Also add comment url when there are 0 comment

polyrabbit · Jul 2, 2024 · eb87437 · eb87437
1 parent e938b54
commit eb87437
Show file tree

Hide file tree

Showing 3 changed files with 5 additions and 4 deletions.
diff --git a/hacker_news/parser.py b/hacker_news/parser.py
@@ -64,8 +64,9 @@ def parse_news_list(self):
                 submit_time = self.human2datetime(submit_time)
             # In case of no comments yet
             comment_dom = subtext_dom.find('a', string=re.compile(r'\d+.+comment')) or Null
+            discuss_dom = subtext_dom.find('a', string=re.compile(r'discuss')) or Null
             comment_cnt = re.search(r'\d+', comment_dom.get_text() or '0').group()
-            comment_url = self.get_comment_url(comment_dom['href'])
+            comment_url = self.get_comment_url(comment_dom['href']) or self.get_comment_url(discuss_dom['href'])
 
             items.append(News(
                 rank=rank,

diff --git a/publish.py b/publish.py
@@ -109,7 +109,7 @@ def gen_feed(news_list):
                      (
                              ' <a href="%s" target="_blank">[summary]</a>' % f'{config.site}/#{news.slug()}'),
                      (
-                         ' <a href="%s" target="_blank">[comments]</a>' % news.comment_url if news.comment_url and news.comment_url else '')),
+                         ' <a href="%s" target="_blank">[comments]</a>' % news.comment_url if news.comment_url else '')),
                  author={
                      'name': news.author,
                      'uri': news.author_link

diff --git a/test/test_html_parser.py b/test/test_html_parser.py
@@ -237,12 +237,12 @@ def test_arxiv_content(self):
     def test_link_intensive_wikipedia(self):
         parser = parser_factory('https://en.wikipedia.org/wiki/Google_Sidewiki')
         content = parser.get_content()
-        self.assertTrue(content.startswith('Google Sidewiki was a web annotation tool from Google'))
+        self.assertTrue(content.startswith('Google Sidewiki was a web annotation tool from Google'), msg=content[:100])
 
     def test_dynamic_js_page(self):
         parser = parser_factory('https://www.science.org/content/article/u-s-wants-change-how-researchers-get-access-huge-trove-health-data-many-don-t-idea')
         content = parser.get_content()
-        self.assertTrue(content.startswith('Health researchers'))
+        self.assertTrue(content.startswith('Health researchers'), msg=content[:100])
 
     def test_longer_meta_description(self):
         html_doc = """