Struct ScrapeOptions 

pub struct ScrapeOptions {

    pub formats: Vec<Format>,
    pub headers: BTreeMap<String, String>,
    pub include_tags: Vec<String>,
    pub exclude_tags: Vec<String>,
    pub only_main_content: bool,
    pub timeout: Option<u64>,
    pub wait_for: u64,
    pub mobile: bool,
    pub actions: Vec<Value>,
    pub location: Option<Location>,
    pub parsers: Option<Value>,
    pub remove_base64_images: bool,
    pub block_ads: bool,
    pub proxy: Option<String>,
    pub egress: Option<String>,
    pub skip_tls_verification: Option<bool>,
    pub max_age: Option<u64>,
    pub min_age: Option<u64>,
    pub store_in_cache: bool,
    pub engine: Option<String>,
    pub discover_scripts: bool,
    pub if_none_match: Option<String>,
    pub if_modified_since: Option<String>,
    pub ignore_robots_txt: bool,
    pub store_snapshot: bool,
    pub query_filter: Option<QueryFilter>,
    pub chunking: Option<Value>,
}

单页抓取选项（Firecrawl 的 scrapeOptions）。

Fields

formats: Vec<Format>

headers: BTreeMap<String, String>

include_tags: Vec<String>

exclude_tags: Vec<String>

only_main_content: bool

timeout: Option<u64>

毫秒。

wait_for: u64

毫秒。

mobile: bool

actions: Vec<Value>

location: Option<Location>

parsers: Option<Value>

remove_base64_images: bool

block_ads: bool

proxy: Option<String>

basic、auto 放行，其余取值返回 UNSUPPORTED_OPTION。

egress: Option<String>

pagesift 扩展：走服务端配置的哪个命名出口（[[egress]]）。只用于 HTTP 抓取； 指定了出口时不升级到浏览器（浏览器不走这个出口，出口地址会不一致）。

skip_tls_verification: Option<bool>

Firecrawl 默认跳过 TLS 校验；pagesift 始终校验证书，这个字段只接受、不生效。

max_age: Option<u64>

毫秒。

min_age: Option<u64>

毫秒。

store_in_cache: bool

engine: Option<String>

http、browser、auto（默认）。

discover_scripts: bool

pagesift extension: bounded, stateless same-origin external JS discovery. Requires engine=http and links; never silently runs for ordinary scrapes.

if_none_match: Option<String>

if_modified_since: Option<String>

ignore_robots_txt: bool

单页抓取可以由调用方关闭 robots 检查（PRD F-2.4）。

store_snapshot: bool

query_filter: Option<QueryFilter>

只保留正文里和查询相关的段落（BM25），见 QueryFilter。不给时输出完整正文。

chunking: Option<Value>

pagesift 扩展：把（过滤后的）正文 Markdown 分块，结果在 chunks。例如 {"type": "recursive", "size": 400}（RAG 推荐）、{"type": "headings", "maxLevel": 2}、 {"type": "sliding_window", "window": 200, "step": 100}；策略见 pagesift-extract 的 ChunkStrategy。

Implementations

impl ScrapeOptions

pub fn wants(&self, kind: &str) -> bool

Trait Implementations

impl Clone for ScrapeOptions

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 ScrapeOptions

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

Formats the value using the given formatter.

impl Default for ScrapeOptions

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ScrapeOptions

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for ScrapeOptions

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for ScrapeOptions

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 ScrapeOptions