Add example of check for fulltext

2 files changed, 13 insertions, 1 deletions

diff --git a/article_epub/publisher.py b/article_epub/publisher.py
index 4161e78..7216d7d 100644
--- a/article_epub/publisher.py
+++ b/article_epub/publisher.py
@@ -21,6 +21,9 @@ class Publisher(object):
     def get_final_url(self):
         pass
 
+    def check_fulltext(self):
+        pass
+
     def soupify(self):
         """Get HTML from article's page"""
         self.get_final_url()
@@ -107,6 +110,7 @@ class Publisher(object):
                     +self.journal+'. '+' doi: '+self.doi
     
     def extract_data(self):
+        self.check_fulltext()
         print('Extracting data from HTML...',end='',flush=True)
         self.get_doi()
         self.get_metadata()
diff --git a/article_epub/publishers/sciencedirect.py b/article_epub/publishers/sciencedirect.py
index 6ca4d8f..2078a45 100644
--- a/article_epub/publishers/sciencedirect.py
+++ b/article_epub/publishers/sciencedirect.py
@@ -1,10 +1,18 @@
 from article_epub.publisher import Publisher, register_publisher
+import sys
 
 class ScienceDirect(Publisher):
     """Class for Science Direct (Elsevier) articles"""
 
     domains = ["sciencedirect.com","elsevier.com"]
-    
+
+    def check_fulltext(self):
+        if self.soup.find('div',class_='Body') == None:
+            print('Error: Can\'t access fulltext of article')
+            sys.exit()
+        else:
+            return(True)
+
     def get_doi(self):
         if self.doi == None:
             doi_raw = self.soup.find('a',class_='doi').get('href').split('/')