Skip to main content

Crate spider_lib

Crate spider_lib 

Source

Re-exports§

pub use downloader::Downloader;
pub use middleware::Middleware;
pub use pipeline::Pipeline;
pub use builder::CrawlerBuilder;
pub use crawler::Crawler;
pub use error::PipelineError;
pub use error::SpiderError;
pub use item::ParseOutput;
pub use item::ScrapedItem;
pub use request::Request;
pub use response::Response;
pub use scheduler::Scheduler;
pub use spider::Spider;
pub use downloaders::reqwest_client::ReqwestClientDownloader;
pub use middlewares::http_cache::HttpCacheMiddleware;
pub use middlewares::rate_limit::RateLimitMiddleware;
pub use middlewares::referer::RefererMiddleware;
pub use middlewares::retry::RetryMiddleware;
pub use middlewares::robots_txt::RobotsTxtMiddleware;
pub use middlewares::user_agent::UserAgentMiddleware;
pub use pipelines::console_writer::ConsoleWriterPipeline;
pub use pipelines::csv_exporter::CsvExporterPipeline;
pub use pipelines::deduplication::DeduplicationPipeline;
pub use pipelines::json_writer::JsonWriterPipeline;
pub use pipelines::jsonl_writer::JsonlWriterPipeline;
pub use tokio;

Modules§

builder
checkpoint
crawler
downloader
downloaders
error
item
middleware
middlewares
pipeline
pipelines
prelude
A “prelude” for users of the spider-lib crate.
request
response
scheduler
spider
state
utils

Structs§

DashMap
DashMap is an implementation of a concurrent associative array/hashmap in Rust.

Attribute Macros§

async_trait
scraped_item
A procedural macro to derive the ScrapedItem trait.