Struct CrawlerBuilder

Source

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

Implementations§

Source §

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

Source

pub fn new(spider: S) -> Self
where D: Default,

Creates a new CrawlerBuilder for a given spider.

Examples found in repository ?

examples/quotes_scraper.rs (line 79)

73async fn main() -> Result<(), SpiderError> {
74    tracing_subscriber::fmt()
75        .with_env_filter("info,spider_lib=debug")
76        .without_time()
77        .init();
78
79    let crawler = CrawlerBuilder::<_, ReqwestClientDownloader>::new(QuotesSpider)
80        .add_pipeline(DeduplicationPipeline::new(&["text"]))
81        .add_pipeline(CsvExporterPipeline::<QuoteItem>::new("output/quotes.csv")?)
82        .add_middleware(HttpCacheMiddleware::builder().build()?)
83        .add_middleware(UserAgentMiddleware::builder().build()?)
84        .add_middleware(RobotsTxtMiddleware::new())
85        .add_middleware(
86            RefererMiddleware::new()
87                .same_origin_only(true)
88                .max_chain_length(100)
89                .include_fragment(false),
90        )
91        .with_checkpoint_path("output/quotes.bin")
92        .with_checkpoint_interval(Duration::from_secs(15))
93        .max_concurrent_downloads(5)
94        .max_parser_workers(2)
95        .max_concurrent_pipelines(2)
96        .build()
97        .await?;
98
99    crawler.start_crawl().await?;
100
101    Ok(())
102}

Source

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

Sets the maximum number of concurrent downloads.

Examples found in repository ?

examples/quotes_scraper.rs (line 93)

73async fn main() -> Result<(), SpiderError> {
74    tracing_subscriber::fmt()
75        .with_env_filter("info,spider_lib=debug")
76        .without_time()
77        .init();
78
79    let crawler = CrawlerBuilder::<_, ReqwestClientDownloader>::new(QuotesSpider)
80        .add_pipeline(DeduplicationPipeline::new(&["text"]))
81        .add_pipeline(CsvExporterPipeline::<QuoteItem>::new("output/quotes.csv")?)
82        .add_middleware(HttpCacheMiddleware::builder().build()?)
83        .add_middleware(UserAgentMiddleware::builder().build()?)
84        .add_middleware(RobotsTxtMiddleware::new())
85        .add_middleware(
86            RefererMiddleware::new()
87                .same_origin_only(true)
88                .max_chain_length(100)
89                .include_fragment(false),
90        )
91        .with_checkpoint_path("output/quotes.bin")
92        .with_checkpoint_interval(Duration::from_secs(15))
93        .max_concurrent_downloads(5)
94        .max_parser_workers(2)
95        .max_concurrent_pipelines(2)
96        .build()
97        .await?;
98
99    crawler.start_crawl().await?;
100
101    Ok(())
102}

Source

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

Sets the maximum number of concurrent parser workers.

Examples found in repository ?

examples/quotes_scraper.rs (line 94)

73async fn main() -> Result<(), SpiderError> {
74    tracing_subscriber::fmt()
75        .with_env_filter("info,spider_lib=debug")
76        .without_time()
77        .init();
78
79    let crawler = CrawlerBuilder::<_, ReqwestClientDownloader>::new(QuotesSpider)
80        .add_pipeline(DeduplicationPipeline::new(&["text"]))
81        .add_pipeline(CsvExporterPipeline::<QuoteItem>::new("output/quotes.csv")?)
82        .add_middleware(HttpCacheMiddleware::builder().build()?)
83        .add_middleware(UserAgentMiddleware::builder().build()?)
84        .add_middleware(RobotsTxtMiddleware::new())
85        .add_middleware(
86            RefererMiddleware::new()
87                .same_origin_only(true)
88                .max_chain_length(100)
89                .include_fragment(false),
90        )
91        .with_checkpoint_path("output/quotes.bin")
92        .with_checkpoint_interval(Duration::from_secs(15))
93        .max_concurrent_downloads(5)
94        .max_parser_workers(2)
95        .max_concurrent_pipelines(2)
96        .build()
97        .await?;
98
99    crawler.start_crawl().await?;
100
101    Ok(())
102}

Source

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

Sets the maximum number of concurrent pipelines.

Examples found in repository ?

examples/quotes_scraper.rs (line 95)

73async fn main() -> Result<(), SpiderError> {
74    tracing_subscriber::fmt()
75        .with_env_filter("info,spider_lib=debug")
76        .without_time()
77        .init();
78
79    let crawler = CrawlerBuilder::<_, ReqwestClientDownloader>::new(QuotesSpider)
80        .add_pipeline(DeduplicationPipeline::new(&["text"]))
81        .add_pipeline(CsvExporterPipeline::<QuoteItem>::new("output/quotes.csv")?)
82        .add_middleware(HttpCacheMiddleware::builder().build()?)
83        .add_middleware(UserAgentMiddleware::builder().build()?)
84        .add_middleware(RobotsTxtMiddleware::new())
85        .add_middleware(
86            RefererMiddleware::new()
87                .same_origin_only(true)
88                .max_chain_length(100)
89                .include_fragment(false),
90        )
91        .with_checkpoint_path("output/quotes.bin")
92        .with_checkpoint_interval(Duration::from_secs(15))
93        .max_concurrent_downloads(5)
94        .max_parser_workers(2)
95        .max_concurrent_pipelines(2)
96        .build()
97        .await?;
98
99    crawler.start_crawl().await?;
100
101    Ok(())
102}

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.

Examples found in repository ?

examples/quotes_scraper.rs (line 82)

73async fn main() -> Result<(), SpiderError> {
74    tracing_subscriber::fmt()
75        .with_env_filter("info,spider_lib=debug")
76        .without_time()
77        .init();
78
79    let crawler = CrawlerBuilder::<_, ReqwestClientDownloader>::new(QuotesSpider)
80        .add_pipeline(DeduplicationPipeline::new(&["text"]))
81        .add_pipeline(CsvExporterPipeline::<QuoteItem>::new("output/quotes.csv")?)
82        .add_middleware(HttpCacheMiddleware::builder().build()?)
83        .add_middleware(UserAgentMiddleware::builder().build()?)
84        .add_middleware(RobotsTxtMiddleware::new())
85        .add_middleware(
86            RefererMiddleware::new()
87                .same_origin_only(true)
88                .max_chain_length(100)
89                .include_fragment(false),
90        )
91        .with_checkpoint_path("output/quotes.bin")
92        .with_checkpoint_interval(Duration::from_secs(15))
93        .max_concurrent_downloads(5)
94        .max_parser_workers(2)
95        .max_concurrent_pipelines(2)
96        .build()
97        .await?;
98
99    crawler.start_crawl().await?;
100
101    Ok(())
102}

Source

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

Adds an item pipeline to the crawler.

Examples found in repository ?

examples/quotes_scraper.rs (line 80)

73async fn main() -> Result<(), SpiderError> {
74    tracing_subscriber::fmt()
75        .with_env_filter("info,spider_lib=debug")
76        .without_time()
77        .init();
78
79    let crawler = CrawlerBuilder::<_, ReqwestClientDownloader>::new(QuotesSpider)
80        .add_pipeline(DeduplicationPipeline::new(&["text"]))
81        .add_pipeline(CsvExporterPipeline::<QuoteItem>::new("output/quotes.csv")?)
82        .add_middleware(HttpCacheMiddleware::builder().build()?)
83        .add_middleware(UserAgentMiddleware::builder().build()?)
84        .add_middleware(RobotsTxtMiddleware::new())
85        .add_middleware(
86            RefererMiddleware::new()
87                .same_origin_only(true)
88                .max_chain_length(100)
89                .include_fragment(false),
90        )
91        .with_checkpoint_path("output/quotes.bin")
92        .with_checkpoint_interval(Duration::from_secs(15))
93        .max_concurrent_downloads(5)
94        .max_parser_workers(2)
95        .max_concurrent_pipelines(2)
96        .build()
97        .await?;
98
99    crawler.start_crawl().await?;
100
101    Ok(())
102}

Source

pub fn with_checkpoint_path<P: AsRef<Path>>(self, path: P) -> Self

Enables checkpointing and sets the path for the checkpoint file.

Examples found in repository ?

examples/quotes_scraper.rs (line 91)

73async fn main() -> Result<(), SpiderError> {
74    tracing_subscriber::fmt()
75        .with_env_filter("info,spider_lib=debug")
76        .without_time()
77        .init();
78
79    let crawler = CrawlerBuilder::<_, ReqwestClientDownloader>::new(QuotesSpider)
80        .add_pipeline(DeduplicationPipeline::new(&["text"]))
81        .add_pipeline(CsvExporterPipeline::<QuoteItem>::new("output/quotes.csv")?)
82        .add_middleware(HttpCacheMiddleware::builder().build()?)
83        .add_middleware(UserAgentMiddleware::builder().build()?)
84        .add_middleware(RobotsTxtMiddleware::new())
85        .add_middleware(
86            RefererMiddleware::new()
87                .same_origin_only(true)
88                .max_chain_length(100)
89                .include_fragment(false),
90        )
91        .with_checkpoint_path("output/quotes.bin")
92        .with_checkpoint_interval(Duration::from_secs(15))
93        .max_concurrent_downloads(5)
94        .max_parser_workers(2)
95        .max_concurrent_pipelines(2)
96        .build()
97        .await?;
98
99    crawler.start_crawl().await?;
100
101    Ok(())
102}

Source

pub fn with_checkpoint_interval(self, interval: Duration) -> Self

Sets the interval for periodic checkpointing.

Examples found in repository ?

examples/quotes_scraper.rs (line 92)

73async fn main() -> Result<(), SpiderError> {
74    tracing_subscriber::fmt()
75        .with_env_filter("info,spider_lib=debug")
76        .without_time()
77        .init();
78
79    let crawler = CrawlerBuilder::<_, ReqwestClientDownloader>::new(QuotesSpider)
80        .add_pipeline(DeduplicationPipeline::new(&["text"]))
81        .add_pipeline(CsvExporterPipeline::<QuoteItem>::new("output/quotes.csv")?)
82        .add_middleware(HttpCacheMiddleware::builder().build()?)
83        .add_middleware(UserAgentMiddleware::builder().build()?)
84        .add_middleware(RobotsTxtMiddleware::new())
85        .add_middleware(
86            RefererMiddleware::new()
87                .same_origin_only(true)
88                .max_chain_length(100)
89                .include_fragment(false),
90        )
91        .with_checkpoint_path("output/quotes.bin")
92        .with_checkpoint_interval(Duration::from_secs(15))
93        .max_concurrent_downloads(5)
94        .max_parser_workers(2)
95        .max_concurrent_pipelines(2)
96        .build()
97        .await?;
98
99    crawler.start_crawl().await?;
100
101    Ok(())
102}

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.

Examples found in repository ?

examples/quotes_scraper.rs (line 96)

73async fn main() -> Result<(), SpiderError> {
74    tracing_subscriber::fmt()
75        .with_env_filter("info,spider_lib=debug")
76        .without_time()
77        .init();
78
79    let crawler = CrawlerBuilder::<_, ReqwestClientDownloader>::new(QuotesSpider)
80        .add_pipeline(DeduplicationPipeline::new(&["text"]))
81        .add_pipeline(CsvExporterPipeline::<QuoteItem>::new("output/quotes.csv")?)
82        .add_middleware(HttpCacheMiddleware::builder().build()?)
83        .add_middleware(UserAgentMiddleware::builder().build()?)
84        .add_middleware(RobotsTxtMiddleware::new())
85        .add_middleware(
86            RefererMiddleware::new()
87                .same_origin_only(true)
88                .max_chain_length(100)
89                .include_fragment(false),
90        )
91        .with_checkpoint_path("output/quotes.bin")
92        .with_checkpoint_interval(Duration::from_secs(15))
93        .max_concurrent_downloads(5)
94        .max_parser_workers(2)
95        .max_concurrent_pipelines(2)
96        .build()
97        .await?;
98
99    crawler.start_crawl().await?;
100
101    Ok(())
102}