Changed get_wikipedia_article to be more robust

Will now fall back to wiki if local copy isn't avail

dev_scripts/dex_info_writer.py

@@ -40,11 +40,28 @@ def _wiki_mirror_url(wikipedia_url: str) -> str:
 
 
 def fetch_wikipedia_article(wikipedia_url: str) -> str:
-    """Fetch a Wikipedia article, using the local Kiwix mirror if WIKI_LINK is set."""
+    """Fetch a Wikipedia article, using the local Kiwix mirror if WIKI_LINK is set.
+    Falls back to live Wikipedia if the mirror doesn't have the article.
+    Raises requests.HTTPError if neither source has it."""
     wikipedia_url = wikipedia_url.replace(" ", "_")
-    url = _wiki_mirror_url(wikipedia_url) if os.environ.get("WIKI_LINK") else wikipedia_url
-    response = requests.get(url, timeout=10)
-    response.raise_for_status()
+
+    urls_to_try = []
+    if os.environ.get("WIKI_LINK"):
+        urls_to_try.append(_wiki_mirror_url(wikipedia_url))
+    urls_to_try.append(wikipedia_url)
+
+    response = None
+    for url in urls_to_try:
+        r = requests.get(url, timeout=10)
+        if r.status_code == 404:
+            print(f"  Not found at {url}, trying next source...")
+            continue
+        r.raise_for_status()
+        response = r
+        break
+
+    if response is None:
+        raise requests.HTTPError(f"Article not found in any source: {wikipedia_url}")
 
     soup = BeautifulSoup(response.text, "html.parser")
 
@@ -164,7 +181,11 @@ if __name__ == "__main__":
                 continue
 
             print(f"[{i}/{total}] Generating entry for {specie['common_name']}...")
-            description = prompt_llm(specie["wikipedia_url"])
+            try:
+                description = prompt_llm(specie["wikipedia_url"])
+            except requests.HTTPError:
+                print(f"  No article found, skipping.")
+                continue
             description = re.sub(r"[^A-Za-z0-9.,!?'\-: ]", "", description)
             print(f"  {description}")
             writer.writerow([taxon_id, specie["common_name"], description])