From 4eed12039fca7322305b550933b94856a408fed2 Mon Sep 17 00:00:00 2001
From: Ken Kellner <ken@kenkellner.com>
Date: Sat, 21 Apr 2018 14:17:16 -0400
Subject: Handle Elsevier redirects better

---
 article_epub/utilities.py | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/article_epub/utilities.py b/article_epub/utilities.py
index 60a2d97..b9da761 100644
--- a/article_epub/utilities.py
+++ b/article_epub/utilities.py
@@ -1,6 +1,7 @@
 import requests
 from bs4 import BeautifulSoup
 import sys
+from urllib.parse import unquote
 
 def url_from_title(title):
     print("Getting URL from title......")
@@ -33,7 +34,16 @@ def url_from_title(title):
 
 def url_from_doi(doi):
     print("Getting URL from DOI........",end='',flush=True)
-    url = requests.get('https://doi.org/'+doi,
-            headers={'User-Agent':'Mozilla/5.0'}).url
+    r = requests.get('https://doi.org/'+doi,
+            headers={'User-Agent':'Mozilla/5.0'})
+
+    #To handle Elsevier linkinghub redirects
+    soup = BeautifulSoup(r.content,'html.parser')
+    if soup.find('input',{'id':'redirectURL'}) is not None:
+        url_raw = soup.find('input',{'id':'redirectURL'})['value']
+        url = unquote(url_raw.split('_returnURL')[0])
+    else:
+        url = r.url
+
     print('done')
     return(url)
-- 
cgit v1.2.3