StatCollector

spider_lib::prelude

Struct StatCollector

pub struct StatCollector {Show 20 fields
    pub start_time: Instant,
    pub requests_enqueued: AtomicUsize,
    pub requests_sent: AtomicUsize,
    pub requests_succeeded: AtomicUsize,
    pub requests_failed: AtomicUsize,
    pub requests_retried: AtomicUsize,
    pub requests_scheduled_for_retry: AtomicUsize,
    pub requests_dropped: AtomicUsize,
    pub retry_delay_in_flight_ms: AtomicU64,
    pub responses_received: AtomicUsize,
    pub responses_from_cache: AtomicUsize,
    pub response_status_counts: Arc<DashMap<u16, usize>>,
    pub total_bytes_downloaded: AtomicUsize,
    pub items_scraped: AtomicUsize,
    pub items_processed: AtomicUsize,
    pub items_dropped_by_pipeline: AtomicUsize,
    pub queue_depth: AtomicUsize,
    pub parser_backlog: AtomicUsize,
    pub pipeline_backlog: AtomicUsize,
    pub retry_backlog: AtomicUsize,
    /* private fields */
}

Expand description

Core runtime types and traits used to define and run a crawl. Collects and stores various statistics about the crawler’s operation.

Fields§

§start_time: Instant§requests_enqueued: AtomicUsize§requests_sent: AtomicUsize§requests_succeeded: AtomicUsize§requests_failed: AtomicUsize§requests_retried: AtomicUsize§requests_scheduled_for_retry: AtomicUsize§requests_dropped: AtomicUsize§retry_delay_in_flight_ms: AtomicU64§responses_received: AtomicUsize§responses_from_cache: AtomicUsize§response_status_counts: Arc<DashMap<u16, usize>>§total_bytes_downloaded: AtomicUsize§items_scraped: AtomicUsize§items_processed: AtomicUsize§items_dropped_by_pipeline: AtomicUsize§queue_depth: AtomicUsize§parser_backlog: AtomicUsize§pipeline_backlog: AtomicUsize§retry_backlog: AtomicUsize

Implementations§

impl StatCollector

pub fn snapshot(&self) -> MetricsSnapshot

Returns a public immutable snapshot of the current crawl metrics.

pub fn record_request_time(&self, _url: &str, duration: Duration)

Records the time taken for a request.

pub fn average_request_time(&self) -> Option<Duration>

Calculates the average request time across all recorded requests.

pub fn fastest_request_time(&self) -> Option<Duration>

Gets the fastest request time among all recorded requests.

pub fn slowest_request_time(&self) -> Option<Duration>

Gets the slowest request time among all recorded requests.

pub fn request_time_count(&self) -> usize

Gets the total number of recorded request times.

pub fn get_request_time(&self, url: &str) -> Option<Duration>

Gets the request time for a specific URL.

pub fn get_all_request_times(&self) -> Vec<(String, Duration)>

Gets all recorded request times as a vector of (URL, Duration) pairs.

pub fn record_parsing_time(&self, duration: Duration)

Records the time taken for parsing a response.

pub fn average_parsing_time(&self) -> Option<Duration>

Calculates the average parsing time across all recorded parses.

pub fn fastest_parsing_time(&self) -> Option<Duration>

Gets the fastest parsing time among all recorded parses.

pub fn slowest_parsing_time(&self) -> Option<Duration>

Gets the slowest parsing time among all recorded parses.

pub fn parsing_time_count(&self) -> usize

Gets the total number of recorded parsing times.

pub fn clear_request_times(&self)

Clears all recorded request times.

pub fn clear_parsing_times(&self)

Clears all recorded parsing times.

pub fn to_json_string(&self) -> Result<String, SpiderError>

Converts the snapshot into a JSON string.

pub fn to_json_string_pretty(&self) -> Result<String, SpiderError>

Converts the snapshot into a pretty-printed JSON string.

pub fn to_markdown_string(&self) -> String

Exports the current statistics to a Markdown formatted string.

pub fn to_live_report_string(&self) -> String

Exports current statistics to the text layout used for terminal output.

Trait Implementations§

impl Debug for StatCollector

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

Formats the value using the given formatter. Read more

impl Default for StatCollector

fn default() -> StatCollector

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

impl Display for StatCollector

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

Formats the value using the given formatter. Read more

impl Serialize for StatCollector

fn serialize<S>( &self, serializer: S, ) -> Result<<S as Serializer>::Ok, <S as Serializer>::Error>
where S: Serializer,

Serialize this value into the given Serde serializer. Read more

Auto Trait Implementations§

impl !Freeze for StatCollector

impl !RefUnwindSafe for StatCollector

impl Send for StatCollector

impl Sync for StatCollector

impl Unpin for StatCollector

impl !UnwindSafe for StatCollector

Blanket Implementations§

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

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more

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

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more

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

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

Mutably borrows from an owned value. Read more

impl<T> From<T> for T

fn from(t: T) -> T

Returns the argument unchanged.

impl<T> Instrument for T

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

Instruments this type with the provided [Span], returning an Instrumented wrapper. Read more

fn in_current_span(self) -> Instrumented<Self>

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

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

fn into(self) -> U

Calls U::from(self).

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

impl<T> Pointable for T

const ALIGN: usize

The alignment of pointer.

type Init = T

The type for initializers.

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

Initializes a with the given initializer. Read more

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

Dereferences the given pointer. Read more

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

Mutably dereferences the given pointer. Read more

unsafe fn drop(ptr: usize)

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

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>,

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

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

impl<T> ToString for T
where T: Display + ?Sized,

fn to_string(&self) -> String

Converts the given value to a String. Read more

impl<T> ToStringFallible for T
where T: Display,

fn try_to_string(&self) -> Result<String, TryReserveError>

ToString::to_string, but without panic on OOM.

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

type Error = Infallible

The type returned in the event of a conversion error.

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

Performs the conversion.

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

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

The type returned in the event of a conversion error.

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

Performs the conversion.

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

Attaches the provided Subscriber to this type, returning a [WithDispatch] wrapper. Read more

fn with_current_subscriber(self) -> WithDispatch<Self>

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