Ajout des imports Mobilizon

Fix #307

experimentations/get_mobilizon.py

@@ -0,0 +1,44 @@
+#!/usr/bin/python3
+# coding: utf-8
+
+import os
+import json
+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.downloader import *
+from src.agenda_culturel.import_tasks.extractor import *
+from src.agenda_culturel.import_tasks.importer import *
+from src.agenda_culturel.import_tasks.custom_extractors import *
+
+
+
+
+
+if __name__ == "__main__":
+
+    u2e = URL2Events(SimpleDownloader(), mobilizon.CExtractor())
+    url = "https://mobilizon.fr/@attac63/events?"
+    url_human = "htthttps://mobilizon.fr/@attac63/events"
+
+    try:
+        events = u2e.process(url, url_human, cache = "cache-attac63.html", default_values = {}, published = True)
+
+        exportfile = "events-attac63.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

@@ -160,6 +160,8 @@ def run_recurrent_import_internal(rimport, downloader, req_id):
         extractor = mille_formes.CExtractor()
     elif rimport.processor == RecurrentImport.PROCESSOR.AMISCERISES:
         extractor = amisdutempsdescerises.CExtractor()
+    elif rimport.processor == RecurrentImport.PROCESSOR.MOBILIZON:
+        extractor = mobilizon.CExtractor()
     else:
         extractor = None
 

src/agenda_culturel/import_tasks/custom_extractors/mobilizon.py

@@ -0,0 +1,182 @@
+from ..extractor import *
+import json
+import dateutil.parser
+from datetime import datetime, timezone
+import requests
+from urllib.parse import urlparse
+from bs4 import BeautifulSoup
+
+import logging
+
+logger = logging.getLogger(__name__)
+
+# A class dedicated to get events from les amis du temps des cerises
+# Website https://amisdutempsdescerises.org/
+class CExtractor(Extractor):
+
+    def __init__(self):
+        super().__init__()
+        self.no_downloader = True
+
+    # Source code adapted from https://framagit.org/Marc-AntoineA/mobilizon-client-python
+    def _request(self, body, data):
+
+            headers = {}
+
+            response = requests.post(url=self._api_end_point, json={ "query": body, "variables": data }, headers=headers)
+
+            if response.status_code == 200:
+                response_json = response.json()
+                if 'errors' in response_json:
+                    raise Exception(f'Errors while requesting { body }. { str(response_json["errors"]) }')
+
+                return response_json['data']
+            else:
+                raise Exception(f'Error while requesting. Status code: { response.status_code }')
+
+    def _oncoming_events_number(self):
+
+        query = '''
+query($preferredUsername: String!, $afterDatetime: DateTime) {
+    group(preferredUsername: $preferredUsername) {
+        organizedEvents(afterDatetime: $afterDatetime) {
+            total,
+        }
+    }
+}
+        '''
+        today = datetime.now(timezone.utc).isoformat()
+        data = {
+            'preferredUsername': self._group_id,
+            'afterDatetime': today
+        }
+        r = self._request(query, data)
+        return r['group']['organizedEvents']['total']
+
+
+    def _oncoming_events(self):
+        def _oncoming_events_page(page):
+            query = '''
+query($preferredUsername: String!, $afterDatetime: DateTime, $page: Int) {
+    group(preferredUsername: $preferredUsername) {
+        organizedEvents(afterDatetime: $afterDatetime, page: $page) {
+            elements {
+                id,
+                title,
+                url,
+                beginsOn,
+                endsOn,
+                options {
+                showStartTime,
+                showEndTime,
+                timezone
+                },
+                attributedTo {
+                avatar {
+                    url,
+                }
+                name,
+                preferredUsername,
+                },
+                description,
+                onlineAddress,
+                physicalAddress {
+                locality,
+                description,
+                region
+                },
+                tags {
+                title,
+                id,
+                slug
+                },
+                picture {
+                url
+                },
+                status
+            }
+        }
+    }
+}
+        '''
+
+            today = datetime.now(timezone.utc).isoformat()
+            data = {
+                'preferredUsername': self._group_id,
+                'afterDatetime': today,
+                'page': page
+            }
+            r = self._request(query, data)
+            return r['group']['organizedEvents']['elements']
+
+        number_events = self._oncoming_events_number()
+
+        events = []
+        page = 1
+        while len(events) < number_events:
+            events.extend(_oncoming_events_page(page))
+            page += 1
+        return events
+
+    def extract(
+        self, content, url, url_human=None, default_values=None, published=False
+    ):
+        self.set_header(url)
+        self.clear_events()
+
+        if "@" in url:
+
+            # TODO: quand on a
+            # https://mobilizon.fr/@xr_clermont_ferrand@mobilizon.extinctionrebellion.fr/events
+            # on doit retourner :
+            # https://mobilizon.extinctionrebellion.fr/@xr_clermont_ferrand/events
+
+            # split url to identify server url and actor id
+            elems = [x for x in url.split('/') if len(x) > 0 and x[0] == "@"]
+            if len(elems) == 1:
+                params = elems[0].split('@')
+                if len(params) == 2:
+                    self._api_end_point = "https://" + urlparse(url).netloc + "/api"
+                    self._group_id = params[1]
+                else:
+                    self._api_end_point = "https://" + params[2] + "/api"
+                    self._group_id = params[1]
+
+                events = self._oncoming_events()
+
+
+                for e in events:
+                    title = e["title"]
+                    event_url = e["url"]
+                    image = e["picture"]["url"]
+                    location = e["physicalAddress"]["description"] + ', ' + e["physicalAddress"]["locality"]
+                    soup = BeautifulSoup(e["description"], "html.parser")
+                    
+                    description = soup.text
+                    start = dateutil.parser.isoparse(e["beginsOn"])
+                    end = dateutil.parser.isoparse(e["endsOn"])
+
+                    start_day = start.date()
+                    start_time = start.time() if e["options"]["showStartTime"] else None
+                    end_day = end.date()
+                    end_time = end.time() if e["options"]["showEndTime"] else None
+
+
+                    self.add_event(
+                        default_values,
+                        title,
+                        None,
+                        start_day,
+                        location,
+                        description,
+                        [],
+                        uuids=[event_url],
+                        recurrences=None,
+                        url_human=event_url,
+                        start_time=start_time,
+                        published=published,
+                        image=image,
+                        end_day=end_day,
+                        end_time=end_time)
+        
+        return self.get_structure()

src/agenda_culturel/import_tasks/extractor.py

@@ -21,6 +21,11 @@ class Extractor(ABC):
         self.downloader = None
         self.has_2nd_method = False
 
+        # defined it to true in herited classes will
+        # avoid the importer to use the downloader on the url
+        # (used for extractors that are self-sufficient)
+        self.no_downloader = False
+        
         # parameters used by the downloader to get the content
         self.referer = ""
         self.data = None

src/agenda_culturel/migrations/0147_alter_recurrentimport_processor.py

@@ -0,0 +1,18 @@
+# Generated by Django 4.2.9 on 2025-02-12 14:17
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('agenda_culturel', '0146_alter_recurrentimport_processor'),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name='recurrentimport',
+            name='processor',
+            field=models.CharField(choices=[('ical', 'ical'), ('icalnobusy', 'ical no busy'), ('icalnovc', 'ical no VC'), ('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')], default='ical', max_length=20, verbose_name='Processor'),
+        ),
+    ]

src/agenda_culturel/models.py

@@ -2135,6 +2135,7 @@ class RecurrentImport(models.Model):
         IGUANA = 'iguana', _('Agenda iguana (médiathèques)')
         MILLEFORMES = 'Mille formes', _('Mille formes')
         AMISCERISES = 'Amis cerises', _('Les Amis du Temps des Cerises')
+        MOBILIZON = 'Mobilizon', _('Mobilizon')
 
     class DOWNLOADER(models.TextChoices):
         SIMPLE = "simple", _("simple")

src/requirements.txt

@@ -46,3 +46,4 @@ emoji==2.14.0
 django-honeypot==1.2.1
 django-autoslug==1.9.9
 django-debug-toolbar-template-profiler==2.1.0
+requests==2.32.3