archivebox.crawls.admin

Module Contents

Classes

URLFiltersWidget
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

archivebox.crawls.admin.render_snapshots_list(snapshots_qs, limit=20, crawl=None)

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

class archivebox.crawls.admin.URLFiltersWidget

Bases: django.forms.Widget

render(name, value, attrs=None, renderer=None)

value_from_datadict(data, files, name)

class archivebox.crawls.admin.URLFiltersField

Bases: django.forms.Field

widget

None

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

clean_tags_editor()

clean_url_filters()

save(commit=True)

class archivebox.crawls.admin.CrawlAdmin

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

form

None

list_display

(‘id’, ‘created_at’, ‘created_by’, ‘max_depth’, ‘max_urls’, ‘max_size’, ‘label’, ‘notes’, ‘urls_prev…

sort_fields

(‘id’, ‘created_at’, ‘created_by’, ‘max_depth’, ‘max_urls’, ‘max_size’, ‘label’, ‘notes’, ‘schedule_…

search_fields

(‘id’, ‘created_by__username’, ‘max_depth’, ‘max_urls’, ‘max_size’, ‘label’, ‘notes’, ‘schedule_id’,…

readonly_fields

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

fieldsets

((‘URLs’,), (‘Info’,), (‘Settings’,), (‘Status’,), (‘Relations’,), (‘Timestamps’,), (‘Snapshots’,))

add_fieldsets

((‘URLs’,), (‘Info’,), (‘Settings’,), (‘Status’,), (‘Relations’,))

list_filter

(‘max_depth’, ‘max_urls’, ‘schedule’, ‘created_by’, ‘status’, ‘retry_at’)

ordering

[‘-created_at’, ‘-retry_at’]

list_per_page

100

actions

[‘delete_selected_batched’]

change_actions

[‘recrawl’]

get_queryset(request)

Optimize queries with select_related and annotations.

get_fieldsets(request, obj=None)

get_urls()

delete_selected_batched(request, queryset)

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

recrawl(request, obj)

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

num_snapshots(obj)

snapshots(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)

schedule_str(obj)

urls_preview(obj)

health_display(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)

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)