{% if not embedded %}
diff --git a/manual/virtual_libraries.rst b/manual/virtual_libraries.rst index f695bb0e45..9432bb04ef 100644 --- a/manual/virtual_libraries.rst +++ b/manual/virtual_libraries.rst @@ -94,6 +94,13 @@ You can quickly use the current search as a temporary virtual library by clicking the :guilabel:`Virtual Library` button and choosing the :guilabel:`*current search` entry. +You can display all available virtual libraries as tabs above the book list. +This is particularly handy if you like switching between virtual libraries very +often. Click the :guilabel:`Virtual Library` button and select :guilabel:`Show +virtual libraries as tabs`. You can re-arrange the tabs by drag and drop and +close ones you do not want to see. Closed tabs can be restored by +right-clicking on the tab bar. + Using additional restrictions ------------------------------- diff --git a/recipes/10minutos.recipe b/recipes/10minutos.recipe new file mode 100644 index 0000000000..4c2f8a7ec7 --- /dev/null +++ b/recipes/10minutos.recipe @@ -0,0 +1,50 @@ +#!/usr/bin/env python + +__license__ = 'GPL v3' +__author__ = '2013, Carlos Alves'
+'''
+10minutos.com.uy
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class General(BasicNewsRecipe):
+ title = '10minutos'
+ __author__ = 'Carlos Alves'
+ description = 'Noticias de Salto - Uruguay'
+ tags = 'news, sports'
+ language = 'es_UY'
+ timefmt = '[%a, %d %b, %Y]'
+ use_embedded_content = False
+ recursion = 5
+ encoding = 'utf8'
+ remove_javascript = True
+ no_stylesheets = True
+
+ oldest_article = 2
+ max_articles_per_feed = 100
+ keep_only_tags = [dict(name='div', attrs={'class':'post-content'})]
+
+ remove_tags = [
+ dict(name='div', attrs={'class':['hr', 'titlebar', 'navigation']}),
+ dict(name='p', attrs={'class':'post-meta'}),
+ dict(name=['object','link'])
+ ]
+
+ extra_css = '''
+ h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
+ h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
+ h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
+ p {font-family:Arial,Helvetica,sans-serif;}
+ '''
+ feeds = [
+ (u'Articulos', u'http://10minutos.com.uy/feed/')
+ ]
+
+ def get_cover_url(self):
+ return 'http://10minutos.com.uy/a/img/logo.png'
+
+ def preprocess_html(self, soup):
+ for item in soup.findAll(style=True):
+ del item['style']
+ return soup
diff --git a/recipes/acrimed.recipe b/recipes/acrimed.recipe
new file mode 100644
index 0000000000..acd98a063a
--- /dev/null
+++ b/recipes/acrimed.recipe
@@ -0,0 +1,30 @@
+# vim:fileencoding=utf-8
+from __future__ import unicode_literals
+
+__license__ = 'GPL v3'
+__copyright__ = '2012'
+'''
+acrimed.org
+'''
+
+import re
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Acrimed(BasicNewsRecipe):
+ title = u'Acrimed'
+ __author__ = 'Gaëtan Lehmann'
+ oldest_article = 30
+ max_articles_per_feed = 100
+ auto_cleanup = True
+ auto_cleanup_keep = '//div[@class="crayon article-chapo-4112 chapo"]'
+ language = 'fr'
+ masthead_url = 'http://www.acrimed.org/IMG/siteon0.gif'
+ feeds = [(u'Acrimed', u'http://www.acrimed.org/spip.php?page=backend')]
+
+ preprocess_regexps = [
+ (re.compile(r'(.*) - Acrimed \| Action Critique M.*dias '), lambda m: '' + m.group(1) + ' '),
+ (re.compile(r' tag contains article content
- nextPageContent = nextPageSoup.findAll('section')[7]
+ nextPageContent = nextPageSoup.findAll('article')[0]
newPosition = len(nextPageContent.contents)
- self.appendPage(nextPageSoup,nextPageContent,newPosition)
+ self.appendPage(nextPageSoup, nextPageContent, newPosition)
nextPageContent.extract()
pageNav.extract()
- appendTag.insert(position,nextPageContent)
+ appendTag.insert(position, nextPageContent)
def preprocess_html(self, soup):
self.appendPage(soup, soup.body, 3)
return soup
+
diff --git a/recipes/daily_express.recipe b/recipes/daily_express.recipe
new file mode 100644
index 0000000000..dc55d3f0b8
--- /dev/null
+++ b/recipes/daily_express.recipe
@@ -0,0 +1,88 @@
+import re
+from calibre.web.feeds.news import BasicNewsRecipe
+class AdvancedUserRecipe1376229553(BasicNewsRecipe):
+ title = u'Daily Express'
+ __author__ = 'Dave Asbury'
+ # 9-9-13 added article author and now use (re.compile(r'>[\w].+? News<'
+ encoding = 'utf-8'
+ remove_empty_feeds = True
+ #remove_javascript = True
+ no_stylesheets = True
+ oldest_article = 1
+ max_articles_per_feed = 10
+ #auto_cleanup = True
+ compress_news_images = True
+ compress_news_images_max_size = 30
+ ignore_duplicate_articles = {'title', 'url'}
+ masthead_url = 'http://cdn.images.dailyexpress.co.uk/img/page/express_logo.png'
+
+ preprocess_regexps = [
+
+ (re.compile(r'widget', re.IGNORECASE | re.DOTALL), lambda match: ''),
+ (re.compile(r'Related articles', re.IGNORECASE | re.DOTALL), lambda match: ''),
+ (re.compile(r'Add Your Comment<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
+ (re.compile(r'>More [\w].+?<', re.IGNORECASE), lambda match: '><'),
+ (re.compile(r'>[\w].+? News<', re.IGNORECASE), lambda match: '><'),
+ #(re.compile(r'Health News<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
+ #(re.compile(r'Car News<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
+ #(re.compile(r'TV & Radio News<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
+ #(re.compile(r'Food & Recipe News<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
+ #(re.compile(r'More City & Business<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
+ #(re.compile(r'Travel News<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
+ #(re.compile(r'Garden News<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
+ #(re.compile(r'Fashion & Beauty News<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
+ #(re.compile(r'More Personal Finance<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
+ #(re.compile(r''
+__copyright__ = '2009-2013, Darko Miletic '
'''
-elargentino.com
+diagonales.infonews.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
-from calibre.ebooks.BeautifulSoup import Tag
class Diagonales(BasicNewsRecipe):
title = 'Diagonales'
__author__ = 'Darko Miletic'
- description = 'El nuevo diario de La Plata'
- publisher = 'ElArgentino.com'
+ description = 'Para estar bien informado sobre los temas de actualidad. Conoce sobre pais, economia, deportes, mundo, espectaculos, sociedad, entrevistas y tecnologia.'
+ publisher = 'INFOFIN S.A.'
category = 'news, politics, Argentina, La Plata'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
- language = 'es_AR'
-
- lang = 'es-AR'
- direction = 'ltr'
- INDEX = 'http://www.elargentino.com/medios/122/Diagonales.html'
+ language = 'es_AR'
+ publication_type = 'newspaper'
+ delay = 1
+ remove_empty_feeds = True
extra_css = ' .titulo{font-size: x-large; font-weight: bold} .volantaImp{font-size: small; font-weight: bold} '
- 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} "'
+ conversion_options = {
+ 'comment' : description
+ , 'tags' : category
+ , 'publisher' : publisher
+ , 'language' : language
+ }
keep_only_tags = [dict(name='div', attrs={'class':'ContainerPop'})]
+ remove_tags = [dict(name='link')]
- remove_tags = [dict(name='link')]
-
- feeds = [(u'Articulos', u'http://www.elargentino.com/Highlights.aspx?ParentType=Section&ParentId=122&Content-Type=text/xml&ChannelDesc=Diagonales')]
+ feeds = [
+ (u'Pais' , u'http://diagonales.infonews.com/Highlights.aspx?ParentType=Section&ParentId=112&Content-Type=text/xml&ChannelDesc=Pa%C3%ADs')
+ ,(u'Deportes' , u'http://diagonales.infonews.com/Highlights.aspx?ParentType=Section&ParentId=106&Content-Type=text/xml&ChannelDesc=Deportes')
+ ,(u'Economia' , u'http://diagonales.infonews.com/Highlights.aspx?ParentType=Section&ParentId=107&Content-Type=text/xml&ChannelDesc=Econom%C3%ADa')
+ ,(u'Sociedad' , u'http://diagonales.infonews.com/Highlights.aspx?ParentType=Section&ParentId=109&Content-Type=text/xml&ChannelDesc=Sociedad')
+ ,(u'Mundo' , u'http://diagonales.infonews.com/Highlights.aspx?ParentType=Section&ParentId=113&Content-Type=text/xml&ChannelDesc=Mundo')
+ ,(u'Espectaculos', u'http://diagonales.infonews.com/Highlights.aspx?ParentType=Section&ParentId=114&Content-Type=text/xml&ChannelDesc=Espect%C3%A1culos')
+ ,(u'Entrevistas' , u'http://diagonales.infonews.com/Highlights.aspx?ParentType=Section&ParentId=115&Content-Type=text/xml&ChannelDesc=Entrevistas')
+ ,(u'Tecnologia' , u'http://diagonales.infonews.com/Highlights.aspx?ParentType=Section&ParentId=118&Content-Type=text/xml&ChannelDesc=Tecnolog%C3%ADa')
+ ]
def print_version(self, url):
main, sep, article_part = url.partition('/nota-')
article_id, rsep, rrest = article_part.partition('-')
- return u'http://www.elargentino.com/Impresion.aspx?Id=' + article_id
-
- def preprocess_html(self, soup):
- 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
-
- def get_cover_url(self):
- cover_url = None
- soup = self.index_to_soup(self.INDEX)
- cover_item = soup.find('div',attrs={'class':'colder'})
- if cover_item:
- clean_url = self.image_url_processor(None,cover_item.div.img['src'])
- cover_url = 'http://www.elargentino.com' + clean_url + '&height=600'
- return cover_url
-
- def image_url_processor(self, baseurl, url):
- base, sep, rest = url.rpartition('?Id=')
- img, sep2, rrest = rest.partition('&')
- return base + sep + img
+ return u'http://diagonales.infonews.com/Impresion.aspx?Id=' + article_id
diff --git a/recipes/diario_el_pueblo.recipe b/recipes/diario_el_pueblo.recipe
new file mode 100644
index 0000000000..4cfab9eb32
--- /dev/null
+++ b/recipes/diario_el_pueblo.recipe
@@ -0,0 +1,51 @@
+#!/usr/bin/env python
+
+__license__ = 'GPL v3'
+__author__ = '2013, Carlos Alves '
+'''
+diarioelpueblo.com.uy
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class General(BasicNewsRecipe):
+ title = 'Diario El Pueblo'
+ __author__ = 'Carlos Alves'
+ description = 'Noticias de Salto - Uruguay'
+ tags = 'news, sports'
+ language = 'es_UY'
+ timefmt = '[%a, %d %b, %Y]'
+ use_embedded_content = False
+ recursion = 5
+ encoding = 'utf8'
+ remove_javascript = True
+ no_stylesheets = True
+
+ oldest_article = 2
+ max_articles_per_feed = 100
+ keep_only_tags = [dict(name='div', attrs={'class':'post-alt blog'})]
+
+ remove_tags = [
+ dict(name='div', attrs={'class':['hr', 'titlebar', 'volver-arriba-right','navigation']}),
+ dict(name='div', attrs={'id':'comment','id':'suckerfish','id':'crp_related'}),
+ dict(name='h3', attrs={'class':['post_date']}),
+ dict(name=['object','link'])
+ ]
+
+ extra_css = '''
+ h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
+ h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
+ h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
+ p {font-family:Arial,Helvetica,sans-serif;}
+ '''
+ feeds = [
+ (u'Articulos', u'http://www.diarioelpueblo.com.uy/feed')
+ ]
+
+ def get_cover_url(self):
+ return 'http://www.diarioelpueblo.com.uy/wp-content/uploads/2013/06/Cabezal_Web1.jpg'
+
+ def preprocess_html(self, soup):
+ for item in soup.findAll(style=True):
+ del item['style']
+ return soup
diff --git a/recipes/diario_salto.recipe b/recipes/diario_salto.recipe
new file mode 100644
index 0000000000..799233db4d
--- /dev/null
+++ b/recipes/diario_salto.recipe
@@ -0,0 +1,50 @@
+#!/usr/bin/env python
+
+__license__ = 'GPL v3'
+__author__ = '2013, Carlos Alves '
+'''
+diarisalto.com.uy
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class General(BasicNewsRecipe):
+ title = 'Diario Salto'
+ __author__ = 'Carlos Alves'
+ description = 'Noticias de Salto - Uruguay'
+ tags = 'news, sports'
+ language = 'es_UY'
+ timefmt = '[%a, %d %b, %Y]'
+ use_embedded_content = False
+ recursion = 5
+ encoding = 'utf8'
+ remove_javascript = True
+ no_stylesheets = True
+
+ oldest_article = 2
+ max_articles_per_feed = 100
+ keep_only_tags = [dict(name='div', attrs={'class':'post'})]
+
+ remove_tags = [
+ dict(name='div', attrs={'class':['hr', 'titlebar', 'navigation']}),
+ dict(name='div', attrs={'id':'comment'}),
+ dict(name=['object','link'])
+ ]
+
+ extra_css = '''
+ h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
+ h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
+ h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
+ p {font-family:Arial,Helvetica,sans-serif;}
+ '''
+ feeds = [
+ (u'Articulos', u'http://www.diariosalto.com.uy/feed/atom')
+ ]
+
+ def get_cover_url(self):
+ return 'http://diariosalto.com.uy/demo/wp-content/uploads/2011/12/diario-salto_logo-final-b-b.png'
+
+ def preprocess_html(self, soup):
+ for item in soup.findAll(style=True):
+ del item['style']
+ return soup
diff --git a/recipes/dilbert.recipe b/recipes/dilbert.recipe
index ed2771debf..e98c9212a9 100644
--- a/recipes/dilbert.recipe
+++ b/recipes/dilbert.recipe
@@ -6,6 +6,7 @@ DrMerry added cover Image 2011-11-12
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import BeautifulSoup
import re
class DilbertBig(BasicNewsRecipe):
@@ -16,7 +17,7 @@ class DilbertBig(BasicNewsRecipe):
oldest_article = 15
max_articles_per_feed = 100
no_stylesheets = True
- use_embedded_content = True
+ use_embedded_content = False
encoding = 'utf-8'
publisher = 'UNITED FEATURE SYNDICATE, INC.'
category = 'comic'
@@ -30,25 +31,14 @@ class DilbertBig(BasicNewsRecipe):
,'publisher' : publisher
}
- feeds = [(u'Dilbert', u'http://feed.dilbert.com/dilbert/daily_strip' )]
-
- def get_article_url(self, article):
- return article.get('feedburner_origlink', None)
+ feeds = [(u'Dilbert', u'http://feed.dilbert.com/dilbert/daily_strip')]
preprocess_regexps = [
(re.compile('strip\..*\.gif', re.DOTALL|re.IGNORECASE), lambda match: 'strip.zoom.gif')
]
def preprocess_html(self, soup):
- for tag in soup.findAll(name='a'):
- if tag['href'].find('http://feedads') >= 0:
- tag.extract()
- return soup
+ for tag in soup.findAll(name='input'):
+ image = BeautifulSoup('
')
+ return image
- extra_css = '''
- h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
- h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
- img {max-width:100%; min-width:100%;}
- p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
- body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
- '''
diff --git a/recipes/dilemaveche.recipe b/recipes/dilemaveche.recipe
index 72920600f7..33e9a263b0 100644
--- a/recipes/dilemaveche.recipe
+++ b/recipes/dilemaveche.recipe
@@ -6,46 +6,87 @@ __copyright__ = u'2011, Silviu Cotoar\u0103'
'''
dilemaveche.ro
'''
-
from calibre.web.feeds.news import BasicNewsRecipe
class DilemaVeche(BasicNewsRecipe):
- title = u'Dilema Veche'
- __author__ = u'Silviu Cotoar\u0103'
- description = 'Sint vechi, domnule! (I.L. Caragiale)'
- publisher = u'Adev\u0103rul Holding'
- oldest_article = 5
- language = 'ro'
- max_articles_per_feed = 100
- no_stylesheets = True
- use_embedded_content = False
- category = 'Ziare'
- encoding = 'utf-8'
- cover_url = 'http://dilemaveche.ro/sites/all/themes/dilema/theme/dilema_two/layouter/dilema_two_homepage/logo.png'
-
- conversion_options = {
- 'comments' : description
- ,'tags' : category
- ,'language' : language
- ,'publisher' : publisher
- }
-
- keep_only_tags = [
- dict(name='div', attrs={'class':'c_left_column'})
- ]
-
- remove_tags = [
- dict(name='div', attrs={'id':['adshop_widget_428x60']}) ,
- dict(name='div', attrs={'id':['gallery']})
- ]
-
- remove_tags_after = [
- dict(name='div', attrs={'id':['adshop_widget_428x60']})
- ]
-
- feeds = [
- (u'Feeds', u'http://dilemaveche.ro/rss.xml')
+ # apare vinerea, mai pe dupa-masa,depinde de Luiza cred (care se semneaza ca fiind creatorul fiecarui articol in feed-ul RSS)
+ title = u'Dilema Veche'
+ __author__ = 'song2' # inspirat din scriptul pentru Le Monde. Inspired from the Le Monde script
+ description = '"Sint vechi, domnule!" (I.L. Caragiale)'
+ publisher = 'Adevarul Holding'
+ oldest_article = 7
+ max_articles_per_feed = 200
+ encoding = 'utf8'
+ language = 'ro'
+ masthead_url = 'http://www.dilemaveche.ro/sites/all/themes/dilema/theme/dilema_two/layouter/dilema_two_homepage/logo.png'
+ publication_type = 'magazine'
+ feeds = [
+ ('Editoriale si opinii - Situatiunea', 'http://www.dilemaveche.ro/taxonomy/term/37/0/feed'),
+ ('Editoriale si opinii - Pe ce lume traim', 'http://www.dilemaveche.ro/taxonomy/term/38/0/feed'),
+ ('Editoriale si opinii - Bordeie si obiceie', 'http://www.dilemaveche.ro/taxonomy/term/44/0/feed'),
+ ('Editoriale si opinii - Talc Show', 'http://www.dilemaveche.ro/taxonomy/term/44/0/feed'),
+ ('Tema saptamanii', 'http://www.dilemaveche.ro/taxonomy/term/19/0/feed'),
+ ('La zi in cultura - Dilema va recomanda', 'http://www.dilemaveche.ro/taxonomy/term/58/0/feed'),
+ ('La zi in cultura - Carte', 'http://www.dilemaveche.ro/taxonomy/term/14/0/feed'),
+ ('La zi in cultura - Film', 'http://www.dilemaveche.ro/taxonomy/term/13/0/feed'),
+ ('La zi in cultura - Muzica', 'http://www.dilemaveche.ro/taxonomy/term/1341/0/feed'),
+ ('La zi in cultura - Arte performative', 'http://www.dilemaveche.ro/taxonomy/term/1342/0/feed'),
+ ('La zi in cultura - Arte vizuale', 'http://www.dilemaveche.ro/taxonomy/term/1512/0/feed'),
+ ('Societate - Ieri cu vedere spre azi', 'http://www.dilemaveche.ro/taxonomy/term/15/0/feed'),
+ ('Societate - Din polul opus', 'http://www.dilemaveche.ro/taxonomy/term/41/0/feed'),
+ ('Societate - Mass comedia', 'http://www.dilemaveche.ro/taxonomy/term/43/0/feed'),
+ ('Societate - La singular si la plural', 'http://www.dilemaveche.ro/taxonomy/term/42/0/feed'),
+ ('Oameni si idei - Educatie', 'http://www.dilemaveche.ro/taxonomy/term/46/0/feed'),
+ ('Oameni si idei - Polemici si dezbateri', 'http://www.dilemaveche.ro/taxonomy/term/48/0/feed'),
+ ('Oameni si idei - Stiinta si tehnologie', 'http://www.dilemaveche.ro/taxonomy/term/46/0/feed'),
+ ('Dileme on-line', 'http://www.dilemaveche.ro/taxonomy/term/005/0/feed')
]
+ remove_tags_before = dict(name='div',attrs={'class':'spacer_10'})
+ remove_tags = [
+ dict(name='div', attrs={'class':'art_related_left'}),
+ dict(name='div', attrs={'class':'controale'}),
+ dict(name='div', attrs={'class':'simple_overlay'}),
+ ]
+ remove_tags_after = [dict(id='facebookLike')]
+ remove_javascript = True
+ no_stylesheets = True
+ remove_empty_feeds = True
+ extra_css = """
+ body{font-family: Georgia,Times,serif }
+ img{margin-bottom: 0.4em; display:block}
+ """
+ needs_subscription = 'optional'
+ cover_margins = (10, 15, '#ffffff')
+
+ def get_browser(self):
+ br = BasicNewsRecipe.get_browser(self)
+ if self.username is not None and self.password is not None:
+ br.open('http://dilemaveche.ro/user/login')
+ br.select_form(nr=0)
+ br['username'] = self.username
+ br['password'] = self.password
+ br.submit()
+ return br
+
+ def get_cover_url(self):
+ cover_url = None
+ soup = self.index_to_soup('http://dilemaveche.ro')
+ link_item = soup.find('div',attrs={'class':'box_dr_pdf_picture'})
+ if link_item and link_item.a:
+ cover_url = link_item.a['href']
+ br = BasicNewsRecipe.get_browser()
+ try:
+ br.open(cover_url)
+ except: # daca nu gaseste pdf-ul
+ self.log("\nPDF indisponibil")
+ link_item = soup.find('div',attrs={'class':'box_dr_pdf_picture'})
+ if link_item and link_item.img:
+ cover_url = link_item.img['src']
+ br = BasicNewsRecipe.get_browser()
+ try:
+ br.open(cover_url)
+ except: # daca nu gaseste nici imaginea mica mica
+ print('Mama lor de nenorociti! nu este nici pdf nici imagine')
+ cover_url ='http://www.dilemaveche.ro/sites/all/themes/dilema/theme/dilema_two/layouter/dilema_two_homepage/logo.png'
+ return cover_url
- def preprocess_html(self, soup):
- return self.adeify_images(soup)
diff --git a/recipes/dot_net.recipe b/recipes/dot_net.recipe
index 6b39b8c97e..33c53d4757 100644
--- a/recipes/dot_net.recipe
+++ b/recipes/dot_net.recipe
@@ -11,30 +11,31 @@ class dotnetMagazine (BasicNewsRecipe):
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
+ auto_cleanup = True
# recursion = 1
language = 'en'
remove_empty_feeds = True
extra_css = ' body{font-family: Arial,Helvetica,sans-serif } img{margin-bottom: 0.4em} '
cover_url = u'http://media.netmagazine.futurecdn.net/sites/all/themes/netmag/logo.png'
- remove_tags_after = dict(name='footer', id=lambda x:not x)
- remove_tags_before = dict(name='header', id=lambda x:not x)
+ #remove_tags_after = dict(name='footer', id=lambda x:not x)
+ #remove_tags_before = dict(name='header', id=lambda x:not x)
- remove_tags = [
- dict(name='div', attrs={'class': 'item-list'}),
- dict(name='h4', attrs={'class': 'std-hdr'}),
- dict(name='div', attrs={'class': 'item-list share-links'}), # removes share links
- dict(name=['script', 'noscript']),
- dict(name='div', attrs={'id': 'comments-form'}), # comment these out if you want the comments to show
- dict(name='div', attrs={'id': re.compile('advertorial_block_($|| )')}),
- dict(name='div', attrs={'id': 'right-col'}),
- dict(name='div', attrs={'id': 'comments'}), # comment these out if you want the comments to show
- dict(name='div', attrs={'class': 'item-list related-content'}),
+ #remove_tags = [
+ #dict(name='div', attrs={'class': 'item-list'}),
+ #dict(name='h4', attrs={'class': 'std-hdr'}),
+ #dict(name='div', attrs={'class': 'item-list share-links'}), # removes share links
+ #dict(name=['script', 'noscript']),
+ #dict(name='div', attrs={'id': 'comments-form'}), # comment these out if you want the comments to show
+ #dict(name='div', attrs={'id': re.compile('advertorial_block_($|| )')}),
+ #dict(name='div', attrs={'id': 'right-col'}),
+ #dict(name='div', attrs={'id': 'comments'}), # comment these out if you want the comments to show
+ #dict(name='div', attrs={'class': 'item-list related-content'}),
- ]
+ #]
feeds = [
- (u'net', u'http://feeds.feedburner.com/net/topstories?format=xml')
+ (u'net', u'http://feeds.feedburner.com/creativebloq/')
]
def skip_ad_pages(self, soup):
diff --git a/recipes/el_correo.recipe b/recipes/el_correo.recipe
index 110c19d7ba..235d5e0fc7 100644
--- a/recipes/el_correo.recipe
+++ b/recipes/el_correo.recipe
@@ -3,10 +3,10 @@ __license__ = 'GPL v3'
__copyright__ = '08 Januery 2011, desUBIKado'
__author__ = 'desUBIKado'
__description__ = 'Daily newspaper from Biscay'
-__version__ = 'v0.08'
-__date__ = '08, Januery 2011'
+__version__ = 'v0.10'
+__date__ = '07, August 2013'
'''
-[url]http://www.elcorreo.com/[/url]
+http://www.elcorreo.com/
'''
import time
@@ -24,6 +24,7 @@ class heraldo(BasicNewsRecipe):
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
+ masthead_url = 'http://www.elcorreo.com/vizcaya/noticias/201002/02/Media/logo-elcorreo-nuevo.png'
language = 'es'
timefmt = '[%a, %d %b, %Y]'
encoding = 'iso-8859-1'
@@ -33,15 +34,15 @@ class heraldo(BasicNewsRecipe):
feeds = [
(u'Portada', u'http://www.elcorreo.com/vizcaya/portada.xml'),
(u'Local', u'http://www.elcorreo.com/vizcaya/rss/feeds/vizcaya.xml'),
- (u'Internacional', u'hhttp://www.elcorreo.com/vizcaya/rss/feeds/internacional.xml'),
- (u'Econom\xeda', u'http://www.elcorreo.com/vizcaya/rss/feeds/economia.xml'),
+ (u'Internacional', u'hhttp://www.elcorreo.com/vizcaya/rss/feeds/internacional.xml'),
+ (u'Econom\xeda', u'http://www.elcorreo.com/vizcaya/rss/feeds/economia.xml'),
(u'Pol\xedtica', u'http://www.elcorreo.com/vizcaya/rss/feeds/politica.xml'),
- (u'Opini\xf3n', u'http://www.elcorreo.com/vizcaya/rss/feeds/opinion.xml'),
- (u'Deportes', u'http://www.elcorreo.com/vizcaya/rss/feeds/deportes.xml'),
+ (u'Opini\xf3n', u'http://www.elcorreo.com/vizcaya/rss/feeds/opinion.xml'),
+ (u'Deportes', u'http://www.elcorreo.com/vizcaya/rss/feeds/deportes.xml'),
(u'Sociedad', u'http://www.elcorreo.com/vizcaya/rss/feeds/sociedad.xml'),
- (u'Cultura', u'http://www.elcorreo.com/vizcaya/rss/feeds/cultura.xml'),
- (u'Televisi\xf3n', u'http://www.elcorreo.com/vizcaya/rss/feeds/television.xml'),
- (u'Gente', u'http://www.elcorreo.com/vizcaya/rss/feeds/gente.xml')
+ (u'Cultura', u'http://www.elcorreo.com/vizcaya/rss/feeds/cultura.xml'),
+ (u'Televisi\xf3n', u'http://www.elcorreo.com/vizcaya/rss/feeds/television.xml'),
+ (u'Gente', u'http://www.elcorreo.com/vizcaya/rss/feeds/gente.xml')
]
keep_only_tags = [
@@ -54,14 +55,14 @@ class heraldo(BasicNewsRecipe):
dict(name='div', attrs={'class':['mod_lomas','bloque_lomas','blm_header','link-app3','link-app4','botones_listado']}),
dict(name='div', attrs={'class':['navegacion_galeria','modulocanalpromocion','separa','separacion','compartir','tags_relacionados']}),
dict(name='div', attrs={'class':['moduloBuscadorDeportes','modulo-gente','moddestacadopeq','OpcArt','articulopiniones']}),
- dict(name='div', attrs={'class':['modulo-especial','publiEspecial']}),
- dict(name='div', attrs={'id':['articulopina']}),
+ dict(name='div', attrs={'class':['modulo-especial','publiEspecial','carruselNoticias','vj','modulocomun2']}),
+ dict(name='div', attrs={'id':['articulopina','webs_asociadas']}),
dict(name='br', attrs={'class':'clear'}),
dict(name='form', attrs={'name':'frm_conversor2'})
]
remove_tags_before = dict(name='div' , attrs={'class':'articulo '})
- remove_tags_after = dict(name='div' , attrs={'class':'comentarios'})
+ remove_tags_after = dict(name='div' , attrs={'class':'robapaginas'})
def get_cover_url(self):
cover = None
@@ -69,10 +70,8 @@ class heraldo(BasicNewsRecipe):
year = str(st.tm_year)
month = "%.2d" % st.tm_mon
day = "%.2d" % st.tm_mday
- #[url]http://img.kiosko.net/2011/01/02/es/elcorreo.750.jpg[/url]
- #[url]http://info.elcorreo.com/pdf/06012011-viz.pdf[/url]
- cover='http://info.elcorreo.com/pdf/'+ day + month + year +'-viz.pdf'
-
+ # http://info.elcorreo.com/pdf/07082013-viz.pdf
+ cover='http://info.elcorreo.com/pdf/'+ day + month + year +'-viz.pdf'
br = BasicNewsRecipe.get_browser(self)
try:
br.open(cover)
@@ -92,29 +91,27 @@ class heraldo(BasicNewsRecipe):
img{margin-bottom: 0.4em}
'''
-
-
preprocess_regexps = [
- # To present the image of the embedded video
+ # Para presentar la imagen de los video incrustados
(re.compile(r'var RUTA_IMAGEN', re.DOTALL|re.IGNORECASE), lambda match: '![]()
'),
(re.compile(r'var SITIO = "elcorreo";', re.DOTALL|re.IGNORECASE), lambda match: '
-
-
+
+
{% endif %}
@@ -62,7 +59,7 @@
diff --git a/manual/virtual_libraries.rst b/manual/virtual_libraries.rst index f695bb0e45..9432bb04ef 100644 --- a/manual/virtual_libraries.rst +++ b/manual/virtual_libraries.rst @@ -94,6 +94,13 @@ You can quickly use the current search as a temporary virtual library by clicking the :guilabel:`Virtual Library` button and choosing the :guilabel:`*current search` entry. +You can display all available virtual libraries as tabs above the book list. +This is particularly handy if you like switching between virtual libraries very +often. Click the :guilabel:`Virtual Library` button and select :guilabel:`Show +virtual libraries as tabs`. You can re-arrange the tabs by drag and drop and +close ones you do not want to see. Closed tabs can be restored by +right-clicking on the tab bar. + Using additional restrictions ------------------------------- diff --git a/recipes/10minutos.recipe b/recipes/10minutos.recipe new file mode 100644 index 0000000000..4c2f8a7ec7 --- /dev/null +++ b/recipes/10minutos.recipe @@ -0,0 +1,50 @@ +#!/usr/bin/env python + +__license__ = 'GPL v3' +__author__ = '2013, Carlos Alves