Add single crawl info api at /crawls/{crawl_id} (#418)

* backend: crawl info apis:
- add /crawls/{crawl_id} api endpoint which just lists the crawl info, without resolving the individual files
- move /crawls/{crawl_id}.json -> /crawls/{crawl_id}/replay.json for clarity that it's used for replay

* frontend: update api for new replay.json endpoint

backend/btrixcloud/crawls.py

@@ -173,6 +173,7 @@ class CrawlOps:
         archive: Optional[Archive] = None,
         cid: uuid.UUID = None,
         collid: uuid.UUID = None,
+        crawl_id: str = None,
         exclude_files=True,
         running_only=False,
     ):
@@ -193,6 +194,9 @@ class CrawlOps:
         if running_only:
             query["state"] = {"$in": ["running", "starting", "stopping"]}
 
+        if crawl_id:
+            query["_id"] = crawl_id
+
         # pylint: disable=duplicate-code
         aggregate = [
             {"$match": query},
@@ -613,7 +617,7 @@ def init_crawls_api(
         return {"deleted": res}
 
     @app.get(
-        "/archives/all/crawls/{crawl_id}.json",
+        "/archives/all/crawls/{crawl_id}/replay.json",
         tags=["crawls"],
         response_model=CrawlOut,
     )
@@ -624,13 +628,43 @@ def init_crawls_api(
         return await ops.get_crawl(crawl_id, None)
 
     @app.get(
-        "/archives/{aid}/crawls/{crawl_id}.json",
+        "/archives/{aid}/crawls/{crawl_id}/replay.json",
         tags=["crawls"],
         response_model=CrawlOut,
     )
     async def get_crawl(crawl_id, archive: Archive = Depends(archive_crawl_dep)):
         return await ops.get_crawl(crawl_id, archive)
 
+    @app.get(
+        "/archives/all/crawls/{crawl_id}",
+        tags=["crawls"],
+        response_model=ListCrawlOut,
+    )
+    async def list_single_crawl_admin(crawl_id, user: User = Depends(user_dep)):
+        if not user.is_superuser:
+            raise HTTPException(status_code=403, detail="Not Allowed")
+
+        crawls = await ops.list_crawls(crawl_id=crawl_id)
+        print("crawls", crawls)
+        if len(crawls) < 1:
+            raise HTTPException(status_code=404, detail="crawl_not_found")
+
+        return crawls[0]
+
+    @app.get(
+        "/archives/{aid}/crawls/{crawl_id}",
+        tags=["crawls"],
+        response_model=ListCrawlOut,
+    )
+    async def list_single_crawl(
+        crawl_id, archive: Archive = Depends(archive_crawl_dep)
+    ):
+        crawls = await ops.list_crawls(archive, crawl_id=crawl_id)
+        if len(crawls) < 1:
+            raise HTTPException(status_code=404, detail="crawl_not_found")
+
+        return crawls[0]
+
     @app.post(
         "/archives/{aid}/crawls/{crawl_id}/scale",
         tags=["crawls"],

backend/test/test_run_crawl.py

@@ -81,7 +81,7 @@ def test_wait_for_complete():
 
     while True:
         r = requests.get(
-            f"{api_prefix}/archives/{archive_id}/crawls/{crawl_id}.json",
+            f"{api_prefix}/archives/{archive_id}/crawls/{crawl_id}/replay.json",
             headers=headers,
         )
         data = r.json()
@@ -105,6 +105,13 @@ def test_wait_for_complete():
     wacz_size = data["resources"][0]["size"]
     wacz_hash = data["resources"][0]["hash"]
 
+def test_crawl_info():
+    r = requests.get(
+        f"{api_prefix}/archives/{archive_id}/crawls/{crawl_id}",
+        headers=headers,
+    )
+    data = r.json()
+    assert data["fileSize"] == wacz_size
 
 def test_download_wacz():
     r = requests.get(host_prefix + wacz_path)

frontend/src/pages/archive/crawl-detail.ts

@@ -560,7 +560,7 @@ export class CrawlDetail extends LiteElement {
     const bearer = this.authState?.headers?.Authorization?.split(" ", 2)[1];
 
     // for now, just use the first file until multi-wacz support is fully implemented
-    const replaySource = `/api/archives/${this.crawl?.aid}/crawls/${this.crawlId}.json?auth_bearer=${bearer}`;
+    const replaySource = `/api/archives/${this.crawl?.aid}/crawls/${this.crawlId}/replay.json?auth_bearer=${bearer}`;
     //const replaySource = this.crawl?.resources?.[0]?.path;
 
     const canReplay = replaySource && this.hasFiles;
@@ -881,7 +881,7 @@ export class CrawlDetail extends LiteElement {
 
   private async getCrawl(): Promise<Crawl> {
     const data: Crawl = await this.apiFetch(
-      `${this.crawlsAPIBaseUrl || this.crawlsBaseUrl}/${this.crawlId}.json`,
+      `${this.crawlsAPIBaseUrl || this.crawlsBaseUrl}/${this.crawlId}/replay.json`,
       this.authState!
     );