From f28a2953622f8d944eee48e0fe0edafc6746a015 Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Tue, 18 Nov 2014 14:28:54 +0530
Subject: [PATCH] Update Nikkei News

---
 recipes/nikkei_news.recipe | 37 ++++++++++++++++++++++---------------
 1 file changed, 22 insertions(+), 15 deletions(-)

diff --git a/recipes/nikkei_news.recipe b/recipes/nikkei_news.recipe
index 9a974e9596..fa677c4c77 100644
--- a/recipes/nikkei_news.recipe
+++ b/recipes/nikkei_news.recipe
@@ -26,30 +26,32 @@ class NikkeiNet_paper_subscription(BasicNewsRecipe):
 #                       {'class':"cmnc-zoom"},
                        {'class':"cmn-hide"},
                        {'name':'form'},
+                       {'class':'cmn-print_headline cmn-clearfix'},
+                       {'id':'ABOUT_NIKKEI'},
                   ]
     remove_tags_after = {'class':"cmn-indent"}
 
     def get_browser(self):
         br = BasicNewsRecipe.get_browser(self)
 
-        #pp.pprint(self.parse_index())
-        #exit(1)
+        # pp.pprint(self.parse_index())
+        # exit(1)
 
-        #br.set_debug_http(True)
-        #br.set_debug_redirects(True)
-        #br.set_debug_responses(True)
+        # br.set_debug_http(True)
+        # br.set_debug_redirects(True)
+        # br.set_debug_responses(True)
 
         if self.username is not None and self.password is not None:
             print "-------------------------open top page-------------------------------------"
             br.open('http://www.nikkei.com/')
             print "-------------------------open first login form-----------------------------"
-            try: 
+            try:
                 url = br.links(url_regex="www.nikkei.com/etc/accounts/login").next().url
             except StopIteration:
                 url = 'http://www.nikkei.com/etc/accounts/login?dps=3&pageflag=top&url=http%3A%2F%2Fwww.nikkei.com%2F'
-            br.open(url)     #br.follow_link(link)
+            br.open(url)  # br.follow_link(link)
             #response = br.response()
-            #print response.get_data()
+            # print response.get_data()
             print "-------------------------JS redirect(send autoPostForm)--------------------"
             br.select_form(name='autoPostForm')
             br.submit()
@@ -64,9 +66,9 @@ class NikkeiNet_paper_subscription(BasicNewsRecipe):
             br.select_form(nr=0)
             br.submit()
 
-            #br.set_debug_http(False)
-            #br.set_debug_redirects(False)
-            #br.set_debug_responses(False)
+            # br.set_debug_http(False)
+            # br.set_debug_redirects(False)
+            # br.set_debug_responses(False)
         return br
 
     def cleanup(self):
@@ -77,18 +79,18 @@ class NikkeiNet_paper_subscription(BasicNewsRecipe):
         print "-------------------------get index of paper--------------------------------"
         result = []
         soup = self.index_to_soup('http://www.nikkei.com/paper/')
-        #soup = self.index_to_soup(self.test_data())
+        # soup = self.index_to_soup(self.test_data())
         sections = soup.findAll('div', 'cmn-section kn-special JSID_baseSection')
-	if len(sections) == 0:
+        if len(sections) == 0:
             sections = soup.findAll('div', 'cmn-section kn-special')
         for sect in sections:
             sect_title = sect.find('h3', 'cmnc-title').string
             sect_result = []
             for elem in sect.findAll(attrs={'class':['cmn-article_title']}):
-                if elem.span.a == None  or  elem.span.a['href'].startswith('javascript') :
+                if elem.span.a is None or elem.span.a['href'].startswith('javascript') :
                     continue
                 url = 'http://www.nikkei.com' + elem.span.a['href']
-                url = re.sub("/article/", "/print-article/", url) # print version.
+                url = re.sub("/article/", "/print-article/", url)  # print version.
                 span = elem.span.a.span
                 if ((span is not None) and (len(span.contents) > 1)):
                     title = span.contents[1].string
@@ -97,3 +99,8 @@ class NikkeiNet_paper_subscription(BasicNewsRecipe):
             result.append([sect_title, sect_result])
         return result
 
+    def populate_article_metadata(self, article, soup, first):
+        elm = soup.find('div', {"class":"cmn-article_text JSID_key_fonttxt"})
+        elm_text = ''.join([s.string for s in elm])
+        article.summary = elm_text
+        article.text_summary = elm_text