Initial commit

.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/

fetch_data.py

@@ -0,0 +1,62 @@
+import re
+from io import StringIO
+import csv
+import json
+
+import requests
+
+
+def get_megalithic_data(country=1):
+    def megalithic_url(country):
+        return 'https://www.megalithic.co.uk/cache/csvmap_country{}.csv'.format(country)
+
+    # Megalithic doesn't really want people scraping
+    response = requests.get(
+        megalithic_url(country),
+        headers={
+            'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:122.0) Gecko/20100101 Firefox/122.0'
+        }
+    )
+    if response.status_code != 200:
+        raise Exception('Failed to fetch data from Megalithic.UK: {}'.format(response.text))
+
+    content = StringIO(response.text)
+    reader = csv.DictReader(content, delimiter='|')
+
+    data = []
+    for row in reader:
+        data.append({
+            'lat': row['lat'],
+            'lng': row['lng'],
+            'name': row['Name'],
+        })
+
+    return data
+
+
+def get_stone_circles_data():
+    response = requests.get('http://www.stone-circles.org.uk/stone/Cluster/Coords/coords.js')
+
+    if response.status_code != 200:
+        raise Exception('Failed to fetch data from stone-circles.org.uk: {}'.format(response.text))
+
+    content = re.match(
+        r'.+ = \[(\[.+]),?];',
+        response.text.replace('\n', '')
+    )
+    content = re.sub(r'\\(?!")', '', content.groups()[0])
+    arr = json.loads('[{}]'.format(content))
+
+    data = []
+    for item in arr:
+        data.append({
+            'lat': item[0],
+            'lng': item[1],
+            'name': re.match(r'.+<a .+>(.+)</a>', item[2]).groups()[0],
+        })
+
+    return data
+
+
+if __name__ == '__main__':
+    all_data = get_megalithic_data() + get_stone_circles_data()

requirements.txt

@@ -0,0 +1,2 @@
+requests~=2.31
+pandas~=2.2