From e7a4d9ac8e01524a88f47f87b0f14c14f7704e07 Mon Sep 17 00:00:00 2001
From: Tim Sutton <tim@kartoza.com>
Date: Mon, 16 Jan 2023 22:08:41 +0000
Subject: [PATCH] Fix #88 disable flickr harvest by default

---
 README.md      | 12 ++++++++++++
 fetch_feeds.py | 29 +++++++++++++++++++++--------
 2 files changed, 33 insertions(+), 8 deletions(-)

diff --git a/README.md b/README.md
index e991e63c1..e8ee58b6a 100644
--- a/README.md
+++ b/README.md
@@ -221,6 +221,18 @@ There is a github action that will run the tests automatically on PR submission,
 
 See ```.github/workflows/e2e.yml```
 
+## Content Harvesting
+
+You can harvest data from various feeds using the fetch_feeds.py script. By default
+flickr harvesting is disabled in this script so run it manually and review the content
+to see if it is suitable for publication on our site.
+
+```bash
+./fetch_feeds.py --flickr=yes
+```
+
+This script is run nightly as a github action (see .github/workflows/update-feeds.yml).
+
 ## Search Functionality 
 The search functionality uses both [FuseJS](https://fusejs.io/) and [MarkJS](https://markjs.io/).
 
diff --git a/fetch_feeds.py b/fetch_feeds.py
index 9c6d8c882..17a424306 100755
--- a/fetch_feeds.py
+++ b/fetch_feeds.py
@@ -5,6 +5,7 @@
 # (c) Tim Sutton, 2023
 
 import requests
+import argparse
 import json
 import shutil
 import os
@@ -168,16 +169,28 @@ def fetch_blog_feed(showcase_type, rss_url):
             print(f"Writing: {image_filename}")
         del response   
 
+
+parser = argparse.ArgumentParser(description='Import items from various feeds.')
+parser.add_argument(
+    "--flickr", 
+    help="Import flickr items (defaults to no)",
+    default="no",
+    type=bool, 
+    required=False)
+parser.parse_args()
+args = parser.parse_args()
+
 fetch_funders()
 
-fetch_flickr_screenshots(
-    showcase_type="map",
-    rss_url = "https://api.flickr.com/services/feeds/groups_pool.gne?id=2244553@N22&lang=en-us&format=atom"
-)
-fetch_flickr_screenshots(
-    showcase_type="screenshot",
-    rss_url = "https://api.flickr.com/services/feeds/groups_pool.gne?id=2327386@N22&lang=en-us&format=atom"
-)
+if args.flickr:
+    fetch_flickr_screenshots(
+        showcase_type="map",
+        rss_url = "https://api.flickr.com/services/feeds/groups_pool.gne?id=2244553@N22&lang=en-us&format=atom"
+    )
+    fetch_flickr_screenshots(
+        showcase_type="screenshot",
+        rss_url = "https://api.flickr.com/services/feeds/groups_pool.gne?id=2327386@N22&lang=en-us&format=atom"
+    )
 
 # Planet blog aggregator
 fetch_blog_feed(