Import du caméléon

Fix #115

experimentations/get_lecameleon_events.py

@@ -0,0 +1,44 @@
+#!/usr/bin/python3
+# coding: utf-8
+
+import json
+import os
+import sys
+
+# getting the name of the directory
+# where the this file is present.
+current = os.path.dirname(os.path.realpath(__file__))
+
+# Getting the parent directory name
+# where the current directory is present.
+parent = os.path.dirname(current)
+
+# adding the parent directory to
+# the sys.path.
+sys.path.append(parent)
+sys.path.append(parent + "/src")
+
+from src.agenda_culturel.import_tasks.custom_extractors import lecameleon
+from src.agenda_culturel.import_tasks.downloader import SimpleDownloader
+from src.agenda_culturel.import_tasks.importer import URL2Events
+
+if __name__ == "__main__":
+    u2e = URL2Events(SimpleDownloader(), lecameleon.CExtractor())
+    url = "https://lesrdvducameleon.wixsite.com/lesrdv/les-spectacles"
+    url_human = "https://lesrdvducameleon.wixsite.com/lesrdv/les-spectacles"
+
+    try:
+        events = u2e.process(
+            url,
+            url_human,
+            cache="cache-lecameleon.xml",
+            default_values={},
+            published=True,
+        )
+
+        exportfile = "events-lecameleon.json"
+        print("Saving events to file {}".format(exportfile))
+        with open(exportfile, "w") as f:
+            json.dump(events, f, indent=4, default=str)
+    except Exception as e:
+        print("Exception: " + str(e))

src/agenda_culturel/celery.py

@@ -24,6 +24,7 @@ from .import_tasks.custom_extractors import (
     laraymonde,
     mille_formes,
     amisdutempsdescerises,
+    lecameleon,
 )
 from .import_tasks.downloader import (
     ChromiumHeadlessDownloader,
@@ -204,6 +205,8 @@ def run_recurrent_import_internal(rimport, downloader, req_id):
         extractor = amisdutempsdescerises.CExtractor()
     elif rimport.processor == RecurrentImport.PROCESSOR.MOBILIZON:
         extractor = mobilizon.CExtractor()
+    elif rimport.processor == RecurrentImport.PROCESSOR.LECAMELEON:
+        extractor = lecameleon.CExtractor()
     else:
         extractor = None
 

src/agenda_culturel/import_tasks/custom_extractors/lecameleon.py

@@ -0,0 +1,81 @@
+from bs4 import BeautifulSoup
+from datetime import date
+
+from ..twosteps_extractor import TwoStepsExtractorNoPause
+from ..extractor import Extractor
+
+
+# A class dedicated to get events from Le Caméléon
+# URL: https://lesrdvducameleon.wixsite.com/lesrdv/les-spectacles
+class CExtractor(TwoStepsExtractorNoPause):
+    def __init__(self):
+        super().__init__()
+        self.today = date.today()
+
+    def build_event_url_list(self, content, infuture_days=180):
+        soup = BeautifulSoup(content, "html.parser")
+
+        links = soup.select("a[data-anchor='event-details']")
+        if links:
+            for lk in links:
+                self.add_event_url(lk["href"])
+
+    def add_event_from_content(
+        self,
+        event_content,
+        event_url,
+        url_human=None,
+        default_values=None,
+        published=False,
+    ):
+        soup = BeautifulSoup(event_content, "html.parser")
+
+        title = soup.select_one("[data-hook='event-title']").text
+        d = soup.select_one("[data-hook='event-full-date']").text
+        location = soup.select_one("[data-hook='event-full-location']").text
+        description = (
+            soup.select_one("[data-hook='about-section-text']").get_text(separator="\n")
+            + "\n"
+            + soup.select_one("[data-hook='event-description']").get_text(
+                separator="\n"
+            )
+        )
+        img = soup.select_one("[data-hook='event-image'] img")
+
+        els = d.split(",")
+        if len(els) > 1:
+            start_day = Extractor.parse_french_date(
+                els[0], default_year_by_proximity=self.today
+            )
+            end_day = start_day
+            es = els[1].split("–")
+            start_time = Extractor.parse_french_time(es[0])
+            end_time = Extractor.parse_french_time(es[1])
+        else:
+            start_day = None
+            start_time = None
+            start_time = None
+            end_time = None
+
+        image = img["src"].split(".jpg")[0] + ".jpg"
+        image_alt = img["alt"]
+
+        self.add_event_with_props(
+            default_values,
+            event_url,
+            title,
+            None,
+            start_day,
+            location,
+            description,
+            [],
+            recurrences=None,
+            uuids=[event_url],
+            url_human=event_url,
+            start_time=start_time,
+            end_day=end_day,
+            end_time=end_time,
+            published=published,
+            image=image,
+            image_alt=image_alt,
+        )

src/agenda_culturel/migrations/0160_alter_recurrentimport_processor.py

@@ -0,0 +1,44 @@
+# Generated by Django 4.2.19 on 2025-03-16 14:27
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("agenda_culturel", "0159_event_editing_user"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="recurrentimport",
+            name="processor",
+            field=models.CharField(
+                choices=[
+                    ("ical", "ical"),
+                    ("icalnobusy", "ical no busy"),
+                    ("icalnovc", "ical no VC"),
+                    ("ical naive tz", "ical naive timezone"),
+                    ("lacoope", "lacoope.org"),
+                    ("lacomedie", "la comédie"),
+                    ("lefotomat", "le fotomat"),
+                    ("lapucealoreille", "la puce à l'oreille"),
+                    ("Plugin wordpress MEC", "Plugin wordpress MEC"),
+                    ("Facebook events", "Événements d'une page FB"),
+                    ("Billetterie CF", "Billetterie Clermont-Ferrand"),
+                    ("arachnee", "Arachnée concert"),
+                    ("rio", "Le Rio"),
+                    ("raymonde", "La Raymonde"),
+                    ("apidae", "Agenda apidae tourisme"),
+                    ("iguana", "Agenda iguana (médiathèques)"),
+                    ("Mille formes", "Mille formes"),
+                    ("Amis cerises", "Les Amis du Temps des Cerises"),
+                    ("Mobilizon", "Mobilizon"),
+                    ("Le Caméléon", "Le caméléon"),
+                ],
+                default="ical",
+                max_length=20,
+                verbose_name="Processor",
+            ),
+        ),
+    ]

src/agenda_culturel/models.py

@@ -2617,6 +2617,7 @@ class RecurrentImport(models.Model):
         MILLEFORMES = "Mille formes", _("Mille formes")
         AMISCERISES = "Amis cerises", _("Les Amis du Temps des Cerises")
         MOBILIZON = "Mobilizon", _("Mobilizon")
+        LECAMELEON = "Le Caméléon", _("Le caméléon")
 
     class DOWNLOADER(models.TextChoices):
         SIMPLE = "simple", _("simple")