Fast fail for unknown urls

datahugger/__main__.py

@@ -14,8 +14,12 @@
 from datahugger.exceptions import DOIError
 
 
-def _red(s):
-    return f"\u001b[31m{s}\u001b[0m"
+def print_red(s):
+    print(f"\u001b[31m{s}\u001b[0m")
+
+
+def print_green(s):
+    print(f"\u001b[32m{s}\u001b[0m")
 
 
 def main():
@@ -94,15 +98,21 @@ def main():
         if logging.DEBUG == logging.root.level:
             raise doi_err
         else:
-            print(_red(f"DOI Error: {doi_err}"))
+            print_red(f"Error: {doi_err}")
+            print("")
+            print("Check if your DOI is correct at doi.org. Is the DOI valid?")
+            print("Please request support in the issue tracker:")
+            print("")
+            print("\thttps://github.com/J535D165/datahugger/issues/new/choose")
+            print()
             exit(1)
 
     except Exception as err:
         # raise error when log level is DEBUG
         if logging.DEBUG == logging.root.level:
             raise err
         else:
-            print(_red(f"Error: {err}"))
+            print_red(f"Error: {err}")
             print("")
             print("Do you think this is a data repository that needs to be supported?")
             print("Please request support in the issue tracker:")
@@ -112,7 +122,7 @@ def main():
             exit(1)
 
     if args.progress:
-        print("\u001b[32mDataset successfully downloaded.\u001b[0m")
+        print_green("Dataset successfully downloaded.")
 
 
 if __name__ == "__main__":

datahugger/api.py

@@ -179,9 +179,7 @@ def _base_request(
     if uri.hostname in URL_RESOLVE:
         r = requests.head(url, allow_redirects=True)
         if r.status_code == 404 and r.url and r.url.startswith("https://doi.org"):
-            raise DOIError(
-                f"DOI cannot be found in the DOI System, see https://doi.org/{doi}"
-            )
+            raise DOIError(f"DOI {doi} not found in the DOI system")
         elif r.status_code == 405:
             # head request not allowed, try get request
             r = requests.get(url, allow_redirects=True)
@@ -326,6 +324,9 @@ def _resolve_service(url, doi):
 def _resolve_service_from_netloc(url):
     uri = urlparse(url)
 
+    if not uri.hostname:
+        return None
+
     logging.info(f"Resolve service for netloc '{uri.hostname}'")
     if uri.hostname in SERVICES_NETLOC.keys():
         return SERVICES_NETLOC[uri.hostname]
@@ -338,6 +339,9 @@ def _resolve_service_from_netloc(url):
 
 
 def _resolve_service_with_re3data(doi):
+    if not doi:
+        return None
+
     logging.info("Resolve service with datacite and re3data")
     publisher = get_datapublisher_from_doi(doi)
     logging.info(f"Datacite publisher of dataset: {publisher}")