Ajout (pas finalisé) de l'import Cour des 3 Coquins

experimentations/get_c3c_events.py

@@ -0,0 +1,43 @@
+#!/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)
+
+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(), c3c.CExtractor())
+    url = "https://billetterie-c3c.clermont-ferrand.fr/"
+    url_human = "https://billetterie-c3c.clermont-ferrand.fr/"
+
+    try:
+        events = u2e.process(url, url_human, cache = "cache-c3c.html", default_values = {"location": "La Cour des 3 Coquins"}, published = True)
+
+        exportfile = "events-c3c.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/import_tasks/custom_extractors/c3c.py

@@ -0,0 +1,100 @@
+from ..generic_extractors import *
+from bs4 import BeautifulSoup
+
+# A class dedicated to get events from La Cour des 3 Coquins
+# URL: https://billetterie-c3c.clermont-ferrand.fr//
+class CExtractor(TwoStepsExtractor):
+    nom_lieu = "La Cour des 3 Coquins"
+
+    def category_c3c2agenda(self, category):
+        if not category:
+            return None
+        mapping = {"Théâtre": "Théâtre", "Concert": "Concert", "Projection": "Cinéma"}
+        if category in mapping:
+            return mapping[category]
+        else:
+            return None
+
+    def build_event_url_list(self, content):
+        soup = BeautifulSoup(content, "html.parser")
+
+        events = soup.select("div.fiche-info")
+
+        for e in events:
+            e_url = e.select_one("a.btn.lien_savoir_plus")["href"]
+            if e_url != "":
+                e_url = self.url + "/" + e_url
+                self.add_event_url(e_url)
+
+    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("h1")
+        if title:
+            title = title.text
+
+        image = soup.select_one("#media .swiper-slide img")
+        if image:
+            image = image["src"]
+        else:
+            image = None
+            
+        description = soup.select_one(".presentation")
+        duree = soup.select_one("#criteres .DUREE-V .valeur-critere li")
+        if duree is not None:
+            duree = self.parse_french_time(duree.text)
+
+        location = self.nom_lieu
+        tags = []
+        for t in soup.select(".sous-titre span"):
+            classes = t.get("class")
+            if classes and len(classes) > 0:
+                if classes[0].startswith("LIEU-"):
+                    location = t.text
+                elif classes[0].startswith("THEMATIQUE-"):
+                    tag = self.category_c3c2agenda(t.text)
+                    if tag is not None:
+                        tags.append(tag)
+
+        # TODO: parser les dates, récupérer les heures ()
+    
+            
+
+        print("EVENT ", event_url)
+        print("- ", title)
+        print("- ", image)
+        print("- ", len(description))
+        print("- ", duree)
+        print("- ", location)
+        print("- ", tags)
+        print("- ", dates)
+
+        return
+
+
+        url_human = event_url
+
+        self.add_event_with_props(
+            event_url,
+            None,
+            None,
+            start_day,
+            location,
+            description,
+            tags,
+            recurrences=None,
+            uuids=[event_url],
+            url_human=url_human,
+            start_time=start_time,
+            end_day=end_day,
+            end_time=end_time,
+            published=published,
+            image=image,
+        )

src/agenda_culturel/import_tasks/extractor.py

@@ -102,6 +102,13 @@ class Extractor(ABC):
                     h = m.group(1)
                     m = "0"
                     s = "0"
+                else:
+                    # format minutes
+                    m = re.search("([0-9]+)[ ]*(?:mn|min|Min|Mn)", text)
+                    if m:
+                        h = "0"
+                        m = m.group(1)
+                        s = "0"
                     else:
                         return None