1 files changed, 48 insertions, 0 deletions
diff --git a/megapixels/commands/msc/flickr_list_to_csv.py b/megapixels/commands/msc/flickr_list_to_csv.py
new file mode 100644
index 00000000..f107db60
--- /dev/null
+++ b/megapixels/commands/msc/flickr_list_to_csv.py
@@ -0,0 +1,48 @@
+import click
+
+from app.utils.logger_utils import Logger
+
+log = Logger.getLogger()
+
+fp_in = '/data_store/datasets/msc/embassies/embassy-list.txt'
+fp_out = '/data_store/datasets/msc/embassies/embassies_on_flickr.csv'
+
+@click.command()
+@click.option('-i', '--input', 'opt_fp_in', required=True, default=fp_in,
+  help='Input directory')
+@click.option('-o', '--output', 'opt_fp_out', required=True, default=fp_out,
+  help='Output file')
+@click.pass_context
+def cli(ctx, opt_fp_in, opt_fp_out):
+  """Convert embassy list to CSV"""
+  
+  import sys
+  from glob import glob
+  from os.path import join
+  from pathlib import Path
+  import time
+
+  import pandas as pd
+  from tqdm import tqdm
+
+  from app.utils import file_utils
+
+  log = Logger.getLogger()
+  log.info('converting flickr list to CSV')
+  
+  items = []
+
+  embassies = file_utils.load_text(opt_fp_in)
+
+  for embassy in tqdm(embassies):
+    splits = embassy.split(' ')
+    url = splits[0].strip()
+    title = ' '.join(splits[1:]).strip()
+    username = Path(url).stem
+    items.append({'title': title, 'url': url, 'username': username})
+
+  df = pd.DataFrame.from_dict(items)
+  df.to_csv(opt_fp_out, index=False)
+  log.debug(f'Wrote {len(df)} lines')
+
+