osbot-utils 1.52.0__py3-none-any.whl → 1.53.0__py3-none-any.whl

osbot_utils/utils/Http.py

@@ -1,15 +1,22 @@
 import json
 import os
+import re
 import socket
 import ssl
+import unicodedata
 from time import sleep
-from urllib.parse import quote, urljoin, urlparse
+from urllib.parse import quote, urljoin, urlparse, urlunparse
 from   urllib.request import Request, urlopen
 
+from osbot_utils.utils.Str import html_decode
+
+from osbot_utils.utils.Misc import url_decode
+
 from osbot_utils.utils.Files import save_bytes_as_file, file_size, file_bytes, file_open_bytes, file_create
 from osbot_utils.utils.Python_Logger import Python_Logger
 
-URL_CHECK_HOST_ONLINE = 'https://www.google.com'
+URL_CHECK_HOST_ONLINE         = 'https://www.google.com'
+URL_JOIN_SAFE__MAX_ITERATIONS = 5
 
 def current_host_offline(url_to_use=URL_CHECK_HOST_ONLINE):
     return current_host_online(url_to_use=url_to_use) is False
@@ -148,15 +155,34 @@ def url_join_safe(base_path, path=''):
     if not isinstance(base_path, str) or not isinstance(path, str):
         return None
 
-    if not base_path.endswith('/'):                                         # Ensure that the base path ends with '/'
+    max_iterations   = URL_JOIN_SAFE__MAX_ITERATIONS
+
+    path = unicodedata.normalize('NFC', path)
+    path_normalised = path
+    for _ in range(max_iterations):
+        fixed_segments = []
+        for segment in path_normalised.split('/'):
+            segment_decoded = html_decode(url_decode(segment))
+            fixed_segment = re.sub(r'[^a-zA-Z0-9\-_.]+', '-', segment_decoded)
+            fixed_segment = fixed_segment.replace("..", "-")
+            if fixed_segment:
+                fixed_segments.append(fixed_segment)
+        path_cleaned = '/'.join(fixed_segments)
+
+        if path_cleaned == path_normalised:
+            break
+        path_normalised = path_cleaned
+    else:
+        return None                                                         # If we exit the loop without breaking, return None
+
+    if not base_path.endswith('/'):                                          # Ensure that the base path ends with '/'
         base_path += '/'
 
-    if path.startswith('/'):                                                 # Remove leading '/' from path
-        path = path[1:]
+    if path_normalised.startswith('/'):                                      # Remove leading '/' from path
+        path_normalised = path_normalised[1:]
 
-    path_quoted     = quote(path)
-    path_normalised = path_quoted.replace("..", "")             # Quote the path to encode special characters and prevent directory traversal
-    joined_path     = urljoin(base_path, path_normalised)                    # Join the base path and normalized path
+    path_quoted     = quote(path_normalised,  safe='/')                      # Quote the path to encode special characters
+    joined_path     = urljoin(base_path, path_quoted)                        # Join the base path and normalized path
     parsed_base     = urlparse(base_path)                                    # Parse and verify the result
     parsed_joined   = urlparse(joined_path)
 

osbot_utils/version

@@ -1 +1 @@
-v1.52.0
+v1.53.0

{osbot_utils-1.52.0.dist-info → osbot_utils-1.53.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: osbot_utils
-Version: 1.52.0
+Version: 1.53.0
 Summary: OWASP Security Bot - Utils
 Home-page: https://github.com/owasp-sbot/OSBot-Utils
 License: MIT
@@ -22,7 +22,7 @@ Description-Content-Type: text/markdown
 
 Powerful Python util methods and classes that simplify common apis and tasks.
 
-![Current Release](https://img.shields.io/badge/release-v1.52.0-blue)
+![Current Release](https://img.shields.io/badge/release-v1.53.0-blue)
 [![codecov](https://codecov.io/gh/owasp-sbot/OSBot-Utils/graph/badge.svg?token=GNVW0COX1N)](https://codecov.io/gh/owasp-sbot/OSBot-Utils)
 
 

{osbot_utils-1.52.0.dist-info → osbot_utils-1.53.0.dist-info}/RECORD

@@ -280,7 +280,7 @@ osbot_utils/utils/Env.py,sha256=XMwF5BrtpoPJdOraswAFPrcQ3tRTocjqvA8I61eOCJw,5741
 osbot_utils/utils/Exceptions.py,sha256=KyOUHkXQ_6jDTq04Xm261dbEZuRidtsM4dgzNwSG8-8,389
 osbot_utils/utils/Files.py,sha256=7fdqbfFyo6Ow5Repi_dZAzHqGb0XYh6tDALYAy42pBY,22522
 osbot_utils/utils/Functions.py,sha256=0E6alPJ0fJpBiJgFOWooCOi265wSRyxxXAJ5CELBnso,3498
-osbot_utils/utils/Http.py,sha256=YHHHRpy_QtH-Q_jaSuDwWRl-mmKBiC0DzfDew3l7fgg,6079
+osbot_utils/utils/Http.py,sha256=vFvD-xLkkXLTJvmYGourMLoUOfkZx_KBSLmo1RX73jM,7043
 osbot_utils/utils/Int.py,sha256=PmlUdU4lSwf4gJdmTVdqclulkEp7KPCVUDO6AcISMF4,116
 osbot_utils/utils/Json.py,sha256=7COxBlZRnpxtpNqpmzMPYkcKTnCok-s686nT27oiKEQ,6489
 osbot_utils/utils/Json_Cache.py,sha256=mLPkkDZN-3ZVJiDvV1KBJXILtKkTZ4OepzOsDoBPhWg,2006
@@ -298,8 +298,8 @@ osbot_utils/utils/Toml.py,sha256=SD6IA4-mrtoBXcI0dIGKV9POMQNd6WYKvmDQq7GQ6ZQ,143
 osbot_utils/utils/Version.py,sha256=Ww6ChwTxqp1QAcxOnztkTicShlcx6fbNsWX5xausHrg,422
 osbot_utils/utils/Zip.py,sha256=G6Hk_hDcm9yvWzhTKzhT0R_6f0NBIAchHqMxGb3kfh4,14037
 osbot_utils/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-osbot_utils/version,sha256=8vEHTopueL8q72Dw7rD-UnsLBahO-qnshWhrIIA_f-A,8
-osbot_utils-1.52.0.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-osbot_utils-1.52.0.dist-info/METADATA,sha256=oAWX7EihUIYgMTuzzWfOEO0z4XKdrRWi-J1ap0ksrlE,1266
-osbot_utils-1.52.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-osbot_utils-1.52.0.dist-info/RECORD,,
+osbot_utils/version,sha256=cfLGcb-cU0atx9PN7uRd-7SjRkvlf2gUwCK4UUZZCt8,8
+osbot_utils-1.53.0.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+osbot_utils-1.53.0.dist-info/METADATA,sha256=PQqhK7mvfVoonWblVF3oPIdHKqP7CXisueyqZiBVCeE,1266
+osbot_utils-1.53.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+osbot_utils-1.53.0.dist-info/RECORD,,