diff --git a/resources/recipes/180.recipe b/resources/recipes/180.recipe new file mode 100644 index 0000000000..5158bb99e0 --- /dev/null +++ b/resources/recipes/180.recipe @@ -0,0 +1,50 @@ +#!/usr/bin/env python + +__license__ = 'GPL v3' +__author__ = '2010, Gustavo Azambuja ' +''' +180.com.uy +''' + +from calibre.web.feeds.news import BasicNewsRecipe + +class Noticias(BasicNewsRecipe): + title = '180.com.uy' + __author__ = 'Gustavo Azambuja' + description = 'Noticias de Uruguay' + language = 'es' + timefmt = '[%a, %d %b, %Y]' + use_embedded_content = False + recursion = 5 + encoding = 'utf-8' + remove_javascript = True + no_stylesheets = True + + oldest_article = 2 + max_articles_per_feed = 100 + keep_only_tags = [dict(name='div', attrs={'class':'tef-md tef-md-seccion-sociedad'})] + remove_tags = [ + dict(name=['object','link']) + ] + + remove_attributes = ['width','height', 'style', 'font', 'color'] + + 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'Titulares', u'http://www.180.com.uy/feed.php') + ] + + def get_cover_url(self): + return 'http://www.180.com.uy/tplef/img/logo.gif' + + + def preprocess_html(self, soup): + for item in soup.findAll(style=True): + del item['style'] + return soup + diff --git a/resources/recipes/bitacora.recipe b/resources/recipes/bitacora.recipe new file mode 100644 index 0000000000..a36eb52988 --- /dev/null +++ b/resources/recipes/bitacora.recipe @@ -0,0 +1,58 @@ +#!/usr/bin/env python + +__license__ = 'GPL v3' +__author__ = '2010, Gustavo Azambuja ' +''' +bitacora.com.uy +''' + +from calibre.web.feeds.news import BasicNewsRecipe + +class General(BasicNewsRecipe): + title = 'bitacora.com.uy' + __author__ = 'Gustavo Azambuja' + description = 'Noticias de Uruguay' + language = 'es' + timefmt = '[%a, %d %b, %Y]' + use_embedded_content = False + recursion = 5 + encoding = 'iso-8859-1' + remove_javascript = True + no_stylesheets = True + + oldest_article = 2 + max_articles_per_feed = 100 + keep_only_tags = [dict(id=['txt'])] + remove_tags = [ + dict(name='div', attrs={'class':'tablafoot'}), + dict(name=['object','h4']), + dict(name=['object','link']) + ] + + remove_attributes = ['width','height', 'style', 'font', 'color'] + + 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'Titulares', u'http://www.bitacora.com.uy/anxml.cgi?15') + ] + + def get_cover_url(self): + cover_url = None + index = 'http://www.bitacora.com.uy' + soup = self.index_to_soup(index) + link_item = soup.find('img',attrs={'class':'imgtapa'}) + if link_item: + cover_url = "http://www.bitacora.com.uy/"+link_item['src'] + return cover_url + + + def preprocess_html(self, soup): + for item in soup.findAll(style=True): + del item['style'] + return soup + diff --git a/resources/recipes/cosmopolitan.recipe b/resources/recipes/cosmopolitan.recipe new file mode 100644 index 0000000000..d7d3db7e0c --- /dev/null +++ b/resources/recipes/cosmopolitan.recipe @@ -0,0 +1,69 @@ +#!/usr/bin/env python + +__license__ = 'GPL v3' +__author__ = '2010, Gustavo Azambuja ' +''' +Muy Interesante +''' + +from calibre.web.feeds.news import BasicNewsRecipe + +class General(BasicNewsRecipe): + title = 'Cosmopolitan' + __author__ = 'Gustavo Azambuja' + description = 'Revista Cosmopolitan, Edicion Espanola' + language = 'es' + timefmt = '[%a, %d %b, %Y]' + use_embedded_content = False + recursion = 1 + encoding = 'utf8' + remove_javascript = True + no_stylesheets = True + conversion_options = {'linearize_tables': True} + + oldest_article = 180 + max_articles_per_feed = 100 + keep_only_tags = [ + dict(id=['contenido']), + dict(name='td', attrs={'class':['contentheading', 'txt_articulo']}) + ] + remove_tags = [ + dict(name='div', attrs={'class':['breadcrumb', 'bloque1', 'article', 'bajo_title', 'tags_articles', 'otrosenlaces_title', 'otrosenlaces_parent', 'compartir']}), + dict(name='div', attrs={'id':'comment'}), + dict(name='table', attrs={'class':'pagenav'}), + dict(name=['object','link']) + ] + remove_attributes = ['width','height', 'style', 'font', 'color'] + + 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;} + img {float:left; clear:both; margin:10px} + p {font-family:Arial,Helvetica,sans-serif;} + ''' + feeds = [ + (u'Articulos', u'http://feeds.feedburner.com/cosmohispano/FSSt') + ] + + def preprocess_html(self, soup): + attribs = [ 'style','font','valign' + ,'colspan','width','height' + ,'rowspan','summary','align' + ,'cellspacing','cellpadding' + ,'frames','rules','border' + ] + for item in soup.body.findAll(name=['table','td','tr','th','caption','thead','tfoot','tbody','colgroup','col']): + item.name = 'div' + for attrib in attribs: + if item.has_key(attrib): + del item[attrib] + return soup + + def get_cover_url(self): + index = 'http://www.cosmohispano.com/revista' + soup = self.index_to_soup(index) + link_item = soup.find('img',attrs={'class':'img_portada'}) + if link_item: + cover_url = "http://www.cosmohispano.com"+link_item['src'] + return cover_url diff --git a/resources/recipes/el_pais_uy.recipe b/resources/recipes/el_pais_uy.recipe new file mode 100644 index 0000000000..b474b5c232 --- /dev/null +++ b/resources/recipes/el_pais_uy.recipe @@ -0,0 +1,67 @@ +#!/usr/bin/env python + +__license__ = 'GPL v3' +__author__ = '2010, Gustavo Azambuja ' +''' +http://www.elpais.com.uy/ +''' + +from calibre.web.feeds.news import BasicNewsRecipe + +class General(BasicNewsRecipe): + title = 'Diario El Pais' + __author__ = 'Gustavo Azambuja' + description = 'Noticias | Uruguay' + language = 'es' + timefmt = '[%a, %d %b, %Y]' + use_embedded_content = False + recursion = 2 + encoding = 'iso-8859-1' + remove_javascript = True + no_stylesheets = True + + oldest_article = 2 + max_articles_per_feed = 100 + keep_only_tags = [ + dict(name='h1'), + dict(name='div', attrs={'id':'Contenido'}) + ] + remove_tags = [ + dict(name='div', attrs={'class':['date_text', 'comments', 'form_section', 'share_it']}), + dict(name='div', attrs={'id':['relatedPosts', 'spacer', 'banner_izquierda', 'right_container']}), + dict(name='p', attrs={'class':'FacebookLikeButton'}), + dict(name=['object','form']), + dict(name=['object','table']) ] + + 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'Ultimo Momento', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=umomento'), + (u'Editorial', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=editorial'), + (u'Nacional', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=nacional'), + (u'Internacional', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=internacional'), + (u'Espectaculos', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=espectaculos'), + (u'Deportes', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=deportes'), + (u'Ciudades', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=ciudades'), + (u'Economia', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=economia') + ] + + def get_cover_url(self): + cover_url = None + index = 'http://www.elpais.com.uy' + soup = self.index_to_soup(index) + link_item = soup.find('div',attrs={'class':'boxmedio box257'}) + print link_item + if link_item: + cover_url = 'http://www.elpais.com.uy'+link_item.img['src'] + return cover_url + + def preprocess_html(self, soup): + for item in soup.findAll(style=True): + del item['style'] + return soup + diff --git a/resources/recipes/freeway.recipe b/resources/recipes/freeway.recipe new file mode 100644 index 0000000000..cb6d41ebb2 --- /dev/null +++ b/resources/recipes/freeway.recipe @@ -0,0 +1,100 @@ +#!/usr/bin/env python + +__license__ = 'GPL v3' +__author__ = '2010, Gustavo Azambuja ' +''' +http://freeway.com.uy +''' + +from calibre.web.feeds.news import BasicNewsRecipe + +class General(BasicNewsRecipe): + title = 'freeway.com.uy' + __author__ = 'Gustavo Azambuja' + description = 'Revista Freeway, Montevideo, Uruguay' + language = 'es' + timefmt = '[%a, %d %b, %Y]' + use_embedded_content = False + recursion = 1 + encoding = 'utf8' + remove_javascript = True + no_stylesheets = True + conversion_options = {'linearize_tables': True} + + oldest_article = 180 + max_articles_per_feed = 100 + keep_only_tags = [ + dict(id=['contenido']), + dict(name='a', attrs={'class':'titulo_art_ppal'}), + dict(name='img', attrs={'class':'recuadro'}), + dict(name='td', attrs={'class':'txt_art_ppal'}) + ] + remove_tags = [ + dict(name=['object','link']) + ] + remove_attributes = ['width','height', 'style', 'font', 'color'] + + 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;} + img {float:left; clear:both; margin:10px} + p {font-family:Arial,Helvetica,sans-serif;} + ''' + + def parse_index(self): + feeds = [] + for title, url in [('Articulos', 'http://freeway.com.uy/revista/')]: + articles = self.art_parse_section(url) + if articles: + feeds.append((title, articles)) + return feeds + + def art_parse_section(self, url): + soup = self.index_to_soup(url) + div = soup.find(attrs={'id': 'tbl_1'}) + + current_articles = [] + for tag in div.findAllNext(attrs = {'class': 'ancho_articulos'}): + if tag.get('class') == 'link-list-heading': + break + for td in tag.findAll('td'): + a = td.find('a', attrs= {'class': 'titulo_articulos'}) + if a is None: + continue + title = self.tag_to_string(a) + url = a.get('href', False) + if not url or not title: + continue + if url.startswith('/'): + url = 'http://freeway.com.uy'+url + p = td.find('p', attrs= {'class': 'txt_articulos'}) + description = self.tag_to_string(p) + self.log('\t\tFound article:', title) + self.log('\t\t\t', url) + self.log('\t\t\t', description) + current_articles.append({'title': title, 'url': url, 'description':description, 'date':''}) + + return current_articles + + def preprocess_html(self, soup): + attribs = [ 'style','font','valign' + ,'colspan','width','height' + ,'rowspan','summary','align' + ,'cellspacing','cellpadding' + ,'frames','rules','border' + ] + for item in soup.body.findAll(name=['table','td','tr','th','caption','thead','tfoot','tbody','colgroup','col']): + item.name = 'div' + for attrib in attribs: + if item.has_key(attrib): + del item[attrib] + return soup + + def get_cover_url(self): + #index = 'http://www.cosmohispano.com/revista' + #soup = self.index_to_soup(index) + #link_item = soup.find('img',attrs={'class':'img_portada'}) + #if link_item: + # cover_url = "http://www.cosmohispano.com"+link_item['src'] + return 'http://freeway.com.uy/_upload/_n_foto_grande/noticia_1792_tapanoviembre2010.jpg' diff --git a/resources/recipes/la_diaria.recipe b/resources/recipes/la_diaria.recipe new file mode 100644 index 0000000000..d89eb465dd --- /dev/null +++ b/resources/recipes/la_diaria.recipe @@ -0,0 +1,48 @@ +#!/usr/bin/env python + +__license__ = 'GPL v3' +__author__ = '2010, Gustavo Azambuja ' +''' +ladiaria.com.uy +''' + +from calibre.web.feeds.news import BasicNewsRecipe + +class General(BasicNewsRecipe): + title = 'La Diaria' + __author__ = 'Gustavo Azambuja' + description = 'Noticias de Uruguay' + language = 'es' + 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(id=['article'])] + remove_tags = [ + dict(name='div', attrs={'class':['byline', 'hr', 'titlebar', 'volver-arriba-right']}), + dict(name='div', attrs={'id':'discussion'}), + 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://ladiaria.com/feeds/articulos') + ] + + def get_cover_url(self): + return 'http://ladiaria.com/edicion/imagenportada/' + + def preprocess_html(self, soup): + for item in soup.findAll(style=True): + del item['style'] + return soup diff --git a/resources/recipes/la_razon_bo.recipe b/resources/recipes/la_razon_bo.recipe index b7cd59d043..18a00d6763 100644 --- a/resources/recipes/la_razon_bo.recipe +++ b/resources/recipes/la_razon_bo.recipe @@ -8,7 +8,7 @@ from calibre import strftime from calibre.web.feeds.news import BasicNewsRecipe class LaRazon_Bol(BasicNewsRecipe): - title = 'La Razón - Bolivia' + title = u'La Razón - Bolivia' __author__ = 'Darko Miletic' description = 'El diario nacional de Bolivia' publisher = 'Praxsis S.R.L.' diff --git a/resources/recipes/montevideo_com.recipe b/resources/recipes/montevideo_com.recipe new file mode 100644 index 0000000000..cabd4181d6 --- /dev/null +++ b/resources/recipes/montevideo_com.recipe @@ -0,0 +1,56 @@ +#!/usr/bin/env python + +__license__ = 'GPL v3' +__author__ = '2010, Gustavo Azambuja ' +''' +http://www.montevideo.com.uy +''' + +from calibre.web.feeds.news import BasicNewsRecipe + +class Noticias(BasicNewsRecipe): + title = 'Montevideo COMM' + __author__ = 'Gustavo Azambuja' + description = 'Noticias de Uruguay' + language = 'es' + timefmt = '[%a, %d %b, %Y]' + use_embedded_content = False + recursion = 5 + encoding = 'utf-8' + remove_javascript = True + no_stylesheets = True + + oldest_article = 2 + max_articles_per_feed = 100 + keep_only_tags = [dict(id=['txt'])] + remove_tags = [ + dict(name=['object','link']) + ] + + remove_attributes = ['width','height', 'style', 'font', 'color'] + + 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'Destacados', u'http://www.montevideo.com.uy/anxml.aspx?58'), + (u'Noticias', u'http://www.montevideo.com.uy/anxml.aspx?59'), + (u'Tecnologia', u'http://www.montevideo.com.uy/anxml.aspx?133'), + (u'Tiempo Libre', u'http://www.montevideo.com.uy/anxml.aspx?60'), + # (u'Deportes', u'http://www.montevideo.com.uy/anxml.aspx?968'), + # (u'Pantallazo', u'http://www.montevideo.com.uy/anxml.aspx?1022'), + (u'Gastronomia', u'http://www.montevideo.com.uy/anxml.aspx?1023') + ] + + def get_cover_url(self): + return 'http://sphotos.ak.fbcdn.net/hphotos-ak-snc1/hs276.snc1/10319_147339559330_147337559330_2625816_6636564_n.jpg' + + + def preprocess_html(self, soup): + for item in soup.findAll(style=True): + del item['style'] + return soup + diff --git a/resources/recipes/observa_digital.recipe b/resources/recipes/observa_digital.recipe new file mode 100644 index 0000000000..375d67236c --- /dev/null +++ b/resources/recipes/observa_digital.recipe @@ -0,0 +1,63 @@ +#!/usr/bin/env python + +__license__ = 'GPL v3' +__author__ = '2010, Gustavo Azambuja ' +''' +observa.com.uy +''' + +from calibre.web.feeds.news import BasicNewsRecipe + +class Noticias(BasicNewsRecipe): + title = 'Observa Digital' + __author__ = '2010, Gustavo Azambuja ' + description = 'Noticias desde Uruguay' + language = 'es' + 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(id=['contenido'])] + remove_tags = [ + dict(name='div', attrs={'id':'contenedorVinculadas'}), + dict(name='p', attrs={'id':'nota_firma'}), + dict(name=['object','link']) + ] + + remove_attributes = ['width','height', 'style', 'font', 'color'] + + 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'Actualidad', u'http://www.observa.com.uy/RSS/actualidad.xml'), + (u'Deportes', u'http://www.observa.com.uy/RSS/deportes.xml'), + (u'Vida', u'http://www.observa.com.uy/RSS/vida.xml'), + (u'Ciencia y Tecnologia', u'http://www.observa.com.uy/RSS/ciencia.xml') + ] + + def get_cover_url(self): + cover_url = None + index = 'http://www.elobservador.com.uy/elobservador/nav_portada.asp?suplemento=dia' + soup = self.index_to_soup(index) + link_item = soup.find('img',attrs={'usemap':'#mapeo_imagenes'}) + if link_item: + cover_url = 'http://www.elobservador.com.uy'+link_item['src'].strip() + + print cover_url + + return cover_url + + + def preprocess_html(self, soup): + for item in soup.findAll(style=True): + del item['style'] + return soup diff --git a/resources/recipes/revista_bla.recipe b/resources/recipes/revista_bla.recipe new file mode 100644 index 0000000000..15c7e7fb3f --- /dev/null +++ b/resources/recipes/revista_bla.recipe @@ -0,0 +1,54 @@ +#!/usr/bin/env python + +__license__ = 'GPL v3' +__author__ = '2010, Gustavo Azambuja ' +''' +http://www.revistabla.com +''' + +from calibre.web.feeds.news import BasicNewsRecipe + +class Noticias(BasicNewsRecipe): + title = 'Revista Bla' + __author__ = 'Gustavo Azambuja' + description = 'Moda | Uruguay' + language = 'es' + timefmt = '[%a, %d %b, %Y]' + use_embedded_content = False + recursion = 5 + encoding = 'utf8' + remove_javascript = True + no_stylesheets = True + + oldest_article = 20 + max_articles_per_feed = 100 + keep_only_tags = [dict(id=['body_container'])] + remove_tags = [ + dict(name='div', attrs={'class':['date_text', 'comments', 'form_section', 'share_it']}), + dict(name='div', attrs={'id':['relatedPosts', 'spacer', 'banner_izquierda', 'right_container']}), + dict(name='p', attrs={'class':'FacebookLikeButton'}), + 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.revistabla.com/feed/') + ] + + def get_cover_url(self): + cover_url = None + index = 'http://www.revistabla.com' + soup = self.index_to_soup(index) + link_item = soup.find('div',attrs={'class':'header_right'}) + if link_item: + cover_url = link_item.img['src'] + return cover_url + + def preprocess_html(self, soup): + for item in soup.findAll(style=True): + del item['style'] + return soup diff --git a/resources/recipes/revista_muy.recipe b/resources/recipes/revista_muy.recipe index e452a6f053..b101fe97ce 100644 --- a/resources/recipes/revista_muy.recipe +++ b/resources/recipes/revista_muy.recipe @@ -108,3 +108,10 @@ class RevistaMuyInteresante(BasicNewsRecipe): feeds.append((title, articles)) return feeds + def get_cover_url(self): + index = 'http://www.muyinteresante.es/revista' + soup = self.index_to_soup(index) + link_item = soup.find('img',attrs={'class':'img_portada'}) + if link_item: + cover_url = "http://www.muyinteresante.es"+link_item['src'] + return cover_url diff --git a/resources/recipes/telepolis.recipe b/resources/recipes/telepolis.recipe index 1009dca275..4ca57f8275 100644 --- a/resources/recipes/telepolis.recipe +++ b/resources/recipes/telepolis.recipe @@ -3,12 +3,12 @@ __license__ = 'GPL v3' __copyright__ = '2009, Gerhard Aigner ' -''' http://www.derstandard.at - Austrian Newspaper ''' + import re from calibre.web.feeds.news import BasicNewsRecipe class TelepolisNews(BasicNewsRecipe): - title = u'Telepolis (News)' + title = u'Telepolis (News+Artikel)' __author__ = 'Gerhard Aigner' publisher = 'Heise Zeitschriften Verlag GmbH & Co KG' description = 'News from telepolis' @@ -20,16 +20,16 @@ class TelepolisNews(BasicNewsRecipe): encoding = "utf-8" language = 'de_AT' - use_embedded_content = False + use_embedded_content =False remove_empty_feeds = True preprocess_regexps = [(re.compile(r']*>', re.DOTALL|re.IGNORECASE), lambda match: ''), (re.compile(r'', re.DOTALL|re.IGNORECASE), lambda match: ''),] - keep_only_tags = [dict(name = 'table',attrs={'class':'blogtable'})] - remove_tags = [dict(name='img'), dict(name='td',attrs={'class':'blogbottom'})] + keep_only_tags = [dict(name = 'td',attrs={'class':'bloghead'}),dict(name = 'td',attrs={'class':'blogfliess'})] + remove_tags = [dict(name='img'), dict(name='td',attrs={'class':'blogbottom'}), dict(name='td',attrs={'class':'forum'})] - feeds = [(u'News', u'http://www.heise.de/tp/news.rdf')] + feeds = [(u'News', u'http://www.heise.de/tp/news-atom.xml')] html2lrf_options = [ '--comment' , description @@ -41,7 +41,7 @@ class TelepolisNews(BasicNewsRecipe): def get_article_url(self, article): '''if the linked article is of kind artikel don't take it''' - if (article.link.count('artikel') > 0) : + if (article.link.count('artikel') > 1) : return None return article.link @@ -49,3 +49,5 @@ class TelepolisNews(BasicNewsRecipe): mtag = '' soup.head.insert(0,mtag) return soup + + diff --git a/setup/installer/windows/freeze.py b/setup/installer/windows/freeze.py index dc3dd33604..118b6690f0 100644 --- a/setup/installer/windows/freeze.py +++ b/setup/installer/windows/freeze.py @@ -132,7 +132,7 @@ class Win32Freeze(Command, WixMixIn): shutil.copytree(self.j(comext, 'shell'), self.j(sp_dir, 'win32com', 'shell')) shutil.rmtree(comext) - for pat in (r'numpy', r'PyQt4\uic\port_v3'): + for pat in (r'PyQt4\uic\port_v3', ): x = glob.glob(self.j(self.lib_dir, 'site-packages', pat))[0] shutil.rmtree(x) diff --git a/setup/installer/windows/notes.rst b/setup/installer/windows/notes.rst index 281cd8668e..45aa4d2afb 100644 --- a/setup/installer/windows/notes.rst +++ b/setup/installer/windows/notes.rst @@ -19,7 +19,7 @@ Set CMAKE_PREFIX_PATH environment variable to C:\cygwin\home\kovid\sw This is where all dependencies will be installed. -Add C:\Python26\Scripts and C:\Python26 to PATH +Add C:\Python27\Scripts and C:\Python27 to PATH Install setuptools from http://pypi.python.org/pypi/setuptools If there are no windows binaries already compiled for the version of python you are using then download the source and run the following command in the folder where the source has been unpacked:: @@ -28,7 +28,7 @@ If there are no windows binaries already compiled for the version of python you Run the following command to install python dependencies:: - easy_install --always-unzip -U ipython mechanize pyreadline python-dateutil dnspython cssutils clientform + easy_install --always-unzip -U ipython mechanize pyreadline python-dateutil dnspython cssutils clientform pycrypto Install BeautifulSoup 3.0.x manually into site-packages (3.1.x parses broken HTML very poorly) diff --git a/src/calibre/devices/kobo/driver.py b/src/calibre/devices/kobo/driver.py index 934dc0879e..174441c276 100644 --- a/src/calibre/devices/kobo/driver.py +++ b/src/calibre/devices/kobo/driver.py @@ -229,6 +229,10 @@ class KOBO(USBMS): #Delete the volume_shortcovers second cursor.execute('delete from volume_shortcovers where volumeid = ?', t) + # Delete the rows from content_keys + if self.dbversion >= 8: + cursor.execute('delete from content_keys where volumeid = ?', t) + # Delete the chapters associated with the book next t = (ContentID,ContentID,) cursor.execute('delete from content where BookID = ? or ContentID = ?', t) diff --git a/src/calibre/ebooks/metadata/isbndb.py b/src/calibre/ebooks/metadata/isbndb.py index 615b4ab818..cd39f8a0e1 100644 --- a/src/calibre/ebooks/metadata/isbndb.py +++ b/src/calibre/ebooks/metadata/isbndb.py @@ -140,7 +140,7 @@ def create_books(opts, args, timeout=5.): tans = [ISBNDBMetadata(book) for book in fetch_metadata(url, timeout=timeout)] #remove duplicates ISBN - return dict((book.isbn, book) for book in tans).values() + return list(dict((book.isbn, book) for book in tans).values()) def main(args=sys.argv): parser = option_parser() diff --git a/src/calibre/library/__init__.py b/src/calibre/library/__init__.py index 0f8e5e5496..8ff23c0a0a 100644 --- a/src/calibre/library/__init__.py +++ b/src/calibre/library/__init__.py @@ -6,3 +6,53 @@ def db(path=None): from calibre.library.database2 import LibraryDatabase2 from calibre.utils.config import prefs return LibraryDatabase2(path if path else prefs['library_path']) + + +def generate_test_db(library_path, + num_of_records=20000, + num_of_authors=6000, + num_of_tags=10000, + tag_length=7, + author_length=7, + title_length=10, + max_authors=10, + max_tags=10 + ): + import random, string, os, sys, time + + if not os.path.exists(library_path): + os.makedirs(library_path) + + def randstr(length): + return ''.join(random.choice(string.letters) for i in + xrange(length)) + + all_tags = [randstr(tag_length) for j in xrange(num_of_tags)] + print 'Generated', num_of_tags, 'tags' + all_authors = [randstr(author_length) for j in xrange(num_of_authors)] + print 'Generated', num_of_authors, 'authors' + all_titles = [randstr(title_length) for j in xrange(num_of_records)] + print 'Generated', num_of_records, 'titles' + + testdb = db(library_path) + + print 'Creating', num_of_records, 'records...' + + start = time.time() + + for i, title in enumerate(all_titles): + print i+1, + sys.stdout.flush() + authors = random.randint(1, max_authors) + authors = [random.choice(all_authors) for i in xrange(authors)] + tags = random.randint(0, max_tags) + tags = [random.choice(all_tags) for i in xrange(tags)] + from calibre.ebooks.metadata.book.base import Metadata + mi = Metadata(title, authors) + mi.tags = tags + testdb.import_book(mi, []) + + t = time.time() - start + print '\nGenerated', num_of_records, 'records in:', t, 'seconds' + print 'Time per record:', t/float(num_of_records) + diff --git a/src/calibre/library/catalog.py b/src/calibre/library/catalog.py index ffd7769f17..33525f6540 100644 --- a/src/calibre/library/catalog.py +++ b/src/calibre/library/catalog.py @@ -405,10 +405,7 @@ class BIBTEX(CatalogPlugin): else : template_citation = u'%s' % str(entry["id"]) - if asccii_bibtex : - return bibtexclass.ValidateCitationKey(template_citation.encode('ascii', 'replace')) - else : - return bibtexclass.ValidateCitationKey(template_citation) + return bibtexclass.ValidateCitationKey(template_citation) self.fmt = path_to_output.rpartition('.')[2] self.notification = notification @@ -478,7 +475,7 @@ class BIBTEX(CatalogPlugin): #Initialize BibTeX class bibtexc = BibTeX() - + #Entries writing after Bibtex formating (or not) if bibfile_enc != 'ascii' : bibtexc.ascii_bibtex = False diff --git a/src/calibre/library/database2.py b/src/calibre/library/database2.py index 8e7002097a..21a54a4dd6 100644 --- a/src/calibre/library/database2.py +++ b/src/calibre/library/database2.py @@ -1248,15 +1248,20 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns): traceback.print_exc() else: raise + path_changed = False if set_title and mi.title: - self.set_title(id, mi.title, commit=False) + self._set_title(id, mi.title) + path_changed = True if set_authors: if not mi.authors: mi.authors = [_('Unknown')] authors = [] for a in mi.authors: authors += string_to_authors(a) - self.set_authors(id, authors, notify=False, commit=False) + self._set_authors(id, authors) + path_changed = True + if path_changed: + self.set_path(id, index_is_id=True) if mi.author_sort: doit(self.set_author_sort, id, mi.author_sort, notify=False, commit=False) @@ -1348,13 +1353,7 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns): result.append(r) return ' & '.join(result).replace('|', ',') - def set_authors(self, id, authors, notify=True, commit=True): - ''' - Note that even if commit is False, the db will still be committed to - because this causes the location of files to change - - :param authors: A list of authors. - ''' + def _set_authors(self, id, authors): if not authors: authors = [_('Unknown')] self.conn.execute('DELETE FROM books_authors_link WHERE book=?',(id,)) @@ -1379,25 +1378,30 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns): ss = self.author_sort_from_book(id, index_is_id=True) self.conn.execute('UPDATE books SET author_sort=? WHERE id=?', (ss, id)) - self.dirtied([id], commit=False) - if commit: - self.conn.commit() self.data.set(id, self.FIELD_MAP['authors'], ','.join([a.replace(',', '|') for a in authors]), row_is_id=True) self.data.set(id, self.FIELD_MAP['author_sort'], ss, row_is_id=True) + + def set_authors(self, id, authors, notify=True, commit=True): + ''' + Note that even if commit is False, the db will still be committed to + because this causes the location of files to change + + :param authors: A list of authors. + ''' + self._set_authors(id, authors) + self.dirtied([id], commit=False) + if commit: + self.conn.commit() self.set_path(id, index_is_id=True) if notify: self.notify('metadata', [id]) - def set_title(self, id, title, notify=True, commit=True): - ''' - Note that even if commit is False, the db will still be committed to - because this causes the location of files to change - ''' + def _set_title(self, id, title): if not title: - return - if not isinstance(title, unicode): + return False + if isbytestring(title): title = title.decode(preferred_encoding, 'replace') self.conn.execute('UPDATE books SET title=? WHERE id=?', (title, id)) self.data.set(id, self.FIELD_MAP['title'], title, row_is_id=True) @@ -1405,6 +1409,15 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns): self.data.set(id, self.FIELD_MAP['sort'], title_sort(title), row_is_id=True) else: self.data.set(id, self.FIELD_MAP['sort'], title, row_is_id=True) + return True + + def set_title(self, id, title, notify=True, commit=True): + ''' + Note that even if commit is False, the db will still be committed to + because this causes the location of files to change + ''' + if not self._set_title(id, title): + return self.set_path(id, index_is_id=True) self.dirtied([id], commit=False) if commit: @@ -2072,13 +2085,11 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns): (id, title, series_index, aus)) self.data.books_added([id], self) - self.set_path(id, True) - self.conn.commit() if mi.timestamp is None: mi.timestamp = utcnow() if mi.pubdate is None: mi.pubdate = utcnow() - self.set_metadata(id, mi, ignore_errors=True) + self.set_metadata(id, mi, ignore_errors=True, commit=True) if cover is not None: try: self.set_cover(id, cover) @@ -2114,13 +2125,11 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns): id = obj.lastrowid self.data.books_added([id], self) ids.append(id) - self.set_path(id, True) - self.conn.commit() if mi.timestamp is None: mi.timestamp = utcnow() if mi.pubdate is None: mi.pubdate = utcnow() - self.set_metadata(id, mi) + self.set_metadata(id, mi, commit=True, ignore_errors=True) npath = self.run_import_plugins(path, format) format = os.path.splitext(npath)[-1].lower().replace('.', '').upper() stream = lopen(npath, 'rb') @@ -2154,12 +2163,11 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns): (title, series_index, aus)) id = obj.lastrowid self.data.books_added([id], self) - self.set_path(id, True) if mi.timestamp is None: mi.timestamp = utcnow() if mi.pubdate is None: mi.pubdate = utcnow() - self.set_metadata(id, mi, ignore_errors=True) + self.set_metadata(id, mi, ignore_errors=True, commit=True) if preserve_uuid and mi.uuid: self.set_uuid(id, mi.uuid, commit=False) for path in formats: diff --git a/src/calibre/startup.py b/src/calibre/startup.py index e384153993..e74660d0bc 100644 --- a/src/calibre/startup.py +++ b/src/calibre/startup.py @@ -129,7 +129,7 @@ if not _run_once: def __getattribute__(self, attr): if attr in ('name', '__enter__', '__str__', '__unicode__', - '__repr__'): + '__repr__', '__exit__'): return object.__getattribute__(self, attr) fobject = object.__getattribute__(self, 'fobject') return getattr(fobject, attr) @@ -155,6 +155,11 @@ if not _run_once: fobject.__enter__() return self + def __exit__(self, *args): + fobject = object.__getattribute__(self, 'fobject') + return fobject.__exit__(*args) + + m = mode[0] random = len(mode) > 1 and mode[1] == '+' binary = mode[-1] == 'b' diff --git a/src/calibre/utils/bibtex.py b/src/calibre/utils/bibtex.py index 09868ccdb1..b78e4cc002 100644 --- a/src/calibre/utils/bibtex.py +++ b/src/calibre/utils/bibtex.py @@ -69,6 +69,9 @@ from UserDict import UserDict from calibre.constants import preferred_encoding from calibre.utils.mreplace import MReplace +from calibre.constants import preferred_encoding +from calibre.utils.mreplace import MReplace + utf8enc2latex_mapping = { # This is a mapping of Unicode characters to LaTeX equivalents. # The information has been extracted from @@ -2465,7 +2468,7 @@ utf8enc2latex_mapping = { u'\U0001d7fd': '$\\mathtt{7}$', u'\U0001d7fe': '$\\mathtt{8}$', u'\U0001d7ff': '$\\mathtt{9}$', - + #Items from simple list u'\u0106': "{\\a\\'C}", u'\u0408': '{\\CYRJE}', @@ -2853,10 +2856,10 @@ class BibTeX: # This substitution is based on the description of cite key restrictions at # http://bibdesk.sourceforge.net/manual/BibDesk%20Help_2.html self.invalid_cit = re.compile(u'[ "@\',\\#}{~%&$^]') - self.upper = re.compile(u'[' + + self.upper = re.compile(u'[' + string.uppercase.decode(preferred_encoding) + u']') self.escape = re.compile(u'[~#&%_]') - + def ValidateCitationKey(self, text): """ removes characters not allowed in BibTeX keys @@ -2893,7 +2896,7 @@ class BibTeX: return self.escape.sub(lambda m: u'\\%s' % m.group(), text) #Calibre functions - #Option to go to official ASCII Bibtex or unofficial UTF-8 + #Option to go to official ASCII Bibtex or unofficial UTF-8 #Go from an unicode entry to ASCII Bibtex format without encoding def utf8ToBibtex(self, text): if len(text) == 0: diff --git a/src/calibre/web/feeds/recipes/collection.py b/src/calibre/web/feeds/recipes/collection.py index 5b34ddab0b..a513cf3880 100644 --- a/src/calibre/web/feeds/recipes/collection.py +++ b/src/calibre/web/feeds/recipes/collection.py @@ -61,6 +61,11 @@ def serialize_recipe(urn, recipe_class): def serialize_collection(mapping_of_recipe_classes): collection = E.recipe_collection() + '''for u, x in mapping_of_recipe_classes.items(): + print 11111, u, repr(x.title) + if isinstance(x.title, str): + x.title.decode('ascii') + ''' for urn in sorted(mapping_of_recipe_classes.keys(), key=lambda key: getattr(mapping_of_recipe_classes[key], 'title', 'zzz')):