Skip to content
Snippets Groups Projects
Select Git revision
  • 46fd2c351b4845079953574c4b2b82948c21958b
  • master default protected
2 results

tp3-git.iml

Blame
    • Code owners
    Assign users and groups as approvers for specific file changes. Learn more.
    aggreg.py 3.11 KiB
    1
    2
    3
    4
    5
    6
    7
    8
    9
    10
    11
    12
    13
    14
    15
    16
    17
    18
    19
    20
    21
    22
    23
    24
    25
    26
    27
    28
    29
    30
    31
    32
    33
    34
    35
    36
    37
    38
    39
    40
    41
    42
    43
    44
    45
    46
    47
    48
    49
    50
    51
    52
    53
    54
    55
    56
    57
    58
    59
    60
    61
    62
    63
    64
    65
    66
    67
    68
    69
    70
    71 
    

    

    

    import feedparser
from urllib.parse import urlparse
from datetime import datetime
import time
from argparse import ArgumentParser
import yaml

def charge_urls(liste_url: list[str]) -> list[dict[str, any] | None]:
    # if the key 'bozo' is true, then the feed had an error during processing, so we set it to None
    return [
        feed if not (feed := feedparser.parse(url))['bozo'] else None
        for url in liste_url
    ]


def fusion_flux(liste_url: list[str], liste_flux: list[dict[str, any] | None],
                tri_chrono: bool) -> list[dict[str, str]]:
    feeds = [{
        'titre': entry.title,
        'categorie': entry.category,
        'serveur': urlparse(entry.title_detail.base).netloc,
        'date_publi': entry.published,
        'lien': entry.link,
        'description': entry.description,
        'guid': entry.guid
    } for feed in liste_flux if feed is not None for entry in feed['entries']]
    if tri_chrono:
        feeds.sort(key=lambda e: datetime.strptime(e['date_publi'],
                                                   "%a, %d %b %Y %H:%M"),
                   reverse=True)
    else:
        feeds.sort(
            key=lambda e: ["CRITICAL", "MAJOR", "MINOR"].index(e['categorie']))
    return feeds


def genere_html(liste_evenements: list[dict[str, str]],
                chemin_html: str) -> None:
    output = "<!DOCTYPE html><html lang=\"en\"><head><meta charset=\"utf-8\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1\"><title>Events log</title><link rel=\"stylesheet\" href=\"css/feed.css\" type=\"text/css\"/></head><body><article><header><h1 class=\"maintitle\">Events log</h1></header>"
    output += f"<p class=\"currenttime\">{time.asctime()}</p>"
    output += f"<div class=\"container\">"
    for evenement in liste_evenements:
        output += f"<article class=\"event {evenement['categorie'].lower()}\"><header>"
        output += f"<h2>{evenement['titre']}</h2>"
        output += f"<p class=\"server\">from: {evenement['serveur']}</p>"
        output += "</header>"
        output += f"<p>{evenement['date_publi']}</p>"
        output += f"<p>{evenement['categorie']}</p>"
        output += f"<p class=\"guid\">{evenement['guid']}</p>"
        output += f"<p><a href=\"eventlink\"{evenement['lien']}\">{evenement['lien']}</a></p>"
        output += f"<p>{evenement['description']}</p>"
        output += "</article>"
    output += "</div></article></body></html>"
    with open(chemin_html, "w") as outputfile:
        outputfile.write(output)


def main():
    parser = ArgumentParser(description="obtain events feeds from RSS and compile them into a nice webpage")
    parser.add_argument("-c", "--config", help="specifies a config path instead of the default config path %(default)s", default="/etc/eventswrangler.yml")
    configpath = parser.parse_args().config
    with open(configpath) as file:
        conf = yaml.safe_load(file)
    urls = [source + '/' + conf['rss-name'] for source in conf['sources']]
    feeds = charge_urls(urls)
    fusioned = fusion_flux(urls, feeds, conf['tri-chrono'])
    genere_html(fusioned, conf['destination'])

if __name__ == "__main__":
    main()