cleanup wacz patch

src/auto_archiver/core/orchestrator.py

@@ -90,7 +90,9 @@ class ArchivingOrchestrator:
         if cached_result:
             logger.debug("Found previously archived entry")
             for d in self.databases:
-                d.done(cached_result, cached=True)
+                try: d.done(cached_result, cached=True)
+                except Exception as e:
+                    logger.error(f"ERROR database {d.name}: {e}: {traceback.format_exc()}")
             return cached_result
 
         # 3 - call archivers until one succeeds
@@ -120,6 +122,9 @@ class ArchivingOrchestrator:
             result.status = "nothing archived"
 
         # signal completion to databases and archivers
-        for d in self.databases: d.done(result)
+        for d in self.databases:
+            try: d.done(result)
+            except Exception as e:
+                logger.error(f"ERROR database {d.name}: {e}: {traceback.format_exc()}")
 
         return result

src/auto_archiver/databases/api_db.py

@@ -23,8 +23,7 @@ class AAApiDb(Database):
     def configs() -> dict:
         return {
             "api_endpoint": {"default": None, "help": "API endpoint where calls are made to"},
-            "api_secret": {"default": None, "help": "API Basic authentication secret [deprecating soon]"},
+            "api_token": {"default": None, "help": "API Bearer token."},
-            "api_token": {"default": None, "help": "API Bearer token, to be preferred over secret (Basic auth) going forward"},
             "public": {"default": False, "help": "whether the URL should be publicly available via the API"},
             "author_id": {"default": None, "help": "which email to assign as author"},
             "group_id": {"default": None, "help": "which group of users have access to the archive in case public=false as author"},
@@ -59,7 +58,7 @@ class AAApiDb(Database):
         logger.debug(f"saving archive of {item.get_url()} to the AA API.")
 
         payload = {'result': item.to_json(), 'public': self.public, 'author_id': self.author_id, 'group_id': self.group_id, 'tags': list(self.tags)}
-        headers = {"Authorization": f"Bearer {self.api_secret}"}
+        headers = {"Authorization": f"Bearer {self.api_token}"}
         response = requests.post(os.path.join(self.api_endpoint, "submit-archive"), json=payload, headers=headers)
 
         if response.status_code == 200:

src/auto_archiver/enrichers/wacz_enricher.py

@@ -35,6 +35,23 @@ class WaczArchiverEnricher(Enricher, Archiver):
             "socks_proxy_host": {"default": None, "help": "SOCKS proxy host for browsertrix-crawler, use in combination with socks_proxy_port. eg: user:password@host"},
             "socks_proxy_port": {"default": None, "help": "SOCKS proxy port for browsertrix-crawler, use in combination with socks_proxy_host. eg 1234"},
         }
+    
+    def setup(self) -> None:
+        self.use_docker = os.environ.get('WACZ_ENABLE_DOCKER') or not os.environ.get('RUNNING_IN_DOCKER')
+        self.browsertrix_home_host = os.environ.get('BROWSERTRIX_HOME_HOST')
+        self.browsertrix_home_container = os.environ.get('BROWSERTRIX_HOME_CONTAINER') or self.browsertrix_home_host
+        # create crawls folder if not exists, so it can be safely removed in cleanup
+        if self.use_docker:
+            if self.browsertrix_home_container:
+                os.makedirs(self.browsertrix_home_container, exist_ok=True)
+
+    def cleanup(self) -> None:
+        if self.use_docker:
+            if self.browsertrix_home_container:
+                logger.debug(f"Removing {self.browsertrix_home_container=}")
+                shutil.rmtree(self.browsertrix_home_container, ignore_errors=True)
+
+
 
     def download(self, item: Metadata) -> Metadata:
         # this new Metadata object is required to avoid duplication
@@ -51,8 +68,8 @@ class WaczArchiverEnricher(Enricher, Archiver):
         url = to_enrich.get_url()
 
         collection = random_str(8)
-        browsertrix_home_host = os.environ.get('BROWSERTRIX_HOME_HOST') or os.path.abspath(ArchivingContext.get_tmp_dir())
+        browsertrix_home_host = self.browsertrix_home_host or os.path.abspath(ArchivingContext.get_tmp_dir())
-        browsertrix_home_container = os.environ.get('BROWSERTRIX_HOME_CONTAINER') or browsertrix_home_host
+        browsertrix_home_container = self.browsertrix_home_container or browsertrix_home_host
 
         cmd = [
             "crawl",
@@ -69,9 +86,7 @@ class WaczArchiverEnricher(Enricher, Archiver):
             "--timeout", str(self.timeout)]
 
         # call docker if explicitly enabled or we are running on the host (not in docker)
-        use_docker = os.environ.get('WACZ_ENABLE_DOCKER') or not os.environ.get('RUNNING_IN_DOCKER')
+        if self.use_docker:
-
-        if use_docker:
             logger.debug(f"generating WACZ in Docker for {url=}")
             logger.debug(f"{browsertrix_home_host=} {browsertrix_home_container=}")
             if self.docker_commands:
@@ -103,7 +118,7 @@ class WaczArchiverEnricher(Enricher, Archiver):
             logger.error(f"WACZ generation failed: {e}")
             return False
 
-        if use_docker:
+        if self.use_docker:
             wacz_fn = os.path.join(browsertrix_home_container, "collections", collection, f"{collection}.wacz")
         else:
             wacz_fn = os.path.join("collections", collection, f"{collection}.wacz")
@@ -116,7 +131,7 @@ class WaczArchiverEnricher(Enricher, Archiver):
         if self.extract_media or self.extract_screenshot:
             self.extract_media_from_wacz(to_enrich, wacz_fn)
 
-        if use_docker:
+        if self.use_docker:
             jsonl_fn = os.path.join(browsertrix_home_container, "collections", collection, "pages", "pages.jsonl")
         else:
             jsonl_fn = os.path.join("collections", collection, "pages", "pages.jsonl")

src/auto_archiver/formatters/templates/html_template.html

@@ -177,14 +177,23 @@
     }
 
     async function run() {
-        await PreviewCertificates();
+        let setupFunctions = [
-        await PreviewText();
+            previewCertificates,
-        await enableCopyLogic();
+            previewText,
-        await enableCollapsibleLogic();
+            enableCopyLogic,
-        await setupSafeView();
+            enableCollapsibleLogic,
+            setupSafeView
+        ];
+        setupFunctions.forEach(async f => {
+            try {
+                await f();
+            } catch (e) {
+                console.error(`Error in ${f.name}: ${e}`);
+            }
+        });
     }
 
-    async function PreviewCertificates() {
+    async function previewCertificates() {
         await Promise.all(
             Array.from(document.querySelectorAll(".pem-certificate")).map(async el => {
                 let certificate = await (await fetch(el.getAttribute("pem"))).text();
@@ -202,7 +211,7 @@
         console.log("certificate preview done");
     }
 
-    async function PreviewText() {
+    async function previewText() {
         await Promise.all(
             Array.from(document.querySelectorAll(".text-preview")).map(async el => {
                 let textContent = await (await fetch(el.getAttribute("url"))).text();

src/auto_archiver/version.py

@@ -3,7 +3,7 @@ _MAJOR = "0"
 _MINOR = "9"
 # On main and in a nightly release the patch should be one ahead of the last
 # released build.
-_PATCH = "0"
+_PATCH = "4"
 # This is mainly for nightly builds which have the suffix ".dev$DATE". See
 # https://semver.org/#is-v123-a-semantic-version for the semantics.
 _SUFFIX = ""