Merge pull request #126 from openzim/upgrade_deps

Upgrade dependencies and rename html module

.pre-commit-config.yaml

@@ -12,11 +12,11 @@ repos:
     hooks:
       - id: black
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.8.3
+    rev: v0.9.0
     hooks:
       - id: ruff
   - repo: https://github.com/RobertCraigie/pyright-python
-    rev: v1.1.390
+    rev: v1.1.391
     hooks:
       - id: pyright
         name: pyright (system)

README.md

@@ -72,9 +72,6 @@ There are three main ways to install and use `mindtouch2zim` from most recommend
 
 ## Usage
 
-> [!WARNING]
-> This project is still a work in progress and isn't ready for use yet, the commands below are examples only.
-
 ```sh
 # Get help
 docker run -v output:/output ghcr.io/openzim/mindtouch mindtouch2zim --help

scraper/pyproject.toml

@@ -12,7 +12,7 @@ dependencies = [
   "requests==2.32.3",
   "types-requests==2.32.0.20241016",
   "kiwixstorage==0.9.0",
-  "pydantic==2.10.3",
+  "pydantic==2.10.5",
   "schedule==1.2.2",
   "beautifulsoup4==4.12.3",
   "types-beautifulsoup4==4.12.0.20241020",
@@ -21,7 +21,7 @@ dependencies = [
   "pif==0.8.2",
   "backoff==2.2.1",
   "joblib==1.4.2",
-  "Jinja2==3.1.4",
+  "Jinja2==3.1.5",
 ]
 dynamic = ["authors", "classifiers", "keywords", "license", "version", "urls"]
 
@@ -33,9 +33,9 @@ additional-keywords = ["mindouch", "nice", "cxone", "expert"]
 
 [project.optional-dependencies]
 scripts = ["invoke==2.2.0"]
-lint = ["black==24.10.0", "ruff==0.8.3"]
-check = ["pyright==1.1.390"]
-test = ["pytest==8.3.4", "coverage==7.6.9"]
+lint = ["black==24.10.0", "ruff==0.9.0"]
+check = ["pyright==1.1.391"]
+test = ["pytest==8.3.4", "coverage==7.6.10"]
 dev = [
   "pre-commit==4.0.1",
   "debugpy==1.8.11",

scraper/src/mindtouch2zim/client.py

@@ -9,7 +9,7 @@
 
 from mindtouch2zim.context import Context
 from mindtouch2zim.errors import APITokenRetrievalError, MindtouchParsingError
-from mindtouch2zim.html import get_soup
+from mindtouch2zim.html_utils import get_soup
 
 context = Context.get()
 logger = context.logger

scraper/src/mindtouch2zim/processor.py

@@ -51,8 +51,8 @@
 from mindtouch2zim.context import Context
 from mindtouch2zim.download import stream_file
 from mindtouch2zim.errors import NoIllustrationFoundError
-from mindtouch2zim.html import get_text
 from mindtouch2zim.html_rewriting import HtmlUrlsRewriter
+from mindtouch2zim.html_utils import get_text
 from mindtouch2zim.libretexts.detailed_licensing import rewrite_detailed_licensing
 from mindtouch2zim.libretexts.glossary import rewrite_glossary
 from mindtouch2zim.libretexts.index import rewrite_index

scraper/tests/test_client.py

@@ -3,7 +3,7 @@
 from mindtouch2zim.client import (
     _get_welcome_text_from_home,  # pyright: ignore[reportPrivateUsage]
 )
-from mindtouch2zim.html import get_soup
+from mindtouch2zim.html_utils import get_soup
 
 
 @pytest.mark.parametrize(