From 0fcf2ea0cb587b308259d5bae38441f419c62155 Mon Sep 17 00:00:00 2001
From: Carson Davis <CarsonReidDavis@gmail.com>
Date: Mon, 25 Nov 2024 19:01:36 -0600
Subject: [PATCH] handle network errors and arbitrary errors during title
 resolution

---
 sde_collections/models/delta_patterns.py |  2 +-
 sde_collections/utils/title_resolver.py  | 46 +++++++++++++-----------
 2 files changed, 26 insertions(+), 22 deletions(-)

diff --git a/sde_collections/models/delta_patterns.py b/sde_collections/models/delta_patterns.py
index 0d2310a3..ae3e92ea 100644
--- a/sde_collections/models/delta_patterns.py
+++ b/sde_collections/models/delta_patterns.py
@@ -425,7 +425,7 @@ def generate_title_for_url(self, url_obj) -> tuple[str, str | None]:
 
         try:
             return resolve_title(self.title_pattern, context), None
-        except (ValueError, ValidationError) as e:
+        except Exception as e:
             return None, str(e)
 
     def apply(self) -> None:
diff --git a/sde_collections/utils/title_resolver.py b/sde_collections/utils/title_resolver.py
index 20211bf7..165065d9 100644
--- a/sde_collections/utils/title_resolver.py
+++ b/sde_collections/utils/title_resolver.py
@@ -63,29 +63,33 @@ def resolve_xpath(xpath: str, url: str) -> str:
     if not is_valid_xpath(xpath):
         raise ValueError(f"The xpath, {xpath}, is not valid.")
 
-    response = requests.get(url)
-
-    if response.ok:
-        tree = html.fromstring(response.content)
-        values = tree.xpath(xpath)
-
-        if len(values) == 1:
-            if isinstance(values[0], str):
-                text_content = values[0]
-            else:
-                text_content = values[0].text
-
-            if text_content:
-                text_content = clean_text(text_content)
-                return text_content
+    try:
+        response = requests.get(url)
+
+        if response.ok:
+            tree = html.fromstring(response.content)
+            values = tree.xpath(xpath)
+
+            if len(values) == 1:
+                if isinstance(values[0], str):
+                    text_content = values[0]
+                else:
+                    text_content = values[0].text
+
+                if text_content:
+                    text_content = clean_text(text_content)
+                    return text_content
+                else:
+                    raise ValueError(f"The element at the xpath, {xpath}, does not contain any text content.")
+            elif len(values) > 1:
+                raise ValueError(f"More than one element found for the xpath, {xpath}")
             else:
-                raise ValueError(f"The element at the xpath, {xpath}, does not contain any text content.")
-        elif len(values) > 1:
-            raise ValueError(f"More than one element found for the xpath, {xpath}")
+                raise ValueError(f"No element found for the xpath, {xpath}")
         else:
-            raise ValueError(f"No element found for the xpath, {xpath}")
-    else:
-        raise ValueError(f"Failed to retrieve the {url}. Status code: {response.status_code}")
+            raise ValueError(f"Failed to retrieve the {url}. Status code: {response.status_code}")
+
+    except requests.RequestException as e:
+        raise ValueError(f"Network error while accessing {url}: {str(e)}")
 
 
 def parse_title(input_string: str) -> list[tuple[str, str]]: