Struct CrawlerBuilder

Source

pub struct CrawlerBuilder<S: Spider, D = ReqwestClientDownloader>where
    D: Downloader,
{ /* private fields */ }

Implementations§

Source §

impl<S: Spider> CrawlerBuilder<S>

Source

pub fn new(spider: S) -> Self

Creates a new CrawlerBuilder for a given spider.

Source §

impl<S: Spider, D: Downloader> CrawlerBuilder<S, D>

Source

pub fn max_concurrent_downloads(self, limit: usize) -> Self

Sets the maximum number of concurrent downloads.

Source

pub fn max_parser_workers(self, limit: usize) -> Self

Sets the maximum number of concurrent parser workers.

Source

pub fn max_concurrent_pipelines(self, limit: usize) -> Self

Sets the maximum number of concurrent pipelines.

Source

pub fn downloader(self, downloader: D) -> Self

Sets a custom downloader for the crawler.

Source

pub fn add_middleware<M>(self, middleware: M) -> Self
where D: Downloader, M: Middleware<D::Client> + Send + Sync + 'static,

Adds a middleware to the crawler.

Source

pub fn add_pipeline(self, pipeline: P) -> Self
where P: Pipeline<S::Item> + 'static,

Adds an item pipeline to the crawler.

Source

pub async fn build(self) -> Result<Crawler<S, D::Client>, SpiderError>
where D: Downloader + Send + Sync + 'static, D::Client: Send + Sync,

Builds the Crawler instance, initializing and passing the StatCollector along with other configured components.

Trait Implementations§

Source §

impl<S: Spider, D: Default + Downloader> Default for CrawlerBuilder<S, D>

Source §

fn default() -> Self

Returns the “default value” for a type. Read more

Auto Trait Implementations§

§

impl<S, D = ReqwestClientDownloader> !UnwindSafe for CrawlerBuilder<S, D>

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 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> Pointable for T

Source §

const ALIGN: usize

The alignment of pointer.

Source §

type Init = T

The type for initializers.

Source §

unsafe fn init(init: <T as Pointable>::Init) -> usize

Initializes a with the given initializer. Read more

Source §

unsafe fn deref<'a>(ptr: usize) -> &'a T

Dereferences the given pointer. Read more

Source §

unsafe fn deref_mut<'a>(ptr: usize) -> &'a mut T

Mutably dereferences the given pointer. Read more

Source §

unsafe fn drop(ptr: usize)

Drops the object pointed to by the given pointer. Read more

Source §

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

Source §

fn and<P, B, E>(self, other: P) -> And<T, P>
where T: Policy<B, E>, P: Policy<B, E>,

Create a new Policy that returns Action::Follow only if self and other return Action::Follow. Read more

Source §

fn or<P, B, E>(self, other: P) -> Or<T, P>
where T: Policy<B, E>, P: Policy<B, E>,

Create a new Policy that returns Action::Follow if either self or other returns Action::Follow. Read more

Source §

impl<T> Same for T

Source §

type Output = T

Should always be Self

Source §

impl<T, U> TryFrom 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>::Error>

Performs the conversion.

Source §

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

Source §

type Error = >::Error

The type returned in the event of a conversion error.

Source §

fn try_into(self) -> Result<U, >::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

CrawlerBuilder

Struct CrawlerBuilder Copy item path

Implementations§

impl<S: Spider> CrawlerBuilder<S>

pub fn new(spider: S) -> Self

impl<S: Spider, D: Downloader> CrawlerBuilder<S, D>

pub fn max_concurrent_downloads(self, limit: usize) -> Self

pub fn max_parser_workers(self, limit: usize) -> Self

pub fn max_concurrent_pipelines(self, limit: usize) -> Self

pub fn downloader(self, downloader: D) -> Self

pub fn add_middleware<M>(self, middleware: M) -> Selfwhere D: Downloader, M: Middleware<D::Client> + Send + Sync + 'static,

pub fn add_pipeline<P>(self, pipeline: P) -> Selfwhere P: Pipeline<S::Item> + 'static,

pub async fn build(self) -> Result<Crawler<S, D::Client>, SpiderError>where D: Downloader + Send + Sync + 'static, D::Client: Send + Sync,

Trait Implementations§

impl<S: Spider, D: Default + Downloader> Default for CrawlerBuilder<S, D>

fn default() -> Self

Auto Trait Implementations§

impl<S, D> Freeze for CrawlerBuilder<S, D>where D: Freeze, S: Freeze,

impl<S, D = ReqwestClientDownloader> !RefUnwindSafe for CrawlerBuilder<S, D>

impl<S, D> Send for CrawlerBuilder<S, D>

impl<S, D> Sync for CrawlerBuilder<S, D>

impl<S, D> Unpin for CrawlerBuilder<S, D>where D: Unpin, S: Unpin,

impl<S, D = ReqwestClientDownloader> !UnwindSafe for CrawlerBuilder<S, D>

Blanket Implementations§

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

fn type_id(&self) -> TypeId

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

fn borrow(&self) -> &T

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

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

impl<T> From<T> for T

fn from(t: T) -> T

impl<T> Instrument for T

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

fn in_current_span(self) -> Instrumented<Self>

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

fn into(self) -> U

impl<T> Pointable for T

const ALIGN: usize

type Init = T

unsafe fn init(init: <T as Pointable>::Init) -> usize

unsafe fn deref<'a>(ptr: usize) -> &'a T

unsafe fn deref_mut<'a>(ptr: usize) -> &'a mut T

unsafe fn drop(ptr: usize)

impl<T> PolicyExt for Twhere T: ?Sized,

fn and<P, B, E>(self, other: P) -> And<T, P>where T: Policy<B, E>, P: Policy<B, E>,

fn or<P, B, E>(self, other: P) -> Or<T, P>where T: Policy<B, E>, P: Policy<B, E>,

impl<T> Same for T

type Output = T

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

type Error = Infallible

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

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

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

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

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

fn vzip(self) -> V

impl<T> WithSubscriber for T

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

fn with_current_subscriber(self) -> WithDispatch<Self>

Struct CrawlerBuilder

pub fn add_middleware<M>(self, middleware: M) -> Self
where D: Downloader, M: Middleware<D::Client> + Send + Sync + 'static,

pub fn add_pipeline<P>(self, pipeline: P) -> Self
where P: Pipeline<S::Item> + 'static,

pub async fn build(self) -> Result<Crawler<S, D::Client>, SpiderError>
where D: Downloader + Send + Sync + 'static, D::Client: Send + Sync,

impl<S, D> Freeze for CrawlerBuilder<S, D>
where D: Freeze, S: Freeze,

impl<S, D> Unpin for CrawlerBuilder<S, D>
where D: Unpin, S: Unpin,

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

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

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

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

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

fn and<P, B, E>(self, other: P) -> And<T, P>
where T: Policy<B, E>, P: Policy<B, E>,

fn or<P, B, E>(self, other: P) -> Or<T, P>
where T: Policy<B, E>, P: Policy<B, E>,

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

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

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

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