From be8f1d134681caaa15485246b65551a67e5bd5a5 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Mon, 24 Feb 2020 17:38:42 -0800
Subject: ingest: handle missing chemrxvi tag

---
 python/sandcrawler/html.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'python')

diff --git a/python/sandcrawler/html.py b/python/sandcrawler/html.py
index e993e74..c76d7a2 100644
--- a/python/sandcrawler/html.py
+++ b/python/sandcrawler/html.py
@@ -303,7 +303,7 @@ def extract_fulltext_url(html_url, html_body):
     if "://chemrxiv.org/articles/" in html_url or '.figshare.org/articles/' in html_url:
         # <script id="app-data" type="text/json"> [...] </script>
         json_tag = soup.find('script', id="app-data", attrs={"type": "text/json"})
-        if json_tag.string:
+        if json_tag and json_tag.string:
             app_data = json.loads(json_tag.string)
             # "exportPdfDownloadUrl": "https://s3-eu-west-1.amazonaws.com/itempdf74155353254prod/10101419/Biradical_Formation_by_Deprotonation_in_Thiazole-Derivatives__The_Hidden_Nature_of_Dasatinib_v1.pdf"
             url = app_data.get('article', {}).get('exportPdfDownloadUrl')
-- 
cgit v1.2.3