prepare v1.12.0 (#664)

adbar · Jul 30, 2024 · c60395c · c60395c
1 parent 9338dff
commit c60395c
Show file tree

Hide file tree

Showing 3 changed files with 24 additions and 2 deletions.
diff --git a/HISTORY.md b/HISTORY.md
@@ -1,6 +1,28 @@
 ## History / Changelog
 
 
+### 1.12.0
+
+Breaking change:
+- enforce fixed list of output formats, deprecate `-out` on the CLI (#647)
+
+Faster, more accurate extraction:
+- review link and structure checks (#653)
+- improve justext fallback (#652)
+- baseline: prevent LXML error in JSON-LD (#643), do not use as backup extraction (#646)
+- review XPaths for undesirable content (#645)
+
+Bugfixes and maintenance:
+- CLI fix: markdown format should trigger `include_formatting` (#649)
+- images fix: use a length threshold on src attribute (#654)
+- XML-TEI: replace RelaxNG by DTD, remove pickle, and update (#655)
+- formatting & markdown fix: add newlines (#656)
+- table fix: prevent `MemoryError` & `ValueError` during conversion to text (#658)
+
+Documentation:
+- update `crawls.rst`: `known` is an unexpected argument, by @tommytyc in #638
+
+
 ### 1.11.0
 
 Breaking change:

diff --git a/setup.py b/setup.py
@@ -110,7 +110,7 @@ def get_long_description():
         "certifi",
         "charset_normalizer >= 3.0.1; python_version < '3.7'",
         "charset_normalizer >= 3.2.0; python_version >= '3.7'",
-        "courlan >= 1.1.0",
+        "courlan >= 1.2.0",
         "htmldate >= 1.8.1",
         "importlib_metadata; python_version < '3.8'",
         "justext >= 3.0.1",

diff --git a/trafilatura/__init__.py b/trafilatura/__init__.py
@@ -9,7 +9,7 @@
 __author__ = 'Adrien Barbaresi and contributors'
 __license__ = "Apache-2.0"
 __copyright__ = 'Copyright 2019-2024, Adrien Barbaresi'
-__version__ = '1.11.0'
+__version__ = '1.12.0'
 
 
 import logging