Struct RefererMiddleware

Source

pub struct RefererMiddleware {
    pub same_origin_only: bool,
    pub max_chain_length: usize,
    pub include_fragment: bool,
    /* private fields */
}

Expand description

Referer middleware that automatically sets Referer headers based on the navigation chain

Fields§

§same_origin_only: bool

Whether to use same-origin only referer

§max_chain_length: usize

Maximum referer chain length to keep in memory

§include_fragment: bool

Whether to include fragment in referer URL

Implementations§

Source §

impl RefererMiddleware

Source

pub fn new() -> Self

Create a new RefererMiddleware with default config

Examples found in repository ?

examples/quotes_scraper.rs (line 86)

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 same_origin_only(self, same_origin_only: bool) -> Self

Set whether to use same-origin only referer.

Examples found in repository ?

examples/quotes_scraper.rs (line 87)

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_chain_length(self, max_chain_length: usize) -> Self

Set the maximum referer chain length to keep in memory.

Examples found in repository ?

examples/quotes_scraper.rs (line 88)

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 include_fragment(self, include_fragment: bool) -> Self

Set whether to include the fragment in the referer URL.

Examples found in repository ?

examples/quotes_scraper.rs (line 89)

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}