Preventing unmanaged ressources from being deemed as downloaded. Handling image/tiff content-type.

utils/fix_links.py

@@ -13,7 +13,7 @@ def translate_content_type( content_type ):
     output = content_type
 
     # TODO: complete the following list!
-    types = ['pdf', 'html', 'zip', 'xml', 'javascript', 'json', 'csv']
+    types = ['pdf', 'html', 'zip', 'xml', 'javascript', 'json', 'csv', 'tiff']
 
     for the_type in types:
         if the_type in content_type:
@@ -26,6 +26,10 @@ def translate_content_type( content_type ):
     if content_type == 'application/vnd.ms-excel':
         output = 'XLS'
 
+    print('S ********************')
+    print(output)
+    print('E ********************')
+
     return output
 
 
@@ -53,6 +57,12 @@ def protocol_to_formats_and_services( links ):
         elif link['protocol'] == 'SOS':
             output[k]['formats'] = ['JSON', 'XML']
             output[k]['service'] = 'SOS'
+        elif link['protocol'] == 'HTML':
+            # in order to prevent HTML ressources to be deemed as downloadable
+            pass
+        elif link['protocol'].startswith("WWW:"):
+            # in order to prevent HTML ressources to be deemed as downloadable
+            pass
         else:
             output[k]['formats'] = [ link['protocol'] ]
 
@@ -83,7 +93,7 @@ def fix_links( links, credentials=None ):
         # FIX links in which the declared protocol is as bizarre as "WWW:LINK-1.0-http--link"
         # The KML protocol needs also to be fixed.
         if 'protocol' in link.keys() and any( [x in link['protocol'] for x in ['WWW', 'kml', 'html', 'null'] ] ):
-            print()
+            #print()
             #print(link['url'])
             try:
                 # let's try getting the information from the Web Server...
@@ -121,7 +131,7 @@ def fix_links( links, credentials=None ):
             except Exception as e:
                 logging.debug(e)
                 # ...otherwise, we make a guess on the basis of the information carried by the URL
-                known_formats = ['ecw', 'pdf', 'zip', 'kml', 'json', 'tif', 'tiff', 'csv', 'sos']
+                known_formats = ['ecw', 'pdf', 'zip', 'kml', 'json', 'tif', 'tiff', 'csv'] # sos
 
                 for known_format in known_formats:
                     if link['url'].lower().endswith(known_format):