Orchestrator

halldyll_core::orchestrator

Struct Orchestrator 

Source 
pub struct Orchestrator { /* private fields */ }
Expand description

Main orchestrator

Implementations§

Source§

impl Orchestrator

Source

pub fn new(config: Config) -> Result<Self>

Create a new orchestrator

Source

pub fn with_browser_pool(self, pool: BrowserPool) -> Self

Configure the browser pool for JS rendering

Source

pub async fn scrape(&self, url: &Url) -> Result<ScrapeResult>

Scrape a single URL with full pipeline

Source

pub async fn crawl( &self, seeds: Vec<Url>, max_pages: Option<usize>, ) -> Result<Vec<Document>>

Crawl starting from seed URLs

Source

pub fn metrics(&self) -> &MetricsCollector

Access to metrics

Source

pub fn documents(&self) -> &NormalizedStore

Access to document store

Source

pub fn snapshots(&self) -> &SnapshotStore

Access to snapshot store

Source

pub fn frontier(&self) -> &Frontier

Access to frontier

Source

pub fn url_dedup(&self) -> &UrlDedup

Access to URL dedup

Source

pub fn content_dedup(&self) -> &ContentDedup

Access to content dedup

Source

pub fn allowlist_mut(&mut self) -> &mut DomainAllowlist

Configure the allowlist

Source

pub fn ip_blocker_mut(&mut self) -> &mut IpBlocker

Configure IP blocker

Source

pub fn limits_mut(&mut self) -> &mut ResourceLimits

Configure resource limits

Source

pub fn config(&self) -> &Config

Get configuration

Source

pub fn logger(&self) -> &StructuredLogger

Get logger

Auto Trait Implementations§

Blanket Implementations§

Source§

impl<T> Any for T
where T: 'static + ?Sized,

Source§

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more
Source§

impl<T> Borrow<T> for T
where T: ?Sized,

Source§

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more
Source§

impl<T> BorrowMut<T> for T
where T: ?Sized,

Source§

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more
Source§

impl<T> From<T> for T

Source§

fn from(t: T) -> T

Returns the argument unchanged.

Source§

impl<T> Instrument for T

Source§

fn instrument(self, span: Span) -> Instrumented<Self>

Instruments this type with the provided Span, returning an Instrumented wrapper. Read more
Source§

fn in_current_span(self) -> Instrumented<Self>

Instruments this type with the current Span, returning an Instrumented wrapper. Read more
Source§

impl<T, U> Into<U> for T
where U: From<T>,

Source§

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

Source§

impl<T> Same for T

Source§

type Output = T

Should always be Self
Source§

impl<T, U> TryFrom<U> for T
where U: Into<T>,

Source§

type Error = Infallible

The type returned in the event of a conversion error.
Source§

fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>

Performs the conversion.
Source§

impl<T, U> TryInto<U> for T
where U: TryFrom<T>,

Source§

type Error = <U as TryFrom<T>>::Error

The type returned in the event of a conversion error.
Source§

fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>

Performs the conversion.
Source§

impl<V, T> VZip<V> for T
where V: MultiLane<T>,

Source§

fn vzip(self) -> V

Source§

impl<T> WithSubscriber for T

Source§

fn with_subscriber<S>(self, subscriber: S) -> WithDispatch<Self>
where S: Into<Dispatch>,

Attaches the provided Subscriber to this type, returning a WithDispatch wrapper. Read more
Source§

fn with_current_subscriber(self) -> WithDispatch<Self>

Attaches the current default Subscriber to this type, returning a WithDispatch wrapper. Read more