Mini RSS Reader in 1h - TP Idgeo

.gitignore

# 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/
*.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
.hypothesis/
.pytest_cache/

# Translations
*.mo
*.pot

# Django stuff:
*.log
local_settings.py
db.sqlite3

# Flask stuff:
instance/
.webassets-cache

# Scrapy stuff:
.scrapy

# Sphinx documentation
docs/_build/

# PyBuilder
target/

# Jupyter Notebook
.ipynb_checkpoints

# IPython
profile_default/
ipython_config.py

# pyenv
.python-version

# celery beat schedule file
celerybeat-schedule

# 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/

## Custom

*.html
.vscode/

README.md

RSS Mini Reader - TP CQP Geom 2021

Prérequis :

• Python 3.8+ (sur Windows, voir cet article)

Sur Windows :

# environnement virtuel
py -3.8 -m venv .venv
.\.venv\Scripts\activate

# dépendances
python -m pip install -U pip
python -m pip install -U setuptools wheel
python -m pip install -U -r requirements.txt

# exécution
python .\script.py

Ouvrir le fichier output.html dans votre navigateur.

configuration.json

{
  "feeds": [
    {
      "name": "Geotribu",
      "url": "https://static.geotribu.fr/feed_rss_created.xml",
      "last_guid": null
    },
    {
      "name": "CartoNumerique",
      "url": "https://cartonumerique.blogspot.com/feeds/posts/default?alt=rss",
      "last_guid": null
    },
    {
      "name": "Idgeo",
      "url": "https://www.idgeo.fr/feed/",
      "last_guid": null
    }
  ],
  "client": {
    "last_run": null,
    "debug": true
  }
}

requirements.txt

# project
feedparser<6.1
jinja2<3.1

script.py

#! python3  # noqa: E265

# standard library
import json
import logging
from pathlib import Path

# 3rd party
import feedparser
from jinja2 import Environment, select_autoescape, FileSystemLoader

# log
logging.basicConfig(level=logging.INFO)

# variables
configuration_path = Path("configuration.json")
limit_length_by_feed = 5
template_path = Path(__file__).parent / "template.jinja"

# read configuration file
with configuration_path.open(mode="r", encoding="UTF-8") as stream_json:
    config = json.load(stream_json)

logging.info(
    "{} feeds configured: {}".format(
        len(config.get("feeds")),
        ", ".join([i.get("name") for i in config.get("feeds")]),
    )
)

# parse feeds and store data
data_feeds = {}

for f in config.get("feeds"):
    logging.info(f"Parsing feed: {f.get('name')}")
    parsed_feed = feedparser.parse(f.get("url"))

    # check feed health
    if parsed_feed.get("bozo") == 0:
        logging.info("Feed is healthy")
    else:
        logging.warning("Feed is not healthy")
        continue

    # parse items
    for i in parsed_feed.entries[:limit_length_by_feed]:
        data_feeds[i.guid] = {
            "title": i.title,
            "link": i.link,
            "description": i.description,
            "published": i.published,
            "source": f.get("name"),
        }
        if len(i.enclosures):
            data_feeds.get(i.guid)["illustration"] = i.enclosures[0].get("href")

# Create output file

env = Environment(
    autoescape=select_autoescape(["html", "xml"]),
    loader=FileSystemLoader(Path(__file__).parent),
)
template = env.get_template(template_path.name)

with open("output.html", mode="w", encoding="UTF8") as fifeed_created:
    fifeed_created.write(
        template.render(feeds_items=data_feeds, title="Coucou les CQP Geom")
    )

template.jinja

<!DOCTYPE html>
<html lang="fr">
<head>
    <title>Agrégat de flux</title>
</head>
<body>
    <h1>{{ title }}</h1>

    {% for item in feeds_items.values() %}
        <h2><a href="{{ item.link }} _target="blank">{{ item.title }}</a></h2>
        <p>Source : {{ item.source }}</p>
        <p>{{ item.description }}</p>
        <img src="{{ item.illustration }}" alt="{{ item.title }}">
        <hr>
        <br>
    {% endfor %}

</body>
</html>