Skip articles that belongs to an obsolete rubrique

spip2pelican.py

@@ -13,7 +13,7 @@ from yaml_cleaner import strip_invalid, remove_date
 
 
 AUTHORS = "Groupe Calcul"
-CATEGORIES = {4: "journees", 39: "formations", 6: "paysage", 10: "paysage", 14: "paysage", 2: "groupe",
+CATEGORIES = {4: "journees", 39: "formations", 6: "paysage", 10: "paysage", 14: "paysage", 2: "groupe", 49: "skip",
               -1: "spip_divers"}
 ATTACHMENTS_PREFIX = "attachments/spip/"
 yaml = YAML(typ='safe')
@@ -21,7 +21,6 @@ yaml = YAML(typ='safe')
 
 # TODO: handle mix of italic and bold : { {{Marc Poinot}} (ONERA)}
 # TODO: convert <img…|…> images
-# TODO: Remove articles that belong to rubrique 49 ("Formations organisées par les méso-centres")
 
 def header(s):
     """
@@ -92,6 +91,15 @@ def link(s):
                         if rub_url:
                             # [text->rub#]
                             id_rub = int(rub_url.group(1))
+                            category = categories_table[id_rub]
+                            if category == 'skip':
+                                msg = f"  WARNING: link to a skipped rubrique {id_rub}\n"
+                                msg += f"    text: {text}\n"
+                                msg += f"    url:  {url}\n"
+                                msg += "  -> nullify URL"
+                                print(msg)
+                                new_url = ""
+                            else:
                                 new_url = os.path.join(f"{categories_table[id_rub]}.html")
                         else:
                             # [text->path_to_file]
@@ -177,7 +185,10 @@ def spip_to_pelican(spip, categories):
     This is the content of my super blog post.
     """
 
-    if not spip['texte']:
+    category = categories[spip['id_rubrique']]
+    if category == 'skip':
+        skip_reason = "it belongs to a skipped rubrique"
+    elif not spip['texte']:
         skip_reason = "empty content"
     elif spip['statut'] != 'publie':
         skip_reason = "not published"
@@ -194,7 +205,6 @@ def spip_to_pelican(spip, categories):
         title = spip_to_markdown(spip['titre'])
         date = spip['date']
         modified = spip['date_modif']
-        category = categories[spip['id_rubrique']]
         tags = []
         summary = spip['descriptif']
         authors = AUTHORS