From f4703f602bbbf669b8b5de5ad1d69138163dc286 Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Fri, 30 Dec 2016 08:36:52 +0530
Subject: [PATCH] Update Clarin. Fixes #1653113 [Updated recipe for
 Clarin](https://bugs.launchpad.net/calibre/+bug/1653113)

---
 recipes/clarin.recipe    |  36 +++++++++++++++++++++++-------------
 recipes/icons/clarin.png | Bin 600 -> 684 bytes
 2 files changed, 23 insertions(+), 13 deletions(-)

diff --git a/recipes/clarin.recipe b/recipes/clarin.recipe
index a5b57875e0..616cb7c8cd 100644
--- a/recipes/clarin.recipe
+++ b/recipes/clarin.recipe
@@ -1,6 +1,10 @@
+#!/usr/bin/env  python2
+# -*- mode: python -*-
+# -*- coding: utf-8 -*-
+
 from __future__ import unicode_literals
 __license__ = 'GPL v3'
-__copyright__ = '2008-2015, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2008-2016, Darko Miletic <darko.miletic at gmail.com>'
 '''
 clarin.com
 '''
@@ -27,9 +31,8 @@ class Clarin(BasicNewsRecipe):
     needs_subscription = 'optional'
     INDEX = 'http://www.clarin.com'
     LOGIN = 'https://app-pase.clarin.com/pase-registracion/app/pase/ingresarNavegable?execution=e1s1'
-    masthead_url = 'http://www.clarin.com/static/CLAClarinV3/images/logo.png'
-    cover_url = strftime(
-        'http://tapas.clarin.com/tapa/%Y/%m/%d/%Y%m%d_thumb.jpg')
+    masthead_url = 'http://www.clarin.com/images/logo_clarin.svg'
+    cover_url = strftime('http://tapas.clarin.com/tapa/%Y/%m/%d/%Y%m%d_thumb.jpg')
     extra_css             = """
                                body{font-family: Arial,Helvetica,sans-serif}
                                h2{font-family: Georgia,serif; font-size: xx-large}
@@ -41,18 +44,24 @@ class Clarin(BasicNewsRecipe):
         'comment': description, 'tags': category, 'publisher': publisher, 'language': language
     }
 
-    remove_tags_before = dict(attrs={'class': 'int-nota-title'})
+    keep_only_tags = [
+                      dict(name='p'  , attrs={'class'   : 'volanta'}),
+                      dict(name='h1' , attrs={'itemprop': 'headline'}),
+                      dict(name='div', attrs={'class'   : 'bajada'}),
+                      dict(name='div', attrs={'class'   : 'body-nota'})
+                     ]
     remove_tags = [
         dict(name=['meta', 'base', 'link', 'iframe', 'embed', 'object']),
-        dict(attrs={'class': ['tags-bar', 'breadcrumb', 'share-bar']}),
-        dict(attrs={'id': ['relacionadas']})
+        dict(attrs={'class': ['tags-bar', 'breadcrumb', 'share-bar', 'share']}),
+        dict(name='div', attrs={'class': lambda x: x and 'r-nota' in x.split()}),
+        dict(attrs={'id': ['relacionadas']}),
+        dict(name='a', attrs={'class':'content-new'})
     ]
     remove_tags_after = dict(name='div', attrs={'id': 'relacionadas'})
     remove_attributes = ['lang']
 
     feeds = [
-
-    (u'Pagina principal', u'http://www.clarin.com/rss/'),
+    (u'Lo Ultimo', u'http://www.clarin.com/rss/lo-ultimo/'),
     (u'Politica', u'http://www.clarin.com/rss/politica/'),
     (u'Deportes', u'http://www.clarin.com/rss/deportes/'),
     (u'Mundo', u'http://www.clarin.com/rss/mundo/'),
@@ -67,10 +76,11 @@ class Clarin(BasicNewsRecipe):
         br = BasicNewsRecipe.get_browser(self)
         br.open(self.INDEX)
         if self.username is not None and self.password is not None:
-            data = urllib.urlencode({'ingresar_ingresar_paseForm': 'ingresar_ingresar_paseForm', 'ingresar_ingresar_email_paseInputComponent': self.username, 'ingresar_ingresar_palabraClave_paseInputComponent': self.password, 'ingresar_ingresar_ingresar_paseButton': 'Ingresar', 'javax.faces.ViewState': 'e1s1'  # noqa
+            data = urllib.urlencode({'ingresar_ingresar_paseForm': 'ingresar_ingresar_paseForm',
+                                     'ingresar_ingresar_email_paseInputComponent': self.username,
+                                     'ingresar_ingresar_palabraClave_paseInputComponent': self.password,
+                                     'ingresar_ingresar_ingresar_paseButton': 'Ingresar',
+                                     'javax.faces.ViewState': 'e1s1'  # noqa
                                      })
             br.open(self.LOGIN, data)
         return br
-
-    def get_article_url(self, article):
-        return article.get('guid',  None)
diff --git a/recipes/icons/clarin.png b/recipes/icons/clarin.png
index 258d2e16cb5b0ab032a90fbc3110f84eae34f091..98767b97f2d4c64d84869b53cfb6ed40ccd01bb2 100644
GIT binary patch
delta 661
zcmV;G0&4x(1gr&+BYyw{b3#c}2nYxWd<bNS00009a7bBm000ie000ie0hKEb8vp<T
zPDw;TR5*=wlS@d{VHCxG_dgF6GgOQS#2m*Wdn}`eQI-k?qMIVH7P)Cxs|un;n<%1a
z5e7j)5VVP+A_`Kp!eTa=7!*Ni8A*kTqN7gpf1DO$<7jr^TYr3)d(OS*<9x;<h}Fd&
zp<0YR2GxKGJ|lI930@gP6S@7CdvU33HnUS;wTp!_2qh%{QiQ<={|I<g9l^M@G|@l~
zF5d}Licxel%*Pv90hjo0OkK8Uqj_HrzD*J-S&2U}27v*24G{*r98q411?~SO6UO5g
zLBTB6+d=q58-LRbV-~$8)|TNCYx1m0OC8^8l%h;iAf3M|Nm5!0Hf_}mA-PoVcQBeV
zUP2hrIah{50cm|B#VE_pT!7QZV0;4Jyv4Tcn(Iq7;9I=Yw{=QUsA(Lzlq;|en!=O}
zN2JG3l*PHr8V9+Q%eNYNR(a1sj?x++WQF9%HsUctQhy&PY^<m7=3STxWhMg*e3{!X
z4=D{eIKLVEl)tl{aNld3p6BFWX{V_5Aa=1G0^rU=h(^Kn;blL0<Y5*96M~<N!CrOu
zY5|_T(D?FVsqLgRmCV#`-`6xDdBn4i>{8i`T3U*g_TFX5K_KlrtWg~4QFo>`>q!-x
zHA6(6t$+C|&?hQNGC7gzBn6VBM8CA7RqE)O-{|;RB|#ps%w((b(!{qd44ZUFlJs?0
znw-wDlTgwz%~CW!o!Eh;6Du`J>dcbg4=EL0p(Kuc*2}ZlQ<r$%!kp%Q8M97F37`Sk
v&h@LSQt6SPi0a{hbRw)&m+@mJm-7eiO@~Q^1`gPl00000NkvXXu0mjfntm!G

delta 576
zcmV-G0>AyN1=s|TBYy%PNkl<Zc-noEZEI3-7>E4^L9ldBK5aTjqv&bWqLn}kf}jP_
z%K#Py6$B8_CkT3CK@bq5A|M#OFZOnu*-SluTaAg?h^$%tQKg7f&((dDBa|udL)3F!
z=Xc-Sj#{mjk?2mTo2IT+Dms1gw2lu9>CMGu4cPx@9QAs=EPvs@0RTQ-ze%!Z0M#>y
z+O?nZ#z#!RVl9F02IuD<lN2!S8zDA+h{*IAvM&|@uviD60i>!8H|(Z-&)vRD!sX@V
z@oC=7Jw)en{KTXp&s3{bDl(d*xD?T)gh3q|Ai(dh-^iZ7OhRfK@@8Xf59;s~<$NB%
z0_|vrF*vLfeSbbSX74p5h35;rod}cM+K2K4P`*)8y<S!(k5Vj^tfqeplrN;!;4sP1
zPS(#|B;oX6Y;h9XJ3&k!<q4v;xrtr6!Y_fP`ac5ys1^xEuaA|h*LZ(xmiXBjRv$e<
z?LL5V2Z%e}q@T`X+V$H6-Vt6)i)=IsKw&-2TKE`-jDMCI7$Q18$>!%T&`}_8>|mJO
za)kW-2dwVc*MOBj)L3Nl#vN*a98L#;Y+41!P=W2u&5KZeN4Y#iPMqR<p#adFzg-a0
zhU`GbkOYx^Sdr>}qO!;j@7C<2=`64SJGLy=?<Y0?3;?rvVBJOtAtG8Lmz(I!1%3#C
zeWC4=mN}r@g6+4<XLfN3zy>=>%9bD_pl+q#uU{RR(z;mGfEJ)zGJgPM=qiZ<3Jy*H
O0000<MNUMnLSTX*SQH-s