Ajout d'un historique de toutes les relations des jeux de données (hasversion...)

1-enrich-with-datacite/concatenate-enrich-dois.py

@@ -66,6 +66,7 @@ if temp_rows :
 			df_fresh.loc[df_fresh.index[i], "doi"] = result[0]
 			df_fresh.loc[df_fresh.index[i], "relation_nbInstances"] = result[1]
 			df_fresh.loc[df_fresh.index[i], "relation_nbCitation"] = result[2]
+			df_fresh.loc[df_fresh.index[i], "relations_all"] = str(result[3])
 		else:
 			to_del.append(i)
 			

1-enrich-with-datacite/z_personal_functions.py

 import requests, json
 
-def get_origin_version(doi, count=0, cited=0):
+def get_origin_version(doi, count=0, cited=0, history=[]):
     cited = 0
     req = requests.get( f"https://api.datacite.org/dois/{doi}" )
     res = req.json()
-    result = (doi, count, cited)
+    result = (doi, count, cited, history)
     try:
         related = res["data"]["attributes"]["relatedIdentifiers"]
     except:
@@ -13,17 +13,17 @@ def get_origin_version(doi, count=0, cited=0):
         ignore = False
         duplicate = False
         for i in related:
-            if i["relationType"] == "IsVersionOf" and i.get("relatedIdentifierType") == "DOI": 
+            history.append([i.get("relationType"), i.get("relatedIdentifier")])
+            if i.get("relationType") == "IsVersionOf" and i.get("relatedIdentifierType") == "DOI": 
                 ignore = True
-                elem_to_save_i = i["relatedIdentifier"]
-                # supprimer le doi courant s'il apparait dans la liste
-            if i["relationType"] == "isCitedBy" and i.get("relatedIdentifierType") == "DOI": cited += 1
-            if i["relationType"] == "IsIdenticalTo" and i.get("relatedIdentifierType") == "DOI":
+                elem_to_save_i = i.get("relatedIdentifier")
+            if i.get("relationType") == "isCitedBy" and i.get("relatedIdentifierType") == "DOI": cited += 1
+            if i.get("relationType") == "IsIdenticalTo" and i.get("relatedIdentifierType") == "DOI":
                 duplicate = True
-                elem_to_save_d = i["relatedIdentifier"]
+                elem_to_save_d = i.get("relatedIdentifier")
         if duplicate and not(ignore):
-            result = (elem_to_save_d, count, cited)
-        if ignore: result = get_origin_version(elem_to_save_i, count+1, cited)
+            result = (elem_to_save_d, count, cited, history)
+        if ignore: result = get_origin_version(elem_to_save_i, count+1, cited, history)
     return result
 
 def get_md_from_datacite( doi ) :