From caf721267904187d87377d2a6272f614915b16e0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Tomasz=20D=C5=82ugosz?= <tomek3d@gmail.com>
Date: Tue, 18 Feb 2014 00:24:56 +0100
Subject: [PATCH] =?UTF-8?q?Go=C5=9B=C4=87=20Niedzielny:=20add=20cover,=20i?=
 =?UTF-8?q?mprove=20image=20captions,=20add=20publisher?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 recipes/gosc_full.recipe | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/recipes/gosc_full.recipe b/recipes/gosc_full.recipe
index 4a8b13c139..5903e809e1 100644
--- a/recipes/gosc_full.recipe
+++ b/recipes/gosc_full.recipe
@@ -10,9 +10,9 @@ import re
 from lxml import html
 
 class GN(BasicNewsRecipe):
-
     __author__ = 'Piotr Kontek, Tomasz Długosz'
     title = u'Gość Niedzielny - pełny numer'
+    publisher = 'Wydawnictwo Kurii Metropolitalnej w Katowicach'
     description = 'Ogólnopolski tygodnik katolicki - pełny numer sprzed 4 tygodni'
     encoding = 'utf-8'
     no_stylesheets = True
@@ -28,7 +28,7 @@ class GN(BasicNewsRecipe):
 
     def parse_index(self):
         soup = self.index_to_soup('http://gosc.pl' + self.find_last_issue())
-        #self.masthead = 'http://www.gosc.pl' + soup.find('div',attrs={'class':'fl-w100 release-wp'}).findAll('a')[-4].contents[0]['src']
+        self.cover_url = 'http://www.gosc.pl' + soup.find('div',attrs={'class':'fl-w100 release-wp'}).findAll('a')[-4].contents[0]['src']
         feeds = []
         # wstepniak
         a = soup.find('div',attrs={'class':'release-wp-b'}).find('a')
@@ -74,6 +74,10 @@ class GN(BasicNewsRecipe):
     def postprocess_html(self, soup, first_fetch):
         for r in soup.findAll(attrs={'class':'pgr'}):
             r.extract()
+        for r in soup.findAll(attrs={'class':['di_dr', 'doc_image']}):
+            del r['style']
+        for r in soup.findAll(attrs={'class':'cm-i-a'}):
+            r.replaceWith( r.prettify() + '<div style="clear:both"></div>')
         return soup
 
     keep_only_tags = [
@@ -81,7 +85,7 @@ class GN(BasicNewsRecipe):
     ]
 
     remove_tags = [
-        dict(name='p', attrs={'class':['r tr', 'l l-2', 'wykop']}),
+        dict(name='p', attrs={'class':['r tr', 'l l-2', 'wykop', 'tags']}),
         dict(name='div', attrs={'class':['doc_actions', 'cf', 'fr1_cl']}),
         dict(name='div', attrs={'id':'vote'}),
         dict(name='a', attrs={'class':'img_enlarge'})
@@ -90,6 +94,6 @@ class GN(BasicNewsRecipe):
     extra_css = '''
             h1 {font-size:150%}
             p.limiter {font-size:150%; font-weight: bold}
-            span.cm-i-a {text-transform:uppercase;}
-            span.cm-i-p {font-style:italic; font-size:70%}
+            span.cm-i-a {text-transform:uppercase;font-size:50%}
+            span.cm-i-p {font-style:italic; font-size:70%;text-align:right}
         '''