Merge pull request #383 from sparcs-kaist/hotfix/portal-crawl-no-src-img

Fix no src img exception

apps/core/management/scripts/portal_crawler.py

@@ -101,6 +101,9 @@ def _get_new_url_and_save_to_s3(url, session):
         hash = enc.hexdigest()[:20]
         filename = f'files/portal_image_{hash}.{url.split("_")[-1]}'
 
+        if url.startswith("/board"):
+            url = str(BASE_URL) + url
+
         r = session.get(url, stream=True, cookies=COOKIES)
         if r.status_code == 200:
             s3 = boto3.client("s3")
@@ -112,6 +115,8 @@ def _save_portal_image(html, session):
         soup = bs(html, "lxml")
         for child in soup.find_all("img", {}):
             old_url = child.attrs.get("src")
+            if old_url is None:
+                continue
             new_url = _get_new_url_and_save_to_s3(old_url, session)
             child["src"] = new_url