Struct CrawlRequest 

pub struct CrawlRequest {

    pub url: String,
    pub include_paths: Vec<String>,
    pub exclude_paths: Vec<String>,
    pub max_discovery_depth: Option<usize>,
    pub max_depth: Option<u64>,
    pub limit: usize,
    pub crawl_entire_domain: bool,
    pub allow_external_links: bool,
    pub allow_subdomains: Option<bool>,
    pub ignore_robots_txt: bool,
    pub sitemap: String,
    pub ignore_query_parameters: bool,
    pub delay: Option<f64>,
    pub max_concurrency: Option<usize>,
    pub scrape_options: ScrapeOptions,
    pub webhook: Option<Value>,
    pub query: Option<String>,
    pub adaptive: Option<AdaptiveOptions>,
    pub scope: Option<CrawlScope>,
    pub attachments: bool,
    pub attachment_limit: Option<usize>,
}

Fields

url: String

include_paths: Vec<String>

exclude_paths: Vec<String>

max_discovery_depth: Option<usize>

max_depth: Option<u64>

Firecrawl v1 的 maxDepth：只做上限校验，抓取深度仍看 maxDiscoveryDepth。

limit: usize

crawl_entire_domain: bool

allow_external_links: bool

allow_subdomains: Option<bool>

没给时：带 query 的爬取默认允许同一站点（可注册域名相同）的子域名，广度优先爬取不允许。

ignore_robots_txt: bool

sitemap: String

ignore_query_parameters: bool

delay: Option<f64>

Seconds.

max_concurrency: Option<usize>

scrape_options: ScrapeOptions

webhook: Option<Value>

query: Option<String>

adaptive: Option<AdaptiveOptions>

scope: Option<CrawlScope>

路径范围怎么定（PageSift 扩展）。crawlEntireDomain: true 等同于 domain。 不填时普通爬取是 auto，带查询的爬取是 domain（相关性打分决定往哪走，路径前缀只会挡路： 首页跳到 /top/ 的站点，招生页在 /inst/ 下）。

attachments: bool

带查询的爬取：相关页面上同站点的 PDF/Office 文档也抓回来解析（PageSift 扩展）。

attachment_limit: Option<usize>

附件的数量上限，默认等于 limit。

Trait Implementations

impl Clone for CrawlRequest

fn clone(&self) -> Self

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for CrawlRequest

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for CrawlRequest

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for CrawlRequest

fn eq(&self, other: &Self) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl Serialize for CrawlRequest

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for CrawlRequest