added oop demo script

2 files changed, 29 insertions, 0 deletions

diff --git a/oop_demo.py b/oop_demo.py
new file mode 100644
index 00000000..2d76a6c4
--- /dev/null
+++ b/oop_demo.py
@@ -0,0 +1,28 @@
+from sec_certs.dataset import CCDataset, DatasetJSONEncoder
+from pathlib import Path
+from datetime import datetime
+import logging
+import json
+
+
+def main():
+    logging.basicConfig(level=logging.INFO)
+    start = datetime.now()
+
+    # Create empty dataset
+    dset = CCDataset({}, Path('./debug_dataset'), 'sample_dataset', 'sample dataset description')
+
+    # Load metadata for certificates from CSV and HTML sources
+    dset.get_certs_from_web()
+    logging.info(f'Finished parsing. Have dataset with {len(dset)} certificates.')
+
+    # Dump dataset into JSON
+    with open('./debug_dataset/cc_full_dataset.json', 'w') as handle:
+        json.dump(dset, handle, cls=DatasetJSONEncoder, indent=4)
+
+    end = datetime.now()
+    logging.info(f'The computation took {(end-start)} seconds.')
+
+
+if __name__ == '__main__':
+    main()
diff --git a/sec_certs/dataset.py b/sec_certs/dataset.py
index c430929b..ad26d7b1 100644
--- a/sec_certs/dataset.py
+++ b/sec_certs/dataset.py
@@ -133,6 +133,7 @@ class CCDataset(Dataset):
         """
         self.web_dir.mkdir(parents=True, exist_ok=True)
 
+        logging.info('Downloading required csv and html files.')
         html_items = [(x, self.web_dir / y) for y, x in self.html_products.items()]
         csv_items = [(x, self.web_dir / y) for y, x in self.csv_products.items()]
         helpers.download_parallel(html_items, num_threads=8)