Ajout (temporaire) d'exports pour traquer les problèmes d'import des pages

Voir #244

src/agenda_culturel/import_tasks/custom_extractors/fbevents.py

@@ -3,6 +3,12 @@ from ..extractor_facebook import FacebookEvent
 import json5
 from bs4 import BeautifulSoup
 import json
+import os
+from datetime import datetime
+
+import logging
+
+logger = logging.getLogger(__name__)
 
 
 # A class dedicated to get events from a facebook events page
@@ -13,10 +19,24 @@ class CExtractor(TwoStepsExtractor):
     def build_event_url_list(self, content):
         soup = BeautifulSoup(content, "html.parser")
 
+        found = False
         links = soup.find_all("a")
         for link in links:
             if link.get("href").startswith('https://www.facebook.com/events/'):
                 self.add_event_url(link.get('href').split('?')[0])
+                found = True
+
+        if not found:
+            directory = "errors/"
+            if not os.path.exists(directory):
+                os.makedirs(directory)
+            now = datetime.now()
+            filename = directory + now.strftime("%Y%m%d_%H%M%S") + ".html"
+            logger.warning("cannot find any event link in events page. Save content page in " + filename)
+            with open(filename, "w") as text_file:
+                text_file.write(content)
+
+                
 
 
     def add_event_from_content(
@@ -42,4 +62,7 @@ class CExtractor(TwoStepsExtractor):
                 event["published"] = published
 
                 self.add_event(default_values, **event)
+        else:
+            logger.warning("cannot find any event in page")
+