Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 18:24:30 -04:00
Code Issues Packages Projects Releases Wiki Activity

Pull from trunk

Browse Source
This commit is contained in:
Kovid Goyal 2010-09-30 09:56:56 -06:00
commit 0c794fdbed
13 changed files with 252 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
resources/recipes/ajc.recipe
View File

@ -16,6 +16,7 @@ class AdvancedUserRecipe1282101454(BasicNewsRecipe):
title = 'The AJC'
timefmt = ' [%a,%d %B %Y %I:%M %p]'
__author__ = 'TonytheBookworm'
language = 'en'
description = 'News from Atlanta and USA'
publisher = 'The Atlanta Journal'
category = 'news, politics, USA'

2
resources/recipes/china_economic_net.recipe
View File

@ -26,7 +26,7 @@ class AdvancedUserRecipe1278162597(BasicNewsRecipe):
remove_javascript = True
use_embedded_content = False
no_stylesheets = True
language = 'zh-cn'
language = 'zh_CN'
encoding = 'gb2312'
conversion_options = {'linearize_tables':True}

40
resources/recipes/cinebel_be.recipe Normal file
View File

@ -0,0 +1,40 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Lionel Bergeret <lbergeret at gmail.com>'
'''
cinebel.be
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Cinebel(BasicNewsRecipe):
title = u'Cinebel'
__author__ = u'Lionel Bergeret'
description = u'Cinema news from Belgium in French'
publisher = u'cinebel.be'
category = 'news, cinema, movie, Belgium'
oldest_article = 3
encoding = 'utf8'
language = 'fr_BE'
max_articles_per_feed = 20
no_stylesheets = True
use_embedded_content = False
timefmt = ' [%d %b %Y]'
keep_only_tags = [
dict(name = 'span', attrs = {'class': 'movieMainTitle'})
,dict(name = 'div', attrs = {'id': 'filmPoster'})
,dict(name = 'div', attrs = {'id': 'filmDefinition'})
,dict(name = 'div', attrs = {'id': 'synopsis'})
]
feeds = [
(u'Les sorties de la semaine' , u'http://www.cinebel.be/Servlets/RssServlet?languageCode=fr&rssType=0' )
,(u'Top 10' , u'http://www.cinebel.be/Servlets/RssServlet?languageCode=fr&rssType=2' )
]
def get_cover_url(self):
cover_url = 'http://www.cinebel.be/portal/resources/common/logo_index.gif'
return cover_url

11
resources/recipes/dhnet_be.recipe
View File

@ -6,6 +6,7 @@ __copyright__ = '2008, Lionel Bergeret <lbergeret at gmail.com>'
dhnet.be
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class DHNetBe(BasicNewsRecipe):
@ -15,7 +16,7 @@ class DHNetBe(BasicNewsRecipe):
publisher = u'dhnet.be'
category = 'news, Belgium'
oldest_article = 3
language = 'fr'
language = 'fr_BE'
max_articles_per_feed = 20
no_stylesheets = True
@ -29,6 +30,10 @@ class DHNetBe(BasicNewsRecipe):
feeds = [
(u'La Une' , u'http://www.dhnet.be/rss' )
,(u'La Une Sports' , u'http://www.dhnet.be/rss/dhsports/' )
,(u'La Une Info' , u'http://www.dhnet.be/rss/dhinfos/' )
,(u'La Une Sports' , u'http://www.dhnet.be/rss/dhsports/' )
,(u'La Une Info' , u'http://www.dhnet.be/rss/dhinfos/' )
]
def get_cover_url(self):
cover_url = strftime('http://pdf-online.dhnet.be/pdfonline/image/%Y%m%d/dh_%Y%m%d_nam_infoge_001.pdf.L.jpg')
return cover_url

1
resources/recipes/journalgazette.recipe
View File

@ -11,6 +11,7 @@ class AdvancedUserRecipe1283666183(BasicNewsRecipe):
title = u'Journal Gazette Ft. Wayne IN'
__author__ = 'cynvision'
oldest_article = 1
language = 'en'
max_articles_per_feed = 8
no_stylesheets = True
remove_javascript = True

43
resources/recipes/lalibre_be.recipe Normal file
View File

@ -0,0 +1,43 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Lionel Bergeret <lbergeret at gmail.com>'
'''
lalibre.be
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class LaLibre(BasicNewsRecipe):
title = u'La Libre Belgique'
__author__ = u'Lionel Bergeret'
description = u'News from Belgium in French'
publisher = u'lalibre.be'
category = 'news, Belgium'
oldest_article = 3
language = 'fr_BE'
max_articles_per_feed = 20
no_stylesheets = True
use_embedded_content = False
timefmt = ' [%d %b %Y]'
keep_only_tags = [
dict(name = 'div', attrs = {'id': 'articleHat'})
,dict(name = 'p', attrs = {'id': 'publicationDate'})
,dict(name = 'div', attrs = {'id': 'articleText'})
]
feeds = [
(u'L\'actu' , u'http://www.lalibre.be/rss/?section=10' )
,(u'Culture' , u'http://www.lalibre.be/rss/?section=5' )
,(u'Economie' , u'http://www.lalibre.be/rss/?section=3' )
,(u'Libre Entreprise' , u'http://www.lalibre.be/rss/?section=904' )
,(u'Sports' , u'http://www.lalibre.be/rss/?section=2' )
,(u'Societe' , u'http://www.lalibre.be/rss/?section=12' )
]
def get_cover_url(self):
cover_url = strftime('http://pdf-online.lalibre.be/pdfonline/image/%Y%m%d/llb_%Y%m%d_nam_libre_001.pdf.L.jpg')
return cover_url

54
resources/recipes/lameuse_be.recipe Normal file
View File

@ -0,0 +1,54 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Lionel Bergeret <lbergeret at gmail.com>'
'''
lameuse.be
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class LaMeuse(BasicNewsRecipe):
title = u'La Meuse'
__author__ = u'Lionel Bergeret'
description = u'News from Belgium in French'
publisher = u'lameuse.be'
category = 'news, Belgium'
oldest_article = 3
encoding = 'utf8'
language = 'fr_BE'
max_articles_per_feed = 20
no_stylesheets = True
use_embedded_content = False
timefmt = ' [%d %b %Y]'
keep_only_tags = [
dict(name = 'div', attrs = {'id': 'article'})
]
remove_tags = [
dict(name = 'div', attrs = {'class': 'sb-group'})
,dict(name = 'div', attrs = {'id': 'share'})
,dict(name = 'div', attrs = {'id': 'commentaires'})
]
feeds = [
(u'Actualite', u'http://www.lameuse.be/services/fils_rss/actualite/index.xml' )
,(u'Belgique', u'http://www.lameuse.be/services/fils_rss/actualite/belgique/index.xml' )
,(u'Monde', u'http://www.lameuse.be/services/fils_rss/actualite/monde/index.xml' )
,(u'Societe', u'http://www.lameuse.be/services/fils_rss/actualite/societe/index.xml' )
,(u'Faits Divers', u'http://www.lameuse.be/services/fils_rss/actualite/faits_divers/index.xml' )
,(u'Economie', u'http://www.lameuse.be/services/fils_rss/actualite/economie/index.xml' )
,(u'Science', u'http://www.lameuse.be/services/fils_rss/actualite/science/index.xml' )
,(u'Sante', u'http://www.lameuse.be/services/fils_rss/actualite/sante/index.xml' )
,(u'Insolite', u'http://www.lameuse.be/services/fils_rss/magazine/insolite/index.xml' )
,(u'Cinema', u'http://www.lameuse.be/services/fils_rss/culture/cinema/index.xml' )
,(u'Musique', u'http://www.lameuse.be/services/fils_rss/culture/musique/index.xml' )
,(u'Livres', u'http://www.lameuse.be/services/fils_rss/culture/livres/index.xml' )
]
def get_cover_url(self):
cover_url = strftime('http://pdf.lameuse.be/pdf/lameuse_%Y-%m-%d_LIEG_ACTUALITE_1.PDF')
return cover_url

40
resources/recipes/lavenir_be.recipe Normal file
View File

@ -0,0 +1,40 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Lionel Bergeret <lbergeret at gmail.com>'
'''
lavenir.net
'''
from calibre.web.feeds.news import BasicNewsRecipe
class LAvenir(BasicNewsRecipe):
title = u'L\'Avenir'
__author__ = u'Lionel Bergeret'
description = u'News from Belgium in French'
publisher = u'lavenir.net'
category = 'news, Belgium'
oldest_article = 3
encoding = 'utf8'
language = 'fr_BE'
max_articles_per_feed = 20
no_stylesheets = True
use_embedded_content = False
timefmt = ' [%d %b %Y]'
keep_only_tags = [
dict(name = 'div', attrs = {'class': 'photo'})
,dict(name = 'p', attrs = {'class': 'intro'})
,dict(name = 'div', attrs = {'class': 'article-body'})
]
feeds = [
(u'Belgique' , u'http://www.lavenir.net/rss.aspx?foto=1&intro=1&section=info&info=df156511-c24f-4f21-81c3-a5d439a9cf4b' )
,(u'Monde' , u'http://www.lavenir.net/rss.aspx?foto=1&intro=1&section=info&info=1642237c-66b9-4e8a-a8c1-288d61fefe7e' )
,(u'Societe' , u'http://www.lavenir.net/rss.aspx?foto=1&intro=1&section=info&info=12e1a2f4-7e03-4cf1-afec-016869072317' )
]
def get_cover_url(self):
cover_url = 'http://www.lavenir.net/extra/Static/journal/Pdf/1/UNE_Nationale.PDF'
return cover_url

17
resources/recipes/lesoir_be.recipe
View File

@ -6,6 +6,7 @@ __copyright__ = '2008, Lionel Bergeret <lbergeret at gmail.com>'
lesoir.be
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class LeSoirBe(BasicNewsRecipe):
@ -15,7 +16,7 @@ class LeSoirBe(BasicNewsRecipe):
publisher = u'lesoir.be'
category = 'news, Belgium'
oldest_article = 3
language = 'fr'
language = 'fr_BE'
max_articles_per_feed = 20
no_stylesheets = True
@ -35,9 +36,13 @@ class LeSoirBe(BasicNewsRecipe):
feeds = [
(u'Belgique' , u'http://www.lesoir.be/actualite/belgique/rss.xml' )
,(u'France' , u'http://www.lesoir.be/actualite/france/rss.xml' )
,(u'Monde' , u'http://www.lesoir.be/actualite/monde/rss.xml' )
,(u'Regions' , u'http://www.lesoir.be/regions/rss.xml' )
,(u'Vie du Net' , u'http://www.lesoir.be/actualite/vie_du_net/rss.xml' )
,(u'Petite Gazette' , u'http://www.lesoir.be/actualite/sciences/rss.xml' )
,(u'France' , u'http://www.lesoir.be/actualite/france/rss.xml' )
,(u'Monde' , u'http://www.lesoir.be/actualite/monde/rss.xml' )
,(u'Regions' , u'http://www.lesoir.be/regions/rss.xml' )
,(u'Vie du Net' , u'http://www.lesoir.be/actualite/vie_du_net/rss.xml' )
,(u'Petite Gazette' , u'http://www.lesoir.be/actualite/sciences/rss.xml' )
]
def get_cover_url(self):
cover_url = strftime( 'http://pdf.lesoir.be/pdf/%Y-%m-%d_BRUX_UNE_1.PDF')
return cover_url

1
resources/recipes/onionavclub.recipe
View File

@ -12,6 +12,7 @@ class BBC(BasicNewsRecipe):
title = u'The Onion AV Club'
__author__ = 'Stephen Williams'
description = 'Film, Television and Music Reviews'
language = 'en'
no_stylesheets = True
oldest_article = 2
max_articles_per_feed = 100

50
resources/recipes/oriental_daily.recipe Normal file
View File

@ -0,0 +1,50 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Larry Chan <larry1chan at gmail.com>'
'''
oriental daily
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
class OrientalDaily(BasicNewsRecipe):
title = 'Oriental Dailly'
__author__ = 'Larry Chan'
description = 'News from HK'
oldest_article = 2
max_articles_per_feed = 100
simultaneous_downloads = 5
no_stylesheets = True
#delay = 1
use_embedded_content = False
encoding = 'utf8'
publisher = 'Oriental Daily'
category = 'news, HK, world'
language = 'zh'
publication_type = 'newsportal'
extra_css = ' body{ font-family: Verdana,Helvetica,Arial,sans-serif } .introduction{font-weight: bold} .story-feature{display: block; padding: 0; border: 1px solid; width: 40%; font-size: small} .story-feature h2{text-align: center; text-transform: uppercase} '
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
,'linearize_tables': True
}
remove_tags_after = dict(id='bottomNavCTN')
keep_only_tags = [
dict(name='div', attrs={'id':['leadin', 'contentCTN-right']})
]
remove_tags = [
dict(name='div', attrs={'class':['largeAdsCTN', 'contentCTN-left', 'textAdsCTN', 'footerAds clear']}),
dict(name='div', attrs={'id':['articleNav']})
]
remove_attributes = ['width','height','href']
feeds = [(u'Oriental Daily', u'http://orientaldaily.on.cc/rss/news.xml')]

1
resources/recipes/technology_review.recipe
View File

@ -7,6 +7,7 @@ class TechnologyReview(BasicNewsRecipe):
description = 'MIT Technology Magazine'
publisher = 'Technology Review Inc.'
category = 'Technology, Innovation, R&D'
language = 'en'
oldest_article = 14
max_articles_per_feed = 100
No_stylesheets = True

1
src/calibre/utils/localization.py
View File

@ -112,6 +112,7 @@ _extra_lang_codes = {
'en_CN' : _('English (China)'),
'es_PY' : _('Spanish (Paraguay)'),
'de_AT' : _('German (AT)'),
'fr_BE' : _('French (BE)'),
'nl' : _('Dutch (NL)'),
'nl_BE' : _('Dutch (BE)'),
'und' : _('Unknown')