API

type Dictionary<T = any> = {
    [index: string]: T,
}

type Config = {
    maxNestedLevel?: number;

    fields?: Field;

    export?: ExportConfig;
}

type ExportConfig = {
    name: string;
}

type Field = Dictionary<Query>

type Query = string | {
    areaType?: string,
    area?: Selector,
    type?: string,
    selector?: Selector,
    fields?: Field,
    repeated?: boolean,
    recursive?: boolean,
    callback?: ((field: any) => any),
} | CallbackSelector

type CallbackSelector<I = any, O = any> = (content: I) => O | O[]

type Selector = string | RegExp | CallbackSelector

type UrlAbsoluteMatch = string

type UrlRegexMatch = RegExp

type UrlCallbackMatch = (url: string) => boolean

type UrlMatch = UrlAbsoluteMatch | UrlRegexMatch | UrlCallbackMatch

方法名	说明
registerExtractor(name: string, extractor: IExtractor): void	注册一个提取器
registerExporter(name: string, exporter: IExporter): void	注册一个导出器
findExtractor(name: string): IExtractor<any, I, O>	从已注册的提取器列表中获取指定名字的提取器
findExporter(name: string): IExporter<O>	从已注册的导出器列表中获取指定名字的导出器
findUrls(content: string): string[]	使用css:a[href] @href选择器从content中提取出所有的url
isUrlMatch(url: string, patterns: UrlMatch[]): boolean	判断指定的url是否满足任一UrlMatch模式
parseSelector(selector: string): { type: string, selector: string }	解析字符串形式的TypedSelector
fetchSingleField(type: string, selector: any, content: I): O	使用指定的选择器提取单个字段
fetchRepeatedField(type: string, selector: any, content: I): O[]	使用指定的选择器提取单个重复字段
extract(content: I, fields?: Field): O	从content中提取多个字段
export(data: O, name?: string): void	使用指定的或默认导出器导出数据

方法名	说明
extractOne(selector: T, content: I): O	提取单个字段
extractAll(selector: T, content: I): O[]	提取单个重复字段

方法名	说明
export(data: T, config: ExportConfig): void	导出数据