hhhhh
wjdwekfe>>>>>
dsjfw<<<<dksfmjk owqkdo
` ``` 解析方式一： ``` const parser = new Parser.Parser({ onopentag(name, attributes) { console.info(`jsoup onopentag name --> ${name} attributes --> ${attributes}`) }, ontext(text) { console.info("jsoup text -->", text); }, onopentagname(name) { console.info("jsoup tagName -->", name); }, onattribute(name, value) { console.info(`jsoup attribName name --> ${name} value --> ${value}`) }, onclosetag(tagname) { console.info("jsoup closeTag --> ", tagname); }, }); parser.write(html); parser.end(); 或 const handler = new DomHandler((error, dom) => { if (error) { // Handle error } else { // Parsing completed, do something } }); const parser = new Parser.Parser(handler, { decodeEntities: true }); parser.write(html); parser.end(); ``` 解析方式二： ``` let dom: Document = Parser.parseDocument(html) ``` 3. 获取Html - 获取HTML文本方式一：通过URL获取HTML文本 ``` let httpRequest = http.createHttp() httpRequest.request('http://106.15.92.248/share/html.txt') .then((data) => { console.log("jsoup url html=" + JSON.stringify(data)) if (data.result && typeof data.result === 'string') { parser.write(data.result); parser.end(); } }) .catch((err) => { console.error('jsoup connect error:' + JSON.stringify(err)); }) ``` - 获取HTML文本方式二：通过文件流获取HTML文本 ``` var dom = Jsoup.parseHtmlFromFile(stream, html.length) ``` - 获取HTML文本方式三：通过rawfile获取HTML文本 ``` // 注意：需要先在MainAbility中为该变量赋值： globalThis.Context = this.context; if (!globalThis.Context) { console.log('jsoup global Context is undefined'); return; } var filePath = globalThis.Context.filesDir + '/testHtml.html'; globalThis.Context.resourceManager.getRawFile(filePath) .then((data) => { var textDecoder = new util.TextDecoder("utf-8", { ignoreBOM: true }) var result: string = textDecoder.decode(data, { stream: false }) console.log("jsoup getHtmlFromRawFile text=" + result); this.createFile(filePath); this.writeFile(filePath, result); }) .catch((err) => { console.log("jsoup getHtmlFromRawFile err=" + err) }) ``` - 获取HTML文本方式四：通过文件路径获取HTML文本 ``` if (!globalThis.Context) { console.log('jsoup global Context is undefined'); return; } var filePath = globalThis.Context.filesDir + '/testHtml.html'; fileio.readText(filePath) .then((data) => { console.log("jsoup getHtmlFromFilePath text=" + data); parser.write(data); parser.end(); }) .catch((err) => { console.log("jsoup getHtmlFromFilePath err=" + err) }) ``` 4. 提取HTML属性 ``` // 提取CSS Jsoup.parseCSS(html) ``` 对解析过的Dom对象进行提取操作： ``` // 根据标签名称获取元素 let element = DomUtils.getElementsByTagName('style', dom) // 获取文本 let text = DomUtils.getText(element) // 判断元素是否为tag let isTag = DomUtils.isTag(element[0]) // 判断元素是否为CDATA let isCDATA = DomUtils.isCDATA(element[0]) // 判断元素是否Text let isText = DomUtils.isText(element[0]) // 判断元素是否为Comment let isComment = DomUtils.isComment(element[0]) // 获取指定元素的子元素 let childrens = DomUtils.getChildren(body[0]) ``` 5. 清理HTML ``` const clean = SanitizeHtml('before
after', {
disallowedTagsMode: 'escape',
allowedTags: [],
allowedAttributes: false
})
```
## 接口说明
1. 解析字符串类型的HTML
方式一：
```
interface ParserOptions {
decodeEntities?: boolean;
lowerCaseTags?: boolean;
lowerCaseAttributeNames?: boolean;
recognizeCDATA?: boolean;
recognizeSelfClosing?: boolean;
}
interface Handler {
onparserinit(parser: Parser): void;
onreset(): void;
onend(): void;
onerror(error: Error): void;
onclosetag(name: string): void;
onopentagname(name: string): void;
onattribute(name: string, value: string, quote?: string | undefined | null): void;
onopentag(name: string, attribs: {
[s: string]: string;
}): void;
ontext(data: string): void;
oncomment(data: string): void;
oncdatastart(): void;
oncdataend(): void;
oncommentend(): void;
onprocessinginstruction(name: string, data: string): void;
}
const parser = new Parser.Parser(cbs: Partial