Struct CrawlJob 

pub struct CrawlJob {

    pub id: i64,
    pub name: String,
    pub seed_url: String,
    pub include_paths: Vec<String>,
    pub exclude_paths: Vec<String>,
    pub max_depth: i64,
    pub same_domain: i64,
    pub allow_subdomains: i64,
    pub extract_mode: String,
    pub extract_schema: Option<Value>,
    pub persona_id: Option<i64>,
    pub respect_robots: i64,
    pub delay_ms: i64,
    pub max_concurrent: i64,
    pub page_budget: i64,
    pub workflow_id: Option<i64>,
    pub data_workflow_id: Option<i64>,
    pub concierge_session_id: Option<i64>,
    pub status: String,
    pub pages_discovered: i64,
    pub pages_done: i64,
    pub pages_failed: i64,
    pub pages_skipped: i64,
    pub workers_active: i64,
    pub current_depth: i64,
    pub error: Option<String>,
    pub cancel_requested: i64,
    pub brand: String,
    pub is_terminal: bool,
    pub created_at: String,
    pub updated_at: Option<String>,
    pub started_at: Option<String>,
    pub completed_at: Option<String>,
    pub extra: Extra,
}

A Dragnet crawl-job status view (api/v1/crawl.rs::to_view over store/crawl_jobs.rs::CrawlJob). One crawl fans a seed URL across a bounded in-process worker pool; extracted pages aggregate under the synthetic CrawlJob::data_workflow_id workflow, read back through the Data API. As with monitor rows, the boolean columns arrive as SQLite 0/1 ints and stay typed as i64 (not coerced).

Fields

id: i64

name: String

seed_url: String

include_paths: Vec<String>

Path-regex allowlist (parsed from JSON-TEXT into an array by the daemon view).

exclude_paths: Vec<String>

Path-regex denylist.

max_depth: i64

same_domain: i64

boolean as 0/1.

allow_subdomains: i64

boolean as 0/1.

extract_mode: String

markdown | schema.

extract_schema: Option<Value>

The JSON schema object driving schema extraction (null for markdown).

persona_id: Option<i64>

respect_robots: i64

boolean as 0/1.

delay_ms: i64

max_concurrent: i64

page_budget: i64

workflow_id: Option<i64>

The synthetic per-crawl workflow the extracted pages aggregate under.

data_workflow_id: Option<i64>

Alias of workflow_id the view adds for the Data API (/v1/workflows/{data_workflow_id}/data).

concierge_session_id: Option<i64>

status: String

queued | mapping | crawling | stopping | completed | failed | cancelled (terminal: the last three) — treat as an open string enum.

pages_discovered: i64

pages_done: i64

pages_failed: i64

pages_skipped: i64

workers_active: i64

current_depth: i64

error: Option<String>

cancel_requested: i64

boolean as 0/1.

brand: String

Always "Dragnet".

is_terminal: bool

Daemon-computed convenience: true for the terminal states.

created_at: String

updated_at: Option<String>

started_at: Option<String>

completed_at: Option<String>

extra: Extra

Trait Implementations

impl Clone for CrawlJob

fn clone(&self) -> CrawlJob

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for CrawlJob

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for CrawlJob

fn default() -> CrawlJob

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for CrawlJob

where CrawlJob: Default,

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for CrawlJob

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.