fix: make portable exports and screenshot deploys reliable

.github/workflows/deploy-publicsite.yml

@@ -50,6 +50,22 @@ jobs:
         env:
           BASE_URL: http://archivebox.localhost:8000
 
+      - name: Verify gallery was generated from this exact revision
+        run: |
+          uv run --no-cache --no-sync python - <<'PY'
+          import json
+          import os
+          import tomllib
+          from pathlib import Path
+
+          provenance = json.loads(Path("publicsite/screenshots/build.json").read_text())
+          version = tomllib.loads(Path("pyproject.toml").read_text())["project"]["version"]
+          assert provenance["revision"] == os.environ["GITHUB_SHA"], provenance
+          assert provenance["version"] == version, provenance
+          assert provenance["capture_count"] >= 3 * 35, provenance
+          assert len(provenance["files"]) == provenance["capture_count"], provenance
+          PY
+
       - name: Setup Pages
         uses: actions/configure-pages@983d7736d9b0ae728b81ab479565c72886d7745b # v5
 

README.md

@@ -682,7 +682,7 @@ It uses all available methods out-of-the-box, but you can disable extractors and
 <summary><i>Expand to see the full list of ways it saves each page...</i></summary>
 
 
-<code>data/archive/{Snapshot.id}/</code><br/>
+<code>data/archive/users/{username}/snapshots/{YYYYMMDD}/{domain}/{Snapshot.id}/</code><br/>
 <ul>
 <li><strong>Index:</strong> <code>index.html</code> &amp; <code>index.json</code> HTML and JSON index files containing metadata and details</li>
 <li><strong>Title</strong>, <strong>Favicon</strong>, <strong>Headers</strong> Response headers, site favicon, and parsed site title</li>
@@ -849,7 +849,7 @@ The on-disk layout is optimized to be easy to browse by hand and durable long-te
                                 ...
 </code></pre>
 
-Each snapshot subfolder includes static metadata and plain extractor output files. ArchiveBox also maintains a backwards-compatible <code>data/archive/TIMESTAMP</code> symlink for each snapshot.
+Each snapshot subfolder includes static metadata and plain extractor output files. Current releases do not create top-level <code>data/archive/TIMESTAMP</code> projections; legacy timestamp directories are migrated into the user-scoped tree by <code>archivebox update --migrate-only</code>.
 
 <h4>Learn More</h4>
 <ul>

archivebox/cli/archivebox_update.py

@@ -561,21 +561,20 @@ def drain_old_archive_dirs(resume_from: str | None = None, batch_size: int = 500
     """
     Drain old archive/ directories (0.8.x → 0.9.x migration).
 
-    Only processes real directories (skips symlinks - those are already migrated).
+    Removes obsolete timestamp symlinks and processes real legacy directories.
     For each old dir found in archive/:
       1. Load or create DB snapshot
       2. Trigger fs migration on save() to move to data/archive/users/{user}/...
-      3. Leave symlink in archive/ pointing to new location
+      3. Remove the old timestamp path after the verified migration commits
 
-    After this drains, archive/ should only contain symlinks and we can trust
-    1:1 mapping between DB and filesystem.
+    After this drains, current snapshot data exists only under archive/users/.
     """
     from archivebox.core.models import Snapshot
     from archivebox.config import CONSTANTS
     from archivebox.crawls.models import Crawl
     from django.utils import timezone
 
-    stats = {"processed": 0, "migrated": 0, "queued": 0, "skipped": 0, "invalid": 0}
+    stats = {"processed": 0, "migrated": 0, "queued": 0, "skipped": 0, "invalid": 0, "removed_symlinks": 0}
     crawl_url_lines: dict[str, list[str]] = {}
     crawl_url_sets: dict[str, set[str]] = {}
     dirty_crawl_ids: set[str] = set()
@@ -606,8 +605,23 @@ def drain_old_archive_dirs(resume_from: str | None = None, batch_size: int = 500
             if changed:
                 Crawl.objects.filter(pk=crawl.pk).update(urls="\n".join(lines), modified_at=timezone.now())
 
-    # Scan for real directories only (skip symlinks - they're already migrated)
+    # Compatibility timestamp projections are harmful in portable exports and
+    # duplicate the obsolete 0.7.x-looking namespace without containing data.
     all_entries = list(os.scandir(archive_dir))
+    for entry in all_entries:
+        entry_path = Path(entry.path)
+        if entry.is_symlink() and Snapshot.is_legacy_archive_dir(entry_path):
+            try:
+                target_path = entry_path.resolve(strict=True)
+                points_into_current_layout = target_path.is_relative_to(CONSTANTS.USERS_DIR.resolve(strict=True))
+            except OSError:
+                points_into_current_layout = False
+
+            if points_into_current_layout:
+                entry_path.unlink(missing_ok=True)
+                stats["removed_symlinks"] += 1
+
+    # Scan real legacy directories only; these still contain data to migrate.
     entries = [
         (e.stat().st_mtime, e.path)
         for e in all_entries

archivebox/core/models.py

@@ -46,8 +46,6 @@ from archivebox.misc.util import (
     sanitize_html_text,
     to_json,
     ts_to_date_str,
-    urldecode,
-    urlencode,
     validate_url,
 )
 from archivebox.plugins.discovery import (
@@ -427,7 +425,7 @@ class SnapshotQuerySet(models.QuerySet):
             else {}
         )
 
-        snapshot_dicts = [s.to_dict(extended=True) for s in self.iterator(chunk_size=500)]
+        snapshot_dicts = [s.to_dict(extended=True, static_export=True) for s in self.iterator(chunk_size=500)]
 
         if with_headers:
             output = {
@@ -461,6 +459,13 @@ class SnapshotQuerySet(models.QuerySet):
 
         template = "static_index.html" if with_headers else "minimal_index.html"
         snapshot_list = list(self.iterator(chunk_size=500))
+        for snapshot in snapshot_list:
+            outputs = snapshot.discover_outputs(include_filesystem_fallback=True)
+            output_paths = [str(output.get("path") or "") for output in outputs]
+            snapshot._public_preview_paths = [
+                path for preferred in ("screenshot/screenshot.png", "screenshot.png") for path in output_paths if path == preferred
+            ]
+            snapshot._public_favicon_paths = [path for path in output_paths if path in ("favicon/favicon.ico", "favicon.ico")]
 
         return render_to_string(
             template,
@@ -472,6 +477,8 @@ class SnapshotQuerySet(models.QuerySet):
                 "time_updated": datetime.now(UTC).strftime("%Y-%m-%d %H:%M"),
                 "links": snapshot_list,
                 "FOOTER_INFO": config.FOOTER_INFO,
+                "STATIC_EXPORT": True,
+                "STATIC_EXPORT_DIR": CONSTANTS.DATA_DIR,
             },
         )
 
@@ -984,7 +991,7 @@ class Snapshot(ModelWithDeleteAfter, ModelWithOutputDir, ModelWithConfig, ModelW
         from django.db import transaction
 
         def finish_snapshot_save():
-            self.ensure_legacy_archive_symlink()
+            self.remove_legacy_archive_symlink()
             self.ensure_crawl_symlink()
             crawl = Crawl.objects.filter(pk=self.crawl_id).first()
             if crawl is None:
@@ -1261,9 +1268,7 @@ class Snapshot(ModelWithDeleteAfter, ModelWithOutputDir, ModelWithConfig, ModelW
         return (old_dir, new_dir)
 
     def _cleanup_old_migration_dir(self, old_dir: Path, new_dir: Path):
-        """
-        Delete old directory and create symlink after successful migration.
-        """
+        """Delete the old directory after its contents are verified at the new path."""
         import logging
         import shutil
 
@@ -1280,20 +1285,11 @@ class Snapshot(ModelWithDeleteAfter, ModelWithOutputDir, ModelWithConfig, ModelW
                 logging.getLogger("archivebox.migration").warning(
                     f"Could not remove old migration directory {old_dir}: {e}",
                 )
-                return  # Don't create symlink if cleanup failed
+                return
 
-        # Create backwards-compat symlink (after old dir is deleted)
-        symlink_path = old_dir  # Same path as old_dir
-        if symlink_path.is_symlink():
-            symlink_path.unlink()
-
-        if not symlink_path.exists():
-            try:
-                symlink_path.symlink_to(new_dir, target_is_directory=True)
-            except OSError as e:
-                logging.getLogger("archivebox.migration").warning(
-                    f"Could not create symlink from {symlink_path} to {new_dir}: {e}",
-                )
+        # Older migration runs may already have left a timestamp projection.
+        if old_dir.is_symlink():
+            old_dir.unlink(missing_ok=True)
 
     # =========================================================================
     # Path Calculation and Migration Helpers
@@ -2273,7 +2269,7 @@ class Snapshot(ModelWithDeleteAfter, ModelWithOutputDir, ModelWithConfig, ModelW
             return calc_tags_str()
         return calc_tags_str()
 
-    def icons(self, path: str | None = None) -> str:
+    def icons(self, path: str | None = None, prefix: str = "/") -> str:
         """Generate HTML icons showing which extractor plugins have succeeded for this snapshot"""
         from django.utils.html import format_html
 
@@ -2360,7 +2356,7 @@ class Snapshot(ModelWithDeleteAfter, ModelWithOutputDir, ModelWithConfig, ModelW
 
             archive_path = path or self.archive_path
             output = ""
-            output_template = '<a href="/{}/{}" class="exists-{}" title="{}">{}</a>'
+            output_template = '<a href="{}{}/{}" class="exists-{}" title="{}">{}</a>'
 
             # Get all plugins from hooks system (sorted by numeric prefix)
             all_plugins = self.__dict__.get("_icons_plugin_names")
@@ -2388,6 +2384,7 @@ class Snapshot(ModelWithDeleteAfter, ModelWithOutputDir, ModelWithConfig, ModelW
                 embed_path = f"{plugin}/" if compact_icons else result.embed_path()
                 output += format_html(
                     output_template,
+                    prefix,
                     archive_path,
                     embed_path,
                     str(bool(existing)),
@@ -2538,35 +2535,6 @@ class Snapshot(ModelWithDeleteAfter, ModelWithOutputDir, ModelWithConfig, ModelW
 
         return current_path
 
-    def ensure_legacy_archive_symlink(self) -> None:
-        """Ensure the legacy archive/<timestamp> path resolves to this snapshot."""
-        import os
-
-        legacy_path = CONSTANTS.ARCHIVE_DIR / self.timestamp
-        target = Path(self.get_storage_path_for_version(self._fs_current_version()))
-
-        if target == legacy_path:
-            return
-
-        legacy_path.parent.mkdir(parents=True, exist_ok=True)
-
-        if legacy_path.exists() or legacy_path.is_symlink():
-            if legacy_path.is_symlink():
-                try:
-                    if legacy_path.resolve() == target.resolve():
-                        return
-                except OSError:
-                    pass
-                legacy_path.unlink(missing_ok=True)
-            else:
-                return
-
-        rel_target = os.path.relpath(target, legacy_path.parent)
-        try:
-            legacy_path.symlink_to(rel_target, target_is_directory=True)
-        except OSError:
-            return
-
     def ensure_crawl_symlink(self, *, crawl_dir: Path | None = None, snapshot_dir: Path | None = None) -> None:
         """Ensure snapshot is symlinked under its crawl output directory."""
         import os
@@ -2606,6 +2574,21 @@ class Snapshot(ModelWithDeleteAfter, ModelWithOutputDir, ModelWithConfig, ModelW
         except OSError:
             return
 
+    def remove_legacy_archive_symlink(self) -> None:
+        """Remove a stale archive/<timestamp> compatibility projection."""
+        legacy_path = CONSTANTS.ARCHIVE_DIR / self.timestamp
+        current_path = self.get_storage_path_for_version(self._fs_current_version())
+        if not legacy_path.is_symlink() or not current_path.exists():
+            return
+
+        try:
+            points_to_current_path = legacy_path.resolve(strict=True) == current_path.resolve(strict=True)
+        except OSError:
+            points_to_current_path = False
+
+        if points_to_current_path:
+            legacy_path.unlink(missing_ok=True)
+
     @cached_property
     def legacy_archive_path(self) -> str:
         return f"{CONSTANTS.ARCHIVE_DIR_NAME}/{self.timestamp}"
@@ -3437,7 +3420,15 @@ class Snapshot(ModelWithDeleteAfter, ModelWithOutputDir, ModelWithConfig, ModelW
     # Serialization Methods
     # =========================================================================
 
-    def to_dict(self, extended: bool = False) -> dict[str, Any]:
+    @property
+    def static_archive_path(self) -> str:
+        """Snapshot output path relative to the data root, for portable exports."""
+        try:
+            return Path(self.output_dir).relative_to(CONSTANTS.DATA_DIR).as_posix()
+        except ValueError:
+            return Path(self.output_dir).as_posix()
+
+    def to_dict(self, extended: bool = False, static_export: bool = False) -> dict[str, Any]:
         """Convert Snapshot to a dictionary (replacement for Link._asdict())"""
         from archivebox.core.routes_util import build_snapshot_url
 
@@ -3468,8 +3459,8 @@ class Snapshot(ModelWithDeleteAfter, ModelWithOutputDir, ModelWithConfig, ModelW
             "extension": self.extension,
             "is_static": self.is_static,
             "is_archived": self.is_archived,
-            "archive_path": self.archive_path,
-            "archive_url": build_snapshot_url(str(self.id), "index.html"),
+            "archive_path": self.static_archive_path if static_export else self.archive_path,
+            "archive_url": f"./{self.static_archive_path}/index.html" if static_export else build_snapshot_url(str(self.id), "index.html"),
             "output_dir": self.output_dir,
             "link_dir": self.output_dir,  # backwards compatibility alias
             "archive_size": archive_size,
@@ -3499,67 +3490,154 @@ class Snapshot(ModelWithDeleteAfter, ModelWithOutputDir, ModelWithConfig, ModelW
         """Write JSON index file for this snapshot to its output directory"""
         output_dir = Path(out_dir) if out_dir is not None else self.output_dir
         path = output_dir / CONSTANTS.JSON_INDEX_FILENAME
-        atomic_write(str(path), self.to_dict(extended=True))
-
-    def write_html_details(self, out_dir: Path | str | None = None) -> None:
-        """Write HTML detail page for this snapshot to its output directory"""
-        from django.template.loader import render_to_string
+        atomic_write(str(path), self.to_dict(extended=True, static_export=True))
 
+    def get_html_details_context(self, request=None, *, static_export_dir: Path | None = None) -> dict[str, Any]:
+        """Build the one context used by both served and on-disk snapshot pages."""
+        from archivebox.config.common import get_request_config
+        from archivebox.core.permissions import get_snapshot_permissions
         from archivebox.core.widgets import TagEditorWidget
         from archivebox.misc.logging_util import printable_filesize
+        from archivebox.progressmonitor.views import progress_endpoint
 
-        output_dir = Path(out_dir) if out_dir is not None else self.output_dir
-        TITLE_LOADING_MSG = "Not yet archived..."
+        runtime_config = get_request_config(request) if request is not None else get_config()
+        self._runtime_config = runtime_config
+        snapshot_permissions = get_snapshot_permissions(self)
+        archive_results = list(self.archiveresult_set.all().order_by("start_ts"))
+        tags = list(self.tags.all())
+        self.__dict__["_admin_archiveresults"] = archive_results
+        self.__dict__["_tags_str_cached"] = ",".join(sorted(tag.name for tag in tags))
+        self.__dict__["num_outputs_cached"] = sum(result.status == ArchiveResult.StatusChoices.SUCCEEDED for result in archive_results)
+        self.__dict__["num_failures_cached"] = sum(result.status == ArchiveResult.StatusChoices.FAILED for result in archive_results)
 
-        preview_priority = [
-            "singlefile",
-            "screenshot",
-            "wget",
-            "dom",
-            "pdf",
-            "readability",
+        hidden_card_plugins = {"archivedotorg", "favicon", "title"}
+        outputs = [
+            output
+            for output in self.discover_outputs(include_filesystem_fallback=True, archive_results=archive_results)
+            if (output.get("size") or 0) > 0 and output.get("name") not in hidden_card_plugins
         ]
+        outputs_by_name: dict[str, dict[str, Any]] = {}
+        result_ids_by_name: dict[str, list[str]] = {}
+        for output in outputs:
+            if output.get("result"):
+                result_ids_by_name.setdefault(output["name"], []).append(str(output["result"].id))
+            current = outputs_by_name.get(output["name"])
+            if current is None or (output.get("size") or 0) > (current.get("size") or 0):
+                outputs_by_name[output["name"]] = output
+        for name, output in outputs_by_name.items():
+            output["result_ids"] = ",".join(result_ids_by_name.get(name, ()))
 
-        outputs = self.discover_outputs(include_filesystem_fallback=True)
-        loose_items, failed_items = self.get_detail_page_auxiliary_items(outputs)
-        outputs_by_plugin = {out["name"]: out for out in outputs}
-        output_size = sum(int(out.get("size") or 0) for out in outputs)
-        is_archived = bool(outputs or self.downloaded_at or self.status == self.StatusChoices.SEALED)
-
-        best_preview_path = "about:blank"
+        hash_index = self.hashes_index
+        loose_items, failed_items = self.get_detail_page_auxiliary_items(
+            outputs,
+            hidden_card_plugins=hidden_card_plugins,
+            archive_results=archive_results,
+        )
+        preview_priority = ("singlefile", "screenshot", "wget", "dom", "pdf", "readability")
+        output_order = {result_type: index for index, result_type in enumerate(outputs_by_name)}
+        ordered_outputs = sorted(
+            outputs_by_name.values(),
+            key=lambda output: (
+                preview_priority.index(output["name"]) if output["name"] in preview_priority else len(preview_priority),
+                output_order.get(output["name"], len(output_order)),
+            ),
+        )
         best_result = {"path": "about:blank", "result": None}
-        for plugin in preview_priority:
-            out = outputs_by_plugin.get(plugin)
-            if out and out.get("path"):
-                best_preview_path = str(out["path"])
-                best_result = out
+        for result_type in preview_priority:
+            if result_type in outputs_by_name:
+                best_result = outputs_by_name[result_type]
                 break
+        if best_result["path"] == "about:blank" and ordered_outputs:
+            best_result = ordered_outputs[0]
 
-        if best_preview_path == "about:blank" and outputs:
-            best_preview_path = str(outputs[0].get("path") or "about:blank")
-            best_result = outputs[0]
+        non_compact_outputs = [output for output in ordered_outputs if not output.get("is_compact") and not output.get("is_metadata")]
+        compact_outputs = [output for output in ordered_outputs if output.get("is_compact") or output.get("is_metadata")]
+        archive_dates = [result.start_ts for result in archive_results if result.start_ts]
+        output_size = sum(int(output.get("size") or 0) for output in ordered_outputs)
+        has_outputs = bool(ordered_outputs)
+        is_archived = has_outputs or self.status == self.StatusChoices.SEALED
+        snapshot_status = str(self.status or "").lower()
+        status_label_by_state = {
+            "queued": ("queued", "info"),
+            "started": ("running", "warning"),
+            "paused": ("paused", "default"),
+            "sealed": ("archived", "success"),
+        }
+        if has_outputs:
+            status_label, status_color = ("archived", "success") if is_archived else ("partial", "warning")
+        else:
+            status_label, status_color = status_label_by_state.get(snapshot_status, ("not yet archived", "danger"))
+
+        related_snapshots = list(
+            type(self)
+            .objects.filter(url=self.url)
+            .exclude(id=self.id)
+            .only("id", "url", "bookmarked_at", "created_at", "downloaded_at", "output_size")
+            .order_by("-bookmarked_at", "-created_at", "-timestamp")[:25],
+        )
+        related_years_map: dict[int, list[Snapshot]] = {}
+        for snapshot in [self, *related_snapshots]:
+            snapshot_date = snapshot.bookmarked_at or snapshot.created_at or snapshot.downloaded_at
+            if snapshot_date:
+                related_years_map.setdefault(snapshot_date.year, []).append(snapshot)
+        related_years = []
+        for year, snapshots in related_years_map.items():
+            snapshots.sort(
+                key=lambda snapshot: snapshot.bookmarked_at or snapshot.created_at or snapshot.downloaded_at or timezone.now(),
+                reverse=True,
+            )
+            related_years.append({"year": year, "latest": snapshots[0], "snapshots": snapshots})
+        related_years.sort(key=lambda item: item["year"], reverse=True)
+
+        warc_path = next(
+            (rel_path for rel_path in hash_index if rel_path.startswith("warc/") and ".warc" in Path(rel_path).name),
+            "warc/",
+        )
+        user = getattr(request, "user", None)
         tag_widget = TagEditorWidget()
-        context = {
-            **self.to_dict(extended=True),
-            "snapshot": self,
-            "title": htmldecode(self.resolved_title or (self.base_url if is_archived else TITLE_LOADING_MSG)),
-            "url_str": htmldecode(urldecode(self.base_url)),
-            "archive_url": urlencode(f"warc/{self.timestamp}") or "about:blank",
+        return {
+            "id": str(self.id),
+            "snapshot_id": str(self.id),
+            "progress_endpoint": progress_endpoint("snapshot", self.id) if request is not None else "",
+            "progress_auto_expand": snapshot_status in {"queued", "started", "paused"},
+            "url": self.url,
+            "archive_path": self.archive_path_from_db,
+            "title": htmldecode(self.resolved_title or (self.base_url if is_archived else "Not yet archived...")),
             "extension": self.extension or "html",
             "tags": self.tags_str() or "untagged",
-            "size": printable_filesize(output_size) if output_size else "pending",
-            "status": "archived" if is_archived else "not yet archived",
-            "status_color": "success" if is_archived else "danger",
-            "oldest_archive_date": ts_to_date_str(self.oldest_archive_date),
-            "best_preview_path": best_preview_path,
+            "size": printable_filesize(output_size) if output_size else "—",
+            "status": status_label,
+            "status_color": status_color,
+            "snapshot_state": snapshot_status,
+            "has_outputs": has_outputs,
+            "snapshot_permissions": snapshot_permissions,
+            "snapshot_permissions_icon": {"public": "👥", "unlisted": "🔗", "private": "🔒"}.get(snapshot_permissions, "👥"),
+            "bookmarked_date": self.bookmarked_date,
+            "downloaded_datestr": self.downloaded_datestr,
+            "num_outputs": self.num_outputs,
+            "num_failures": self.num_failures,
+            "oldest_archive_date": ts_to_date_str(min(archive_dates) if archive_dates else None),
+            "warc_path": warc_path,
+            "archiveresults": [*non_compact_outputs, *compact_outputs],
             "best_result": best_result,
-            "archiveresults": outputs,
+            "snapshot": self,
+            "CONFIG": runtime_config,
+            "related_snapshots": related_snapshots,
+            "related_years": related_years,
             "loose_items": loose_items,
             "failed_items": failed_items,
-            "related_snapshots": [],
-            "related_years": [],
-            "title_tags": [{"name": tag.name, "style": tag_widget._tag_style(tag.name)} for tag in self.tags.all().order_by("name")],
+            "can_delete_outputs": bool(user and user.is_authenticated and user.is_active and user.is_superuser),
+            "title_tags": [{"name": tag.name, "style": tag_widget._tag_style(tag.name)} for tag in sorted(tags, key=lambda tag: tag.name)],
+            "STATIC_EXPORT": static_export_dir is not None,
+            "STATIC_EXPORT_DIR": static_export_dir,
         }
+
+    def write_html_details(self, out_dir: Path | str | None = None) -> None:
+        """Write the unified snapshot detail page with portable filesystem URLs."""
+        from django.template.loader import render_to_string
+
+        output_dir = Path(out_dir) if out_dir is not None else self.output_dir
+        context = self.get_html_details_context(static_export_dir=output_dir)
         rendered_html = render_to_string("core/snapshot.html", context)
         atomic_write(str(output_dir / CONSTANTS.HTML_INDEX_FILENAME), rendered_html)
 

archivebox/core/templatetags/core_tags.py

@@ -2,6 +2,7 @@ import os
 from html import unescape
 from pathlib import Path
 from typing import Any
+from urllib.parse import quote
 
 from abx_plugins.plugins.archivewebpage.replay_preview import is_replay_target as is_archivewebpage_replay_target
 from django import template
@@ -11,6 +12,7 @@ from django.utils.html import escape
 from django.utils.safestring import mark_safe
 from django.utils.text import Truncator
 
+from archivebox.config import CONSTANTS
 from archivebox.core.routes_util import (
     build_snapshot_url,
     get_admin_base_url,
@@ -28,6 +30,7 @@ register = template.Library()
 
 _TEXT_PREVIEW_EXTS = (".json", ".jsonl", ".txt", ".csv", ".tsv", ".xml", ".yml", ".yaml", ".md", ".log")
 _IMAGE_PREVIEW_EXTS = (".png", ".jpg", ".jpeg", ".gif", ".webp", ".bmp", ".ico", ".avif")
+_STATIC_URL_SAFE = "/@-._~!$&'()*+,;="
 
 _MEDIA_FILE_EXTS = {
     ".mp4",
@@ -202,16 +205,70 @@ def _is_root_snapshot_output_path(raw_output_path: str | None) -> bool:
     return normalized in ("", ".", "./", "/", "index.html", "index.json")
 
 
-def _build_snapshot_files_url(snapshot_id: str, request=None, config=None) -> str:
-    return build_snapshot_url(str(snapshot_id), "/?files=1", request=request, config=config)
+def _static_snapshot_base_url(context, snapshot) -> str:
+    start_dir = Path(context["STATIC_EXPORT_DIR"])
+    relative_path = os.path.relpath(Path(snapshot.output_dir), start=start_dir).replace(os.sep, "/")
+    if relative_path == ".":
+        return "."
+    return f"./{quote(relative_path, safe=_STATIC_URL_SAFE)}"
 
 
-def _build_snapshot_preview_url(snapshot_id: str, path: str = "", request=None, config=None, plugin: str = "") -> str:
+def _snapshot_base_url_for_context(context, snapshot) -> str:
+    if context.get("STATIC_EXPORT"):
+        return _static_snapshot_base_url(context, snapshot)
+    return get_snapshot_base_url(
+        str(_snapshot_id(snapshot)),
+        request=context.get("request"),
+        config=context.get("CONFIG"),
+    )
+
+
+def _snapshot_url_for_context(context, snapshot, path: str = "") -> str:
+    if not context.get("STATIC_EXPORT"):
+        return build_snapshot_url(
+            str(_snapshot_id(snapshot)),
+            path,
+            request=context.get("request"),
+            config=context.get("CONFIG"),
+        )
+
+    base_url = _static_snapshot_base_url(context, snapshot)
+    raw_path = str(path or "")
+    if not raw_path:
+        return base_url
+    path_part, separator, query = raw_path.lstrip("/").partition("?")
+    quoted_path = quote(path_part, safe=_STATIC_URL_SAFE)
+    suffix = f"?{query}" if separator else ""
+    return f"{base_url.rstrip('/')}/{quoted_path}{suffix}"
+
+
+def _build_snapshot_files_url(snapshot_id: str, request=None, config=None, base_url: str | None = None) -> str:
+    return (
+        f"{base_url.rstrip('/')}/?files=1"
+        if base_url
+        else build_snapshot_url(str(snapshot_id), "/?files=1", request=request, config=config)
+    )
+
+
+def _build_snapshot_preview_url(
+    snapshot_id: str,
+    path: str = "",
+    request=None,
+    config=None,
+    plugin: str = "",
+    base_url: str | None = None,
+) -> str:
     if path == "about:blank":
         return path
     if _is_root_snapshot_output_path(path):
-        return _build_snapshot_files_url(snapshot_id, request=request, config=config)
-    url = build_snapshot_url(str(snapshot_id), path, request=request, config=config)
+        return _build_snapshot_files_url(snapshot_id, request=request, config=config, base_url=base_url)
+    if base_url:
+        path_part, separator, query = str(path).lstrip("/").partition("?")
+        url = f"{base_url.rstrip('/')}/{quote(path_part, safe=_STATIC_URL_SAFE)}"
+        if separator:
+            url = f"{url}?{query}"
+    else:
+        url = build_snapshot_url(str(snapshot_id), path, request=request, config=config)
     path_parts = Path(path).parts
     plugin = get_plugin_name(plugin) if plugin else (path_parts[0] if len(path_parts) > 1 else "")
     has_plugin_preview = bool(plugin and get_plugin_template(plugin, "full", fallback=False))
@@ -441,23 +498,35 @@ def web_base_url(context) -> str:
     return get_web_base_url(request=context.get("request"), config=context.get("CONFIG"))
 
 
+@register.simple_tag(takes_context=True)
+def static_export_root_url(context) -> str:
+    if not context.get("STATIC_EXPORT"):
+        return ""
+    relative_path = os.path.relpath(CONSTANTS.DATA_DIR, start=Path(context["STATIC_EXPORT_DIR"]))
+    relative_path = relative_path.replace(os.sep, "/")
+    return "./" if relative_path == "." else f"{quote(relative_path, safe=_STATIC_URL_SAFE)}/"
+
+
 @register.simple_tag(takes_context=True)
 def snapshot_base_url(context, snapshot) -> str:
-    snapshot_id = _snapshot_id(snapshot)
-    return get_snapshot_base_url(str(snapshot_id), request=context.get("request"), config=context.get("CONFIG"))
+    return _snapshot_base_url_for_context(context, snapshot)
 
 
 @register.simple_tag(takes_context=True)
 def snapshot_url(context, snapshot, path: str = "") -> str:
-    snapshot_id = _snapshot_id(snapshot)
-    return build_snapshot_url(str(snapshot_id), path, request=context.get("request"), config=context.get("CONFIG"))
+    return _snapshot_url_for_context(context, snapshot, path)
 
 
 @register.simple_tag(takes_context=True)
 def snapshot_archiveresult_url(context, snapshot, plugin: str, filename: str) -> str:
     snapshot_id = str(_snapshot_id(snapshot))
     url_cache = snapshot.__dict__.setdefault("_snapshot_archiveresult_url_cache", {})
-    cache_key = (plugin, filename)
+    cache_key = (
+        plugin,
+        filename,
+        bool(context.get("STATIC_EXPORT")),
+        str(context.get("STATIC_EXPORT_DIR") or ""),
+    )
     if cache_key in url_cache:
         return url_cache[cache_key]
 
@@ -493,7 +562,7 @@ def snapshot_archiveresult_url(context, snapshot, plugin: str, filename: str) ->
         if not isinstance(file_info, dict) or int(file_info.get("size") or 0) <= 0:
             continue
         output_path = filename if file_info.get("root_relative") else f"{plugin}/{filename}"
-        url_cache[cache_key] = build_snapshot_url(snapshot_id, output_path, request=context.get("request"), config=context.get("CONFIG"))
+        url_cache[cache_key] = _snapshot_url_for_context(context, snapshot, output_path)
         return url_cache[cache_key]
 
     url_cache[cache_key] = ""
@@ -502,10 +571,7 @@ def snapshot_archiveresult_url(context, snapshot, plugin: str, filename: str) ->
 
 @register.simple_tag(takes_context=True)
 def snapshot_index_row(context, link) -> str:
-    snapshot_id = str(_snapshot_id(link))
-    request = context.get("request")
-    config = context.get("CONFIG")
-    snapshot_base = get_snapshot_base_url(snapshot_id, request=request, config=config)
+    snapshot_base = _snapshot_base_url_for_context(context, link)
 
     status = getattr(link, "status", None) or "unknown"
     bookmarked_at = getattr(link, "bookmarked_at", None)
@@ -534,22 +600,28 @@ def snapshot_index_row(context, link) -> str:
         tag_cell = '<span class="empty-value">...</span>'
 
     num_outputs = int(getattr(link, "num_outputs", 0) or 0)
-    icons = link.icons() if callable(getattr(link, "icons", None)) else getattr(link, "icons", "")
+    if context.get("STATIC_EXPORT") and callable(getattr(link, "icons", None)):
+        icons = link.icons(path=quote(link.static_archive_path, safe=_STATIC_URL_SAFE), prefix="./")
+    else:
+        icons = link.icons() if callable(getattr(link, "icons", None)) else getattr(link, "icons", "")
     icons_cell = str(icons) if icons else '<span class="empty-value">...</span>'
     archive_size = int(getattr(link, "archive_size", 0) or 0)
     size_cell = file_size(archive_size) if archive_size else '<span class="empty-value">...</span>'
     output_plural = "" if num_outputs == 1 else "s"
+    files_url = _snapshot_url_for_context(context, link, "index.jsonl") if context.get("STATIC_EXPORT") else f"{snapshot_base}/?files=1"
 
     if is_pending:
-        preview_html = (
-            '<span class="snapshot-preview snapshot-preview-spinner" aria-label="Archiving in progress">'
-            f'<img src="{escape(static("spinner.gif"))}" alt="" decoding="async" loading="lazy">'
-            "</span>"
-        )
+        preview_html = '<span class="snapshot-preview snapshot-preview-spinner" aria-label="Archiving in progress"></span>'
+        if not context.get("STATIC_EXPORT"):
+            preview_html = (
+                '<span class="snapshot-preview snapshot-preview-spinner" aria-label="Archiving in progress">'
+                f'<img src="{escape(static("spinner.gif"))}" alt="" decoding="async" loading="lazy">'
+                "</span>"
+            )
     elif "_public_preview_paths" in link.__dict__:
         preview_paths = list(getattr(link, "_public_preview_paths", []) or [])
         if preview_paths:
-            preview_urls = [build_snapshot_url(snapshot_id, path, request=request, config=config) for path in preview_paths]
+            preview_urls = [_snapshot_url_for_context(context, link, path) for path in preview_paths]
             preview_html = (
                 f'<img src="{escape(preview_urls[0])}" '
                 f'data-fallbacks="{escape(",".join(preview_urls[1:]))}" '
@@ -579,7 +651,7 @@ def snapshot_index_row(context, link) -> str:
     if "_public_favicon_paths" in link.__dict__:
         favicon_paths = list(getattr(link, "_public_favicon_paths", []) or [])
         if favicon_paths:
-            favicon_urls = [build_snapshot_url(snapshot_id, path, request=request, config=config) for path in favicon_paths]
+            favicon_urls = [_snapshot_url_for_context(context, link, path) for path in favicon_paths]
             favicon_html = (
                 f'<img src="{escape(favicon_urls[0])}" '
                 f'data-fallbacks="{escape(",".join(favicon_urls[1:]))}" '
@@ -640,7 +712,7 @@ def snapshot_index_row(context, link) -> str:
         </span>
     </td>
     <td class="snapshot-size-cell">
-        <a href="{escape(snapshot_base)}/?files=1" title="View archived files">
+        <a href="{escape(files_url)}" title="View archived file manifest">
             {size_cell}
         </a>
         <small>{num_outputs} output{output_plural}</small>
@@ -660,6 +732,7 @@ def snapshot_preview_url(context, snapshot, path: str = "", result=None) -> str:
         request=context.get("request"),
         config=context.get("CONFIG"),
         plugin=plugin,
+        base_url=_snapshot_base_url_for_context(context, snapshot) if context.get("STATIC_EXPORT") else None,
     )
 
 
@@ -699,24 +772,16 @@ def plugin_card(context, result) -> str:
 
     # Use embed_path() for the display path
     raw_output_path = result.embed_path() or ""
-    output_url = build_snapshot_url(
-        str(result.snapshot_id),
-        raw_output_path or "",
-        request=context.get("request"),
-        config=context.get("CONFIG"),
-    )
+    output_url = _snapshot_url_for_context(context, result.snapshot, raw_output_path or "")
 
     icon_html = get_plugin_icon(plugin)
     plugin_lower = (plugin or "").lower()
     media_file_count = _count_media_files(result) if plugin_lower in ("ytdlp", "yt-dlp", "youtube-dl") else 0
     media_files = _list_media_files(result) if plugin_lower in ("ytdlp", "yt-dlp", "youtube-dl") else []
     if media_files:
-        snapshot_id = str(result.snapshot_id)
-        request = context.get("request")
-        config = context.get("CONFIG")
         for item in media_files:
             path = item.get("path") or ""
-            item["url"] = build_snapshot_url(snapshot_id, path, request=request, config=config) if path else ""
+            item["url"] = _snapshot_url_for_context(context, result.snapshot, path) if path else ""
 
     output_lower = (raw_output_path or "").lower()
     force_text_preview = output_lower.endswith(_TEXT_PREVIEW_EXTS)
@@ -794,12 +859,7 @@ def plugin_full(context, result) -> str:
         raw_output_path = result.embed_path() or ""
     if _is_root_snapshot_output_path(raw_output_path):
         return ""
-    output_url = build_snapshot_url(
-        str(result.snapshot_id),
-        raw_output_path,
-        request=context.get("request"),
-        config=context.get("CONFIG"),
-    )
+    output_url = _snapshot_url_for_context(context, result.snapshot, raw_output_path)
 
     try:
         tpl = template.Template(template_str)

archivebox/core/views.py

@@ -21,7 +21,6 @@ from django.core.paginator import InvalidPage
 from django.db.models import Case, IntegerField, Q, Value, When
 from django.http import Http404, HttpRequest, HttpResponse, HttpResponseForbidden, QueryDict
 from django.shortcuts import redirect, render
-from django.utils import timezone
 from django.utils.decorators import method_decorator
 from django.utils.html import format_html, format_html_join
 from django.utils.safestring import mark_safe
@@ -54,7 +53,6 @@ from archivebox.core.permissions import (
     can_view_snapshot,
     direct_snapshots_queryset,
     filter_personas_by_permissions,
-    get_snapshot_permissions,
     is_admin_user,
     public_snapshots_queryset,
 )
@@ -69,15 +67,12 @@ from archivebox.core.routes_util import (
     host_matches,
 )
 from archivebox.crawls.models import Crawl
-from archivebox.misc.logging_util import printable_filesize
 from archivebox.misc.paginators import AcceleratedPaginator
 from archivebox.misc.serve_static import serve_static_with_byterange_support
 from archivebox.misc.util import (
     base_url,
     filter_queryset_by_uuid_substring,
-    htmldecode,
     sanitize_html_text,
-    ts_to_date_str,
     urldecode,
     validate_url,
     without_fragment,
@@ -85,7 +80,7 @@ from archivebox.misc.util import (
 from archivebox.plugins.discovery import get_plugin_name, get_plugin_template
 from archivebox.plugins.forms import get_plugin_config_binary_urls
 from archivebox.plugins.views import get_config_definition_link
-from archivebox.progressmonitor.views import live_progress_view, progress_endpoint
+from archivebox.progressmonitor.views import live_progress_view
 from archivebox.search.config import (
     get_search_mode,
     get_search_mode_backend,
@@ -332,162 +327,11 @@ class SnapshotView(View):
 
     @staticmethod
     def render_live_index(request, snapshot):
-        TITLE_LOADING_MSG = "Not yet archived..."
-        from archivebox.core.widgets import TagEditorWidget
-
-        # Reuse the middleware-attached config; never re-bootstrap from env + plugin
-        # schemas just to render a snapshot page (that pays ~30ms for no reason).
-        runtime_config = get_request_config(request)
-        snapshot._runtime_config = runtime_config
-        snapshot_permissions = get_snapshot_permissions(snapshot)
-        archive_results = list(snapshot.archiveresult_set.all().order_by("start_ts"))
-        tags = list(snapshot.tags.all())
-        snapshot.__dict__["_admin_archiveresults"] = archive_results
-        snapshot.__dict__["_tags_str_cached"] = ",".join(sorted(tag.name for tag in tags))
-        snapshot.__dict__["num_outputs_cached"] = sum(result.status == ArchiveResult.StatusChoices.SUCCEEDED for result in archive_results)
-        snapshot.__dict__["num_failures_cached"] = sum(result.status == ArchiveResult.StatusChoices.FAILED for result in archive_results)
-        hidden_card_plugins = {"archivedotorg", "favicon", "title"}
-        outputs = [
-            out
-            for out in snapshot.discover_outputs(include_filesystem_fallback=True, archive_results=archive_results)
-            if (out.get("size") or 0) > 0 and out.get("name") not in hidden_card_plugins
-        ]
-        archiveresults = {}
-        result_ids_by_name = {}
-        for output in outputs:
-            if output.get("result"):
-                result_ids_by_name.setdefault(output["name"], []).append(str(output["result"].id))
-            current = archiveresults.get(output["name"])
-            if current is None or (output.get("size") or 0) > (current.get("size") or 0):
-                archiveresults[output["name"]] = output
-        for name, output in archiveresults.items():
-            output["result_ids"] = ",".join(result_ids_by_name.get(name, ()))
-        hash_index = snapshot.hashes_index
-        loose_items, failed_items = snapshot.get_detail_page_auxiliary_items(
-            outputs,
-            hidden_card_plugins=hidden_card_plugins,
-            archive_results=archive_results,
+        return render(
+            template_name="core/snapshot.html",
+            request=request,
+            context=snapshot.get_html_details_context(request=request),
         )
-        preview_priority = [
-            "singlefile",
-            "screenshot",
-            "wget",
-            "dom",
-            "pdf",
-            "readability",
-        ]
-        preferred_types = tuple(preview_priority)
-        output_order = {result_type: index for index, result_type in enumerate(archiveresults.keys())}
-
-        best_result = {"path": "about:blank", "result": None}
-        for result_type in preferred_types:
-            if result_type in archiveresults:
-                best_result = archiveresults[result_type]
-                break
-
-        related_snapshots_qs = SnapshotView.find_snapshots_for_url(
-            snapshot.url,
-            allow_fallback=False,
-        ).only("id", "url", "bookmarked_at", "created_at", "downloaded_at", "output_size")
-        related_snapshots = list(
-            related_snapshots_qs.exclude(id=snapshot.id).order_by("-bookmarked_at", "-created_at", "-timestamp")[:25],
-        )
-        related_years_map: dict[int, list[Snapshot]] = {}
-        for snap in [snapshot, *related_snapshots]:
-            snap_dt = snap.bookmarked_at or snap.created_at or snap.downloaded_at
-            if not snap_dt:
-                continue
-            related_years_map.setdefault(snap_dt.year, []).append(snap)
-        related_years = []
-        for year, snaps in related_years_map.items():
-            snaps_sorted = sorted(
-                snaps,
-                key=lambda s: s.bookmarked_at or s.created_at or s.downloaded_at or timezone.now(),
-                reverse=True,
-            )
-            related_years.append(
-                {
-                    "year": year,
-                    "latest": snaps_sorted[0],
-                    "snapshots": snaps_sorted,
-                },
-            )
-        related_years.sort(key=lambda item: item["year"], reverse=True)
-
-        warc_path = next(
-            (rel_path for rel_path in hash_index if rel_path.startswith("warc/") and ".warc" in Path(rel_path).name),
-            "warc/",
-        )
-
-        ordered_outputs = sorted(
-            archiveresults.values(),
-            key=lambda r: (
-                preferred_types.index(r["name"]) if r["name"] in preferred_types else len(preferred_types),
-                output_order.get(r["name"], len(output_order)),
-            ),
-        )
-        if best_result["path"] == "about:blank" and ordered_outputs:
-            best_result = ordered_outputs[0]
-        non_compact_outputs = [out for out in ordered_outputs if not out.get("is_compact") and not out.get("is_metadata")]
-        compact_outputs = [out for out in ordered_outputs if out.get("is_compact") or out.get("is_metadata")]
-        tag_widget = TagEditorWidget()
-        output_size = sum(int(out.get("size") or 0) for out in ordered_outputs)
-        archive_dates = [result.start_ts for result in archive_results if result.start_ts]
-        has_outputs = bool(ordered_outputs)
-        is_archived = has_outputs or snapshot.status == Snapshot.StatusChoices.SEALED
-        snapshot_status = str(snapshot.status or "").lower()
-        status_label_by_state = {
-            "queued": ("queued", "info"),
-            "started": ("running", "warning"),
-            "paused": ("paused", "default"),
-            "sealed": ("archived", "success"),
-        }
-        if has_outputs and not is_archived:
-            status_label, status_color = ("partial", "warning")
-        elif has_outputs:
-            status_label, status_color = ("archived", "success")
-        else:
-            status_label, status_color = status_label_by_state.get(snapshot_status, ("not yet archived", "danger"))
-
-        context = {
-            "id": str(snapshot.id),
-            "snapshot_id": str(snapshot.id),
-            "progress_endpoint": progress_endpoint("snapshot", snapshot.id),
-            "progress_auto_expand": snapshot_status in {"queued", "started", "paused"},
-            "url": snapshot.url,
-            "archive_path": snapshot.archive_path_from_db,
-            "title": htmldecode(snapshot.resolved_title or (snapshot.base_url if is_archived else TITLE_LOADING_MSG)),
-            "extension": snapshot.extension or "html",
-            "tags": snapshot.tags_str() or "untagged",
-            "size": printable_filesize(output_size) if output_size else "—",
-            "status": status_label,
-            "status_color": status_color,
-            "snapshot_state": snapshot_status,
-            "has_outputs": has_outputs,
-            "snapshot_permissions": snapshot_permissions,
-            "snapshot_permissions_icon": {
-                "public": "👥",
-                "unlisted": "🔗",
-                "private": "🔒",
-            }.get(snapshot_permissions, "👥"),
-            "bookmarked_date": snapshot.bookmarked_date,
-            "downloaded_datestr": snapshot.downloaded_datestr,
-            "num_outputs": snapshot.num_outputs,
-            "num_failures": snapshot.num_failures,
-            "oldest_archive_date": ts_to_date_str(min(archive_dates) if archive_dates else None),
-            "warc_path": warc_path,
-            "archiveresults": [*non_compact_outputs, *compact_outputs],
-            "best_result": best_result,
-            "snapshot": snapshot,  # Pass the snapshot object for template tags
-            "CONFIG": runtime_config,
-            "related_snapshots": related_snapshots,
-            "related_years": related_years,
-            "loose_items": loose_items,
-            "failed_items": failed_items,
-            "can_delete_outputs": bool(request.user.is_authenticated and request.user.is_active and request.user.is_superuser),
-            "title_tags": [{"name": tag.name, "style": tag_widget._tag_style(tag.name)} for tag in sorted(tags, key=lambda tag: tag.name)],
-        }
-        return render(template_name="core/snapshot.html", request=request, context=context)
 
     def get(self, request, path):
         snapshot = None

archivebox/templates/core/snapshot.html

@@ -319,9 +319,9 @@
                 user-select: all;
             }
             .header-toggle {
-                line-height: 12px;
-                font-size: 70px;
-                margin-top: -13px;
+                line-height: 1;
+                font-size: 24px;
+                margin-top: 0;
                 margin-left: 4px;
             }
             @container snapshot-header (max-width: 900px) {
@@ -1475,11 +1475,13 @@
     </head>
     <body>
         <div id="main-frame-wrapper" class="full-page-wrapper" data-has-outputs="{{ has_outputs|yesno:'1,0' }}" data-snapshot-state="{{ snapshot_state }}">
+            {% if not STATIC_EXPORT %}
             {% if snapshot_state == 'queued' or snapshot_state == 'started' or snapshot_state == 'paused' %}
             <div id="snapshot-progress-wrapper">
                 {% include "progressmonitor/progress_monitor.html" with progress_endpoint=progress_endpoint progress_scope="snapshot" %}
             </div>
             {% endif %}
+            {% endif %}
             {% if has_outputs %}
             <iframe id="main-frame"
                     sandbox="allow-same-origin allow-top-navigation-by-user-activation allow-scripts allow-forms"
@@ -1567,8 +1569,9 @@
                 <div class="header-nav">
                     <div class="header-col header-left" style="line-height: 58px; vertical-align: middle">
                         {% web_base_url as web_base %}
-                        <a href="{% if web_base %}{{ web_base }}/public/{% else %}/{% endif %}" class="header-archivebox" title="Go to Public Index...">
-                            <img src="{% if web_base %}{{ web_base }}/static/archive.png{% else %}{% static 'archive.png' %}{% endif %}" alt="Archive Icon">
+                        {% static_export_root_url as static_root %}
+                        <a href="{% if STATIC_EXPORT %}{{ static_root }}index.html{% elif web_base %}{{ web_base }}/public/{% else %}/{% endif %}" class="header-archivebox" title="Go to Public Index...">
+                            <img src="{% if STATIC_EXPORT %}data:image/svg+xml;utf8,&lt;svg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 64 64'&gt;&lt;rect x='8' y='5' width='48' height='54' rx='7' fill='%23fff' opacity='.95'/&gt;&lt;path d='M18 16h28M18 26h28M18 36h20M18 46h24' stroke='%23aa1e55' stroke-width='5' stroke-linecap='round'/&gt;&lt;/svg&gt;{% elif web_base %}{{ web_base }}/static/archive.png{% else %}{% static 'archive.png' %}{% endif %}" alt="Archive Icon">
                             ArchiveBox
                         </a>
                     </div>
@@ -1614,34 +1617,44 @@
                             </div>
                             <div class="badge badge-info">
                                 <span class="badge-label">Size</span>
+                                {% if STATIC_EXPORT %}
+                                <span class="badge-value">{{size}}</span>
+                                {% else %}
                                 <a class="badge-value" href="{% admin_base_url %}/admin/core/snapshot/{{snapshot_id|default:id}}/change/" title="Click to edit this Snapshot in the Admin UI">
                                     {{size}}
                                 </a>
+                                {% endif %}
                             </div>
+                            {% if not STATIC_EXPORT %}
                             <div class="badge badge-default">
                                 <span class="badge-label">Manage</span>
                                 <a class="badge-value" href="{% admin_base_url %}/admin/core/snapshot/{{snapshot_id|default:id}}/change/" title="Click to edit this Snapshot in the Admin UI">
                                     <span class="badge-desktop-icon">✏️</span><span class="badge-mobile-text">Edit</span>
                                 </a>
                             </div>
+                            {% endif %}
                             <div class="badge badge-{{status_color}}">
                                 <span class="badge-label">Status</span>
+                                {% if STATIC_EXPORT %}
+                                <span class="badge-value">{{status|upper}}</span>
+                                {% else %}
                                 <a class="badge-value" href="{% admin_base_url %}/admin/core/snapshot/?q={{snapshot_id|default:id}}" title="Click to see options to pull, re-snapshot, or delete this Snapshot">
                                     {{status|upper}}
                                 </a>
+                                {% endif %}
                             </div>
                         </div>
                         <div class="header-mobile-badges">
-                            <a class="header-mobile-badge" href="{% snapshot_base_url snapshot %}/?files=1" title="Browse all files for this snapshot">
+                            <a class="header-mobile-badge" href="{% if STATIC_EXPORT %}{% snapshot_url snapshot 'index.jsonl' %}{% else %}{% snapshot_base_url snapshot %}/?files=1{% endif %}" title="Browse all files for this snapshot">
                                 <span>{{num_outputs}} Files</span>
                                 <span class="header-mobile-badge-separator">|</span>
                                 <span>{{size}}</span>
                             </a>
-                            <a class="header-mobile-badge" href="{% admin_base_url %}/admin/core/snapshot/{{snapshot_id|default:id}}/change/" title="Edit this snapshot in the Admin UI">
+                            {% if not STATIC_EXPORT %}<a class="header-mobile-badge" href="{% admin_base_url %}/admin/core/snapshot/{{snapshot_id|default:id}}/change/" title="Edit this snapshot in the Admin UI">
                                 <span>{{status|capfirst}}</span>
                                 <span class="header-mobile-badge-separator">|</span>
                                 <span>Edit</span>
-                            </a>
+                            </a>{% endif %}
                         </div>
                         {% if related_years %}
                         <div class="header-year-badges">
@@ -1687,14 +1700,14 @@
                                 </div>
                             </details>
                         {% else %}
-                            <a class="header-date" href="{% web_base_url %}/{{archive_path}}/index.html" title="Date Added: {{bookmarked_date}}  |  First Archived: {{oldest_archive_date|default:downloaded_datestr}}  |  Last Checked: {{downloaded_datestr}}   (UTC)">
+                            <a class="header-date" href="{% snapshot_base_url snapshot %}/index.html" title="Date Added: {{bookmarked_date}}  |  First Archived: {{oldest_archive_date|default:downloaded_datestr}}  |  Last Checked: {{downloaded_datestr}}   (UTC)">
                                 <span class="header-date-label">Captures</span>
                                 {{oldest_archive_date|default:downloaded_datestr|default:bookmarked_date|slice:":10"}}
                             </a>
                         {% endif %}
                         <br/>
                         <div class="external-links">
-                            <a href="{% snapshot_base_url snapshot %}/?files=1" title="Browse the full SNAP_DIR for this snapshot" target="_blank">📁 See all files...</a>
+                            <a href="{% if STATIC_EXPORT %}{% snapshot_url snapshot 'index.jsonl' %}{% else %}{% snapshot_base_url snapshot %}/?files=1{% endif %}" title="Browse the full SNAP_DIR for this snapshot" target="_blank">📁 {% if STATIC_EXPORT %}Snapshot manifest{% else %}See all files...{% endif %}</a>
                             <span class="external-links-separator">|</span>
                             <a href="https://web.archive.org/web/{{url}}" title="Search for a copy of the URL saved in Archive.org" target="_blank" rel="noreferrer">🏛️ Archive.org</a>
                             <!--<a href="https://archive.md/{{url}}" title="Search for a copy of the URL saved in Archive.today" target="_blank" rel="noreferrer">Archive.today</a>  &nbsp;|&nbsp; -->
@@ -1714,7 +1727,7 @@
                         <div class="thumb-card{% if forloop.first %} selected-card{% endif %}" data-plugin-name="{{result.name|plugin_name}}"{% if preview_url %} data-preview-url="{{preview_url}}"{% endif %}{% if display_path %} data-output-path="{{display_path}}"{% endif %}>
                                 <div class="thumb-body">
                                     <div class="thumb-actions">
-                                        <a href="{% snapshot_url snapshot result.name %}/?files=1" data-no-preview="1" title="Open output folder" target="_blank" rel="noopener">📁</a>
+                                        {% if not STATIC_EXPORT %}<a href="{% snapshot_url snapshot result.name %}/?files=1" data-no-preview="1" title="Open output folder" target="_blank" rel="noopener">📁</a>{% endif %}
                                         {% if display_path %}
                                             <a href="{{display_url}}" data-no-preview="1" title="Download output file" download>⬇️</a>
                                         {% endif %}
@@ -1807,7 +1820,6 @@
         </header>
 
         {% if can_delete_outputs %}<input type="hidden" id="delete-output-csrf" value="{{csrf_token}}">{% endif %}
-        <script src="{% static 'jquery.min.js' %}" type="text/javascript"></script>
         {% if can_delete_outputs %}{% include "includes/output_delete_controls.html" %}{% endif %}
 
         <script>
@@ -1932,9 +1944,7 @@
             }
 
             // un-sandbox iframes showing pdfs (required to display pdf viewer)
-            jQuery('iframe').map(function() {
-                attachPreviewFrameHandlers(this)
-            })
+            document.querySelectorAll('iframe').forEach((frame) => attachPreviewFrameHandlers(frame))
 
             function getPreviewHashValueFromHref(href, normalize=false) {
                 if (href == './') {
@@ -2058,8 +2068,8 @@
                     return false
                 }
 
-                jQuery('.selected-card').removeClass('selected-card')
-                jQuery(card).closest('.thumb-card').addClass('selected-card')
+                document.querySelectorAll('.selected-card').forEach((selected) => selected.classList.remove('selected-card'))
+                card.closest('.thumb-card').classList.add('selected-card')
 
                 const nextSrc = isSnapshotRootPreview(target) ? snapshotFilesUrl : target
                 const existingFrame = document.getElementById('main-frame')
@@ -2158,8 +2168,8 @@
 
             function hideSnapshotHeader() {
                 console.log('Collapsing Snapshot header...')
-                jQuery('.header-toggle').text('▸')
-                jQuery('.header-bottom').hide()
+                document.querySelectorAll('.header-toggle').forEach((toggle) => { toggle.textContent = '▸' })
+                document.querySelectorAll('.header-bottom').forEach((header) => { header.hidden = true })
                 try {
                     localStorage.setItem("archivebox-snapshot-header-visible", "false")
                 } catch (e) {
@@ -2168,8 +2178,8 @@
             }
             function showSnapshotHeader() {
                 console.log('Expanding Snapshot header...')
-                jQuery('.header-toggle').text('▾')
-                jQuery('.header-bottom').show()
+                document.querySelectorAll('.header-toggle').forEach((toggle) => { toggle.textContent = '▾' })
+                document.querySelectorAll('.header-bottom').forEach((header) => { header.hidden = false })
                 try {
                     localStorage.setItem("archivebox-snapshot-header-visible", "true")
                 } catch (e) {
@@ -2190,7 +2200,7 @@
             }
             function handleSnapshotHeaderToggle(event) {
                 event.preventDefault()
-                if (jQuery('.header-toggle').text().includes('▾')) {
+                if ([...document.querySelectorAll('.header-toggle')].some((toggle) => toggle.textContent.includes('▾'))) {
                     hideSnapshotHeader()
                 } else {
                     showSnapshotHeader()
@@ -2199,7 +2209,7 @@
             }
 
             // Hide or show the header once when its title row or collapse icon is clicked.
-            jQuery('.header-toggle-trigger').on('click', handleSnapshotHeaderToggle)
+            document.querySelectorAll('.header-toggle-trigger').forEach((trigger) => trigger.addEventListener('click', handleSnapshotHeaderToggle))
 
             // check URL for hash e.g. #git and load relevant preview
             selectInitialPreview()

archivebox/templates/core/static_index.html

@@ -1,258 +1,129 @@
-{% load static core_tags %}
-
+{% load core_tags %}
 <!DOCTYPE html>
 <html lang="en">
-    <head>
-        <title>Archived Sites</title>
-        <meta charset="utf-8" name="viewport" content="width=device-width, initial-scale=1">
-        <style>
-            :root {
-                --bg-main: #efefef;
-                --accent-1: #aa1e55;
-                --accent-2: #ffebeb;
-                --accent-3: #efefef;
-
-                --text-1: #1c1c1c;
-                --text-2: #eaeaea;
-                --text-main: #1a1a1a;
-                --font-main: "Gill Sans", Helvetica, sans-serif;
+<head>
+    <title>Archived Sites</title>
+    <meta charset="utf-8" name="viewport" content="width=device-width, initial-scale=1">
+    <style>
+        * { box-sizing: border-box; }
+        body { margin: 0; background: #f8fafc; color: #0f172a; font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif; }
+        a { color: inherit; }
+        .static-header { display: flex; align-items: center; justify-content: space-between; gap: 16px; padding: 14px 20px; background: #aa1e55; color: #fff; }
+        .static-brand { display: flex; align-items: center; gap: 10px; font-size: 20px; font-weight: 700; text-decoration: none; }
+        .static-brand-mark { display: grid; place-items: center; width: 30px; height: 30px; border-radius: 7px; background: #fff; color: #aa1e55; font-size: 19px; }
+        .static-meta { color: rgba(255,255,255,.82); font-size: 12px; }
+        main { width: min(1500px, 100%); margin: 0 auto; padding: 18px; }
+        .toolbar { display: flex; align-items: center; justify-content: space-between; gap: 12px; margin-bottom: 14px; padding: 10px 12px; border: 1px solid #e2e8f0; border-radius: 10px; background: #fff; box-shadow: 0 1px 2px rgba(15,23,42,.04); }
+        #static-search { width: min(560px, 100%); height: 36px; padding: 7px 11px; border: 1px solid #cbd5e1; border-radius: 7px; font: inherit; font-size: 13px; }
+        .count { color: #64748b; font-size: 12px; white-space: nowrap; }
+        .table-wrap { overflow-x: auto; border: 1px solid #e2e8f0; border-radius: 10px; background: #fff; box-shadow: 0 1px 2px rgba(15,23,42,.04); }
+        table { width: 100%; min-width: 980px; table-layout: fixed; border-collapse: collapse; }
+        th { padding: 9px 10px; border-bottom: 1px solid #e2e8f0; background: #f8fafc; color: #475569; font-size: 11px; letter-spacing: .04em; text-align: left; text-transform: uppercase; }
+        td { padding: 8px 10px; border-bottom: 1px solid #edf2f7; vertical-align: middle; }
+        tbody tr:hover { background: #f8fafc; }
+        tbody tr:last-child td { border-bottom: 0; }
+        .snapshot-time { width: 102px; white-space: nowrap; }
+        .snapshot-time a { display: inline-flex; flex-direction: column; color: #334155; line-height: 1.2; text-decoration: none; }
+        .snapshot-time small { color: #94a3b8; font-size: 11px; }
+        .snapshot-preview-cell { width: 116px; }
+        .snapshot-preview-cell a { display: inline-flex; width: 102px; height: 102px; align-items: center; justify-content: center; }
+        .snapshot-preview { display: block; width: 100px; height: 100px; border: 1px solid #e2e8f0; border-radius: 8px; background: #f8fafc; object-fit: cover; object-position: top; }
+        .snapshot-preview-spinner { display: grid; place-items: center; }
+        .snapshot-preview-spinner::after { width: 20px; height: 20px; border: 2px solid #cbd5e1; border-top-color: #aa1e55; border-radius: 50%; content: ""; animation: spin .8s linear infinite; }
+        .snapshot-title-line { display: flex; align-items: center; gap: 8px; min-width: 0; margin-bottom: 2px; }
+        .snapshot-favicon-link { display: inline-flex; width: 22px; min-width: 22px; height: 22px; align-items: center; justify-content: center; }
+        .link-favicon { display: block; width: 18px; height: 18px; border-radius: 4px; object-fit: contain; }
+        .snapshot-title { overflow: hidden; color: #0f172a; font-size: 14px; font-weight: 650; line-height: 1.25; text-overflow: ellipsis; white-space: nowrap; text-decoration: none; }
+        .snapshot-url { display: block; margin-left: 30px; overflow: hidden; color: #64748b; font-size: 12px; text-overflow: ellipsis; white-space: nowrap; text-decoration: none; }
+        .snapshot-mobile-saved { display: none; }
+        .snapshot-tags-cell { width: 180px; }
+        .snapshot-tags { display: flex; flex-wrap: wrap; gap: 4px; max-height: 46px; overflow: hidden; }
+        .snapshot-tag { max-width: 150px; padding: 2px 7px; overflow: hidden; border: 1px solid #bfdbfe; border-radius: 999px; background: #eff6ff; color: #1d4ed8; font-size: 11px; font-weight: 600; text-overflow: ellipsis; white-space: nowrap; }
+        .snapshot-status-cell { width: 96px; }
+        .snapshot-status { display: inline-flex; min-width: 68px; justify-content: center; padding: 3px 8px; border-radius: 999px; background: #f1f5f9; color: #475569; font-size: 11px; font-weight: 700; text-transform: uppercase; }
+        .status-sealed .snapshot-status, .status-succeeded .snapshot-status { background: #d1fae5; color: #047857; }
+        .status-started .snapshot-status { background: #dbeafe; color: #1d4ed8; }
+        .status-queued .snapshot-status, .status-backoff .snapshot-status { background: #fef3c7; color: #b45309; }
+        .status-failed .snapshot-status { background: #fee2e2; color: #b91c1c; }
+        .snapshot-files-cell { width: 220px; overflow: hidden; }
+        .snapshot-files-cell .files-icons { max-width: 200px; }
+        .snapshot-size-cell { width: 102px; white-space: nowrap; }
+        .snapshot-size-cell a { display: block; color: #334155; font-size: 12px; font-weight: 700; text-decoration: none; }
+        .snapshot-size-cell small, .empty-value { color: #94a3b8; font-size: 10px; }
+        footer { padding: 24px 16px; color: #64748b; font-size: 12px; text-align: center; }
+        @keyframes spin { to { transform: rotate(360deg); } }
+        @media (max-width: 700px) {
+            .static-header, .toolbar { align-items: stretch; flex-direction: column; }
+            main { padding: 10px; }
+            table { min-width: 0; }
+            th:nth-child(n+4), td:nth-child(n+4), th.snapshot-time, td.snapshot-time { display: none; }
+            .snapshot-preview-cell { width: 88px; }
+            .snapshot-preview-cell a { width: 76px; height: 76px; }
+            .snapshot-preview { width: 74px; height: 74px; }
+            .snapshot-mobile-saved { display: block; margin: 4px 0 0 30px; color: #64748b; font-size: 11px; }
+        }
+    </style>
+    <script>
+        function nextPublicSnapshotPreview(img) {
+            const fallbacks = (img.dataset.fallbacks || '').split(',').filter(Boolean)
+            if (fallbacks.length) {
+                img.src = fallbacks.shift()
+                img.dataset.fallbacks = fallbacks.join(',')
+                return
             }
-            /* Dark Mode (WIP) */
-            /*
-            @media (prefers-color-scheme: dark) {
-                :root {
-                    --accent-2: hsl(160, 100%, 96%);
-
-                    --text-1: #eaeaea;
-                    --text-2: #1a1a1a;
-                    --bg-main: #101010;
-                }
-
-                #table-bookmarks_wrapper,
-                #table-bookmarks_wrapper img,
-                tbody td:nth-child(3),
-                tbody td:nth-child(3) span,
-                footer {
-                    filter: invert(100%);
-                }
-            }*/
-
-            html, body {
-                width: 100%;
-                height: 100%;
-                font-size: 18px;
-                font-weight: 200;
-                text-align: center;
-                margin: 0px;
-                padding: 0px;
-                font-family: var(--font-main);
-            }
-
-            .header-top small {
-                font-weight: 200;
-                color: var(--accent-3);
-            }
-            
-            .header-top {
-                width: 100%;
-                height: auto;
-                min-height: 40px;
-                margin: 0px;
-                text-align: center;
-                color: white;
-                font-size: calc(11px + 0.84vw);
-                font-weight: 200;
-                padding: 4px 4px;
-                border-bottom: 3px solid var(--accent-1);
-                background-color: var(--accent-1);
-            }
-            input[type=search] {
-                width: 22vw;
-                border-radius: 4px;
-                border: 1px solid #aeaeae;
-                padding: 3px 5px;
-            }
-            .nav > div {
-                min-height: 30px;
-            }
-            .header-top a {
-                text-decoration: none;
-                color: rgba(0,0,0,0.6);
-            }
-            .header-top a:hover {
-                text-decoration: none;
-                color: rgba(0,0,0,0.9);
-            }
-            .header-top .col-lg-4 {
-                text-align: center;
-                padding-top: 4px;
-                padding-bottom: 4px;
-            }
-            .header-archivebox img {
-                display: inline-block;
-                margin-right: 3px;
-                height: 30px;
-                margin-left: 12px;
-                margin-top: -4px;
-                margin-bottom: 2px;
-            }
-            .header-archivebox img:hover {
-                opacity: 0.5;
-            }
-
-            #table-bookmarks_length, #table-bookmarks_filter {
-                padding-top: 12px;
-                opacity: 0.8;
-                padding-left: 24px;
-                padding-right: 22px;
-                margin-bottom: -16px;
-            }
-            table {
-                padding: 6px;
-                width: 100%;
-            }
-            table thead th {
-                font-weight: 400;
-            }
-            table tr {
-                height: 35px;
-            }
-            tbody tr:nth-child(odd) {
-               background-color: var(--accent-2) !important;
-            }
-            table tr td {
-                white-space: nowrap;
-                overflow: hidden;
-                /*padding-bottom: 0.4em;*/
-                /*padding-top: 0.4em;*/
-                padding-left: 2px;
-                text-align: center;
-            }
-            table tr td a {
-                text-decoration: none;
-            }
-            table tr td img, table tr td object {
-                display: inline-block;
-                margin: auto;
-                height: 24px;
-                width: 24px;
-                padding: 0px;
-                padding-right: 5px;
-                vertical-align: middle;
-                margin-left: 4px;
-            }
-            #table-bookmarks {
-                width: 100%; 
-                overflow-y: scroll;
-                table-layout: fixed;
-            }
-            .dataTables_wrapper {
-                background-color: #fafafa;
-            }
-            table tr a span[data-archived~=False] {
-                opacity: 0.4;
-            }
-            .files-spinner {
-                height: 15px;
-                width: auto;
-                opacity: 0.5;
-                vertical-align: -2px;
-            }
-            .in-progress {
-                display: none;
-            }
-            tr td a.favicon img {
-                padding-left: 6px;
-                padding-right: 12px;
-                vertical-align: -4px;
-            }
-            tr td a.title {
-                font-size: 1.4em;
-                text-decoration:none;
-                color:black;
-            }
-            tr td a.title small {
-                background-color: var(--accent-3);
-                border-radius: 4px;
-                float:right
-            }
-            input[type=search]::-webkit-search-cancel-button {
-                -webkit-appearance: searchfield-cancel-button;
-            }
-            .title-col {
-                text-align: left;
-            }
-            .title-col a {
-                color: black;
-            }
-        </style>
-        <link rel="stylesheet" href="{% static 'bootstrap.min.css' %}">
-        <link rel="stylesheet" href="{% static 'jquery.dataTables.min.css' %}"/>
-        <script src="{% static 'jquery.min.js' %}"></script>
-        <script src="{% static 'jquery.dataTables.min.js' %}"></script>
-        <script>
-            document.addEventListener('error', function(e) {
-              e.target.style.opacity = 0;
-            }, true)
-            jQuery(document).ready(function() {
-                jQuery('#table-bookmarks').DataTable({
-                    stateSave: true, // save state (filtered input, number of entries shown, etc) in localStorage
-                    dom: '<lf<t>ip>', // how to show the table and its helpers (filter, etc) in the DOM
-                    order: [[0, 'desc']],
-                    iDisplayLength: 100,
-                });
-            });
-        </script>
-    </head>
-    <body>
-        <header>
-            <div class="header-top container-fluid">
-                <div class="row nav">
-                    <div class="col-sm-2">
-                        <a href="/" class="header-archivebox">
-                            <img src="{% static 'archive.png' %}" alt="Logo"/>
-                            ArchiveBox: Index
-                        </a>
-                    </div>
-                    <div class="col-sm-10" style="text-align: right">
-                        <a href="/add/">Add Links</a> &nbsp; | &nbsp; 
-                        <a href="/admin/core/snapshot/">Admin</a> &nbsp; | &nbsp; 
-                        <a href="https://github.com/ArchiveBox/ArchiveBox/wiki">Docs</a>
-                    </div>
-                </div>
-            </div>
-        </header>
-        
-        <table id="table-bookmarks">
-            <thead>
-                <tr>
-                    <th class="snapshot-time">Saved</th>
-                    <th class="snapshot-preview-cell">Preview</th>
-                    <th>Snapshot ({{num_links}})</th>
-                    <th class="snapshot-tags-cell">Tags</th>
-                    <th class="snapshot-status-cell">Status</th>
-                    <th class="snapshot-files-cell">Files</th>
-                    <th class="snapshot-size-cell">Size</th>
-                </tr>
-            </thead>
-            <tbody>
-                {% for link in links %}
-                   {% snapshot_index_row link %}
-                {% endfor %}
-            </tbody>
-        </table>
-        <footer>
-            <br/>
-            <center>
-                <small>
-                    Archive created using <a href="https://github.com/ArchiveBox/ArchiveBox" title="Github">ArchiveBox</a>
-                    version <a href="https://github.com/ArchiveBox/ArchiveBox/releases/tag/v{{version}}" title="View source code and release info">v{{version}}</a> &nbsp; | &nbsp; 
-                    Download index as <a href="index.json" title="JSON summary of archived links.">JSON</a>
-                    <br/><br/>
-                    {{FOOTER_INFO}}
-                </small>
-            </center>
-            <br/>
-        </footer>
-    </body>
+            img.style.opacity = 0
+        }
+    </script>
+</head>
+<body>
+    <header class="static-header">
+        <a class="static-brand" href="./index.html"><span class="static-brand-mark">▤</span> ArchiveBox</a>
+        <span class="static-meta">Portable static archive · updated {{ time_updated }}</span>
+    </header>
+    <main>
+        <div class="toolbar">
+            <input id="static-search" type="search" placeholder="Filter title, URL, tag, or status…" autocomplete="off">
+            <span class="count"><span id="visible-count">{{ num_links }}</span> of {{ num_links }} snapshots</span>
+        </div>
+        <div class="table-wrap">
+            <table id="table-bookmarks">
+                <thead>
+                    <tr>
+                        <th class="snapshot-time">Saved</th>
+                        <th class="snapshot-preview-cell">Preview</th>
+                        <th>Snapshot ({{ num_links }})</th>
+                        <th class="snapshot-tags-cell">Tags</th>
+                        <th class="snapshot-status-cell">Status</th>
+                        <th class="snapshot-files-cell">Files</th>
+                        <th class="snapshot-size-cell">Size</th>
+                    </tr>
+                </thead>
+                <tbody>
+                    {% for link in links %}{% snapshot_index_row link %}{% endfor %}
+                </tbody>
+            </table>
+        </div>
+    </main>
+    <footer>
+        Generated by <a href="https://github.com/ArchiveBox/ArchiveBox">ArchiveBox v{{ version }}</a>.
+        <a href="./index.json">Download JSON metadata</a>.<br><br>{{ FOOTER_INFO }}
+    </footer>
+    <script>
+        (() => {
+            const search = document.getElementById('static-search')
+            const rows = [...document.querySelectorAll('#table-bookmarks tbody tr')]
+            const count = document.getElementById('visible-count')
+            search.addEventListener('input', () => {
+                const query = search.value.trim().toLowerCase()
+                let visible = 0
+                rows.forEach((row) => {
+                    const show = !query || row.textContent.toLowerCase().includes(query)
+                    row.hidden = !show
+                    if (show) visible += 1
+                })
+                count.textContent = visible
+            })
+        })()
+    </script>
+</body>
 </html>

archivebox/tests/migrations_helpers.py

@@ -13,6 +13,7 @@ import hashlib
 import sqlite3
 from pathlib import Path
 from datetime import datetime, timezone
+from urllib.parse import urlparse
 
 from archivebox.tests.conftest import cli_env, run_archivebox_cmd
 from archivebox.uuid_compat import uuid7
@@ -1272,6 +1273,24 @@ def filesystem_manifest(root: Path) -> dict[str, tuple[str, str | int]]:
     return manifest
 
 
+def current_snapshot_dir(data_dir: Path, db_path: Path, timestamp: str) -> Path:
+    """Resolve a migrated snapshot's canonical archive/users/... directory."""
+    with sqlite3.connect(db_path) as connection:
+        username, bookmarked_at, snapshot_id, url = connection.execute(
+            """
+            SELECT u.username, s.bookmarked_at, s.id, s.url
+            FROM core_snapshot s
+            JOIN crawls_crawl c ON c.id = s.crawl_id
+            JOIN auth_user u ON u.id = c.created_by_id
+            WHERE s.timestamp = ?
+            """,
+            (timestamp,),
+        ).fetchone()
+    date_bucket = datetime.fromisoformat(bookmarked_at).strftime("%Y%m%d")
+    domain = urlparse(url).hostname or "unknown"
+    return data_dir / "archive" / "users" / username / "snapshots" / date_bucket / domain / snapshot_id
+
+
 def verify_snapshot_count(db_path: Path, expected: int) -> tuple[bool, str]:
     """Verify the number of snapshots in the database."""
     conn = sqlite3.connect(str(db_path))

archivebox/tests/test_cli_list.py

@@ -4,6 +4,7 @@ Verify list emits snapshot JSONL and applies the documented filters.
 """
 
 import json
+from pathlib import Path
 
 import pytest
 from django.contrib.auth import get_user_model
@@ -19,6 +20,40 @@ from archivebox.tests.test_orm_helpers import use_archivebox_db
 pytestmark = pytest.mark.django_db(transaction=True)
 
 
+def test_static_exports_use_filesystem_paths_not_live_django_routes(snapshot):
+    from archivebox.config import CONSTANTS
+    from archivebox.core.models import ArchiveResult
+
+    snapshot_dir = Path(snapshot.output_dir)
+    screenshot_dir = snapshot_dir / "screenshot"
+    screenshot_dir.mkdir(parents=True, exist_ok=True)
+    screenshot_file = screenshot_dir / "screenshot.png"
+    screenshot_file.write_bytes(b"real screenshot")
+    ArchiveResult.objects.create(
+        snapshot=snapshot,
+        plugin="screenshot",
+        hook_name="on_Snapshot__50_screenshot.py",
+        status=ArchiveResult.StatusChoices.SUCCEEDED,
+        output_str="screenshot.png",
+        output_files={"screenshot.png": {"size": screenshot_file.stat().st_size}},
+        output_size=screenshot_file.stat().st_size,
+    )
+    static_path = snapshot_dir.relative_to(CONSTANTS.DATA_DIR).as_posix()
+    queryset = Snapshot.objects.filter(pk=snapshot.pk).prefetch_related("tags")
+
+    html = queryset.to_html(with_headers=True)
+    [record] = json.loads(queryset.to_json(with_headers=False))
+
+    assert f"./{static_path}/index.html" in html
+    assert f"./{static_path}/screenshot/screenshot.png" in html
+    assert f"./{static_path}/index.jsonl" in html
+    assert f"/snapshot/{snapshot.id.hex}" not in html
+    assert "/web/" not in html
+    assert "/static/" not in html
+    assert record["archive_path"] == static_path
+    assert record["archive_url"] == f"./{static_path}/index.html"
+
+
 def test_streaming_json_matches_snapshot_serializer(initialized_archive):
     from archivebox.crawls.models import Crawl
 

archivebox/tests/test_cli_run.py

@@ -1576,7 +1576,7 @@ class TestRecoverOrchestratorState:
         assert snapshot.status == Snapshot.StatusChoices.SEALED
         assert snapshot.fs_version == Snapshot._fs_current_version()
         assert snapshot.output_dir.joinpath("index.html").read_text(encoding="utf-8") == "legacy archive"
-        assert legacy_dir.is_symlink()
+        assert not legacy_dir.exists()
 
     @pytest.mark.django_db(transaction=True)
     def test_run_due_snapshot_migrates_filesystem_after_sealed_parent_reconciliation(self):
@@ -1618,7 +1618,7 @@ class TestRecoverOrchestratorState:
         assert snapshot.status == Snapshot.StatusChoices.SEALED
         assert snapshot.fs_version == Snapshot._fs_current_version()
         assert snapshot.output_dir.joinpath("index.html").read_text(encoding="utf-8") == "legacy archive"
-        assert legacy_dir.is_symlink()
+        assert not legacy_dir.exists()
 
     @pytest.mark.django_db(transaction=True)
     def test_run_due_snapshot_runs_queued_plugin_after_fs_migration(self):

archivebox/tests/test_cli_update_reindex_snapshots.py

@@ -1,6 +1,8 @@
 import json
 import os
 from datetime import datetime, timedelta
+from pathlib import Path
+
 from archivebox.tests.conftest import cli_env, run_archivebox_cmd
 
 import pytest
@@ -120,12 +122,12 @@ def test_update_imports_orphaned_snapshots(tmp_path, initialized_archive):
     assert update_process.returncode == 0, update_process.stderr
 
     with use_archivebox_db(tmp_path):
-        row = Snapshot.objects.values_list("url", "fs_version").get()
+        migrated_snapshot = Snapshot.objects.get()
+        row = (migrated_snapshot.url, migrated_snapshot.fs_version)
+        migrated_dir = Path(migrated_snapshot.output_dir)
 
     assert row == ("https://example.com", Snapshot._fs_current_version())
-    assert legacy_dir.is_symlink()
-
-    migrated_dir = legacy_dir.resolve()
+    assert not legacy_dir.exists()
     assert migrated_dir.exists()
     assert '{"type":"Process","id":"incomplete"}\n' in (migrated_dir / "index.jsonl").read_text()
     assert (migrated_dir / "singlefile.html").exists()
@@ -201,7 +203,7 @@ def test_update_migrates_every_declared_filesystem_version(tmp_path, initialized
 
     assert {path: migrated_tree.get(path) for path in original_tree} == original_tree
     if legacy_layout:
-        assert source_dir.is_symlink()
+        assert not source_dir.exists()
 
     update_process = run_archivebox_cmd(["update", "--migrate-only"], env=env, timeout=90)
     assert update_process.returncode == 0, f"Idempotency update failed: {update_process.stderr}"

archivebox/tests/test_migrations_04_to_09.py

@@ -6,6 +6,7 @@ import sqlite3
 from .migrations_helpers import (
     SCHEMA_0_4,
     create_data_dir_structure,
+    current_snapshot_dir,
     filesystem_manifest,
     run_archivebox_migration_cmd,
     seed_0_4_data,
@@ -94,8 +95,8 @@ def test_oldest_django_collection_migrates_end_to_end_without_data_loss(tmp_path
 
     for timestamp, expected_tree in original_trees.items():
         legacy_dir = tmp_path / "archive" / timestamp
-        assert legacy_dir.is_symlink()
-        migrated_tree = filesystem_manifest(legacy_dir.resolve())
+        assert not legacy_dir.exists()
+        migrated_tree = filesystem_manifest(current_snapshot_dir(tmp_path, db_path, timestamp))
         assert {path: migrated_tree.get(path) for path in expected_tree} == expected_tree
 
     with sqlite3.connect(db_path) as connection:

archivebox/tests/test_migrations_08_to_09.py

@@ -21,6 +21,7 @@ import pytest
 from .migrations_helpers import (
     SCHEMA_0_7,
     SCHEMA_0_8,
+    current_snapshot_dir,
     filesystem_manifest,
     seed_0_8_data,
     seed_0_7_data,
@@ -800,7 +801,7 @@ def test_update_preserves_legacy_folder_timestamp_over_index_float_variant(tmp_p
     conn.close()
 
     assert row == (timestamp,)
-    assert (work_dir / "archive" / timestamp).is_symlink()
+    assert not (work_dir / "archive" / timestamp).exists()
     assert not (work_dir / "archive" / f"{timestamp}.0").exists()
     assert not (work_dir / "invalid").exists()
 
@@ -842,8 +843,8 @@ def test_update_preserves_distinct_legacy_dirs_with_integer_and_float_timestamps
     conn.close()
 
     assert rows == [("1508259732",), ("1508259732.0",)]
-    assert (work_dir / "archive" / "1508259732").is_symlink()
-    assert (work_dir / "archive" / "1508259732.0").is_symlink()
+    assert not (work_dir / "archive" / "1508259732").exists()
+    assert not (work_dir / "archive" / "1508259732.0").exists()
     assert not (work_dir / "invalid").exists()
 
 
@@ -988,8 +989,8 @@ def test_07_filesystem_hop_preserves_complete_output_tree(tmp_path):
 
     for timestamp, expected_tree in original_trees.items():
         legacy_dir = tmp_path / "archive" / timestamp
-        assert legacy_dir.is_symlink()
-        migrated_tree = filesystem_manifest(legacy_dir.resolve())
+        assert not legacy_dir.exists()
+        migrated_tree = filesystem_manifest(current_snapshot_dir(tmp_path, db_path, timestamp))
         assert {path: migrated_tree.get(path) for path in expected_tree} == expected_tree
     assert (destination / "preexisting-output.bin").read_bytes() == b"destination-only output"
 
@@ -1062,7 +1063,10 @@ def test_each_declared_filesystem_hop_preserves_outputs(migration_08_data, fs_ve
     result = run_archivebox_migration_cmd(work_dir, ["update", "--migrate-only"], timeout=180)
     assert result.returncode == 0, result.stderr
 
-    migrated_dir = source_dir.resolve()
+    migrated_dir = current_snapshot_dir(work_dir, db_path, snapshot["timestamp"])
     assert {path: filesystem_manifest(migrated_dir).get(path) for path in expected_tree} == expected_tree
+    if fs_version in ("0.7.0", "0.8.0", "0.8.5"):
+        assert not source_dir.exists()
+        assert not source_dir.is_symlink()
     with sqlite3.connect(db_path) as connection:
         assert connection.execute("SELECT fs_version FROM core_snapshot WHERE id = ?", (snapshot["id"],)).fetchone() == ("0.9.4",)

archivebox/tests/test_ui_admin_snapshot.py

@@ -1,6 +1,8 @@
 """Snapshot model and admin UI tests."""
 
 import json
+import os
+import re
 import shutil
 import warnings
 from pathlib import Path
@@ -21,6 +23,16 @@ pytestmark = pytest.mark.django_db(transaction=True)
 REPO_ROOT = Path(__file__).resolve().parents[2]
 
 
+def test_current_snapshot_layout_has_no_top_level_timestamp_projection(snapshot):
+    from archivebox.config import CONSTANTS
+
+    legacy_path = CONSTANTS.ARCHIVE_DIR / snapshot.timestamp
+
+    assert Path(snapshot.output_dir).is_relative_to(CONSTANTS.ARCHIVE_DIR / "users")
+    assert not legacy_path.exists()
+    assert not legacy_path.is_symlink()
+
+
 @pytest.fixture
 def real_hash_projection(snapshot, cached_abxpkg_lib_dir):
     snapshot.output_dir.mkdir(parents=True, exist_ok=True)
@@ -743,7 +755,61 @@ class TestSnapshotProgressStats:
         assert "wrapper.style.height = `${contentHeight}px`" in rendered
         assert 'class="header-toggle header-toggle-trigger"' not in rendered
         assert "event.preventDefault()" in rendered
-        assert rendered.count(".on('click', handleSnapshotHeaderToggle)") == 1
+        assert rendered.count("addEventListener('click', handleSnapshotHeaderToggle)") == 1
+
+    def test_static_snapshot_detail_uses_same_output_cards_with_relative_files(self, snapshot):
+        from archivebox.config import CONSTANTS
+        from archivebox.core.models import ArchiveResult
+        from archivebox.core.views import SnapshotView
+
+        output_dir = Path(snapshot.output_dir)
+        singlefile_dir = output_dir / "singlefile"
+        singlefile_dir.mkdir(parents=True, exist_ok=True)
+        output_file = singlefile_dir / "singlefile.html"
+        output_file.write_text("<html><body>real static output</body></html>", encoding="utf-8")
+        ArchiveResult.objects.create(
+            snapshot=snapshot,
+            plugin="singlefile",
+            hook_name="on_Snapshot__50_singlefile.py",
+            status=ArchiveResult.StatusChoices.SUCCEEDED,
+            output_str="singlefile.html",
+            output_files={"singlefile.html": {"size": output_file.stat().st_size}},
+            output_size=output_file.stat().st_size,
+        )
+        favicon_dir = output_dir / "favicon"
+        favicon_dir.mkdir(parents=True, exist_ok=True)
+        favicon_file = favicon_dir / "favicon.ico"
+        favicon_file.write_bytes(b"real favicon")
+        ArchiveResult.objects.create(
+            snapshot=snapshot,
+            plugin="favicon",
+            hook_name="on_Snapshot__50_favicon.py",
+            status=ArchiveResult.StatusChoices.SUCCEEDED,
+            output_str="favicon.ico",
+            output_files={"favicon.ico": {"size": favicon_file.stat().st_size}},
+            output_size=favicon_file.stat().st_size,
+        )
+
+        request = RequestFactory().get(f"/{snapshot.url_path}/index.html", HTTP_HOST=ADMIN_TEST_HOST)
+        request.user = AnonymousUser()
+        live_html = SnapshotView.render_live_index(request, snapshot).content.decode()
+
+        snapshot.write_html_details()
+        snapshot.write_json_details()
+        static_html = (output_dir / "index.html").read_text(encoding="utf-8")
+        static_json = json.loads((output_dir / "index.json").read_text(encoding="utf-8"))
+
+        assert re.findall(r'data-plugin-name="([^"]+)"', static_html) == re.findall(r'data-plugin-name="([^"]+)"', live_html)
+        assert 'data-plugin-name="singlefile"' in static_html
+        assert 'href="./singlefile/singlefile.html"' in static_html
+        assert 'data-default-src="./singlefile/singlefile.html"' in static_html
+        assert 'src="./favicon/favicon.ico"' in static_html
+        root_href = os.path.relpath(CONSTANTS.DATA_DIR, start=output_dir).replace(os.sep, "/")
+        assert f'href="{root_href}/index.html" class="header-archivebox"' in static_html
+        assert f"/snapshot/{snapshot.id.hex}" not in static_html
+        assert "/static/jquery.min.js" not in static_html
+        assert static_json["archive_path"].startswith("archive/users/")
+        assert static_json["archive_url"] == f"./{static_json['archive_path']}/index.html"
 
     def test_compact_output_cards_pack_into_dense_grid_rows(self):
         template = (REPO_ROOT / "archivebox" / "templates" / "core" / "snapshot.html").read_text()

archivebox/tests/test_urls.py

@@ -1282,8 +1282,10 @@ class TestUrlRouting:
             assert ">Git<" not in live_html
 
             static_html = Path(snapshot.output_dir, "index.html").read_text(encoding="utf-8", errors="ignore")
-            assert f"http://{snapshot_host}/" in static_html
-            assert f"http://{web_host}/static/archive.png" in static_html
+            assert f"http://{snapshot_host}/" not in static_html
+            assert f"http://{web_host}/static/archive.png" not in static_html
+            assert "data:image/svg+xml" in static_html
+            assert 'href="./' in static_html
             assert "?preview=1" in static_html
             assert "function createMainFrame(previousFrame)" in static_html
             assert "function activateCardPreview(card, link, updateHash=true)" in static_html

bin/generate_ui_screenshot_gallery.py

@@ -4,12 +4,15 @@ import hashlib
 import html
 import json
 import os
+import subprocess
 import struct
 import sys
+import tomllib
+from datetime import datetime, timezone
 from pathlib import Path
 from urllib.parse import urlparse
 
-SOURCE_BASE_URL = "https://github.com/ArchiveBox/ArchiveBox/blob/dev/"
+REPO_DIR = Path(__file__).resolve().parents[1]
 CAPTURE_PROFILES = {
     "desktop": (1600, 1000),
     "tablet": (1024, 1366),
@@ -55,6 +58,24 @@ REQUIRED_VIEW_NAMES = {
 }
 
 
+def build_provenance() -> dict[str, str]:
+    version = tomllib.loads((REPO_DIR / "pyproject.toml").read_text(encoding="utf-8"))["project"]["version"]
+    revision = os.environ.get("GITHUB_SHA", "").strip()
+    if not revision:
+        revision = subprocess.run(
+            ["git", "rev-parse", "HEAD"],
+            cwd=REPO_DIR,
+            check=True,
+            capture_output=True,
+            text=True,
+        ).stdout.strip()
+    return {
+        "version": version,
+        "revision": revision,
+        "generated_at": datetime.now(timezone.utc).isoformat(timespec="seconds"),
+    }
+
+
 def validate_navigation(metadata_path: Path, expected_path: str) -> None:
     navigation = json.loads(metadata_path.read_text(encoding="utf-8"))
     navigation = navigation.get("checks", navigation)
@@ -96,6 +117,8 @@ def append_manifest(manifest_path: Path, screenshot_path: Path) -> None:
 
 
 def build_galleries(manifest_path: Path, markdown_path: Path, html_path: Path) -> None:
+    provenance = build_provenance()
+    source_base_url = f"https://github.com/ArchiveBox/ArchiveBox/blob/{provenance['revision']}/"
     captures = [json.loads(line) for line in manifest_path.read_text(encoding="utf-8").splitlines() if line]
     allow_partial = os.environ.get("UI_SCREENSHOT_ALLOW_PARTIAL") == "1"
     grouped_captures: list[dict[str, object]] = []
@@ -155,7 +178,7 @@ def build_galleries(manifest_path: Path, markdown_path: Path, html_path: Path) -
         route = parsed_url.path or "/"
         if parsed_url.fragment:
             route = f"{route}#{parsed_url.fragment}"
-        source_url = f"{SOURCE_BASE_URL}{capture['source']}"
+        source_url = f"{source_base_url}{capture['source']}"
         markdown_cells = []
         html_figures = []
         for profile, (width, height) in CAPTURE_PROFILES.items():
@@ -211,6 +234,7 @@ def build_galleries(manifest_path: Path, markdown_path: Path, html_path: Path) -
                     "These desktop, tablet, and mobile screenshots cover ArchiveBox's major public and authenticated UI views. "
                     "Raw API endpoints, API documentation, health-check, and error routes are intentionally excluded."
                 ),
+                f"Generated from ArchiveBox `{provenance['version']}` at revision `{provenance['revision']}`.",
                 "",
                 "\n\n".join(markdown_sections),
                 "",
@@ -229,12 +253,33 @@ def build_galleries(manifest_path: Path, markdown_path: Path, html_path: Path) -
         "border:1px solid #cbd5e1;border-radius:8px;background:white;box-shadow:0 8px 24px #0f172a18}code{overflow-wrap:anywhere}"
         "@media(max-width:900px){.shots{grid-template-columns:1fr}body{padding:12px}}"
         '</style></head><body><header><p><a href="../">← ArchiveBox</a></p><h1>ArchiveBox UI Screenshots</h1>'
-        "<p>Generated from the current <code>dev</code> UI at desktop, tablet, and mobile viewports.</p></header><main>"
+        f"<p>Generated from ArchiveBox <code>{html.escape(provenance['version'])}</code> at "
+        f'<a href="https://github.com/ArchiveBox/ArchiveBox/commit/{html.escape(provenance["revision"])}">'
+        f"<code>{html.escape(provenance['revision'][:12])}</code></a> on "
+        f'<time datetime="{html.escape(provenance["generated_at"])}">{html.escape(provenance["generated_at"])}</time>. '
+        "Desktop, tablet, and mobile viewports are captured from the same build.</p></header><main>"
         + "".join(html_sections)
         + "</main></body></html>\n",
         encoding="utf-8",
     )
 
+    file_hashes = {
+        capture["filename"]: hashlib.sha256((html_path.parent / capture["filename"]).read_bytes()).hexdigest() for capture in captures
+    }
+    (html_path.parent / "build.json").write_text(
+        json.dumps(
+            {
+                **provenance,
+                "capture_count": len(captures),
+                "files": file_hashes,
+            },
+            indent=2,
+            sort_keys=True,
+        )
+        + "\n",
+        encoding="utf-8",
+    )
+
     if not allow_partial:
         expected_filenames = {capture["filename"] for capture in captures}
         for screenshot_dir in (markdown_path.parent / "screenshots", html_path.parent):

docs/Merging-Collections.md

@@ -5,7 +5,7 @@ Current ArchiveBox collections cannot be merged safely by copying their `archive
 The workflow below is retained for **legacy collections whose real Snapshot directories are `archive/<timestamp>/`**. `archivebox update` can import those legacy directories into a fresh index.
 
 > [!WARNING]
-> Back up every collection before merging. Confirm that the source entries are real legacy timestamp directories, not compatibility symlinks into `archive/users/...`, and inspect path conflicts instead of allowing one collection to overwrite another.
+> Back up every collection before merging. Confirm that the source entries are real legacy timestamp directories containing data, and inspect path conflicts instead of allowing one collection to overwrite another.
 
 1. Upgrade both old collections to the most recent ArchiveBox version (following instructions above)
   ```bash

docs/Publishing-Your-Archive.md

@@ -56,7 +56,11 @@ location / {
 
 Make sure you're not running any content as CGI or PHP, you only want to serve static files!
 
-Legacy timestamp URLs remain available through compatibility symlinks, for example: `https://demo.archivebox.io/archive/1493350273/wget/en.wikipedia.org/wiki/Dining_philosophers_problem.html`
+The generated links are relative, so the export works at a domain root or a project subpath such as GitHub Pages. Snapshot pages and outputs remain under their real filesystem paths, for example:
+
+`archive/users/alice/snapshots/20260829/example.com/SNAPSHOT_UUID/index.html`
+
+ArchiveBox does not create top-level timestamp symlinks for current snapshots. Run `archivebox update --migrate-only` to move real legacy `archive/<timestamp>/` directories into the user-scoped layout and remove obsolete timestamp projections.
 
 <br/>
 
@@ -71,7 +75,7 @@ Legacy timestamp URLs remain available through compatibility symlinks, for examp
 
 Make sure you understand the dangers of [hosting untrusted HTML/JS/CSS](https://developer.mozilla.org/en-US/docs/Web/Security/Same-origin_policy). The default `SERVER_SECURITY_MODE=auto` uses isolated subdomains with full replay on `*.localhost`, and a one-domain no-JS replay policy on ordinary public or LAN hostnames. Choose `safe-subdomains-fullreplay` only when wildcard DNS and TLS for `*.archive.example.com` are configured; it separates the admin, web, and API control planes from replay content and gives each Snapshot its own replay subdomain.
 
-Do not serve ArchiveBox from a shared subdirectory such as `myapps.example.com/archivebox/`; it cannot provide the required origin isolation. If you do not need JavaScript-capable replay, you can also disable the relevant extractors with `WGET_ENABLED=False` and `DOM_ENABLED=False`.
+Do not serve the authenticated ArchiveBox application from a shared subdirectory such as `myapps.example.com/archivebox/`; it cannot provide the required origin isolation. A standalone static export can be hosted at a project subpath because it contains no authenticated control plane. If you do not need JavaScript-capable replay, you can also disable the relevant extractors with `WGET_ENABLED=False` and `DOM_ENABLED=False`.
 
 More info:
 - https://github.com/ArchiveBox/ArchiveBox/wiki/Security-Overview

docs/Upgrading.md

@@ -53,7 +53,7 @@ The same command is used for initializing a new archive and upgrading an existin
 
 There are three main areas on disk that ArchiveBox modifies during upgrades:
 - `index.sqlite3` contains the SQLite3 DB index that gets upgraded automatically by Django based on the changes in [`archivebox/core/models.py`](https://github.com/ArchiveBox/ArchiveBox/blob/dev/archivebox/core/models.py).
-- `archive/users/<user>/snapshots/<date>/<domain>/<uuid>/index.jsonl` stores per-Snapshot metadata alongside plugin-namespaced output. `archivebox update --migrate-only` may rewrite metadata, migrate older layouts, and maintain legacy timestamp compatibility symlinks.
+- `archive/users/<user>/snapshots/<date>/<domain>/<uuid>/index.jsonl` stores per-Snapshot metadata alongside plugin-namespaced output. `archivebox update --migrate-only` may rewrite metadata, migrate older layouts, and remove obsolete timestamp projections after verified migration.
 - Snapshot output directories and plugin paths can move as filesystem schemas evolve, so the entire `archive/` tree must be backed up with the database.
 
 `ArchiveBox.conf` is migrated through the normal config loader/writer when options are renamed or normalized. Back it up with the rest of the collection and review release notes for config changes.

docs/apidocs/archivebox/archivebox.core.models.md

@@ -1396,14 +1396,6 @@ Bases: {py:obj}`archivebox.base_models.models.ModelWithDeleteAfter.Meta`, {py:ob
 
 ````
 
-````{py:method} ensure_legacy_archive_symlink() -> None
-:canonical: archivebox.core.models.Snapshot.ensure_legacy_archive_symlink
-
-```{autodoc2-docstring} archivebox.core.models.Snapshot.ensure_legacy_archive_symlink
-```
-
-````
-
 ````{py:method} ensure_crawl_symlink(*, crawl_dir: pathlib.Path | None = None, snapshot_dir: pathlib.Path | None = None) -> None
 :canonical: archivebox.core.models.Snapshot.ensure_crawl_symlink