From 9266cfb0a5ab86426302bac5da2d86a2af7e6810 Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Mon, 8 Jun 2009 12:53:58 -0700
Subject: [PATCH] Implement #2564 (Various new recipes)

---
 .../gui2/images/news/elperiodico_catalan.png  | Bin 0 -> 693 bytes
 .../gui2/images/news/elperiodico_spanish.png  | Bin 0 -> 693 bytes
 .../gui2/images/news/expansion_spanish.png    | Bin 0 -> 806 bytes
 src/calibre/web/feeds/recipes/__init__.py     |   4 +-
 .../recipes/recipe_elperiodico_catalan.py     |  55 ++++++++++++++
 .../recipes/recipe_elperiodico_spanish.py     |  55 ++++++++++++++
 .../feeds/recipes/recipe_expansion_spanish.py |  58 +++++++++++++++
 .../web/feeds/recipes/recipe_lavanguardia.py  |  69 ++++++++++++++++++
 src/calibre/web/feeds/recipes/recipe_marca.py |  55 ++++++++++++++
 9 files changed, 295 insertions(+), 1 deletion(-)
 create mode 100644 src/calibre/gui2/images/news/elperiodico_catalan.png
 create mode 100644 src/calibre/gui2/images/news/elperiodico_spanish.png
 create mode 100644 src/calibre/gui2/images/news/expansion_spanish.png
 create mode 100644 src/calibre/web/feeds/recipes/recipe_elperiodico_catalan.py
 create mode 100644 src/calibre/web/feeds/recipes/recipe_elperiodico_spanish.py
 create mode 100644 src/calibre/web/feeds/recipes/recipe_expansion_spanish.py
 create mode 100644 src/calibre/web/feeds/recipes/recipe_lavanguardia.py
 create mode 100644 src/calibre/web/feeds/recipes/recipe_marca.py

diff --git a/src/calibre/gui2/images/news/elperiodico_catalan.png b/src/calibre/gui2/images/news/elperiodico_catalan.png
new file mode 100644
index 0000000000000000000000000000000000000000..96b1d6d453e7ebd4ce63bcfc618c0d1d39982956
GIT binary patch
literal 693
zcmeAS@N?(olHy`uVBq!ia0vp^0wB!61|;P_|4#%`Y)RhkE)4%caKYZ?lYt_f1s;*b
zK-vS0-A-oPfdtD69Mgd`SU*F|v9*U87#Qz)x;TbdoL)Ndptne&%u#!5Q(dzceGAuW
zw0W;-SBYtIYRa3(wWM+HZTSZWl_o9nt`6YR;a9t{b~UG4dxr@}6NmU>2lIfY)|}OM
zkKC19ezNWF-(4pAW$rXCDF40pe)ap``)ZPdyiV3XNVwvDciYWbyZrBNv%GN0>Fzeq
z6kR_4Ih@?7Ec@<CP4CM*_4M7A5})98^KEqNYj53I-fbH7F#RF((a&Oi0w&o~eF9(Z
z?e$g4{(GD2=^d5^BlYuq6HY`u3HP3|J$C79>wD++v2FdydTo8r#Wk5-uWNtyOr7i8
zV;>PRN6vglaiu`+`kVLv_*j}RJkuwzrMK^a>h2jcPcJ^s`(+2?fe!)pwsX@g9{j#y
zay2V-Z@<jzWw|9SGk5NJ^fz|;nNB&qIo`~Fcz=9Mn|bSx(~7FBs!4ycI<IR>XKj)*
zmymlEF2#G`Yt6oxz3V*OIfNp)btea2ZGP$aHK4)V+PmoOTBF&^Jdd9>l(VapUp3FK
zbmgm8J&Phzp8w>|s$G78@p75R)4YHipDOo!(c4tjFk?#4u6g|zmuO%5TC?tM^rBDC
zpZ!~R`shKQ!wkF}Ga2XYyS3oU)-`A5%DPL>at`O%@NMIv#Ydf1{94MfIVw^AVU^v~
zT=B)8>Je-AUhUxd!7HKmqtz~TdMhy6RZCnWN|K9G6H8KcQ-B16k%57wu7R1ZfklX+
zk(G&wm9d4cfw`4|L4j26a+rqP{FKbJN=yxARt6?O1koV&Bp;Nh7(8A5T-G@yGywp7
CBrA&m

literal 0
HcmV?d00001

diff --git a/src/calibre/gui2/images/news/elperiodico_spanish.png b/src/calibre/gui2/images/news/elperiodico_spanish.png
new file mode 100644
index 0000000000000000000000000000000000000000..96b1d6d453e7ebd4ce63bcfc618c0d1d39982956
GIT binary patch
literal 693
zcmeAS@N?(olHy`uVBq!ia0vp^0wB!61|;P_|4#%`Y)RhkE)4%caKYZ?lYt_f1s;*b
zK-vS0-A-oPfdtD69Mgd`SU*F|v9*U87#Qz)x;TbdoL)Ndptne&%u#!5Q(dzceGAuW
zw0W;-SBYtIYRa3(wWM+HZTSZWl_o9nt`6YR;a9t{b~UG4dxr@}6NmU>2lIfY)|}OM
zkKC19ezNWF-(4pAW$rXCDF40pe)ap``)ZPdyiV3XNVwvDciYWbyZrBNv%GN0>Fzeq
z6kR_4Ih@?7Ec@<CP4CM*_4M7A5})98^KEqNYj53I-fbH7F#RF((a&Oi0w&o~eF9(Z
z?e$g4{(GD2=^d5^BlYuq6HY`u3HP3|J$C79>wD++v2FdydTo8r#Wk5-uWNtyOr7i8
zV;>PRN6vglaiu`+`kVLv_*j}RJkuwzrMK^a>h2jcPcJ^s`(+2?fe!)pwsX@g9{j#y
zay2V-Z@<jzWw|9SGk5NJ^fz|;nNB&qIo`~Fcz=9Mn|bSx(~7FBs!4ycI<IR>XKj)*
zmymlEF2#G`Yt6oxz3V*OIfNp)btea2ZGP$aHK4)V+PmoOTBF&^Jdd9>l(VapUp3FK
zbmgm8J&Phzp8w>|s$G78@p75R)4YHipDOo!(c4tjFk?#4u6g|zmuO%5TC?tM^rBDC
zpZ!~R`shKQ!wkF}Ga2XYyS3oU)-`A5%DPL>at`O%@NMIv#Ydf1{94MfIVw^AVU^v~
zT=B)8>Je-AUhUxd!7HKmqtz~TdMhy6RZCnWN|K9G6H8KcQ-B16k%57wu7R1ZfklX+
zk(G&wm9d4cfw`4|L4j26a+rqP{FKbJN=yxARt6?O1koV&Bp;Nh7(8A5T-G@yGywp7
CBrA&m

literal 0
HcmV?d00001

diff --git a/src/calibre/gui2/images/news/expansion_spanish.png b/src/calibre/gui2/images/news/expansion_spanish.png
new file mode 100644
index 0000000000000000000000000000000000000000..58bea2b94e7b4ef6d14ce296f315a5ec57c9b96f
GIT binary patch
literal 806
zcmeAS@N?(olHy`uVBq!ia0vp^3LwnE1|*BCs=fdzwj^(N7l!{JxM1({$v_d#0*}aI
zAngIhZYQ(tK!Rljj_E*J0gT&!&6&%<z~t}g;usQf_~`WgU9TKOj_r>XX9;K0Q&H$>
z6%(@dzU-otw=rSm+Onpp{SSg8j--jd%MD74JMdD+M^-0kvWZYc=c3lLcOGquyPmR$
z?SIXLL&nDH_G<G!pS3YOCLy<C`eFGgL0h79mt4+da8R54Q14FO_B$Ixv_v~}#kd2!
z0yRW_FiiDgof4E|CY>>h&G+&S{fR1>{8c)qH#t2%{nSVzMNo=|jmP0dvIJZC+{YGg
z9zQNm=uM4m+&Ph9TW&GqvB!qis>cgw=$xL&a6Yhp!ri>%ve9e9ESARTv3qH%cs@E;
zX*aV~*-_x!EcGs>lGy!r2UJ&uXfZULO)IWuaN@8z|65R)rSZ4qI=&09zix<I&s-RL
zed77&%pa#0PnxHF{_}%fc`s(HTDARt<H?kwkF!=Y^|&oQ&Ioj>(}}+fX`3Z&&NpYy
zdQoEaqHOm^A=j-zr#J0bYw>Dh?(dY@|H9sAO-PlznIpFE{b7@{J2D@=Kd?}`@A%^z
z)&-*a0imMXa*v-9mVR)9m%EjTt@+?zhC_EYgsr~Iui*2v=;ua;lPQy4SG5RiiCTM`
ziKB_(vI(<#Jj09czke4WJj>8fe|$r7<-GQvHGHmtdHe#)9u{ygXoz)xXJ0Vo-D%@B
zMeDAyANun1XL|gsO*-xJDT{ACDY1IG?UCDJ!OHm=X0z>|ZNL5Y^qCW-cQ0)EDW=HM
zwP?Y`j5o<Zmm2h3SRJ`Cgv-Aq$L?y@)T^&c)jWfAw2w(XD_x;}>|gx(*z2r{ES)Y)
zC!c8FyLWDP&74cuuXDYBzh9v%DdCO2&6jm6!xkU)0;Vz564!{5<f7EXl2qLkAi-c{
zU|^|hV5Vze5n^a$WnyAwY@uslZe?IlAeFlurXe>!B{QuOQ-hh6p_!F2P%}uwss1u`
Ppaup{S3j3^P6<r_WPMcP

literal 0
HcmV?d00001

diff --git a/src/calibre/web/feeds/recipes/__init__.py b/src/calibre/web/feeds/recipes/__init__.py
index a6dabf230f..9b75b60656 100644
--- a/src/calibre/web/feeds/recipes/__init__.py
+++ b/src/calibre/web/feeds/recipes/__init__.py
@@ -45,7 +45,9 @@ recipe_modules = ['recipe_' + r for r in (
            'straitstimes', 'index_hu', 'pcworld_hu', 'hrt', 'rts',
            'h1', 'h2', 'h3', 'phd_comics', 'woz_die', 'elektrolese',
            'climate_progress', 'carta', 'slashdot', 'publico',
-           'the_budget_fashionista'
+           'the_budget_fashionista', 'elperiodico_catalan',
+           'elperiodico_spanish', 'expansion_spanish', 'lavanguardia',
+           'marca',
           )]
 
 import re, imp, inspect, time, os
diff --git a/src/calibre/web/feeds/recipes/recipe_elperiodico_catalan.py b/src/calibre/web/feeds/recipes/recipe_elperiodico_catalan.py
new file mode 100644
index 0000000000..01a9d16d6b
--- /dev/null
+++ b/src/calibre/web/feeds/recipes/recipe_elperiodico_catalan.py
@@ -0,0 +1,55 @@
+#!/usr/bin/env  python
+# -*- coding: utf-8 -*-
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+elperiodico.cat
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import Tag
+
+class ElPeriodico_cat(BasicNewsRecipe):
+    title                 = 'El Periodico de Catalunya'
+    __author__            = 'Darko Miletic'
+    description           = 'Noticias desde Catalunya'
+    publisher             = 'elperiodico.cat'
+    category              = 'news, politics, Spain, Catalunya'
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    delay                 = 1
+    encoding              = 'cp1252'
+    language              = _('Catalan')
+
+    html2lrf_options = [
+                          '--comment'  , description
+                        , '--category' , category
+                        , '--publisher', publisher
+                        ]
+
+    html2epub_options  = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
+
+    feeds              = [(u"Tota l'edició", u'http://www.elperiodico.cat/rss.asp?id=46')]
+
+
+    keep_only_tags = [dict(name='div', attrs={'id':'noticia'})]
+
+    remove_tags        = [
+                              dict(name=['object','link','script'])
+                             ,dict(name='ul',attrs={'class':'herramientasDeNoticia'})
+                             ,dict(name='div', attrs={'id':'inferiores'})
+                         ]
+
+    def print_version(self, url):
+        return url.replace('/default.asp?','/print.asp?')
+
+    def preprocess_html(self, soup):
+        mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
+        soup.head.insert(0,mcharset)
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup
+
diff --git a/src/calibre/web/feeds/recipes/recipe_elperiodico_spanish.py b/src/calibre/web/feeds/recipes/recipe_elperiodico_spanish.py
new file mode 100644
index 0000000000..750e4884e7
--- /dev/null
+++ b/src/calibre/web/feeds/recipes/recipe_elperiodico_spanish.py
@@ -0,0 +1,55 @@
+#!/usr/bin/env  python
+# -*- coding: utf-8 -*-
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+elperiodico.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import Tag
+
+class ElPeriodico_esp(BasicNewsRecipe):
+    title                 = 'El Periodico de Catalunya'
+    __author__            = 'Darko Miletic'
+    description           = 'Noticias desde Catalunya'
+    publisher             = 'elperiodico.com'
+    category              = 'news, politics, Spain, Catalunya'
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    delay                 = 1
+    encoding              = 'cp1252'
+    language              = _('Spanish')
+
+    html2lrf_options = [
+                          '--comment'  , description
+                        , '--category' , category
+                        , '--publisher', publisher
+                        ]
+
+    html2epub_options  = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
+
+    feeds              = [(u"Toda la edición", u'http://www.elperiodico.com/rss.asp?id=46')]
+
+
+    keep_only_tags = [dict(name='div', attrs={'id':'noticia'})]
+
+    remove_tags        = [
+                              dict(name=['object','link','script'])
+                             ,dict(name='ul',attrs={'class':'herramientasDeNoticia'})
+                             ,dict(name='div', attrs={'id':'inferiores'})
+                         ]
+
+    def print_version(self, url):
+        return url.replace('/default.asp?','/print.asp?')
+
+    def preprocess_html(self, soup):
+        mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
+        soup.head.insert(0,mcharset)
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup
+
diff --git a/src/calibre/web/feeds/recipes/recipe_expansion_spanish.py b/src/calibre/web/feeds/recipes/recipe_expansion_spanish.py
new file mode 100644
index 0000000000..2d402d343f
--- /dev/null
+++ b/src/calibre/web/feeds/recipes/recipe_expansion_spanish.py
@@ -0,0 +1,58 @@
+#!/usr/bin/env  python
+# -*- coding: utf-8 -*-
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+www.expansion.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import Tag
+
+class Expansion(BasicNewsRecipe):
+    title                 = 'Diario Expansion'
+    __author__            = 'Darko Miletic'
+    description           = 'Lider de informacion de mercados, economica y politica'
+    publisher             = 'expansion.com'
+    category              = 'news, politics, Spain'
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    delay                 = 1
+    encoding              = 'iso-8859-15'
+    language              = _('Spanish')
+    direction             = 'ltr'
+
+    html2lrf_options = [
+                          '--comment'  , description
+                        , '--category' , category
+                        , '--publisher', publisher
+                        ]
+
+    html2epub_options  = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
+
+    feeds              = [
+                            (u'Ultimas noticias', u'http://rss.expansion.com/rss/descarga.htm?data2=178')
+                           ,(u'Temas del dia'   , u'http://rss.expansion.com/rss/descarga.htm?data2=178')
+                         ]
+
+
+    keep_only_tags = [dict(name='div', attrs={'id':'principal'})]
+
+    remove_tags        = [
+                             dict(name=['object','link','script'])
+                            ,dict(name='div', attrs={'class':['utilidades','tit_relacionadas']})
+                         ]
+
+    remove_tags_after = [dict(name='div', attrs={'class':'tit_relacionadas'})]
+
+    def preprocess_html(self, soup):
+        soup.html['dir' ] = self.direction
+        mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
+        soup.head.insert(0,mcharset)
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup
+
diff --git a/src/calibre/web/feeds/recipes/recipe_lavanguardia.py b/src/calibre/web/feeds/recipes/recipe_lavanguardia.py
new file mode 100644
index 0000000000..1daa2940ba
--- /dev/null
+++ b/src/calibre/web/feeds/recipes/recipe_lavanguardia.py
@@ -0,0 +1,69 @@
+#!/usr/bin/env  python
+# -*- coding: utf-8 -*-
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+www.lavanguardia.es
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import Tag
+
+class LaVanguardia(BasicNewsRecipe):
+    title                 = 'La Vanguardia Digital'
+    __author__            = 'Darko Miletic'
+    description           = u'Noticias desde España'
+    publisher             = 'La Vanguardia'
+    category              = 'news, politics, Spain'
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    delay                 = 1
+    encoding              = 'cp1252'
+    language              = _('Spanish')
+    direction             = 'ltr'
+
+    html2lrf_options = [
+                          '--comment'  , description
+                        , '--category' , category
+                        , '--publisher', publisher
+                        ]
+
+    html2epub_options  = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
+
+    feeds              = [
+                            (u'Ciudadanos'           , u'http://feeds.feedburner.com/lavanguardia/ciudadanos'   )
+                           ,(u'Cultura'              , u'http://feeds.feedburner.com/lavanguardia/cultura'      )
+                           ,(u'Deportes'             , u'http://feeds.feedburner.com/lavanguardia/deportes'     )
+                           ,(u'Economia'             , u'http://feeds.feedburner.com/lavanguardia/economia'     )
+                           ,(u'El lector opina'      , u'http://feeds.feedburner.com/lavanguardia/lectoropina'  )
+                           ,(u'Gente y TV'           , u'http://feeds.feedburner.com/lavanguardia/gente'        )
+                           ,(u'Internacional'        , u'http://feeds.feedburner.com/lavanguardia/internacional')
+                           ,(u'Internet y tecnologia', u'http://feeds.feedburner.com/lavanguardia/internet'     )
+                           ,(u'Motor'                , u'http://feeds.feedburner.com/lavanguardia/motor'        )
+                           ,(u'Politica'             , u'http://feeds.feedburner.com/lavanguardia/politica'     )
+                           ,(u'Sucessos'             , u'http://feeds.feedburner.com/lavanguardia/sucesos'      )
+                         ]
+
+
+    keep_only_tags = [
+                       dict(name='div', attrs={'class':'element1_3'})
+                     ]
+
+    remove_tags        = [
+                             dict(name=['object','link','script'])
+                            ,dict(name='div', attrs={'class':['colC','peu']})
+                         ]
+
+    remove_tags_after = [dict(name='div', attrs={'class':'text'})]
+
+    def preprocess_html(self, soup):
+        soup.html['dir' ] = self.direction
+        mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
+        soup.head.insert(0,mcharset)
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup
+
diff --git a/src/calibre/web/feeds/recipes/recipe_marca.py b/src/calibre/web/feeds/recipes/recipe_marca.py
new file mode 100644
index 0000000000..2920afeb6d
--- /dev/null
+++ b/src/calibre/web/feeds/recipes/recipe_marca.py
@@ -0,0 +1,55 @@
+#!/usr/bin/env  python
+# -*- coding: utf-8 -*-
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+www.marca.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import Tag
+
+class Marca(BasicNewsRecipe):
+    title                 = 'Marca'
+    __author__            = 'Darko Miletic'
+    description           = 'Noticias deportivas'
+    publisher             = 'marca.com'
+    category              = 'news, sports, Spain'
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    delay                 = 1
+    encoding              = 'iso-8859-15'
+    language              = _('Spanish')
+    direction             = 'ltr'
+
+    html2lrf_options = [
+                          '--comment'  , description
+                        , '--category' , category
+                        , '--publisher', publisher
+                        ]
+
+    html2epub_options  = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
+
+    feeds              = [(u'Portada', u'http://rss.marca.com/rss/descarga.htm?data2=425')]
+
+    keep_only_tags = [dict(name='div', attrs={'class':['cab_articulo','col_izq']})]
+
+    remove_tags        = [
+                             dict(name=['object','link','script'])
+                            ,dict(name='div', attrs={'class':['colC','peu']})
+                            ,dict(name='div', attrs={'class':['utilidades estirar','bloque_int_corr estirar']})
+                         ]
+
+    remove_tags_after = [dict(name='div', attrs={'class':'bloque_int_corr estirar'})]
+
+    def preprocess_html(self, soup):
+        soup.html['dir' ] = self.direction
+        mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
+        soup.head.insert(0,mcharset)
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup
+