Feature/packaging meta (#27)

* add classifiers

* update license docs to match new path

NOTICE

@@ -1,4 +1,4 @@
 WordPress Site Extractor
 Copyright 2022-2024 The University of Sheffield
 
-Portions of this code are derived from WPJsonScraper, which is available under the MIT license. For details, see src/extractor/dl/LICENSE.
+Portions of this code are derived from WPJsonScraper, which is available under the MIT license. For details, see src/wpextract/download/LICENSE.

docs/license.md

@@ -12,7 +12,7 @@ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 See the License for the specific language governing permissions and
 limitations under the License.
 
-Portions of this code are derived from [WPJsonScraper](https://github.com/MickaelWalter/wp-json-scraper), which is available under the MIT license. For details, see [src/extractor/dl/ORIGINAL_LICENSE](https://github.com/GateNLP/wordpress-site-extractor/blob/main/src/extractor/dl/ORIGINAL_LICENSE).
+Portions of this code are derived from [WPJsonScraper](https://github.com/MickaelWalter/wp-json-scraper), which is available under the MIT license. For details, see [src/wpextract/download/ORIGINAL_LICENSE](https://github.com/GateNLP/wordpress-site-extractor/blob/main/src/wpextract/dl/ORIGINAL_LICENSE).
 
 ## Acknowledgements
 

pyproject.toml

@@ -1,15 +1,24 @@
 [tool.poetry]
 name="wpextract"
 version="1.0.0rc1"
-description="Create a dataset from the WordPress API"
-authors=["Freddy Heppell <[email protected]>"]
-packages=[
-    { include = "wpextract", from = "src"}
-]
+description="Create datasets from WordPress sites"
 homepage="https://gatenlp.github.io/wordpress-site-extractor/"
+documentation="https://gatenlp.github.io/wordpress-site-extractor/"
 repository="https://github.com/GateNLP/wordpress-site-extractor"
 license="Apache-2.0"
 readme = "README.md"
+authors=["Freddy Heppell <[email protected]>"]
+classifiers = [
+    "Development Status :: 5 - Production/Stablec",
+    "Environment :: Console",
+    "Intended Audience :: Science/Research",
+    "Intended Audience :: Developers",
+    "Operating System :: OS Independent",
+    "Topic :: Software Development :: Libraries :: Python Modules"
+]
+packages=[
+    { include = "wpextract", from = "src"}
+]
 
 [tool.poetry.scripts]
 wpextract = "wpextract.cli:cli"