获取数据工具
gpt-crawler 基于 LLM 的爬虫。配置项:
type Config = {
/** URL to start the crawl, if sitemap is provided then it will be used instead and download all pages in the sitemap */
url: string;
/** Pattern to match against for links on a page to subsequently crawl */
match: string;
/** Selector to grab the inner text from */
selector: string;
/** Don't crawl more than this many pages */
maxPagesToCrawl: number;
/** File name for the finished data */
outputFileName: string;
/** Optional resources to exclude
*
* @example
* ['png','jpg','jpeg','gif','svg','css','js','ico','woff','woff2','ttf','eot','otf','mp4','mp3','webm','ogg','wav','flac','aac','zip','tar','gz','rar','7z','exe','dmg','apk','csv','xls','xlsx','doc','docx','pdf','epub','iso','dmg','bin','ppt','pptx','odt','avi','mkv','xml','json','yml','yaml','rss','atom','swf','txt','dart','webp','bmp','tif','psd','ai','indd','eps','ps','zipx','srt','wasm','m4v','m4a','webp','weba','m4b','opus','ogv','ogm','oga','spx','ogx','flv','3gp','3g2','jxr','wdp','jng','hief','avif','apng','avifs','heif','heic','cur','ico','ani','jp2','jpm','jpx','mj2','wmv','wma','aac','tif','tiff','mpg','mpeg','mov','avi','wmv','flv','swf','mkv','m4v','m4p','m4b','m4r','m4a','mp3','wav','wma','ogg','oga','webm','3gp','3g2','flac','spx','amr','mid','midi','mka','dts','ac3','eac3','weba','m3u','m3u8','ts','wpl','pls','vob','ifo','bup','svcd','drc','dsm','dsv','dsa','dss','vivo','ivf','dvd','fli','flc','flic','flic','mng','asf','m2v','asx','ram','ra','rm','rpm','roq','smi','smil','wmf','wmz','wmd','wvx','wmx','movie','wri','ins','isp','acsm','djvu','fb2','xps','oxps','ps','eps','ai','prn','svg','dwg','dxf','ttf','fnt','fon','otf','cab']
*/
resourceExclusions?: string[];
/** Optional maximum file size in megabytes to include in the output file */
maxFileSize?: number;
/** Optional maximum number tokens to include in the output file */
maxTokens?: number;
};
学术论文
- arXiv。arXiv Xplorer 支持通过自然语言搜索。