From 133003344d2f3ca03123d2a0391f48436166154d Mon Sep 17 00:00:00 2001
From: adish-rmr <adish@hotmail.it>
Date: Fri, 2 Jan 2026 19:17:25 +0100
Subject: [PATCH] fixed dossier full & lead, ricerca non va in errore se almeno
 uno dei tre dossier esiste

---
 src/pif_compiler/services/srv_echa.py | 61 ++++++++++++++++-----------
 1 file changed, 37 insertions(+), 24 deletions(-)

diff --git a/src/pif_compiler/services/srv_echa.py b/src/pif_compiler/services/srv_echa.py
index 07b2957..57d2b85 100644
--- a/src/pif_compiler/services/srv_echa.py
+++ b/src/pif_compiler/services/srv_echa.py
@@ -64,14 +64,16 @@ def get_dossier_info(rmlId: str, type = active) -> dict:
         if type == active:
             return get_dossier_info(rmlId, inactive)
         return {}
-    dossier_info = {
-        "lastUpdatedDate": response_dossier_json['items'][0]['lastUpdatedDate'],
-        "registrationStatus": response_dossier_json['items'][0]['registrationStatus'],
-        "registrationStatusChangedDate": response_dossier_json['items'][0]['registrationStatusChangedDate'],
-        "registrationRole": response_dossier_json['items'][0]['reachDossierInfo']['registrationRole'],
-        "assetExternalId": response_dossier_json['items'][0]['assetExternalId'],
-        "rootKey": response_dossier_json['items'][0]['rootKey']
-    }
+    for dossier in response_dossier_json['items']:
+        if dossier['reachDossierInfo']['dossierSubtype'] == "Article 10 - full" and dossier['reachDossierInfo']['registrationRole'] == "Lead (joint submission)":
+            dossier_info = {
+                "lastUpdatedDate": dossier['lastUpdatedDate'],
+                "registrationStatus": dossier['registrationStatus'],
+                "registrationStatusChangedDate": dossier['registrationStatusChangedDate'],
+                "registrationRole": dossier['reachDossierInfo']['registrationRole'],
+                "assetExternalId": dossier['assetExternalId'],
+                "rootKey": dossier['rootKey']
+            }
     log.info(f"Dossier info retrieved for RML ID {rmlId}")
     return dossier_info
 
@@ -89,30 +91,41 @@ def get_substance_index(assetExternalId : str) -> dict:
     index_data = {}
 
     # Toxicological information : txi
-
-    txi_div = soup.find('div', id='id_7_Toxicologicalinformation')
-    txi_link = txi_div.find('a', class_='das-leaf')
-    txi_href = txi_link['href']
-    index_data['toxicological_information_link'] = LINK_DOSSIER + txi_href + '.html'
-
+    try:
+        txi_div = soup.find('div', id='id_7_Toxicologicalinformation')
+        txi_link = txi_div.find('a', class_='das-leaf')
+        txi_href = txi_link['href']
+        index_data['toxicological_information_link'] = LINK_DOSSIER + txi_href + '.html'
+    except Exception as e:
+        log.error(f"Error retrieving toxicological information link: {e}")
+        index_data['toxicological_information_link'] = None
+        
     # Repeated dose toxicity : rdt
-
-    rdt_div = soup.find('div', id='id_75_Repeateddosetoxicity')
-    rdt_link = rdt_div.find('a', class_='das-leaf')
-    rdt_href = rdt_link['href']
-    index_data['repeated_dose_toxicity_link'] = LINK_DOSSIER + rdt_href + '.html'
+    try:
+        rdt_div = soup.find('div', id='id_75_Repeateddosetoxicity')
+        rdt_link = rdt_div.find('a', class_='das-leaf')
+        rdt_href = rdt_link['href']
+        index_data['repeated_dose_toxicity_link'] = LINK_DOSSIER + rdt_href + '.html'
+    except Exception as e:
+        log.error(f"Error retrieving repeated dose toxicity link: {e}")
+        index_data['repeated_dose_toxicity_link'] = None
 
     # Acute toxicity : at
-
-    at_div = soup.find('div', id='id_72_AcuteToxicity')
-    at_link = at_div.find('a', class_='das-leaf')
-    at_href = at_link['href']
-    index_data['acute_toxicity_link'] = LINK_DOSSIER + at_href + '.html'
+    try:
+        at_div = soup.find('div', id='id_72_AcuteToxicity')
+        at_link = at_div.find('a', class_='das-leaf')
+        at_href = at_link['href']
+        index_data['acute_toxicity_link'] = LINK_DOSSIER + at_href + '.html'
+    except Exception as e:
+        log.error(f"Error retrieving acute toxicity link: {e}")
+        index_data['acute_toxicity_link'] = None
 
     log.info(f"Substance index retrieved for Asset External ID {assetExternalId}")
 
     return index_data
 
+
+
 #endregion
 
 #region ECHA parsing functions of html pages