1 files changed, 47 insertions, 0 deletions
diff --git a/megapixels/commands/search/flickr_url.py b/megapixels/commands/search/flickr_url.py
new file mode 100644
index 00000000..bc205604
--- /dev/null
+++ b/megapixels/commands/search/flickr_url.py
@@ -0,0 +1,47 @@
+"""
+# data input example
+--url https://farm2.staticflickr.com/1252/1366994858_d4a2b377cc_o.jpg
+"""
+
+import click
+
+# datasets
+dataset_keys = ['pipa', 'megaface', 'helen', 'ibm_dif', 'adience', 'who_goes_there', 'vgg_face']
+#dataset_keys = ['pipa']
+
+@click.command()
+@click.option('-u', '--url', 'opt_url', required=True,
+  help='Photo URL')
+@click.option('-o', '--output', 'opt_fp_out',
+  help='Output file CSV')
+@click.pass_context
+def cli(ctx, opt_url, opt_fp_out):
+  """Locate image by URL"""
+
+  import sys
+  from os.path import join
+  from glob import glob
+  from pathlib import Path
+  import time
+
+  import pandas as pd
+  from tqdm import tqdm
+
+  from app.utils.logger_utils import Logger
+
+  log = Logger.getLogger()
+
+  fp_dataset_base = '/data_store/datasets/people/'
+
+  matches = []
+
+  for dk in dataset_keys:
+    
+    fp_filepaths = join(fp_dataset_base, dk, f'metadata/{dk}_filepaths.csv')
+    log.debug(f'loading: {fp_filepaths}')
+    df = pd.read_csv(fp_filepaths)
+    urls = list(df['url'])
+    if opt_url in urls:
+      log.info(f'Found image in {dk}')
+      matches.append(dk)
+