Update flickr_scraper.py (#31)

ultralytics · Jun 22, 2024 · 55527df · 55527df
1 parent 71d636e
commit 55527df
Showing 1 changed file with 10 additions and 25 deletions.
diff --git a/flickr_scraper.py b/flickr_scraper.py
@@ -1,8 +1,8 @@
 # Generated by Glenn Jocher (glenn.jocher@ultralytics.com) for https://github.com/ultralytics
 
 import argparse
-import os
 import time
+from pathlib import Path
 
 from flickrapi import FlickrAPI
 
@@ -26,55 +26,40 @@ def get_urls(search="honeybees on flowers", n=10, download=False):
     )
 
     if download:
-        dir = os.getcwd() + os.sep + "images" + os.sep + search.replace(" ", "_") + os.sep  # save directory
-        if not os.path.exists(dir):
-            os.makedirs(dir)
+        dir_path = Path.cwd() / "images" / search.replace(" ", "_")
+        dir_path.mkdir(parents=True, exist_ok=True)
 
     urls = []
     for i, photo in enumerate(photos):
         if i <= n:
             try:
-                # construct url https://www.flickr.com/services/api/misc.urls.html
                 url = photo.get("url_o")  # original size
                 if url is None:
-                    url = (
-                        f"https://farm{photo.get('farm')}.staticflickr.com/{photo.get('server')}/"
-                        f"{photo.get('id')}_{photo.get('secret')}_b.jpg"
-                    )
+                    url = f"https://farm{photo.get('farm')}.staticflickr.com/{photo.get('server')}/{photo.get('id')}_{photo.get('secret')}_b.jpg"
 
-                # download
                 if download:
-                    download_uri(url, dir)
+                    download_uri(url, dir_path)
 
                 urls.append(url)
-                print("%g/%g %s" % (i, n, url))
+                print(f"{i}/{n} {url}")
             except Exception:
-                print("%g/%g error..." % (i, n))
+                print(f"{i}/{n} error...")
 
         else:
-            # import pandas as pd
-            # urls = pd.Series(urls)
-            # urls.to_csv(search + "_urls.csv")
-            print("Done. (%.1fs)" % (time.time() - t) + ("\nAll images saved to %s" % dir if download else ""))
+            print(f"Done. ({time.time() - t:.1f}s)" + (f"\nAll images saved to {dir_path}" if download else ""))
             break
 
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
-    parser.add_argument("--search", nargs="+", default="honeybees on flowers", help="flickr search term")
-    # parser.add_argument('--search', type=str, default='honeybees on flowers', help='flickr search term')
+    parser.add_argument("--search", nargs="+", default=["honeybees on flowers"], help="flickr search term")
     parser.add_argument("--n", type=int, default=10, help="number of images")
     parser.add_argument("--download", action="store_true", help="download images")
     opt = parser.parse_args()
 
     print(f"nargs {opt.search}")
-    # Check key
     help_url = "https://www.flickr.com/services/apps/create/apply"
     assert key and secret, f"Flickr API key required in flickr_scraper.py L11-12. To apply visit {help_url}"
 
     for search in opt.search:
-        get_urls(
-            search=search,  # search term
-            n=opt.n,  # max number of images
-            download=opt.download,
-        )  # download images
+        get_urls(search=search, n=opt.n, download=opt.download)