From 2639b2417c6db8e4df1d4f3b42f454076f7fa140 Mon Sep 17 00:00:00 2001
From: Adrien Barbaresi <adbar@users.noreply.github.com>
Date: Thu, 30 Mar 2023 16:39:45 +0200
Subject: [PATCH] setup: prepare version 1.5.0 (#317)

* prepare version 1.5.0

* complete changelog
---
 HISTORY.md                  | 18 ++++++++++++++++++
 setup.py                    |  4 ++--
 tests/eval-requirements.txt | 10 +++++-----
 trafilatura/__init__.py     |  2 +-
 4 files changed, 26 insertions(+), 8 deletions(-)

diff --git a/HISTORY.md b/HISTORY.md
index 69660711..2ab54191 100644
--- a/HISTORY.md
+++ b/HISTORY.md
@@ -1,6 +1,24 @@
 ## History / Changelog
 
 
+### 1.5.0
+
+
+Extraction:
+- fixes for metadata extraction with @felipehertzer (#295, #296),  @andremacola (#282, #310), and @edkrueger (#303)
+- pagetype and image urls added to metadata by @andremacola (#282, #310)
+- add as_dict method to Document class with @edkrueger in #306
+- XML output fix with @knit-bee in #315
+- various smaller fixes: lists (#309), XPaths, metadata hardening
+
+Navigation:
+- transfer URL management to courlan.UrlStore (#232, #312)
+- fixes for spider module
+
+Maintenance:
+- simplify code and extend tests
+- underlying packages htmldate and courlan, update setup and docs
+
 
 ### 1.4.1
 
diff --git a/setup.py b/setup.py
index 8e0e2f48..e8877280 100644
--- a/setup.py
+++ b/setup.py
@@ -30,7 +30,7 @@ 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] >= 1.4.1",
+        "htmldate[speed] >= 1.4.2",
         "py3langid >= 0.2.2",
         "pycurl >= 7.45.2",
     ],
@@ -110,7 +110,7 @@ def get_long_description():
         "charset_normalizer >= 3.0.1; python_version < '3.7'",
         "charset_normalizer >= 3.1.0; python_version >= '3.7'",
         "courlan >= 0.9.0",
-        "htmldate >= 1.4.1",
+        "htmldate >= 1.4.2",
         "justext >= 3.0.0",
         "lxml >= 4.9.2",
         "urllib3 >= 1.26, < 2",
diff --git a/tests/eval-requirements.txt b/tests/eval-requirements.txt
index b098d426..0b35508e 100644
--- a/tests/eval-requirements.txt
+++ b/tests/eval-requirements.txt
@@ -1,19 +1,19 @@
-trafilatura==1.4.0
+trafilatura==1.5.0
 
 # alternatives
-beautifulsoup4==4.11.1
+beautifulsoup4==4.12.1
 boilerpy3==1.0.6
 #dragnet==2.0.4  # unmaintained!
-goose3==3.1.12
+goose3==3.1.13
 html2text==2020.1.16
 html-text==0.5.2
-inscriptis==2.3.1
+inscriptis==2.3.2
 justext==3.0.0
 newspaper3k==0.2.8
 news-please==1.5.22
 readabilipy==0.2.0
 readability-lxml==0.8.1
-resiliparse==0.13.7
+resiliparse==0.14.3
 
 # additional data
 #jparser==0.0.20
diff --git a/trafilatura/__init__.py b/trafilatura/__init__.py
index 4d8059a3..1d6a47a8 100644
--- 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__ = '1.4.1'
+__version__ = '1.5.0'
 
 
 import logging