From ab72fba13bb94deceaa0aba0f2b54b2d80928f46 Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Sat, 7 Nov 2009 08:42:47 -0700
Subject: [PATCH] IGN:Split new guardian recipe into sections

---
 resources/images/news/guardian.png | Bin 0 -> 548 bytes
 resources/recipes/guardian.recipe  | 155 +++++++++++++++--------------
 2 files changed, 79 insertions(+), 76 deletions(-)
 create mode 100644 resources/images/news/guardian.png

diff --git a/resources/images/news/guardian.png b/resources/images/news/guardian.png
new file mode 100644
index 0000000000000000000000000000000000000000..64425a3b5574f662bd2058dd0ff2de2f09a98f75
GIT binary patch
literal 548
zcmeAS@N?(olHy`uVBq!ia0vp^0wB!61|;P_|4#%`Y)RhkE)4%caKYZ?lYt_f1s;*b
zK-vS0-A-oPfdtD69Mgd`SU*F|v9*U87#Mv$T^vI!PA?5s^grw%QLAj~o7L5HYFSs;
z#5p;soE=sx93EP2ln>xJXw*6@LiS*wOvl6!vE!=FXQrN7`_9L+P{AWV_q~FOO?mnK
zz3*$k-{XA{U-w8pAZ7NweVj>>3=Cmc7yOiRJ?XF}R^T+l*>Df>Ru6$4W@*XtyO#aC
z_4SY1Q<mtr>&gQU=&Ropy1iUjMD=ydyY-fi4{pqD{?XYKYC0)Lvt<6Abfw0fi@l$2
z`rdzTSNw6#Uzh%I`Ax7XU&_|U8yhSrH>p?Zq(^fZ-y&i0@bq~#Q&t_z_@yCGAYJO~
z`ru6=`-|JN#JASIZx(KGZ)so7pCqX;t#MI`hd66QXgABf3wO@Ezr_&~?R9LG6ubEL
z1wU8)?s&O6CJE@mB(ra>;*Tsv<zA?7aSv^HU$7^p-R9Whm(J?qzTr3J182>=-TrY7
zSL?-%%t<TnOl6B_N~~RVBp|m07|N<8t`Q|Ei6yC4$wjF^iowXhz*5)HP}jgb#K6MJ
z(8S8b49K=JFtE%2!Hl9IH$NpatrDccLf60qh(Zhvtbj^En$3V3J{78~0W~mqy85}S
Ib4q9e073210{{R3

literal 0
HcmV?d00001

diff --git a/resources/recipes/guardian.recipe b/resources/recipes/guardian.recipe
index a493072034..194e20d478 100644
--- a/resources/recipes/guardian.recipe
+++ b/resources/recipes/guardian.recipe
@@ -6,7 +6,10 @@ __docformat__ = 'restructuredtext en'
 '''
 www.guardian.co.uk
 '''
-
+import string
+import re
+from calibre import strftime
+from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Guardian(BasicNewsRecipe):
@@ -42,101 +45,101 @@ class Guardian(BasicNewsRecipe):
                     #full-contents{font-size:small; font-family:Arial,Helvetica,sans-serif;font-weight:normal;}
                     #match-stats-summary{font-size:small; font-family:Arial,Helvetica,sans-serif;font-weight:normal;}
                 '''
-
-
-
-   # feeds = [
-   #     ('Front Page', 'http://www.guardian.co.uk/rss'),
-   #     ('Business', 'http://www.guardian.co.uk/business/rss'),
-   #     ('Sport', 'http://www.guardian.co.uk/sport/rss'),
-   #     ('Culture', 'http://www.guardian.co.uk/culture/rss'),
-   #     ('Money', 'http://www.guardian.co.uk/money/rss'),
-   #     ('Life & Style', 'http://www.guardian.co.uk/lifeandstyle/rss'),
-   #     ('Travel', 'http://www.guardian.co.uk/travel/rss'),
-   #     ('Environment', 'http://www.guardian.co.uk/environment/rss'),
-   #     ('Comment','http://www.guardian.co.uk/commentisfree/rss'),
-   #     ]
-
-   # def get_article_url(self, article):
-   #       url = article.get('guid', None)
-   #       if '/video/' in url or '/flyer/' in url or '/quiz/' in url or \
-   #           '/gallery/' in url  or 'ivebeenthere' in url or \
-   #           'pickthescore' in url or 'audioslideshow' in url :
-   #           url = None
-   #       return url
-
-    def parse_index(self):
-
-            articles = []
-
-
+   
+    def parse_index(self):            
+           
             soup = self.index_to_soup('http://www.guardian.co.uk/theguardian')
              # find cover pic
-            img = soup.find( 'img',attrs ={'alt':'Guardian digital edition'})
-
-            if img is not None:
-                self.cover_url = img['src']
-
+            img = soup.find( 'img',attrs ={'alt':'Guardian digital edition'})        
+            if img is None: return None
+            else:
+                self.cover_url = img['src']                
              # end find cover pic
+            sections = []
+            ans = []
             for li in soup.findAll( 'li'):
-
-                if li.a and li.a.has_key('href'):
-                        url =  li.a['href']
-                        if 'mainsection' in url:
-
-
-                            #find the articles in the Main Section
-
+                section = ''
+                articles = []
+                                
+                if li.a and li.a.has_key('href'):                
+                        url =  li.a['href']                        
+                        if 'mainsection' in url:                            
+                            section = self.tag_to_string(url)
+                            i = len(section)
+                            
+                            index1 = section.rfind('/',0,i)
+                            section = section[index1+1:i]                            
+                            sections.append(section)
+                            
+                            #find the articles in the Main Section  start                          
                             soup = self.index_to_soup(url)
-
+                            date = strftime('%a, %d %b')
+                            descl = []
+                            
+                            for desclist in  soup.findAll(name='div',attrs={'class':"trailtext"}):
+                                descl.append(self.tag_to_string(desclist).strip())
+                            
+                            t = -1
                             for tag in soup.findAll('h3'):
+                                t = t+1
+                                
                                 for a in tag.findAll('a'):
-
-                                    if a and a.has_key('href'):
-
-                                        url2 =  a['href']
-
+                                    
+                                    if t < len(descl):                                   
+                                        desc =  descl[t]
                                     else:
-                                        url2 =''
-
+                                        desc = ''   
+                                    if a and a.has_key('href'):                
+                                        url2 =  a['href']                                        
+                                    else:
+                                        url2 =''                                    
                                     title = self.tag_to_string(a)
-                                    #eliminate duplicates
-                                    if len(articles) == 0:
-                                        desc = 'Main Section'
-                                        date = ''
-                                        articles.append({
+                                                                       
+                                    if len(articles) == 0:    #First article
+                                                                               
+                                         articles.append({
                                                  'title':title,
                                                  'date':date,
                                                  'url':url2,
                                                  'description':desc,
                                                     })
                                     else:
-                                        if len(articles) > 0:
-                                            if {'title':title,'date':date,'url':url2,'description':desc} in articles:
-                                                ulrl2 = ''
-                                    #eliminate duplicates
-                                            else:
-
-                                                desc = 'Main Section'
-                                                date = ''
-                                                articles.append({
+                                        #eliminate duplicates start
+                                        if {'title':title,'date':date,'url':url2,'description':desc} in articles : 
+                                                url2 = ''
+                                        #eliminate duplicates end
+                                        else:
+                                                if 'http://jobs.guardian.co.uk/' in url2:
+                                                    url2 = ''
+                                                else:
+                                                    
+                                                    articles.append({
                                                      'title':title,
                                                      'date':date,
                                                      'url':url2,
-                                                     'description':desc,
-                                                        })
-                            #find the articles in the Main Section
-                else:
-                        url =''
-
-
-
-
-            return [('Current Issue', articles)]
-
+                                                     'description':desc,                                                     
+                                                        })                                                
+                            #find the articles in the Main Section end
+                            ans.append( articles)
+                            
+                        else:
+                                url =''
+                        
+                        
+            titles = map(self.find_title, sections)
+            ans1 = list(zip(titles,ans))
+            
+            return ans1[2:]
+        
+    def find_title(self, section):
+        d = {'topstories':'Top Stories', 'international':'International', 'editorialsandreply':'Editorials and Reply',
+             'commentanddebate':'Comment and Debate','uknews':'UK News','saturday':'Saturday','sunday':'Sunday',
+                'reviews':'Reviews', 'obituaries':'Obituaries'}        
+        
+        return d.get(section, section)
 
     def preprocess_html(self, soup):
-
+          
           for item in soup.findAll(style=True):
               del item['style']