More friendly WARC prefix inside WACZ based on Org slug + Crawl Name / First Seed URL. (#1537)

Supports setting WARC prefix for WARCs inside WACZ to `<org slug>-<slug
[crawl name | first seed host]>`.
- Prefix set via WARC_PREFIX env var, supported in browsertrix-crawler
1.0.0-beta.4 or higher
If crawl name is provided, uses crawl name, other hostname of first
seed. The name is 'sluggified', using lowercase alphanum characters
separated by dashes.

Ex: in an organization called `Default Org`, a crawl of
`https://specs.webrecorder.net/` and no name will have WARCs named:
`default-org-specs-webrecorder-net-....warc.gz`
If the crawl is given the name `SPECS`, the WARCs will be named
`default-org-specs-manual-....warc.gz`

Fixes #412 in a default way.

backend/btrixcloud/crawlconfigs.py

@@ -33,7 +33,7 @@ from .models import (
     CrawlerChannel,
     CrawlerChannels,
 )
-from .utils import dt_now
+from .utils import dt_now, slug_from_name
 
 if TYPE_CHECKING:
     from .orgs import OrgOps
@@ -232,6 +232,7 @@ class CrawlConfigOps:
             run_now=run_now,
             out_filename=out_filename,
             profile_filename=profile_filename or "",
+            warc_prefix=self.get_warc_prefix(org, crawlconfig),
         )
 
         if crawl_id and run_now:
@@ -298,6 +299,7 @@ class CrawlConfigOps:
             run_now=False,
             out_filename=self.default_filename_template,
             profile_filename=profile_filename or "",
+            warc_prefix=self.get_warc_prefix(org, crawlconfig),
         )
 
     async def update_crawl_config(
@@ -841,7 +843,10 @@ class CrawlConfigOps:
 
         try:
             crawl_id = await self.crawl_manager.create_crawl_job(
-                crawlconfig, org.storage, userid=str(user.id)
+                crawlconfig,
+                org.storage,
+                userid=str(user.id),
+                warc_prefix=self.get_warc_prefix(org, crawlconfig),
             )
             await self.add_new_crawl(crawl_id, crawlconfig, user, manual=True)
             return crawl_id
@@ -897,6 +902,21 @@ class CrawlConfigOps:
         """Get crawler image name by id"""
         return self.crawler_images_map.get(crawler_channel or "")
 
+    def get_warc_prefix(self, org: Organization, crawlconfig: CrawlConfig) -> str:
+        """Generate WARC prefix slug from org slug, name or url
+        if no name is provided, hostname is used from url, otherwise
+        url is ignored"""
+        name = crawlconfig.name
+        if not name:
+            if crawlconfig.config.seeds and len(crawlconfig.config.seeds):
+                url = crawlconfig.config.seeds[0].url
+                parts = urllib.parse.urlsplit(url)
+                name = parts.netloc
+
+        name = slug_from_name(name or "")
+        prefix = org.slug + "-" + name
+        return prefix[:80]
+
 
 # ============================================================================
 # pylint: disable=too-many-locals

backend/btrixcloud/crawlmanager.py

@@ -119,6 +119,7 @@ class CrawlManager(K8sAPI):
         run_now: bool,
         out_filename: str,
         profile_filename: str,
+        warc_prefix: str,
     ) -> Optional[str]:
         """add new crawl, store crawl config in configmap"""
 
@@ -139,7 +140,10 @@ class CrawlManager(K8sAPI):
 
         if run_now:
             crawl_id = await self.create_crawl_job(
-                crawlconfig, storage, str(crawlconfig.modifiedBy)
+                crawlconfig,
+                storage,
+                str(crawlconfig.modifiedBy),
+                warc_prefix,
             )
 
         await self._update_scheduled_job(crawlconfig)
@@ -151,6 +155,7 @@ class CrawlManager(K8sAPI):
         crawlconfig: CrawlConfig,
         storage: StorageRef,
         userid: str,
+        warc_prefix: str,
     ) -> str:
         """create new crawl job from config"""
         cid = str(crawlconfig.id)
@@ -169,6 +174,7 @@ class CrawlManager(K8sAPI):
             crawlconfig.crawlTimeout,
             crawlconfig.maxCrawlSize,
             manual=True,
+            warc_prefix=warc_prefix,
         )
 
     async def update_crawl_config(

backend/btrixcloud/k8sapi.py

@@ -86,6 +86,7 @@ class K8sAPI:
         max_crawl_size=0,
         manual=True,
         crawl_id=None,
+        warc_prefix="",
     ):
         """load job template from yaml"""
         if not crawl_id:
@@ -104,6 +105,7 @@ class K8sAPI:
             "storage_name": str(storage),
             "manual": "1" if manual else "0",
             "crawler_channel": crawler_channel,
+            "warc_prefix": warc_prefix,
         }
 
         data = self.templates.env.get_template("crawl_job.yaml").render(params)

backend/btrixcloud/operator.py

@@ -538,6 +538,8 @@ class BtrixOperator(K8sAPI):
         params["storage_filename"] = configmap["STORE_FILENAME"]
         params["restart_time"] = spec.get("restartTime")
 
+        params["warc_prefix"] = spec.get("warcPrefix")
+
         params["redis_url"] = redis_url
 
         if spec.get("restartTime") != status.restartTime:
@@ -1651,26 +1653,10 @@ class BtrixOperator(K8sAPI):
 
         org = await self.org_ops.get_org_by_id(UUID(oid))
 
-        crawl_id, crawljob = self.new_crawl_job_yaml(
+        warc_prefix = None
-            cid,
-            userid=userid,
-            oid=oid,
-            storage=org.storage,
-            crawler_channel=configmap.get("CRAWLER_CHANNEL", "default"),
-            scale=int(configmap.get("INITIAL_SCALE", 1)),
-            crawl_timeout=int(configmap.get("CRAWL_TIMEOUT", 0)),
-            max_crawl_size=int(configmap.get("MAX_CRAWL_SIZE", "0")),
-            manual=False,
-            crawl_id=crawl_id,
-        )
-
-        attachments = list(yaml.safe_load_all(crawljob))
-
-        if crawl_id in crawljobs:
-            attachments[0]["status"] = crawljobs[CJS][crawl_id]["status"]
 
         if not actual_state:
-            # pylint: disable=duplicate-code
+            # cronjob doesn't exist yet
             crawlconfig = await self.crawl_config_ops.get_crawl_config(
                 UUID(cid), UUID(oid)
             )
@@ -1686,11 +1672,35 @@ class BtrixOperator(K8sAPI):
                 print(f"error: missing user for id {userid}")
                 return {"attachments": []}
 
+            warc_prefix = self.crawl_config_ops.get_warc_prefix(org, crawlconfig)
+
             await self.crawl_config_ops.add_new_crawl(
-                crawl_id, crawlconfig, user, manual=False
+                crawl_id,
+                crawlconfig,
+                user,
+                manual=False,
             )
             print("Scheduled Crawl Created: " + crawl_id)
 
+        crawl_id, crawljob = self.new_crawl_job_yaml(
+            cid,
+            userid=userid,
+            oid=oid,
+            storage=org.storage,
+            crawler_channel=configmap.get("CRAWLER_CHANNEL", "default"),
+            scale=int(configmap.get("INITIAL_SCALE", 1)),
+            crawl_timeout=int(configmap.get("CRAWL_TIMEOUT", 0)),
+            max_crawl_size=int(configmap.get("MAX_CRAWL_SIZE", "0")),
+            manual=False,
+            crawl_id=crawl_id,
+            warc_prefix=warc_prefix,
+        )
+
+        attachments = list(yaml.safe_load_all(crawljob))
+
+        if crawl_id in crawljobs:
+            attachments[0]["status"] = crawljobs[CJS][crawl_id]["status"]
+
         return {
             "attachments": attachments,
         }

chart/app-templates/crawl_job.yaml

@@ -24,6 +24,7 @@ spec:
   manual: {{ manual }}
   crawlerChannel: "{{ crawler_channel }}"
   ttlSecondsAfterFinished: 30
+  warcPrefix: "{{ warc_prefix }}"
 
   storageName: "{{ storage_name }}"
 

chart/app-templates/crawler.yaml

@@ -149,6 +149,9 @@ spec:
         - name: STORE_USER
           value: "{{ userid }}"
 
+        - name: WARC_PREFIX
+          value: "{{ warc_prefix }}"
+
     {% if crawler_socks_proxy_host %}
         - name: SOCKS_HOST
           value: "{{ crawler_socks_proxy_host }}"