archivebox.crawls.admin

Module Contents

Classes

MaxDepthListFilter
URLFiltersField
CrawlAdminForm	Custom form for Crawl admin to render urls field as textarea.
CrawlAdmin
CrawlScheduleAdmin

Functions

render_snapshots_list	Render a nice inline list view of snapshots with status, title, URL, and progress.
register_admin

API

class archivebox.crawls.admin.MaxDepthListFilter

Bases: django.contrib.admin.SimpleListFilter

title

‘max depth’

parameter_name

‘max_depth’

lookups(request, model_admin)

queryset(request, queryset)

archivebox.crawls.admin.render_snapshots_list(snapshots_qs, request=None, crawl=None, page_size=50, prefix='snapshots')

Render a nice inline list view of snapshots with status, title, URL, and progress.

class archivebox.crawls.admin.URLFiltersField

Bases: django.forms.Field

widget

‘URLFiltersWidget(…)’

to_python(value)

class archivebox.crawls.admin.CrawlAdminForm(*args, **kwargs)

Bases: django.forms.ModelForm

Custom form for Crawl admin to render urls field as textarea.

Initialization

tags_editor

‘CharField(…)’

url_filters

‘URLFiltersField(…)’

class Meta

model

None

fields

‘all’

widgets

None

static extract_url_line(line)

static regex_escape(text)

classmethod generated_host_allowlist(urls)

static subpath_prefix(pathname)

static parsed_host_and_port(parsed)

classmethod generated_subpath_allowlist(urls)

classmethod derive_filter_toggles(urls, allowlist)

static effective_only_new(crawl=None)

static inherited_only_new(crawl)

clean_tags_editor()

clean_url_filters()

save(commit=True)

class archivebox.crawls.admin.CrawlAdmin(model, admin_site)

Bases: archivebox.base_models.admin.ConfigEditorMixin, archivebox.base_models.admin.BaseModelAdmin

form

None

change_form_template

‘admin/crawls/crawl/change_form.html’

list_select_related

()

paginator

None

show_full_result_count

False

list_display

(‘short_id’, ‘permissions_badge’, ‘created_at’, ‘owner’, ‘depth’, ‘status_with_stop_reason’, ‘pause_…

sort_fields

(‘id’, ‘created_at’, ‘created_by’, ‘max_depth’, ‘label’, ‘notes’, ‘schedule_str’, ‘status’, ‘retry_a…

search_fields

(‘id’, ‘created_by__username’, ‘max_depth’, ‘label’, ‘notes’, ‘schedule_id’, ‘status’, ‘urls’)

readonly_fields

(‘created_at’, ‘modified_at’, ‘stop_reason_display’)

fieldsets

((‘URLs’,), (‘Overview’,), (‘Config’,))

add_fieldsets

((‘URLs’,), (‘Overview’,), (‘Config’,))

list_filter

()

ordering

[‘-created_at’, ‘-retry_at’]

list_per_page

50

actions

[‘pause_selected_crawls’, ‘resume_selected_crawls’, ‘seal_selected_crawls’, ‘delete_selected_batched…

change_actions

[‘recrawl’]

class Media

css

None

js

(‘admin/crawls/crawl_admin.js’,)

changelist_view(request, extra_context=None)

should_annotate_snapshot_counts(request)

hydrate_visible_snapshot_counts(crawls)

get_queryset(request)

Keep joins page-local while computing per-row snapshot counts in the page query.

change_view(request, object_id, form_url='', extra_context=None)

add_view(request, form_url='', extra_context=None)

get_fieldsets(request, obj=None)

get_urls()

get_actions(request)

delete_selected_batched(request, queryset)

Delete crawls in a single transaction to avoid SQLite concurrency issues.

pause_selected_crawls(request, queryset)

resume_selected_crawls(request, queryset)

seal_selected_crawls(request, queryset)

set_crawl_permissions(request, queryset)

update_crawl_permissions(queryset, permissions)

recrawl(request, obj)

Duplicate this crawl as a new crawl with the same URLs and settings.

stop_reason_display(obj)

stop_reason_for_crawl(obj)

limit_config_for_crawl(obj, output_dir)

status_with_stop_reason(obj)

short_id(obj)

owner(obj)

depth(obj)

permissions_badge(obj)

pause_resume_control(obj)

num_archived_snapshots(obj)

num_total_snapshots(obj)

snapshots_changelist(obj)

delete_snapshot_view(request: django.http.HttpRequest, object_id: str, snapshot_id: str)

exclude_domain_view(request: django.http.HttpRequest, object_id: str, snapshot_id: str)

set_permissions_view(request: django.http.HttpRequest, object_id: str)

schedule_str(obj)

urls_preview(obj)

urls_editor(obj)

Editor for crawl URLs.

class archivebox.crawls.admin.CrawlScheduleAdmin

Bases: archivebox.base_models.admin.BaseModelAdmin

list_display

(‘id’, ‘created_at’, ‘created_by’, ‘label’, ‘notes’, ‘template_str’, ‘crawls’, ‘num_crawls’, ‘num_sn…

sort_fields

(‘id’, ‘created_at’, ‘created_by’, ‘label’, ‘notes’, ‘template_str’)

search_fields

(‘id’, ‘created_by__username’, ‘label’, ‘notes’, ‘schedule_id’, ‘template_id’, ‘template__urls’)

readonly_fields

(‘created_at’, ‘modified_at’, ‘crawls’, ‘snapshots’)

fieldsets

((‘Schedule Info’,), (‘Configuration’,), (‘Metadata’,), (‘Crawls’,), (‘Snapshots’,))

list_filter

(‘created_by’,)

ordering

[‘-created_at’]

list_per_page

100

actions

[‘delete_selected’]

get_queryset(request)

change_view(request, object_id, form_url='', extra_context=None)

add_view(request, form_url='', extra_context=None)

get_fieldsets(request, obj=None)

save_model(request, obj, form, change)

template_str(obj)

num_crawls(obj)

num_snapshots(obj)

crawls(obj)

snapshots(obj)

archivebox.crawls.admin.register_admin(admin_site)