Merge pull request #377 from flairNLP/update-telegraph

TheTelegraph: add subheadline selector
flairNLP · Feb 26, 2024 · f117e49 · f117e49
2 parents f856b16 + 54fd984
commit f117e49
Showing 1 changed file with 2 additions and 0 deletions.
diff --git a/src/fundus/publishers/uk/the_telegraph.py b/src/fundus/publishers/uk/the_telegraph.py
@@ -15,6 +15,7 @@
 class TheTelegraphParser(ParserProxy):
     class V1(BaseParser):
         _paragraph_selector = CSSSelector("div.articleBodyText p")
+        _subheadline_selector = CSSSelector("div.articleBodyText h2")
         _summary_selector = CSSSelector("p[itemprop='description']")
         _datetime_selector = CSSSelector("time[itemprop='datePublished']")
 
@@ -24,6 +25,7 @@ def body(self) -> ArticleBody:
                 self.precomputed.doc,
                 summary_selector=self._summary_selector,
                 paragraph_selector=self._paragraph_selector,
+                subheadline_selector=self._subheadline_selector,
             )
             return body