Add pagination for search results

- Add SearchResult dataclass with pagination metadata
- Update search_flickr() to accept page parameter
- Parse total results count from Flickr response
- Add Bootstrap pagination controls to template
- Display total result count in UI
- Update documentation

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

AGENTS.md

@@ -26,7 +26,16 @@ in a `modelExport` JavaScript variable which contains photo metadata.
 
 - Uses browser-like headers (`BROWSER_HEADERS`) to avoid blocks
 - Parses embedded JSON by counting braces (not regex) to handle nested structures
-- Returns `FlickrPhoto` dataclass instances with id, title, username, license, URLs
+- Accepts optional `page` parameter for pagination (25 photos per page)
+- Returns `SearchResult` dataclass containing photos and pagination metadata
+
+### SearchResult Dataclass
+
+Contains search results with pagination info:
+- `photos`: List of `FlickrPhoto` instances
+- `total_photos`: Total number of matching photos
+- `current_page`: Current page number (1-indexed)
+- `total_pages`: Total number of pages (capped at 160 due to Flickr's 4000 result limit)
 
 ### FlickrPhoto Dataclass
 
@@ -78,13 +87,13 @@ Then visit http://localhost:5000/
 Test search functionality:
 ```python
 from main import search_flickr
-photos = search_flickr("Big Ben")
-print(len(photos), photos[0].title, photos[0].license_name)
+result = search_flickr("Big Ben", page=1)
+print(f"{len(result.photos)} photos, {result.total_pages} pages")
+print(result.photos[0].title, result.photos[0].license_name)
 ```
 
 ## Potential Improvements
 
-- Add pagination for search results (currently shows ~25 photos)
 - Cache search results to reduce Flickr requests
 - Add filtering by license type
 - Handle Flickr rate limiting/blocks more gracefully

README.md

@@ -27,6 +27,7 @@ photographers on Flickr whose photos can be used to enhance Wikipedia articles.
   CC BY-SA, CC0, Public Domain) are highlighted with a green badge.
 - **One-click message composition**: Click any photo to compose a permission
   request message with the photo displayed alongside.
+- **Pagination**: Browse through thousands of search results with page navigation.
 - Generate messages to request permission to use photos on Wikipedia.
 - Handle exceptions gracefully and provide detailed error information.
 

main.py

@@ -53,6 +53,9 @@ FLICKR_LICENSES = {
 }
 
 
+PHOTOS_PER_PAGE = 25
+
+
 @dataclasses.dataclass
 class FlickrPhoto:
     """Represents a Flickr photo from search results."""
@@ -78,6 +81,16 @@ class FlickrPhoto:
         return FLICKR_LICENSES.get(self.license, f"License {self.license}")
 
 
+@dataclasses.dataclass
+class SearchResult:
+    """Flickr search results with pagination metadata."""
+
+    photos: list[FlickrPhoto]
+    total_photos: int
+    current_page: int
+    total_pages: int
+
+
 def is_valid_flickr_image_url(url: str) -> bool:
     """Check if URL is a valid Flickr static image URL."""
     valid_prefixes = (
@@ -95,23 +108,25 @@ def is_valid_flickr_image_url(url: str) -> bool:
     return True
 
 
-def search_flickr(search_term: str) -> list[FlickrPhoto]:
+def search_flickr(search_term: str, page: int = 1) -> SearchResult:
     """Search Flickr for photos matching the search term."""
     encoded_term = quote(f'"{search_term}"')
-    url = f"https://flickr.com/search/?view_all=1&text={encoded_term}"
+    url = f"https://flickr.com/search/?view_all=1&text={encoded_term}&page={page}"
 
     response = requests.get(url, headers=BROWSER_HEADERS)
     response.raise_for_status()
 
-    return parse_flickr_search_results(response.text)
+    return parse_flickr_search_results(response.text, page)
 
 
-def parse_flickr_search_results(html: str) -> list[FlickrPhoto]:
+def parse_flickr_search_results(html: str, page: int = 1) -> SearchResult:
     """Parse Flickr search results HTML and extract photo data."""
+    empty_result = SearchResult(photos=[], total_photos=0, current_page=page, total_pages=0)
+
     # Find the modelExport JSON embedded in the page
     start = html.find("modelExport:")
     if start == -1:
-        return []
+        return empty_result
 
     start += len("modelExport:")
     while html[start].isspace():
@@ -148,12 +163,12 @@ def parse_flickr_search_results(html: str) -> list[FlickrPhoto]:
                     break
         i += 1
     else:
-        return []
+        return empty_result
 
     try:
         data = json.loads(json_str)
     except json.JSONDecodeError:
-        return []
+        return empty_result
 
     # Extract photos from the parsed data
     photos: list[FlickrPhoto] = []
@@ -162,18 +177,26 @@ def parse_flickr_search_results(html: str) -> list[FlickrPhoto]:
     photos_models = main.get("search-photos-lite-models", [])
 
     if not photos_models:
-        return []
+        return empty_result
 
-    photos_data = (
-        photos_models[0]
-        .get("data", {})
-        .get("photos", {})
-        .get("data", {})
-        .get("_data", [])
-    )
+    model_data = photos_models[0].get("data", {})
+    photos_container = model_data.get("photos", {}).get("data", {})
+    photos_data = photos_container.get("_data", [])
+    total_photos = photos_container.get("totalItems", 0)
+
+    # Calculate total pages (Flickr caps at 4000 results)
+    total_pages = min(total_photos, 4000) // PHOTOS_PER_PAGE
+    if min(total_photos, 4000) % PHOTOS_PER_PAGE:
+        total_pages += 1
 
     for photo_entry in photos_data:
+        # Skip None entries (placeholders from pagination)
+        if photo_entry is None:
+            continue
+
         pd = photo_entry.get("data", {})
+        if not pd:
+            continue
 
         sizes = pd.get("sizes", {}).get("data", {})
         thumb_data = sizes.get("q", sizes.get("sq", {})).get("data", {})
@@ -202,7 +225,12 @@ def parse_flickr_search_results(html: str) -> list[FlickrPhoto]:
             )
         )
 
-    return photos
+    return SearchResult(
+        photos=photos,
+        total_photos=total_photos,
+        current_page=page,
+        total_pages=total_pages,
+    )
 
 
 @app.errorhandler(werkzeug.exceptions.InternalServerError)
@@ -266,12 +294,14 @@ def start() -> str:
     flickr_url = flask.request.args.get("flickr")
     if not flickr_url:
         # Search Flickr for photos
-        photos = search_flickr(name)
+        page = flask.request.args.get("page", 1, type=int)
+        page = max(1, page)  # Ensure page is at least 1
+        search_result = search_flickr(name, page)
         return flask.render_template(
             "combined.html",
             name=name,
             enwp=enwp,
-            photos=photos,
+            search_result=search_result,
         )
 
     if "/in/" in flickr_url:

templates/combined.html

@@ -15,13 +15,13 @@
       <input type="submit" value="Submit">
     </form>
 
-    {% if name and photos is defined and photos %}
+    {% if name and search_result is defined and search_result.photos %}
 
     <p>Wikipedia article: {{ name }}</p>
-    <p>Select a photo to compose a message:</p>
+    <p>Select a photo to compose a message ({{ search_result.total_photos | default(0) }} results):</p>
 
     <div class="row row-cols-2 row-cols-md-3 row-cols-lg-4 g-3 mb-3">
-      {% for photo in photos %}
+      {% for photo in search_result.photos %}
       <div class="col">
         <div class="card h-100">
           <a href="{{ url_for(request.endpoint, enwp=enwp, flickr=photo.flickr_url, img=photo.medium_url) }}">
@@ -36,6 +36,59 @@
       {% endfor %}
     </div>
 
+    {% if search_result.total_pages > 1 %}
+    <nav aria-label="Search results pagination">
+      <ul class="pagination justify-content-center">
+        {% if search_result.current_page > 1 %}
+        <li class="page-item">
+          <a class="page-link" href="{{ url_for(request.endpoint, enwp=enwp, page=search_result.current_page - 1) }}">Previous</a>
+        </li>
+        {% else %}
+        <li class="page-item disabled">
+          <span class="page-link">Previous</span>
+        </li>
+        {% endif %}
+
+        {% set start_page = [1, search_result.current_page - 2] | max %}
+        {% set end_page = [search_result.total_pages, search_result.current_page + 2] | min %}
+
+        {% if start_page > 1 %}
+        <li class="page-item">
+          <a class="page-link" href="{{ url_for(request.endpoint, enwp=enwp, page=1) }}">1</a>
+        </li>
+        {% if start_page > 2 %}
+        <li class="page-item disabled"><span class="page-link">...</span></li>
+        {% endif %}
+        {% endif %}
+
+        {% for p in range(start_page, end_page + 1) %}
+        <li class="page-item {{ 'active' if p == search_result.current_page else '' }}">
+          <a class="page-link" href="{{ url_for(request.endpoint, enwp=enwp, page=p) }}">{{ p }}</a>
+        </li>
+        {% endfor %}
+
+        {% if end_page < search_result.total_pages %}
+        {% if end_page < search_result.total_pages - 1 %}
+        <li class="page-item disabled"><span class="page-link">...</span></li>
+        {% endif %}
+        <li class="page-item">
+          <a class="page-link" href="{{ url_for(request.endpoint, enwp=enwp, page=search_result.total_pages) }}">{{ search_result.total_pages }}</a>
+        </li>
+        {% endif %}
+
+        {% if search_result.current_page < search_result.total_pages %}
+        <li class="page-item">
+          <a class="page-link" href="{{ url_for(request.endpoint, enwp=enwp, page=search_result.current_page + 1) }}">Next</a>
+        </li>
+        {% else %}
+        <li class="page-item disabled">
+          <span class="page-link">Next</span>
+        </li>
+        {% endif %}
+      </ul>
+    </nav>
+    {% endif %}
+
     <p class="text-muted small">
       <a href="https://flickr.com/search/?view_all=1&text={{ '"' + name + '"' | urlencode }}" target="_blank">View full search on Flickr</a>
     </p>