 0.5em} "'
keep_only_tags = [dict(name='div', attrs={'class':'art_box2'})]
remove_tags = [
dict(name=['embed','object'])
]
feeds = [(u'Alle nieuws', u'http://www.hln.be/rss.xml')]
def preprocess_html(self, soup):
del soup.body['onload']
for item in soup.findAll(style=True):
del item['style']
soup.html['lang'] = self.lang
soup.html['dir' ] = self.direction
mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
soup.head.insert(0,mlang)
soup.head.insert(1,mcharset)
return soup

70
src/calibre/web/feeds/recipes/recipe_tijd.py Normal file
View File

@ -0,0 +1,70 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
www.tijd.be
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class DeTijd(BasicNewsRecipe):
title = 'De Tijd'
__author__ = 'Darko Miletic'
description = 'News from Belgium in Dutch'
publisher = 'De Tijd'
category = 'news, politics, Belgium'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
language = _('Dutch')
lang = 'nl-BE'
direction = 'ltr'
html2lrf_options = [
'--comment' , description
, '--category' , category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\noverride_css=" p {text-indent: 0cm; margin-top: 0em; margin-bottom: 0.5em} "'
keep_only_tags = [dict(name='div', attrs={'id':'lcol'})]
remove_tags = [
dict(name=['embed','object'])
, dict (name='div',attrs={'id':'art_reactwrap'})
]
remove_tags_after = dict(name='div', attrs={'id':'art_author'})
feeds = [
(u'Volledig nieuwsaanbod', u'http://www.tijd.be/rss/nieuws.xml' )
,(u'Markten' , u'http://www.tijd.be/rss/markten.xml' )
,(u'Ondernemingen' , u'http://www.tijd.be/rss/ondernemingen.xml' )
,(u'Chemie-Farma' , u'http://www.tijd.be/rss/chemie_farma.xml' )
,(u'Consumptie' , u'http://www.tijd.be/rss/consumptie.xml' )
,(u'Diensten' , u'http://www.tijd.be/rss/diensten.xml' )
,(u'Energie' , u'http://www.tijd.be/rss/energie.xml' )
,(u'Financen' , u'http://www.tijd.be/rss/financien.xml' )
,(u'Industrie' , u'http://www.tijd.be/rss/industrie.xml' )
,(u'Media' , u'http://www.tijd.be/rss/media_telecom.xml' )
,(u'Technologie' , u'http://www.tijd.be/rss/technologie.xml' )
,(u'Economie & Financien' , u'http://www.tijd.be/rss/economie.xml' )
,(u'Binnenland' , u'http://www.tijd.be/rss/binnenland.xml' )
,(u'Buitenland' , u'http://www.tijd.be/rss/buitenland.xml' )
,(u'De wijde wereld' , u'http://www.tijd.be/rss/cultuur.xml' )
]
def preprocess_html(self, soup):
del soup.body['onload']
for item in soup.findAll(style=True):
del item['style']
soup.html['lang'] = self.lang
soup.html['dir' ] = self.direction
mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
soup.head.insert(0,mlang)
soup.head.insert(1,mcharset)
return soup