Build full tree from root_cat >(cat?)> dataset

dares_to_dbnomics.py

@@ -421,23 +421,28 @@ def extract_dataset(source_dir, category, dataset):
     #For theses categories 
     if category["code"] in [1, 10, 13]:
         # skip first page 'To Read' or 'Synthèse' as mentionned in Analysis
-        return sorted([slugify(n) for n in book.sheet_names()[1:]])
+        return sorted(set([slugify(n) for n in book.sheet_names()[1:]]))
     else:
         # each sheet is a dataset
         datasets = sorted([slugify(n) for n in book.sheet_names()])
         # ugly skip lisez-moi sheet althought **NOT** mentionned
-        return sorted([n for n in datasets if not n.startswith("lisez-moi")])
+        return sorted(set([n for n in datasets if not n.startswith("lisez-moi")]))
 
 def build_datasets(dest_dir, category, datasets):
     '''write category and create dir for datasets'''
-    cat_dir_name = "%i %s" %(category["code"], category["slug"])
     #write category.json into category
-    category_dir_path = os.path.join(dest_dir, cat_dir_name)
+    if "dir_path" in category.keys():
+        category_dir_path  = category["dir_path"]
+    else:    
+        cat_dir_name = "%s %s" %(str(category["code"]), category["slug"])
+        category_dir_path = os.path.join(dest_dir, cat_dir_name)
+    print(category_dir_path)
     category_json = {
             "name": category["slug"],
             "category_code": str(category["code"]),
             "datasets": datasets,
         }
+    print(category_json)
     write_category_to_json(category_json, category_dir_path)
     write_category_to_md(category_json, category_dir_path)
     datasets_dir_path = set([os.path.join(category_dir_path, d) for d in datasets])
@@ -481,15 +486,14 @@ def build_tree(source_dir, dest_dir):
         else:
             
             subcats = build_categories(dest_dir, category, category["sub-categories"])
-            print(subcats)
+            
             # datasets = extract_dataset(source_dir, category, category["sub-category"][0])
             # datasets_path = build_datasets(dest_dir, category, datasets)
-            # for subcat in category["sub-categories"]:
-            #     print(subcat, category)
-                
+            for subcat_d,subcat in zip(subcats, category["sub-categories"]):
+                subcat["dir_path"] = subcat_d
                 # subcats_path = build_datasets(dest_dir, category, subcat)
-                # datasets = extract_datasets(category, subcat, subcat["datasets"][0])
-                # datasets_path = build_datasets(dest_dir, category, datasets) 
+                datasets = extract_dataset(source_dir, subcat, subcat["datasets"][0])
+                datasets_path = build_datasets(category, subcat, datasets) 
 
 def main():
     args = docopt(__doc__)