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

Merge from trunk

Browse Source
This commit is contained in:
Charles Haley 2010-10-21 21:11:17 +01:00
commit cda0402d1c
7 changed files with 93 additions and 46 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
resources/images/news/theecocolapse.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 1.2 KiB

13
resources/recipes/el_pais.recipe
View File

@ -2,7 +2,7 @@
__license__ = 'GPL v3'
__author__ = 'Jordi Balcells, based on an earlier version by Lorenzo Vigentini & Kovid Goyal'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
description = 'Main daily newspaper from Spain - v1.03 (03, September 2010)'
description = 'Main daily newspaper from Spain - v1.04 (19, October 2010)'
__docformat__ = 'restructuredtext en'
'''
@ -32,19 +32,16 @@ class ElPais(BasicNewsRecipe):
remove_javascript = True
no_stylesheets = True
keep_only_tags = [ dict(name='div', attrs={'class':['cabecera_noticia','cabecera_noticia_reportaje','cabecera_noticia_opinion','contenido_noticia','caja_despiece','presentacion']})]
keep_only_tags = [ dict(name='div', attrs={'class':['cabecera_noticia_reportaje estirar','cabecera_noticia_opinion estirar','cabecera_noticia estirar','contenido_noticia','caja_despiece']})]
extra_css = '''
p{style:normal size:12 serif}
'''
extra_css = ' p{text-align: justify; font-size: 100%} body{ text-align: left; font-family: serif; font-size: 100% } h1{ font-family: sans-serif; font-size:200%; font-weight: bolder; text-align: justify; } h2{ font-family: sans-serif; font-size:150%; font-weight: 500; text-align: justify } h3{ font-family: sans-serif; font-size:125%; font-weight: 500; text-align: justify } img{margin-bottom: 0.4em} '
remove_tags = [
dict(name='div', attrs={'class':['zona_superior','pie_enlaces_inferiores','contorno_f','ampliar']}),
dict(name='div', attrs={'class':['limpiar','mod_apoyo','borde_sup','votos','info_complementa','info_relacionada','buscador_m','nav_ant_sig']}),
dict(name='div', attrs={'class':['limpiar','mod_apoyo','borde_sup','votos estirar','info_complementa','info_relacionada','buscador_m','nav_ant_sig']}),
dict(name='div', attrs={'id':['suscribirse suscrito','google_noticia','utilidades','coment','foros_not','pie','lomas','calendar']}),
dict(name='p', attrs={'class':'nav_meses'}),
dict(attrs={'class':['enlaces_m','miniaturas_m']})
dict(attrs={'class':['enlaces_m','miniaturas_m','nav_miniaturas_m']})
]
feeds = [

39
resources/recipes/foxnews.recipe
View File

@ -4,7 +4,6 @@ __copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
foxnews.com
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class FoxNews(BasicNewsRecipe):
@ -21,11 +20,10 @@ class FoxNews(BasicNewsRecipe):
language = 'en'
publication_type = 'newsportal'
remove_empty_feeds = True
extra_css = ' body{font-family: Arial,sans-serif } img{margin-bottom: 0.4em} .caption{font-size: x-small} '
preprocess_regexps = [
(re.compile(r'</title>.*?</head>', re.DOTALL|re.IGNORECASE),lambda match: '</title></head>')
]
extra_css = """
body{font-family: Arial,sans-serif }
.caption{font-size: x-small}
"""
conversion_options = {
'comment' : description
@ -34,27 +32,15 @@ class FoxNews(BasicNewsRecipe):
, 'language' : language
}
remove_attributes = ['xmlns']
keep_only_tags = [
dict(name='div', attrs={'id' :['story','browse-story-content']})
,dict(name='div', attrs={'class':['posts articles','slideshow']})
,dict(name='h4' , attrs={'class':'storyDate'})
,dict(name='h1' , attrs={'xmlns:functx':'http://www.functx.com'})
,dict(name='div', attrs={'class':'authInfo'})
,dict(name='div', attrs={'id':'articleCont'})
]
remove_attributes = ['xmlns','lang']
remove_tags = [
dict(name='div', attrs={'class':['share-links','quigo quigo2','share-text','storyControls','socShare','btm-links']})
,dict(name='div', attrs={'id' :['otherMedia','loomia_display','img-all-path','story-vcmId','story-url','pane-browse-story-comments','story_related']})
,dict(name='ul' , attrs={'class':['tools','tools alt','tools alt2','tabs']})
,dict(name='a' , attrs={'class':'join-discussion'})
,dict(name='ul' , attrs={'class':['tools','tools alt','tools alt2']})
,dict(name='p' , attrs={'class':'see_fullarchive'})
,dict(name=['object','embed','link','script'])
dict(name=['object','embed','link','script','iframe','meta','base'])
,dict(attrs={'class':['user-control','url-description','ad-context']})
]
remove_tags_before=dict(name='h1')
remove_tags_after =dict(attrs={'class':'url-description'})
feeds = [
(u'Latest Headlines', u'http://feeds.foxnews.com/foxnews/latest' )
@ -67,8 +53,5 @@ class FoxNews(BasicNewsRecipe):
,(u'Entertainment' , u'http://feeds.foxnews.com/foxnews/entertainment' )
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return self.adeify_images(soup)
def print_version(self, url):
return url + 'print'

27
resources/recipes/new_scientist.recipe
View File

@ -8,11 +8,11 @@ import re
from calibre.web.feeds.news import BasicNewsRecipe
class NewScientist(BasicNewsRecipe):
title = 'New Scientist - Online News'
title = 'New Scientist - Online News w. subscription'
__author__ = 'Darko Miletic'
description = 'Science news and science articles from New Scientist.'
language = 'en'
publisher = 'New Scientist'
publisher = 'Reed Business Information Ltd.'
category = 'science news, science articles, science jobs, drugs, cancer, depression, computer software'
oldest_article = 7
max_articles_per_feed = 100
@ -21,7 +21,12 @@ class NewScientist(BasicNewsRecipe):
cover_url = 'http://www.newscientist.com/currentcover.jpg'
masthead_url = 'http://www.newscientist.com/img/misc/ns_logo.jpg'
encoding = 'utf-8'
extra_css = ' body{font-family: Arial,sans-serif} img{margin-bottom: 0.8em} '
needs_subscription = 'optional'
extra_css = """
body{font-family: Arial,sans-serif}
img{margin-bottom: 0.8em}
.quotebx{font-size: x-large; font-weight: bold; margin-right: 2em; margin-left: 2em}
"""
conversion_options = {
'comment' : description
@ -33,15 +38,27 @@ class NewScientist(BasicNewsRecipe):
keep_only_tags = [dict(name='div', attrs={'id':['pgtop','maincol','blgmaincol','nsblgposts','hldgalcols']})]
def get_browser(self):
br = BasicNewsRecipe.get_browser()
br.open('http://www.newscientist.com/')
if self.username is not None and self.password is not None:
br.open('https://www.newscientist.com/user/login?redirectURL=')
br.select_form(nr=2)
br['loginId' ] = self.username
br['password'] = self.password
br.submit()
return br
remove_tags = [
dict(name='div' , attrs={'class':['hldBd','adline','pnl','infotext' ]})
,dict(name='div' , attrs={'id' :['compnl','artIssueInfo','artTools','comments','blgsocial','sharebtns']})
,dict(name='p' , attrs={'class':['marker','infotext' ]})
,dict(name='meta' , attrs={'name' :'description' })
,dict(name='a' , attrs={'rel' :'tag' })
,dict(name=['link','base','meta','iframe','object','embed'])
]
remove_tags_after = dict(attrs={'class':['nbpcopy','comments']})
remove_attributes = ['height','width']
remove_attributes = ['height','width','lang']
feeds = [
(u'Latest Headlines' , u'http://feeds.newscientist.com/science-news' )
@ -62,6 +79,8 @@ class NewScientist(BasicNewsRecipe):
return url + '?full=true&print=true'
def preprocess_html(self, soup):
for item in soup.findAll(['quote','quotetext']):
item.name='p'
for tg in soup.findAll('a'):
if tg.string == 'Home':
tg.parent.extract()

46
resources/recipes/theecocolapse.recipe Normal file
View File

@ -0,0 +1,46 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
theeconomiccollapseblog.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class TheEconomicCollapse(BasicNewsRecipe):
title = 'The Economic Collapse'
__author__ = 'Darko Miletic'
description = 'Are You Prepared For The Coming Economic Collapse And The Next Great Depression?'
publisher = 'The Economic Collapse'
category = 'news, politics, USA, economy'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
language = 'en'
remove_empty_feeds = True
extra_css = """
body{font-family: Tahoma,Arial,sans-serif }
img{margin-bottom: 0.4em}
"""
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
remove_tags = [
dict(attrs={'class':'sociable'})
,dict(name=['iframe','object','embed','meta','link','base'])
]
remove_attributes=['lang','onclick','width','height']
keep_only_tags=[dict(attrs={'class':['post-headline','post-bodycopy clearfix','']})]
feeds = [(u'Posts', u'http://theeconomiccollapseblog.com/feed')]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return self.adeify_images(soup)

8
resources/recipes/theeconomictimes_india.recipe
View File

@ -21,8 +21,9 @@ class TheEconomicTimes(BasicNewsRecipe):
language = 'en_IN'
publication_type = 'newspaper'
masthead_url = 'http://economictimes.indiatimes.com/photo/2676871.cms'
extra_css = """ body{font-family: Arial,Helvetica,sans-serif}
.heading1{font-size: xx-large; font-weight: bold} """
extra_css = """
body{font-family: Arial,Helvetica,sans-serif}
"""
conversion_options = {
'comment' : description
@ -31,8 +32,9 @@ class TheEconomicTimes(BasicNewsRecipe):
, 'language' : language
}
keep_only_tags = [dict(attrs={'class':['heading1','headingnext','Normal']})]
keep_only_tags = [dict(attrs={'class':'printdiv'})]
remove_tags = [dict(name=['object','link','embed','iframe','base','table','meta'])]
remove_attributes = ['name']
feeds = [(u'All articles', u'http://economictimes.indiatimes.com/rssfeedsdefault.cms')]

4
src/calibre/library/database2.py
View File

@ -748,10 +748,10 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
return False
def find_identical_books(self, mi):
fuzzy_title_patterns = [(re.compile(pat), repl) for pat, repl in
fuzzy_title_patterns = [(re.compile(pat, re.IGNORECASE), repl) for pat, repl in
[
(r'[\[\](){}<>\'";,:#]', ''),
(r'^(the|a|an) ', ''),
(tweaks.get('title_sort_articles', r'^(a|the|an)\s+'), ''),
(r'[-._]', ' '),
(r'\s+', ' ')
]