From c0d533f7ec29e78bbf2fff4521ec9b46fb88453d Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Sat, 15 Apr 2023 21:24:44 +0530
Subject: [PATCH] Update Frontline and Outlook Magazine

---
 recipes/frontline.recipe     | 56 +++++++++++++++++++-----------------
 recipes/outlook_india.recipe |  3 ++
 2 files changed, 33 insertions(+), 26 deletions(-)

diff --git a/recipes/frontline.recipe b/recipes/frontline.recipe
index b3bd2de3a2..7a95524c8d 100644
--- a/recipes/frontline.recipe
+++ b/recipes/frontline.recipe
@@ -1,7 +1,6 @@
 from collections import defaultdict
 from calibre.web.feeds.news import BasicNewsRecipe, classes
 
-
 class Frontline(BasicNewsRecipe):
     title = u'Frontline'
     __author__ = 'unkn0wn'
@@ -16,18 +15,21 @@ class Frontline(BasicNewsRecipe):
     remove_attributes = ['height', 'width']
     resolve_internal_links = True
     extra_css = '''
-        .overline{ font-size:small; color:#404040; }
-        .person-name { font-size:small; font-weight:bold; }
-        .lead-img-caption, .caption-cont { font-size:small; text-align:center; }
+        .environment, .publish-time, .author { font-size:small; color:#404040; }
+        .caption { font-size:small; text-align:center; }
+        img { display:block; margin:0 auto; }
+        .question {font-weight:bold;}
     '''
 
     keep_only_tags = [
-        classes('article')
+        dict(name='div', attrs={'class':'container article-section'})
     ]
 
     remove_tags = [
-        classes('shareicon-article articleBottomLine secheader mobilesocialicons'),
-        dict(name='h2', attrs={'class':'title'})
+        classes(
+            'breadcrumb comments-shares share-page article-video '
+            'referpara slide-mobile title-patch hide-mobile related-stories'
+        ),
     ]
 
     def preprocess_html(self, soup):
@@ -36,11 +38,11 @@ class Frontline(BasicNewsRecipe):
                 source = img.findPrevious('source', srcset=True)
                 img.extract()
                 if source:
-                    source['src'] = source['srcset']
+                    source['src'] = source['srcset'].replace('_320','_1200')
                     source.name = 'img'
             else:
                 img['src'] = img['data-original']
-        for cap in soup.findAll(**classes('caption-cont')):
+        for cap in soup.findAll(**classes('caption')):
             cap.name = 'figcaption'
         return soup
 
@@ -50,30 +52,32 @@ class Frontline(BasicNewsRecipe):
         return soup
 
     def parse_index(self):
-        soup = self.index_to_soup('https://frontline.thehindu.com/magazine/')
-        issue = soup.find(**classes('sptar-archive-item')).find('a')['href']
-        self.log(issue)
-        soup = self.index_to_soup(issue)
-        time = soup.find(**classes('date')).findNext('h3')
-        if time:
-            self.timefmt = ' ' + self.tag_to_string(time)
-            self.log('Downloading Issue:', self.timefmt)
-        self.cover_url = soup.find(**classes('sptar-cover-item')).find('img')['data-original'].replace('FREE_320', 'FREE_810')
+        soup = self.index_to_soup('https://frontline.thehindu.com/current-issue/')
+            
+        if cover := soup.find('div', attrs={'class':'magazine'}):
+            self.cover_url = cover.find(**classes('sptar-image')).img['data-original'].replace('_320', '_1200')
+            self.log('Cover ', self.cover_url)
+            if desc := cover.find(**classes('sub-text')):
+                self.description = self.tag_to_string(desc)
+            
         feeds_dict = defaultdict(list)
-        for div in soup.findAll('div', attrs={'class':'brief-list-item'}):
-            a = div.find(**classes('brief-title')).find('a')
+        
+        mag = soup.find(**classes('section-magazine'))
+        for div in mag.findAll('div', attrs={'class':'content'}):
+            a = div.find(**classes('title')).find('a')
             url = a['href']
             title = self.tag_to_string(a)
             section = 'Articles'
-            cat = div.find(**classes('brief-cat'))
-            if cat:
+            if cat := div.find(**classes('label')):
                 section = self.tag_to_string(cat)
             desc = ''
-            art = div.find(**classes('artbody'))
-            if art:
+            
+            if art := div.find(**classes('sub-text')):
                 desc = self.tag_to_string(art)
+            if auth := div.find(**classes('author')):
+                desc = self.tag_to_string(auth) + ' | ' + desc
             if not url or not title:
                 continue
             self.log(section, '\n\t', title, '\n\t', desc, '\n\t\t', url)
-            feeds_dict[section].append({"title": title, "url": url})
-        return [(section, articles) for section, articles in feeds_dict.items()]
+            feeds_dict[section].append({"title": title, "url": url, "description": desc})
+        return [(section, articles) for section, articles in feeds_dict.items()]
\ No newline at end of file
diff --git a/recipes/outlook_india.recipe b/recipes/outlook_india.recipe
index f88714f386..a50f177c9d 100644
--- a/recipes/outlook_india.recipe
+++ b/recipes/outlook_india.recipe
@@ -32,6 +32,9 @@ class outlook(BasicNewsRecipe):
         )
     ]
 
+    def get_browser(self):
+        return BasicNewsRecipe.get_browser(self, user_agent='common_words/based')
+
     def parse_index(self):
         soup = self.index_to_soup('https://www.outlookindia.com/magazine')
         div = soup.find('div', attrs={'class':'wrapper'})