Update app.py

app.py

@@ -304,10 +304,10 @@ def flickr_photo_candidate(url):
     return flickr_photo_via_html(username, photo_id, page_url)
 
 
-def flickr_stream_via_html(username, max_images, first):
+def flickr_stream_via_html(username, max_images, first, max_pages=100):
     """Read the photostream pages (newest first), then each photo page."""
     ids, page = [], 1
-    while len(ids) < max_images and page <= 100:
+    while len(ids) < max_images and page <= max_pages:
         u = f"https://www.flickr.com/photos/{username}/" + (f"page{page}/" if page > 1 else "")
         try:
             r = session.get(u, timeout=REQUEST_TIMEOUT)
@@ -339,7 +339,7 @@ def flickr_stream_via_html(username, max_images, first):
     return items
 
 
-def flickr_photo_and_stream(url, max_images, include_stream=True):
+def flickr_photo_and_stream(url, max_images, include_stream=True, max_pages=100):
     """Photo page -> the photographer's public photos, newest to oldest, up to max_images."""
     first = flickr_photo_candidate(url)
     if not first:
@@ -347,7 +347,7 @@ def flickr_photo_and_stream(url, max_images, include_stream=True):
     if not include_stream:
         return [first]
     username, _ = extract_flickr_photo_id(url)
-    items = flickr_stream_via_html(username, max_images, first)
+    items = flickr_stream_via_html(username, max_images, first, max_pages)
     items.sort(key=lambda s: s.get("date_uploaded", ""), reverse=True)
     return items or [first]
 
@@ -649,7 +649,8 @@ def empty_result(message):
     return [], message, [], pd.DataFrame(), pd.DataFrame(), None, None, None, None
 
 
-def find_images(url, max_images, min_width, min_height, remove_duplicates, include_stream=True):
+def find_images(url, max_images, min_width, min_height, remove_duplicates,
+                include_stream=True, max_pages=3):
     url = clean_url(url)
     if not url:
         return empty_result("❌ Please enter a URL.")
@@ -657,6 +658,7 @@ def find_images(url, max_images, min_width, min_height, remove_duplicates, inclu
         return empty_result("❌ Invalid HTTP/HTTPS URL.")
 
     max_images = min(int(max_images), MAX_IMAGES_HARD_LIMIT)
+    max_pages = max(1, int(max_pages or 1))
     min_width = int(min_width or 0)
     min_height = int(min_height or 0)
 
@@ -666,7 +668,7 @@ def find_images(url, max_images, min_width, min_height, remove_duplicates, inclu
     # ---- Find candidates ----
     try:
         photo_list = (
-            flickr_photo_and_stream(url, max_images, include_stream)
+            flickr_photo_and_stream(url, max_images, include_stream, max_pages)
             if is_flickr_url(url) else None
         )
         if photo_list:
@@ -839,6 +841,10 @@ with gr.Blocks(title=APP_TITLE) as demo:
             value=True,
             label="Photo page: also download the photographer's other photos",
         )
+        max_pages = gr.Number(
+            value=3, minimum=1, maximum=100, step=1, precision=0,
+            label="Photostream pages to scrape (stops earlier if Maximum images is reached)",
+        )
 
     with gr.Row():
         find_button = gr.Button("🔎 Find & Analyze Images", variant="primary")
@@ -873,7 +879,8 @@ with gr.Blocks(title=APP_TITLE) as demo:
 
     find_button.click(
         fn=find_images,
-        inputs=[url_input, max_images, min_width, min_height, remove_duplicates, include_stream],
+        inputs=[url_input, max_images, min_width, min_height, remove_duplicates,
+                include_stream, max_pages],
         outputs=[gallery, status, image_state, metadata_table, weekly_table,
                  weekly_plot, xlsx_file, csv_file, plot_file],
     )