googler "Top stories" support https://github.com/jarun/googler/issues/361

0001-Add-experimental-support-for-Top-stories.patch

From 06e70e23f8086bb68d98893bbaeaa9df3639ef89 Mon Sep 17 00:00:00 2001
From: Zhiming Wang <[email protected]>
Date: Sun, 11 Oct 2020 23:19:12 +0800
Subject: [PATCH] Add experimental support for "Top stories"

---
 googler | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/googler b/googler
index b1479a7..e2865d2 100755
--- a/googler
+++ b/googler
@@ -2343,6 +2343,35 @@ class GoogleParser(object):
         cw = lambda s: re.sub(r'[ \t\n\r]+', ' ', s) if s is not None else s
 
         index = 0
+
+        # Try to parse "Top stories".
+        #
+        # Detection doesn't work on all pages! E.g. when I search
+        # "covid" the layout for "Top stories" is simply different....
+        carousel = tree.select('g-section-with-header g-scrolling-carousel')
+        if carousel:
+            # Devise a really crappy strategy to tell a "Top stories"
+            # carousel apart from a Twitter carousel, which unfortunately
+            # shares the same structure.
+            section = next(el for el in carousel.ancestors() if el.tag == 'g-section-with-header')
+            if section.first_element_child().select('title-with-lhs-icon'):
+                # This section contains a title-with-lhs-icon (":newspaper
+                # icon: Top stories") which a Twitter carousel doesn't have,
+                # a good sign...
+                for card in carousel.select_all('g-inner-card'):
+                    heading = card.select('[role=heading]')
+                    title = heading.text
+                    a = card.select('a')
+                    url = a.attr('href')
+                    metadata_node = heading.parent.last_element_child()
+                    metadata = metadata_node.text if metadata_node is not heading else ''
+                    result = Result(index + 1, cw(title), url, '',
+                                    metadata=cw(metadata), sitelinks=[], matches=[])
+                    if result not in self.results:
+                        self.results.append(result)
+                        index += 1
+
+        # Regular results.
         for div_g in tree.select_all('div.g'):
             if div_g.select('.hp-xpdbox'):
                 # Skip smart cards.
-- 
2.28.0