|
2 | 2 |
|
3 | 3 | English | <a href="#cn" style="text-decoration: none">简体中文</a>
|
4 | 4 |
|
5 |
| -Crawl is a Nodejs multifunctional crawler library. Provide configuration to batch fetch HTML, JSON, images, etc. |
| 5 | +XCrawl is a Nodejs multifunctional crawler library. Provide configuration to batch fetch HTML, JSON, images, etc. |
6 | 6 |
|
7 | 7 | ## Install
|
8 | 8 |
|
@@ -45,7 +45,7 @@ Create a crawler instance via new XCrawl.
|
45 | 45 | class XCrawl {
|
46 | 46 | private readonly baseConfig
|
47 | 47 | constructor(baseConfig?: IXCrawlBaseConifg)
|
48 |
| - fetch<T = any>(config: IFetchConfig): Promise<T> |
| 48 | + fetch<T = any>(config: IFetchConfig): Promise<IFetch<T>> |
49 | 49 | fetchFile(config: IFetchFileConfig): Promise<IFetchFile>
|
50 | 50 | fetchHTML(url: string): Promise<JSDOM>
|
51 | 51 | }
|
@@ -108,9 +108,9 @@ function fetchFile(config: IFetchFileConfig): Promise<IFetchFile>
|
108 | 108 |
|
109 | 109 | ```js
|
110 | 110 | const requestConifg = [
|
111 |
| - { url: '/xxxx', method: 'GET' }, |
112 |
| - { url: '/xxxx', method: 'GET' }, |
113 |
| - { url: '/xxxx', method: 'GET' } |
| 111 | + { url: '/xxxx' }, |
| 112 | + { url: '/xxxx' }, |
| 113 | + { url: '/xxxx' } |
114 | 114 | ]
|
115 | 115 |
|
116 | 116 | myXCrawl.fetchFile({
|
@@ -188,6 +188,16 @@ interface IFetchBaseConifg {
|
188 | 188 | }
|
189 | 189 | ```
|
190 | 190 |
|
| 191 | +- IFech |
| 192 | +
|
| 193 | +```ts |
| 194 | +type IFetch<T> = { |
| 195 | + statusCode: number | undefined |
| 196 | + headers: IncomingHttpHeaders // node:http |
| 197 | + data: T |
| 198 | +}[] |
| 199 | +``` |
| 200 | +
|
191 | 201 | - IFetchFile
|
192 | 202 |
|
193 | 203 | ```ts
|
@@ -238,7 +248,7 @@ If you have any **questions** or **needs** , please submit **Issues in** https:/
|
238 | 248 |
|
239 | 249 | <a href="#en" style="text-decoration: none">English</a> | 简体中文
|
240 | 250 |
|
241 |
| -Crawl 是 Nodejs 多功能爬虫库。提供配置即可批量抓取 HTML 、JSON、图片等等。 |
| 251 | +XCrawl 是 Nodejs 多功能爬虫库。提供配置即可批量抓取 HTML 、JSON、图片等等。 |
242 | 252 |
|
243 | 253 | ## 安装
|
244 | 254 |
|
@@ -281,7 +291,7 @@ docsXCrawl.fetchHTML('/zh/get-started').then((jsdom) => {
|
281 | 291 | class XCrawl {
|
282 | 292 | private readonly baseConfig
|
283 | 293 | constructor(baseConfig?: IXCrawlBaseConifg)
|
284 |
| - fetch<T = any>(config: IFetchConfig): Promise<T> |
| 294 | + fetch<T = any>(config: IFetchConfig): Promise<IFetch<T>> |
285 | 295 | fetchFile(config: IFetchFileConfig): Promise<IFetchFile>
|
286 | 296 | fetchHTML(url: string): Promise<JSDOM>
|
287 | 297 | }
|
@@ -344,9 +354,9 @@ function fetchFile(config: IFetchFileConfig): Promise<IFetchFile>
|
344 | 354 |
|
345 | 355 | ```js
|
346 | 356 | const requestConifg = [
|
347 |
| - { url: '/xxxx', method: 'GET' }, |
348 |
| - { url: '/xxxx', method: 'GET' }, |
349 |
| - { url: '/xxxx', method: 'GET' } |
| 357 | + { url: '/xxxx' }, |
| 358 | + { url: '/xxxx' }, |
| 359 | + { url: '/xxxx' } |
350 | 360 | ]
|
351 | 361 |
|
352 | 362 | myXCrawl.fetchFile({
|
@@ -424,6 +434,16 @@ interface IFetchBaseConifg {
|
424 | 434 | }
|
425 | 435 | ```
|
426 | 436 |
|
| 437 | +- IFetch |
| 438 | + |
| 439 | +```ts |
| 440 | +type IFetch<T> = { |
| 441 | + statusCode: number | undefined |
| 442 | + headers: IncomingHttpHeaders // node:http |
| 443 | + data: T |
| 444 | +}[] |
| 445 | +``` |
| 446 | + |
427 | 447 | - IFetchFile
|
428 | 448 |
|
429 | 449 | ```ts
|
|
0 commit comments