tldextract 5.1.2__py3-none-any.whl → 5.1.3__py3-none-any.whl

tldextract/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '5.1.2'
-__version_tuple__ = version_tuple = (5, 1, 2)
+__version__ = version = '5.1.3'
+__version_tuple__ = version_tuple = (5, 1, 3)

tldextract/cache.py

@@ -24,18 +24,6 @@ _DID_LOG_UNABLE_TO_CACHE = False
 
 T = TypeVar("T")
 
-if sys.version_info >= (3, 9):
-
-    def md5(*args: bytes) -> hashlib._Hash:
-        """Use argument only available in newer Python.
-
-        In this file, MD5 is only used for cache location, not security.
-        """
-        return hashlib.md5(*args, usedforsecurity=False)
-
-else:
-    md5 = hashlib.md5
-
 
 def get_pkg_unique_identifier() -> str:
     """Generate an identifier unique to the python version, tldextract version, and python instance.
@@ -51,7 +39,9 @@ def get_pkg_unique_identifier() -> str:
     tldextract_version = "tldextract-" + version
     python_env_name = os.path.basename(sys.prefix)
     # just to handle the edge case of two identically named python environments
-    python_binary_path_short_hash = md5(sys.prefix.encode("utf-8")).hexdigest()[:6]
+    python_binary_path_short_hash = hashlib.md5(
+        sys.prefix.encode("utf-8"), usedforsecurity=False
+    ).hexdigest()[:6]
     python_version = ".".join([str(v) for v in sys.version_info[:-1]])
     identifier_parts = [
         python_version,
@@ -113,8 +103,7 @@ class DiskCache:
             with open(cache_filepath) as cache_file:
                 return json.load(cache_file)
         except (OSError, ValueError) as exc:
-            LOG.error("error reading TLD cache file %s: %s", cache_filepath, exc)
-            raise KeyError("namespace: " + namespace + " key: " + repr(key)) from None
+            raise KeyError("namespace: " + namespace + " key: " + repr(key)) from exc
 
     def set(  # noqa: A003
         self, namespace: str, key: str | dict[str, Hashable], value: object
@@ -238,7 +227,7 @@ def _fetch_url(session: requests.Session, url: str, timeout: int | None) -> str:
 
 def _make_cache_key(inputs: str | dict[str, Hashable]) -> str:
     key = repr(inputs)
-    return md5(key.encode("utf8")).hexdigest()
+    return hashlib.md5(key.encode("utf8"), usedforsecurity=False).hexdigest()
 
 
 def _make_dir(filename: str) -> None:

tldextract/suffix_list.py

@@ -47,7 +47,9 @@ def find_first_response(
                     session=session, url=url, timeout=cache_fetch_timeout
                 )
             except requests.exceptions.RequestException:
-                LOG.exception("Exception reading Public Suffix List url %s", url)
+                LOG.warning(
+                    "Exception reading Public Suffix List url %s", url, exc_info=True
+                )
     finally:
         # Ensure the session is always closed if it's constructed in the method
         if session_created:

tldextract/tldextract.py

@@ -36,7 +36,6 @@ To rejoin the original hostname, if it was indeed a valid, registered hostname:
 
 from __future__ import annotations
 
-import logging
 import os
 import urllib.parse
 from collections.abc import Collection, Sequence
@@ -50,9 +49,6 @@ from .cache import DiskCache, get_cache_dir
 from .remote import lenient_netloc, looks_like_ip, looks_like_ipv6
 from .suffix_list import get_suffix_lists
 
-LOG = logging.getLogger("tldextract")
-
-
 CACHE_TIMEOUT = os.environ.get("TLDEXTRACT_CACHE_TIMEOUT")
 
 PUBLIC_SUFFIX_LIST_URLS = (
@@ -161,13 +157,14 @@ class TLDExtract:
         the `cache_dir` will live in the tldextract directory. You can disable
         the caching functionality of this module by setting `cache_dir` to `None`.
 
-        If the cached version does not exist (such as on the first run), HTTP request the URLs in
-        `suffix_list_urls` in order, until one returns public suffix list data. To disable HTTP
-        requests, set this to an empty sequence.
-
-        The default list of URLs point to the latest version of the Mozilla Public Suffix List and
-        its mirror, but any similar document could be specified. Local files can be specified by
-        using the `file://` protocol. (See `urllib2` documentation.)
+        If the cached version does not exist, such as on the first run, HTTP
+        request the URLs in `suffix_list_urls` in order, and use the first
+        successful response for public suffix definitions. Subsequent, untried
+        URLs are ignored. The default URLs are the latest version of the
+        Mozilla Public Suffix List and its mirror, but any similar document URL
+        could be specified. Local files can be specified by using the `file://`
+        protocol (see `urllib2` documentation). To disable HTTP requests, set
+        this to an empty sequence.
 
         If there is no cached version loaded and no data is found from the `suffix_list_urls`,
         the module will fall back to the included TLD set snapshot. If you do not want
@@ -179,7 +176,9 @@ class TLDExtract:
         suffix, so these domains are excluded by default. If you'd like them
         included instead, set `include_psl_private_domains` to True.
 
-        You can pass additional suffixes in `extra_suffixes` argument without changing list URL
+        You can specify additional suffixes in the `extra_suffixes` argument.
+        These will be merged into whatever public suffix definitions are
+        already in use by `tldextract`, above.
 
         cache_fetch_timeout is passed unmodified to the underlying request object
         per the requests documentation here:

{tldextract-5.1.2.dist-info → tldextract-5.1.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: tldextract
-Version: 5.1.2
+Version: 5.1.3
 Summary: Accurately separates a URL's subdomain, domain, and public suffix, using the Public Suffix List (PSL). By default, this includes the public ICANN TLDs and their exceptions. You can optionally support the Public Suffix List's private domains as well.
 Author-email: John Kurkowski <john.kurkowski@gmail.com>
 License: BSD-3-Clause
@@ -10,12 +10,12 @@ Classifier: Development Status :: 5 - Production/Stable
 Classifier: Topic :: Utilities
 Classifier: License :: OSI Approved :: BSD License
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
-Requires-Python: >=3.8
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: idna
@@ -26,7 +26,6 @@ Provides-Extra: release
 Requires-Dist: build ; extra == 'release'
 Requires-Dist: twine ; extra == 'release'
 Provides-Extra: testing
-Requires-Dist: black ; extra == 'testing'
 Requires-Dist: mypy ; extra == 'testing'
 Requires-Dist: pytest ; extra == 'testing'
 Requires-Dist: pytest-gitignore ; extra == 'testing'
@@ -35,6 +34,7 @@ Requires-Dist: responses ; extra == 'testing'
 Requires-Dist: ruff ; extra == 'testing'
 Requires-Dist: syrupy ; extra == 'testing'
 Requires-Dist: tox ; extra == 'testing'
+Requires-Dist: tox-uv ; extra == 'testing'
 Requires-Dist: types-filelock ; extra == 'testing'
 Requires-Dist: types-requests ; extra == 'testing'
 
@@ -129,8 +129,8 @@ tldextract http://forums.bbc.co.uk
 
 Beware when first calling `tldextract`, it updates its TLD list with a live HTTP
 request. This updated TLD set is usually cached indefinitely in `$HOME/.cache/python-tldextract`.
-To control the cache's location, set TLDEXTRACT_CACHE environment variable or set the
-cache_dir path in TLDExtract initialization.
+To control the cache's location, set the `TLDEXTRACT_CACHE` environment variable or set the
+`cache_dir` path when constructing a `TLDExtract`.
 
 (Arguably runtime bootstrapping like that shouldn't be the default behavior,
 like for production systems. But I want you to have the latest TLDs, especially
@@ -219,10 +219,12 @@ extract = tldextract.TLDExtract(
     fallback_to_snapshot=False)
 ```
 
-The above snippet will fetch from the URL *you* specified, upon first need to download the
-suffix list (i.e. if the cached version doesn't exist).
+If the cached version of public suffix definitions doesn't exist, such as on
+the first run, the above snippet will request the URLs you specified in order,
+and use the first successful response.
 
-If you want to use input data from your local filesystem, just use the `file://` protocol:
+If you want to use input data from your local filesystem, use the `file://`
+protocol with an absolute path:
 
 ```python
 extract = tldextract.TLDExtract(
@@ -231,17 +233,24 @@ extract = tldextract.TLDExtract(
     fallback_to_snapshot=False)
 ```
 
-Use an absolute path when specifying the `suffix_list_urls` keyword argument.
-`os.path` is your friend.
-
-The command line update command can be used with a URL or local file you specify:
+This also works via command line update:
 
 ```zsh
 tldextract --update --suffix_list_url "http://foo.bar.baz"
 ```
 
-This could be useful in production when you don't want the delay associated with updating the suffix
-list on first use, or if you are behind a complex firewall that prevents a simple update from working.
+Using your own URLs could be useful in production when you don't want the delay
+with updating the suffix list on first use, or if you are behind a complex
+firewall.
+
+You can also specify additional suffixes in the `extra_suffixes` param. These
+will be merged into whatever public suffix definitions are already in use by
+`tldextract`.
+
+```python
+extract = tldextract.TLDExtract(
+    extra_suffixes=["foo", "bar", "baz"])
+```
 
 ## FAQ
 
@@ -250,9 +259,9 @@ list on first use, or if you are behind a complex firewall that prevents a simpl
 This project doesn't contain an actual list of public suffixes. That comes from
 [the Public Suffix List (PSL)](https://publicsuffix.org/). Submit amendments there.
 
-(In the meantime, you can tell tldextract about your exception by either
+In the meantime, you can tell tldextract about your exception by either
 forking the PSL and using your fork in the `suffix_list_urls` param, or adding
-your suffix piecemeal with the `extra_suffixes` param.)
+your suffix piecemeal with the `extra_suffixes` param.
 
 ### I see my suffix in [the Public Suffix List (PSL)](https://publicsuffix.org/), but this library doesn't extract it.
 
@@ -309,5 +318,5 @@ tox -e py311
 Automatically format all code:
 
 ```zsh
-black .
+ruff format .
 ```

tldextract-5.1.3.dist-info/RECORD

@@ -0,0 +1,16 @@
+tldextract/.tld_set_snapshot,sha256=ka7u1d_ISlMmXZXPuw57tS347XWiSidWiBfNaVeKL4A,316061
+tldextract/__init__.py,sha256=rZg3DKzS9CTARuF4Tuq50ViILwUktDED89Av8nStNuM,216
+tldextract/__main__.py,sha256=oiZ5EW_lxRLH6Khk6MdzXf7a1Ld5-A3k4wOFRmNNk2o,89
+tldextract/_version.py,sha256=VdKaCcy2qOG-0Ob0KB_SDtakGRI7V4T0oP9kN9zPqhE,411
+tldextract/cache.py,sha256=nrT9VuLmrjHHFxj-Cai97IyUXXenCX6KbHi07mPkzMc,8289
+tldextract/cli.py,sha256=nCzBAFrgAopTK1t5eBRQgeveSgWheUx4LAlAHE_8mzQ,3010
+tldextract/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+tldextract/remote.py,sha256=sklRFbATwPs_S33-KeIu9ixuSWP5w7QXO8jnhi_lgJs,1944
+tldextract/suffix_list.py,sha256=ePH6iOIUBe0JE_mc07a34Nd7tFyfmHgP_mJkFhxzr7c,3947
+tldextract/tldextract.py,sha256=vlCp78tE3R7P__RmQusIz0T9_lq5ZTWDvtFV-tAKPiU,18846
+tldextract-5.1.3.dist-info/LICENSE,sha256=dKIruBYZ9wJFoTWv8hvg2bhDv9TXDQ82u-0EERuGJYg,1527
+tldextract-5.1.3.dist-info/METADATA,sha256=RBH5Qs1hdA36toKVJC8mxKNgSg7edeuKDSY52r096N8,11622
+tldextract-5.1.3.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
+tldextract-5.1.3.dist-info/entry_points.txt,sha256=EStkXC80BetCMp1UDhU3kWuXBo3qDpgKltZTJ1x4x1U,51
+tldextract-5.1.3.dist-info/top_level.txt,sha256=DWZIjV49WP30tyC1KOEP7t-EaS4IRCXQzc0KXAOn_bk,11
+tldextract-5.1.3.dist-info/RECORD,,

{tldextract-5.1.2.dist-info → tldextract-5.1.3.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.43.0)
+Generator: setuptools (75.3.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

tldextract-5.1.2.dist-info/RECORD

@@ -1,16 +0,0 @@
-tldextract/.tld_set_snapshot,sha256=TVya0bCcmRKl_16oPKPIlNmWS09rXrjOKGgYjhvAGLE,238022
-tldextract/__init__.py,sha256=rZg3DKzS9CTARuF4Tuq50ViILwUktDED89Av8nStNuM,216
-tldextract/__main__.py,sha256=oiZ5EW_lxRLH6Khk6MdzXf7a1Ld5-A3k4wOFRmNNk2o,89
-tldextract/_version.py,sha256=iJQJoAO8HGnLsPBpH1rkF4KPbrYxIqs4qAXfUgzhRqQ,411
-tldextract/cache.py,sha256=vsr4ERgNxmBO_mYwXLCMbRRKq1s-IDZZLXoaGIYXmBM,8601
-tldextract/cli.py,sha256=nCzBAFrgAopTK1t5eBRQgeveSgWheUx4LAlAHE_8mzQ,3010
-tldextract/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tldextract/remote.py,sha256=sklRFbATwPs_S33-KeIu9ixuSWP5w7QXO8jnhi_lgJs,1944
-tldextract/suffix_list.py,sha256=TcUpMTZwsicZn6_eHKqA4bjurQrKYde14P-4HT4s4yE,3896
-tldextract/tldextract.py,sha256=oUYLJcgWmeika0teDq2nNI5UCSbAR0c3eosYslVJPUY,18731
-tldextract-5.1.2.dist-info/LICENSE,sha256=dKIruBYZ9wJFoTWv8hvg2bhDv9TXDQ82u-0EERuGJYg,1527
-tldextract-5.1.2.dist-info/METADATA,sha256=dkiY2wl_8M2guJ0MGhGi0YQ9OgZI4vGpJ0I9LMLSGyQ,11464
-tldextract-5.1.2.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-tldextract-5.1.2.dist-info/entry_points.txt,sha256=EStkXC80BetCMp1UDhU3kWuXBo3qDpgKltZTJ1x4x1U,51
-tldextract-5.1.2.dist-info/top_level.txt,sha256=DWZIjV49WP30tyC1KOEP7t-EaS4IRCXQzc0KXAOn_bk,11
-tldextract-5.1.2.dist-info/RECORD,,