fixed the reading of the first paragraphs before H2

Zulko · Aug 3, 2024 · 47fef2d · 47fef2d
1 parent 4144672
commit 47fef2d
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 1 deletion.
diff --git a/data_collection/utils/wikipedia.py b/data_collection/utils/wikipedia.py
@@ -61,7 +61,7 @@ def _extract_sections_from_wikipedia_page(
     # Adding the intro section, before the first h2 tag
     paragraphs = []
     for element in soup.find_all(["p", "h2"]):
-        if element.name == "h2":
+        if element.name == "h2" and element.get_text() != "Contents":
             break
         if element.name == "p":
             paragraphs.append(element.get_text())

diff --git a/public/data/composers.json b/public/data/composers.json
@@ -104,6 +104,14 @@
     "birth_year": 1838,
     "death_year": 1875
   },
+  {
+    "full_name": "Felix Blumenfeld",
+    "wikipedia_url": "https://en.wikipedia.org/wiki/Felix_Blumenfeld",
+    "first_names": "Felix Mikhailovich",
+    "last_name": "Blumenfeld",
+    "birth_year": 1863,
+    "death_year": 1931
+  },
   {
     "full_name": "Luigi Boccherini",
     "first_names": "Luigi",