prepare v1.6.2 (#415)

* prepare v1.6.2 * setup: adjust test versions * fix tests * fix tests * update changes * setup: update dependencies
adbar · Sep 6, 2023 · 5ce31d9 · 5ce31d9
1 parent f101371
commit 5ce31d9
Show file tree

Hide file tree

Showing 4 changed files with 34 additions and 8 deletions.
diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml
@@ -17,20 +17,22 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest]
-        python-version: [3.8, "3.11"]  # "3.12-dev"
+        python-version: ["3.9", "3.11"]
         env: [{ MINIMAL: "true" }, { MINIMAL: "false" }]
         include:
           # custom python versions
           - os: ubuntu-20.04
             python-version: 3.6
+          - os: ubuntu-20.04
+            python-version: 3.7
           - os: macos-latest
             python-version: 3.8
           - os: windows-latest
             python-version: 3.8
-          - os: ubuntu-latest
-            python-version: 3.9
           - os: ubuntu-latest
             python-version: "3.10"
+          - os: ubuntu-latest
+            python-version: "3.12-dev"
     steps:
     # Python and pip setup
     - name: Set up Python ${{ matrix.python-version }}

diff --git a/HISTORY.md b/HISTORY.md
@@ -1,6 +1,29 @@
 ## History / Changelog
 
 
+### 1.6.2
+
+Extraction:
+- more lenient HTML parsing (#370)
+- improved code block support with @idoshamun (#372, #401)
+- convertion of relative links to absolute by @feltcat (#377)
+- remove use of signal from core functions (#384)
+
+Metadata:
+- JSON-LD fix for sitenames by @felipehertzer (#383)
+
+Command-line interface:
+- more robust batch processing (#381)
+- added `--probe` option to CLI to check for extractable content (#378, #392)
+
+Maintenance:
+- simplified code (#408)
+- support for Python 3.12
+- pinned LXML version for MacOS (#393)
+- updated dependencies and parameters (notably `htmldate` and `courlan`)
+- code cleaning by @marksmayo (#406)
+
+
 ### 1.6.1
 
 Extraction:

diff --git a/setup.py b/setup.py
@@ -31,7 +31,7 @@ def get_long_description():
         "brotli",
         "cchardet >= 2.1.7; python_version < '3.11'",  # build issue
         "faust-cchardet >= 2.1.18; python_version >= '3.11'",  # fix for build
-        "htmldate[speed] >= 1.4.3",
+        "htmldate[speed] >= 1.5.1",
         "py3langid >= 0.2.2",
         "pycurl >= 7.45.2",
     ],
@@ -66,6 +66,7 @@ def get_long_description():
         "Programming Language :: Python :: 3.9",
         "Programming Language :: Python :: 3.10",
         "Programming Language :: Python :: 3.11",
+        "Programming Language :: Python :: 3.12",
         "Topic :: Internet :: WWW/HTTP",
         "Topic :: Scientific/Engineering :: Information Analysis",
         "Topic :: Security",
@@ -109,9 +110,9 @@ def get_long_description():
     install_requires=[
         "certifi",
         "charset_normalizer >= 3.0.1; python_version < '3.7'",
-        "charset_normalizer >= 3.1.0; python_version >= '3.7'",
-        "courlan @ git+https://github.com/adbar/courlan",
-        "htmldate >= 1.4.3",
+        "charset_normalizer >= 3.2.0; python_version >= '3.7'",
+        "courlan >= 0.9.4",
+        "htmldate >= 1.5.1",
         "justext >= 3.0.0",
         "lxml >= 4.9.3 ; platform_system != 'Darwin'",
         "lxml == 4.9.2 ; platform_system == 'Darwin'",

diff --git a/trafilatura/__init__.py b/trafilatura/__init__.py
@@ -9,7 +9,7 @@
 __author__ = 'Adrien Barbaresi and contributors'
 __license__ = 'GNU GPL v3+'
 __copyright__ = 'Copyright 2019-2023, Adrien Barbaresi'
-__version__ = '1.6.1'
+__version__ = '1.6.2'
 
 
 import logging