Merge branch 'master' of https://github.com/unkn0w7n/calibre

kovidgoyal · Nov 28, 2024 · 904bccb · 904bccb
2 parents 5e4b2aa + 0adbd16
commit 904bccb
Show file tree

Hide file tree

Showing 2 changed files with 18 additions and 11 deletions.
diff --git a/recipes/economist_world_ahead.recipe b/recipes/economist_world_ahead.recipe
@@ -28,7 +28,7 @@ def process_node(node):
     if ntype == 'PARAGRAPH':
         if node.get('textHtml'):
             return f'<p>{node.get("textHtml")}</p>'
-        return f'<p>{node.get("tex", "")}</p>'
+        return f'<p>{node.get("text", "")}</p>'
     elif ntype == 'IMAGE':
         alt = "" if node.get("altText") is None else node.get("altText")
         cap = ""
@@ -49,6 +49,7 @@ def process_node(node):
         print('** ', ntype)
         return ''
 
+
 def safe_dict(data, *names):
     ans = data
     for x in names:
@@ -187,15 +188,14 @@ class EconomistWorld(BasicNewsRecipe):
     }
 
     def get_browser(self, *args, **kwargs):
-        kwargs['user_agent'] = 'Mozilla/5.0 (Linux; Android 14; 330333QCG Build/AP1A.140705.005; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/125.0.6422.165 Mobile Safari/537.36 Lamarr/3.37.0-3037003 (android)' # noqa
+        kwargs['user_agent'] = (
+            'Mozilla/5.0 (Linux; Android 14; 330333QCG Build/AP1A.140705.005; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/125.0.6422.165 Mobile Safari/537.36 Lamarr/3.37.0-3037003 (android)' # noqa
+        )
         br = BasicNewsRecipe.get_browser(self, *args, **kwargs)
-        br.addheaders += [
-            ('x-requested-with', 'com.economist.lamarr')
-        ]
+        br.addheaders += [('x-requested-with', 'com.economist.lamarr')]
         return br
 
     def economist_test_article(self):
-        self.cover_url = None
         return [('Articles', [{'title':'test',
             'url':'https://www.economist.com/the-world-ahead/2024/11/20/ten-business-trends-for-2025-and-forecasts-for-15-industries'
         }])]
@@ -257,9 +257,12 @@ class EconomistWorld(BasicNewsRecipe):
         # open('/t/raw.html', 'wb').write(raw.encode('utf-8'))
         root_ = parse(raw)
         if '/interactive/' in url:
-            return '<html><body><article><h1>' + root_.xpath('//h1')[0].text + '</h1><em>' \
-                        + 'This article is supposed to be read in a browser' \
-                            + '</em></article></body></html>'
+            return (
+                '<html><body><article><h1>'
+                + root_.xpath('//h1')[0].text + '</h1><em>'
+                + 'This article is supposed to be read in a browser'
+                + '</em></article></body></html>'
+            )
 
         script = root_.xpath('//script[@id="__NEXT_DATA__"]')
 

diff --git a/recipes/indian_express.recipe b/recipes/indian_express.recipe
@@ -45,7 +45,7 @@ class IndianExpress(BasicNewsRecipe):
             'digital-subscriber-only h-text-widget ie-premium ie-first-publish adboxtop adsizes immigrationimg '
             'next-story-wrap ie-ie-share next-story-box brand-logo quote_section ie-customshare osv-ad-class '
             'custom-share o-story-paper-quite ie-network-commenting audio-player-tts-sec o-story-list subscriber_hide '
-            'author-social author-follow author-img premium_widget_below_article'
+            'author-social author-follow author-img premium_widget_below_article author-block'
         )
     ]
 
@@ -136,9 +136,13 @@ class IndianExpress(BasicNewsRecipe):
         return citem['content'].replace('300', '600')
 
     def preprocess_html(self, soup):
-        if h2 := soup.find(attrs={'itemprop': 'description'}):
+        if h2 := (soup.find(attrs={"itemprop": "description"}) or soup.find(**classes("synopsis"))):
             h2.name = 'p'
             h2['id'] = 'sub-d'
+        for span in soup.findAll(
+            "span", attrs={"class": ["ie-custom-caption", "custom-caption"]}
+        ):
+            span["id"] = "img-cap"
         for img in soup.findAll('img', attrs={'data-src': True}):
             img['src'] = img['data-src']
         if span := soup.find('span', content=True, attrs={'itemprop': 'dateModified'}):