replay api: add downloadUrl to replay endpoints to be used by RWP (#2456)

RWP (2.3.3+) can determine if the 'Download Archive' menu item should be
showed based on the value of downloadUrl.
If set to 'null', will hide the menu item:
- set downloadUrl to public collection download for public collections
replay
- set downloadUrl to null for private collection and crawl replay to
hide the download menu item in RWP (otherwise have to add the
auth_header query with bearer token and should assess security before
doing that..)

---------

Co-authored-by: Tessa Walsh <tessa@bitarchivist.net>

backend/btrixcloud/basecrawls.py

@@ -169,11 +169,14 @@ class BaseCrawlOps:
 
                 oid = res.get("oid")
                 if oid:
+                    origin = get_origin(headers)
                     res["pagesQueryUrl"] = (
-                        get_origin(headers)
+                        origin + f"/api/orgs/{oid}/crawls/{crawlid}/pagesSearch"
-                        + f"/api/orgs/{oid}/crawls/{crawlid}/pagesSearch"
                     )
 
+                # this will now disable the downloadUrl in RWP
+                res["downloadUrl"] = None
+
         crawl = CrawlOutWithResources.from_dict(res)
 
         if not skip_resources:

backend/btrixcloud/colls.py

@@ -352,11 +352,21 @@ class CollectionOps:
 
             public = "public/" if public_or_unlisted_only else ""
 
+            origin = get_origin(headers)
+
+            if public_or_unlisted_only:
+                slug = result.get("slug")
+                result["downloadUrl"] = (
+                    origin + f"/api/{public}orgs/{org.slug}/collections/{slug}/download"
+                )
+            else:
+                # disable download link, as not public without auth
+                result["downloadUrl"] = None
+
             if pages_optimized:
                 result["initialPages"] = initial_pages
                 result["pagesQueryUrl"] = (
-                    get_origin(headers)
+                    origin + f"/api/orgs/{org.id}/collections/{coll_id}/{public}pages"
-                    + f"/api/orgs/{org.id}/collections/{coll_id}/{public}pages"
                 )
 
         thumbnail = result.get("thumbnail")

backend/btrixcloud/models.py

@@ -1389,6 +1389,7 @@ class CrawlOutWithResources(CrawlOut):
 
     initialPages: List[PageOut] = []
     pagesQueryUrl: str = ""
+    downloadUrl: Optional[str] = None
 
 
 # ============================================================================
@@ -1518,6 +1519,7 @@ class CollOut(BaseMongoModel):
     initialPages: List[PageOut] = []
     preloadResources: List[PreloadResource] = []
     pagesQueryUrl: str = ""
+    downloadUrl: Optional[str] = None
 
 
 # ============================================================================

backend/test/test_collections.py

@@ -418,6 +418,7 @@ def test_get_collection_replay(crawler_auth_headers, default_org_id):
     assert data["pagesQueryUrl"].endswith(
         f"/orgs/{default_org_id}/collections/{_coll_id}/pages"
     )
+    assert data["downloadUrl"] is None
     assert "preloadResources" in data
 
     resources = data["resources"]
@@ -455,6 +456,7 @@ def test_collection_public(crawler_auth_headers, default_org_id):
     assert data["pagesQueryUrl"].endswith(
         f"/orgs/{default_org_id}/collections/{_coll_id}/public/pages"
     )
+    assert data["downloadUrl"] is not None
     assert "preloadResources" in data
 
     assert r.status_code == 200

backend/test/test_run_crawl.py

@@ -188,6 +188,7 @@ def test_wait_for_complete(admin_auth_headers, default_org_id):
     assert data["pagesQueryUrl"].endswith(
         f"/orgs/{default_org_id}/crawls/{admin_crawl_id}/pagesSearch"
     )
+    assert data["downloadUrl"] is None
 
     # ensure filename matches specified pattern
     # set in default_crawl_filename_template