First version
This commit is contained in:
commit
ced9c0b54f
3 changed files with 343 additions and 0 deletions
224
.gitignore
vendored
Normal file
224
.gitignore
vendored
Normal file
|
|
@ -0,0 +1,224 @@
|
|||
# Byte-compiled / optimized / DLL files
|
||||
__pycache__/
|
||||
*.py[codz]
|
||||
*$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
|
||||
*.lcov
|
||||
.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
|
||||
|
||||
# UV
|
||||
# Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
|
||||
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
||||
# commonly ignored for libraries.
|
||||
# uv.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
|
||||
# poetry.toml
|
||||
|
||||
# pdm
|
||||
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
|
||||
# pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
|
||||
# https://pdm-project.org/en/latest/usage/project/#working-with-version-control
|
||||
# pdm.lock
|
||||
# pdm.toml
|
||||
.pdm-python
|
||||
.pdm-build/
|
||||
|
||||
# pixi
|
||||
# Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
|
||||
# pixi.lock
|
||||
# Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
|
||||
# in the .venv directory. It is recommended not to include this directory in version control.
|
||||
.pixi/*
|
||||
!.pixi/config.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
|
||||
|
||||
# Redis
|
||||
*.rdb
|
||||
*.aof
|
||||
*.pid
|
||||
|
||||
# RabbitMQ
|
||||
mnesia/
|
||||
rabbitmq/
|
||||
rabbitmq-data/
|
||||
|
||||
# ActiveMQ
|
||||
activemq-data/
|
||||
|
||||
# SageMath parsed files
|
||||
*.sage.py
|
||||
|
||||
# Environments
|
||||
.env
|
||||
.envrc
|
||||
.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/
|
||||
|
||||
# Abstra
|
||||
# Abstra is an AI-powered process automation framework.
|
||||
# Ignore directories containing user credentials, local state, and settings.
|
||||
# Learn more at https://abstra.io/docs
|
||||
.abstra/
|
||||
|
||||
# Visual Studio Code
|
||||
# Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
|
||||
# that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
|
||||
# and can be added to the global gitignore or merged into this file. However, if you prefer,
|
||||
# you could uncomment the following to ignore the entire vscode folder
|
||||
# .vscode/
|
||||
# Temporary file for partial code execution
|
||||
tempCodeRunnerFile.py
|
||||
|
||||
# Ruff stuff:
|
||||
.ruff_cache/
|
||||
|
||||
# PyPI configuration file
|
||||
.pypirc
|
||||
|
||||
# Marimo
|
||||
marimo/_static/
|
||||
marimo/_lsp/
|
||||
__marimo__/
|
||||
|
||||
# Streamlit
|
||||
.streamlit/secrets.toml
|
||||
|
||||
.env
|
||||
|
||||
mairie_quincieux.xml
|
||||
114
gen_feed.py
Normal file
114
gen_feed.py
Normal file
|
|
@ -0,0 +1,114 @@
|
|||
import requests
|
||||
import re
|
||||
import datetime
|
||||
import xml.dom.minidom
|
||||
from bs4 import BeautifulSoup
|
||||
from urllib.parse import urlparse
|
||||
from zoneinfo import ZoneInfo
|
||||
from rfeed import *
|
||||
from dotenv import load_dotenv
|
||||
import os
|
||||
import paramiko
|
||||
|
||||
|
||||
class Article:
|
||||
def __init__(self, title: str, link: str):
|
||||
self.title = title
|
||||
self.link = link
|
||||
self.text = ""
|
||||
self._get_time_and_text()
|
||||
|
||||
def _get_time_and_text(self):
|
||||
response = requests.get(self.link)
|
||||
print(f" Retrieving {self.link} to get pub time...")
|
||||
if response.status_code != 200:
|
||||
print("Caramba!")
|
||||
return
|
||||
|
||||
soup = BeautifulSoup(response.text, 'html.parser')
|
||||
|
||||
# Handle date
|
||||
pt = soup.find("meta", property="article:modified_time")
|
||||
pub_time = pt.get("content")
|
||||
self.date = datetime.datetime.fromisoformat(pub_time)
|
||||
|
||||
# Handle text
|
||||
content = [f"<p>{x.text}</p>" for x in soup.find("div", id="content").find_all("p")]
|
||||
self.text = f"<div>{" ".join(content)}</div>"
|
||||
|
||||
|
||||
def __str__(self):
|
||||
return f'{self.title} [{self.date}]'
|
||||
|
||||
def __repr__(self):
|
||||
return self.__str__()
|
||||
|
||||
|
||||
def upload_to_sftp():
|
||||
|
||||
host = os.environ["FTP_HOST"]
|
||||
port = int(os.environ["FTP_PORT"])
|
||||
username = os.environ["FTP_USER"]
|
||||
password = os.environ["FTP_PASSWORD"]
|
||||
|
||||
transport = paramiko.Transport((host, port))
|
||||
transport.connect(username=username, password=password)
|
||||
|
||||
sftp = paramiko.SFTPClient.from_transport(transport)
|
||||
sftp.put("mairie_quincieux.xml", f"www/mairie_quincieux.xml")
|
||||
|
||||
sftp.close()
|
||||
transport.close()
|
||||
|
||||
|
||||
def generate_feed():
|
||||
feed_path = "mairie_quincieux.xml"
|
||||
feed_url = os.environ["WEBSITE"] + "/" + feed_path
|
||||
main_url = "https://www.quincieux.fr/actus/"
|
||||
|
||||
print(f"Retrieving {main_url}...")
|
||||
response = requests.get(main_url)
|
||||
if response.status_code != 200:
|
||||
print(f"Failed to get url: {response.status_code}")
|
||||
return False
|
||||
|
||||
soup = BeautifulSoup(response.text, 'html.parser')
|
||||
articles = []
|
||||
|
||||
small_articles = soup.find_all("article")
|
||||
print(f"Found {len(small_articles)} articles...")
|
||||
for a in small_articles:
|
||||
cat = a.find("div", class_="fiche-article__category").find("div").text
|
||||
titre = a.find("h2").text
|
||||
description = a.find("div", class_="fiche-article__content").find(string=True, recursive=False)
|
||||
link = a.find("a").get("href")
|
||||
articles.append(Article(f"[{cat}] {titre}", link))
|
||||
|
||||
print("Generating feed...")
|
||||
items = []
|
||||
articles = sorted(articles, key=lambda x: x.date, reverse=True)
|
||||
for a in articles:
|
||||
item = Item(title = a.title, link= a.link, guid = Guid(a.link+a.date.isoformat()), pubDate = a.date, description = a.text)
|
||||
items.append(item)
|
||||
feed = Feed(title = "Actus Mairie Quincieux",
|
||||
link = feed_url,
|
||||
description = "Derniers articles",
|
||||
language = "fr-FR",
|
||||
lastBuildDate = datetime.datetime.now(datetime.UTC),
|
||||
items = items)
|
||||
|
||||
print("Writing feed...")
|
||||
with open(feed_path, 'w') as out_rss:
|
||||
dom = xml.dom.minidom.parseString(feed.rss())
|
||||
out_rss.write(dom.toprettyxml())
|
||||
|
||||
print("Uploading feed...")
|
||||
upload_to_sftp()
|
||||
|
||||
print("All done!")
|
||||
return True
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
load_dotenv()
|
||||
generate_feed()
|
||||
5
requirements.txt
Normal file
5
requirements.txt
Normal file
|
|
@ -0,0 +1,5 @@
|
|||
rfeed
|
||||
beautifulsoup4
|
||||
requests
|
||||
paramiko
|
||||
python-dotenv
|
||||
Loading…
Add table
Add a link
Reference in a new issue