11 | 12 | 13 | 14 | 15 | 16 | 17 | 18 | 19 | 20 | 21 | 22 | 23 | 24 | 25 | 26 | 27 | 28 | 29 | 40 | 41 | -------------------------------------------------------------------------------- /demo/test34.html: -------------------------------------------------------------------------------- 1 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | 13 | 14 | 15 | 16 | 17 | 18 | 19 | 20 | 21 | 22 | 23 | 24 | 25 | 29 |

30 |

31 |

32 |

33 | 34 | -------------------------------------------------------------------------------- /compare.js: -------------------------------------------------------------------------------- 1 | const fs = require('fs') 2 | const path = require('path') 3 | let parser = fs.readFileSync(path.resolve(__dirname, `./out/$parser.ast.json`), {encoding: 'utf-8'}) 4 | let browser = fs.readFileSync(path.resolve(__dirname, `./out/$browser.ast.json`), {encoding: 'utf-8'}) 5 | parser = JSON.parse(parser) 6 | browser = JSON.parse(browser) 7 | console.log(parser, browser) 8 | 9 | let count = browser.length > parser.length ? browser.length : parser.length; 10 | for (let i = 0; i < count; i++) { 11 | let a = browser[i] 12 | let b = parser[i] 13 | if (a === undefined) { 14 | debugger 15 | } 16 | if (a.tag.toLowerCase() !== b.tag) { 17 | let resta = [] 18 | let restb = [] 19 | let start = i - 10 < 0 ? 0 : i - 10 20 | for (let s = start; s < i; s++) { 21 | resta.push(browser[s]) 22 | restb.push(parser[s]) 23 | } 24 | resta.push(browser[i]) 25 | restb.push(parser[i]) 26 | for (let s = i; s < i + 10; s++) { 27 | resta.push(browser[s]) 28 | restb.push(parser[s]) 29 | } 30 | debugger 31 | 32 | } 33 | // console.log(browser[i] ? browser[i].tag : "undefined", parser[i] ? parser[i].tag : "undefined") 34 | // expect(browser[i].tag.toLowerCase()).toBe(parser[i].tag) 35 | // console.assert(browser[i].tag.toLowerCase() === parser[i].tag, `${browser[i] ? browser[i].tag : "undefined"}, ${parser[i] ? parser[i].tag : "undefined"}`) 36 | } 37 | -------------------------------------------------------------------------------- /test-server.js: -------------------------------------------------------------------------------- 1 | let http = require('http'); 2 | let url = require('url'); 3 | let util = require('util'); 4 | let fs = require('fs'); 5 | let path = require("path") 6 | const {spawn} = require('child_process'); 7 | const process = require("process"); 8 | 9 | const pour = (cmd, args, opts = { 10 | encoding: 'utf8' 11 | }, stdout = process.stdout, stderr = process.stderr) => { 12 | return new Promise((resolve, reject) => { 13 | const p = spawn(cmd, args, opts); 14 | p.stdout.setEncoding('utf-8'); 15 | p.stdout.on('data', data => { 16 | stdout.write(data, "utf8"); 17 | }); 18 | p.stderr.on('data', data => { 19 | stderr.write(data); 20 | }); 21 | p.on('close', code => { 22 | resolve(code); 23 | }); 24 | }); 25 | } 26 | 27 | async function exec(shell, args, opt) { 28 | console.log(`${shell} ${ 29 | args.join(" ") 30 | }`) 31 | await pour(shell, args, opt); 32 | } 33 | 34 | let server = http.createServer((req, res) => { 35 | var pathname = url.parse(req.url).pathname; // 获取url的pathname (/index.html) 36 | // console.log("file:" + pathname.substring(1)) // 将‘/’去掉 37 | // console.log(__dirname, __filename) 38 | let curPath = path.join(__dirname, pathname) 39 | // console.log(curPath) 40 | fs.readFile(curPath, function (err, data) { // fs模块加载文件 41 | if (err) { 42 | res.writeHead(404, {'Content-Type': 'text/html'}); 43 | } else { 44 | res.writeHead(200, {'Content-Type': 'text/html'}); 45 | res.write(data.toString()); 46 | } 47 | res.end(); 48 | }); 49 | 50 | }); 51 | 52 | server.listen(3000, '127.0.0.1', async () => { 53 | console.log("服务器已经运行，请打开浏览,输入:http://127.0.0.1:3000/ 来进行访问.") 54 | await exec(process.platform === 'win32' ? 'npm.cmd' : "npm", ["run", "test"]) 55 | process.exit(0); 56 | }); 57 | -------------------------------------------------------------------------------- /mycheck/check-dist.js: -------------------------------------------------------------------------------- 1 | const fs = require('fs') 2 | const path = require('path') 3 | const paser = require('../dist/index').paser 4 | 5 | let paths = [ 6 | "demo.html", 7 | "demo1.html", 8 | "demo2.html", 9 | "demo3.html", 10 | "demo4.html", 11 | "demo5.html", 12 | "test4.html", 13 | "test5.html", 14 | "test6.html", 15 | "test7.html", 16 | "test8.html", 17 | "MDN_HTML.html", 18 | "MDN_JavaScript.html", 19 | "CSDN.html", 20 | "CSDN_SPM.html", // error 21 | "test9.html", 22 | "test10.html", 23 | "test11.html", 24 | "test12.html", 25 | "test13.html", 26 | "test14.html", 27 | "test15.html", 28 | "test16.html", 29 | "test17.html", 30 | "test18.html", 31 | "test19.html", 32 | "test20.html", 33 | "test21.html", 34 | "test22.html", 35 | "test23.html", 36 | "google.html", 37 | "005055fd7e2625aba5e8d2d370ea4914a152fe50d16620f896cdf4b1a68ba741.html", 38 | "005055fd7e2625aba5e8d2d370ea4914a152fe50d16620f896cdf4b1a68ba741-origin.html", 39 | "039c4b966d1f2a0c589ac0aad211fe65500ad1cb58c7f45b34251db7056803ec-origin.html", 40 | "0475e5eeadaaca857eea3f36d0eda01937fe672d48be7f98ba6bc7f25ecd63d0.html", 41 | "078cdb456d1beb698aeed86e0f2161e442e9431c4580295f1ba4ece22741068c.html", 42 | "0e55dcdbeb54c88ee87942b9fef7ea5398fa9a1e83493d55844b479506a80fd8.html", 43 | "qidian.html", 44 | "test24.html", 45 | "test25.html", 46 | "test26.html", 47 | ] 48 | 49 | for (let p of paths) { 50 | let code = fs.readFileSync(path.resolve(__dirname, `../demo/${p}`), {encoding: 'utf-8'}) 51 | // console.log(code, 'code') 52 | if (code.length > 0) { 53 | console.time("test") 54 | let ast = paser(code) 55 | console.timeEnd("test") 56 | // console.log(__dirname, __filename) 57 | console.log(path.resolve(__dirname, "../out/", `./${p}.ast.json`)) 58 | fs.writeFileSync(path.resolve(__dirname, "../out/", `./${p}.ast.json`), JSON.stringify(ast, null, 4)) 59 | } 60 | } 61 | -------------------------------------------------------------------------------- /demo/test29.html: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | Document 8 | 9 | 10 | 11 | 第一百七十九章顶级秘法·28分钟前 14 |

15 | 16 | 17 | 第一百七十九章顶级秘法·28分钟前 20 |

21 | 22 | 123 23 | 第一百七十九章顶级秘法·28分钟前 26 |

27 |

28 | 第一百七十九章顶级秘法·28分钟前 31 |

32 |

33 | 第一百七十九章顶级秘法·28分钟前 36 | 37 | 38 | -------------------------------------------------------------------------------- /demo/test37.html: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | Document 8 | 9 | 10 | 11 | 13 |

43 |

44 | 生于1968年，程序员，使用python超过10年。长期从事数据处理工作，先后参与过风云系列卫星、碳卫星、海洋卫星、嫦娥探测器等卫星数据处理。

45 |

46 | 47 | 48 |

567

49 | 50 | 51 | -------------------------------------------------------------------------------- /server.js: -------------------------------------------------------------------------------- 1 | let http = require('http'); 2 | let url = require('url'); 3 | let util = require('util'); 4 | let fs = require('fs'); 5 | let path = require("path") 6 | const {spawn} = require('child_process'); 7 | const process = require("process"); 8 | const { URL, URLSearchParams } = require('url'); 9 | 10 | const pour = (cmd, args, opts = { 11 | encoding: 'utf8' 12 | }, stdout = process.stdout, stderr = process.stderr) => { 13 | return new Promise((resolve, reject) => { 14 | const p = spawn(cmd, args, opts); 15 | p.stdout.setEncoding('utf-8'); 16 | p.stdout.on('data', data => { 17 | stdout.write(data, "utf8"); 18 | }); 19 | p.stderr.on('data', data => { 20 | stderr.write(data); 21 | }); 22 | p.on('close', code => { 23 | resolve(code); 24 | }); 25 | }); 26 | } 27 | 28 | async function exec(shell, args, opt) { 29 | console.log(`${shell} ${ 30 | args.join(" ") 31 | }`) 32 | await pour(shell, args, opt); 33 | } 34 | 35 | let server = http.createServer((req, res) => { 36 | if (path.normalize(decodeURIComponent(req.url)) !== decodeURIComponent(req.url)) { 37 | res.statusCode = 403; 38 | res.end(); 39 | return; 40 | } 41 | const u = decodeURIComponent(req.url) 42 | console.log("decodeURIComponent",u) 43 | // var pathname = url.parse(u).pathname; // 获取url的pathname (/index.html) 44 | console.log("file:" + u.substring(1)) // 将‘/’去掉 45 | // console.log(__dirname, __filename) 46 | let curPath = path.join(__dirname, u.substring(1)) 47 | console.log(curPath) 48 | fs.readFile(curPath, function (err, data) { // fs模块加载文件 49 | if (err) { 50 | res.writeHead(404, {'Content-Type': 'text/html'}); 51 | } else { 52 | res.writeHead(200, {'Content-Type': 'text/html'}); 53 | res.write(data.toString()); 54 | } 55 | res.end(); 56 | }); 57 | 58 | }); 59 | 60 | server.listen(3000, '127.0.0.1', async () => { 61 | console.log("服务器已经运行，请打开浏览,输入:http://127.0.0.1:3000/ 来进行访问.") 62 | // await exec(process.platform === 'win32' ? 'npm.cmd' : "npm", ["run", "test"]) 63 | // process.exit(0); 64 | }); 65 | -------------------------------------------------------------------------------- /script/addSuffixJs.js: -------------------------------------------------------------------------------- 1 | const fs = require("fs").promises 2 | const path = require("path") 3 | 4 | void async function () { 5 | try { 6 | let p = path.resolve(__dirname, "../dist-esmodule") 7 | let paths = await fs.readdir(p) 8 | // console.log(paths) 9 | let stack = [... paths] 10 | while (stack.length) { 11 | let top = stack.pop() 12 | let pat = path.resolve(p, top) 13 | let stat = await fs.stat(pat) 14 | if (stat.isDirectory()) { 15 | let temp = await fs.readdir(pat) 16 | if (temp) { 17 | for (let i of temp) { 18 | stack.push(path.join(top, i)) 19 | } 20 | } 21 | } else { 22 | // console.log(pat) 23 | 24 | let personList = await fs.readFile(pat, {encoding: "utf8"}) 25 | 26 | var regexpNames = /(?:export|import)(?:\s)*?(?:\{)??.*?(?:\})??(?:\s)*?from(?:\s)*?"(.+?)"/gm 27 | 28 | var match = personList.matchAll(regexpNames); 29 | 30 | let count = 0 31 | for (let item of match) { 32 | if (/.js$/.test(item[1])) { 33 | continue 34 | } 35 | let temp = item[0] 36 | let index = item.index + count 37 | let now = temp.replace(item[1], `${ 38 | item[1] 39 | }.js`) 40 | let past = personList.slice(0, index) 41 | let feature = personList.slice(index + temp.length, personList.length) 42 | personList = `${past}${now}${feature}` 43 | count = count + 3 44 | } 45 | 46 | await fs.writeFile(pat, personList, {encoding: "utf8"}) 47 | } 48 | } 49 | // for (let item of paths) { 50 | // let pat = path.resolve(p, item) 51 | // console.log(pat) 52 | // let stat = await fs.stat(pat) 53 | // console.log(stat.isDirectory()) 54 | // } 55 | } catch (error) { 56 | console.log(error) 57 | } 58 | 59 | }() 60 | -------------------------------------------------------------------------------- /mycheck/check.ts: -------------------------------------------------------------------------------- 1 | const fs = require('fs') 2 | const path = require('path') 3 | import { paser } from '../src/index' 4 | 5 | let paths = [ 6 | // "demo.html", 7 | // "demo1.html", 8 | // "demo2.html", 9 | // "demo3.html", 10 | // "demo4.html", 11 | // "demo5.html", 12 | // "test4.html", 13 | // "test5.html", 14 | // "test6.html", 15 | // "test7.html", 16 | // "test8.html", 17 | // "MDN_HTML.html", 18 | // "MDN_JavaScript.html", 19 | // "CSDN.html", 20 | // "CSDN_SPM.html", 21 | // "test9.html", 22 | // "test10.html", 23 | // "test11.html", 24 | // "test12.html", 25 | // "test13.html", 26 | // "test14.html", 27 | // "test15.html", 28 | // "test16.html", 29 | // "test17.html", 30 | // "test18.html", 31 | // "test19.html", 32 | // "test20.html", 33 | // "test21.html", 34 | // "test22.html", 35 | // "test23.html", 36 | // "google.html", 37 | // "005055fd7e2625aba5e8d2d370ea4914a152fe50d16620f896cdf4b1a68ba741.html", 38 | // "005055fd7e2625aba5e8d2d370ea4914a152fe50d16620f896cdf4b1a68ba741-origin.html", 39 | // "039c4b966d1f2a0c589ac0aad211fe65500ad1cb58c7f45b34251db7056803ec-origin.html", 40 | // "0475e5eeadaaca857eea3f36d0eda01937fe672d48be7f98ba6bc7f25ecd63d0.html", 41 | // "078cdb456d1beb698aeed86e0f2161e442e9431c4580295f1ba4ece22741068c.html", 42 | // "0e55dcdbeb54c88ee87942b9fef7ea5398fa9a1e83493d55844b479506a80fd8.html", 43 | // "qidian.html", 44 | // "test24.html", 45 | // "test25.html", 46 | // "test26.html", 47 | // "qidian1.html", 48 | // "test27.html", 49 | // "test28.html", 50 | // "test30.html", 51 | // "test31.html", 52 | // "test32.html", 53 | // "test33.html", 54 | // "test34.html", 55 | // "test35.html", 56 | // "test36.html", 57 | // "test38.html", 58 | // "test40.html", 59 | ] 60 | 61 | for (let p of paths) { 62 | let code = fs.readFileSync(path.resolve(__dirname, `../demo/${p}`), { encoding: 'utf-8' }) 63 | // console.log(code, 'code') 64 | if (code.length > 0) { 65 | // console.time("test") 66 | let ast = paser(code, true) 67 | // console.timeEnd("test") 68 | // console.log(__dirname, __filename) 69 | console.log(path.resolve(__dirname, "../out/", `./${p}.ast.json`)) 70 | fs.writeFileSync(path.resolve(__dirname, "../out/", `./${p}.ast.json`), JSON.stringify(ast, null, 4)) 71 | } 72 | } 73 | -------------------------------------------------------------------------------- /demo/test18.html: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | Document 8 | 9 | 10 |

13 | Tweet 17 |

26 | 27 | 30 |
Share 33 | this
35 | 37 | 38 |
Email 41 |
Print 44 |

46 | 47 | -------------------------------------------------------------------------------- /demo/test16.html: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | Document 8 | 9 | 10 | 11 | 12 | 17 | 23 | 24 | 25 | 26 | 27 | -------------------------------------------------------------------------------- /test/test25.spec.ts: -------------------------------------------------------------------------------- 1 | import { test, expect } from '@playwright/test'; 2 | const request = require("request-promise") 3 | import { parse } from '../src/parser' 4 | 5 | function getAll(source, type) { 6 | let current = source; 7 | let res = [] 8 | let stack = Array.isArray(current) ? current : [current]; 9 | while (stack.length) { 10 | let top = stack.pop(); 11 | // console.log([top]) 12 | if (type === "browser") { 13 | if (top.nodeName === "#comment") { 14 | continue 15 | } 16 | if (top.nodeName === "#text" && /[\r\n]+/.test(top.data)) { 17 | continue 18 | } 19 | res.push({ tag: top.tagName ? top.tagName : "text", content: top.data }) 20 | } else if (type === "parser") { 21 | if (top.type === "comment") { 22 | continue 23 | } 24 | if (top.type === "text" && /[\r\n]+/.test(top.content)) { 25 | continue 26 | } 27 | res.push({ tag: top.tag ? top.tag : "text", content: top.content }) 28 | } 29 | if (top.childNodes) { 30 | stack.push(...top.childNodes) 31 | } else if (top.children) { 32 | stack.push(...top.children) 33 | } 34 | } 35 | return res 36 | } 37 | 38 | test('test25.html', async ({ page }) => { 39 | // encodeURIComponent 40 | let url = "http://127.0.0.1:3000/demo/test25.html" 41 | await page.goto(url, { 42 | referer: "", 43 | // timeout: 30, 44 | waitUntil: "domcontentloaded" 45 | }); 46 | 47 | await page.evaluateHandle(`document.body.classList.add("body")`) 48 | 49 | // const name = await page.innerText('title'); 50 | // expect(name).toBe('Document'); 51 | // const elementHandle = await page.$('body'); 52 | // console.log(elementHandle) 53 | // const bodyElement = elementHandle.asElement() 54 | // console.log(bodyElement) 55 | 56 | // const aHandle = await page.evaluateHandle('document'); 57 | // console.log(aHandle) 58 | 59 | // const aHandle = await page.evaluateHandle(() => document.body); 60 | // let doc = await aHandle.jsonValue() 61 | // console.log(doc) 62 | // const resultHandle = await page.evaluateHandle(body => body.innerHTML, aHandle); 63 | // const jsonValue = await resultHandle.jsonValue() 64 | // console.log(jsonValue); 65 | // await resultHandle.dispose(); 66 | 67 | const aHandle = await page.evaluateHandle(`(${getAll.toString()})(Array.from(document.childNodes),"browser")`); 68 | // console.log(aHandle) 69 | const browser: any = await aHandle.jsonValue() 70 | 71 | let html = await request({ 72 | method: "GET", 73 | uri: url, 74 | headers: { 75 | "Accept": "*/*", 76 | "Accept-Encoding": "deflate, br", 77 | "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6", 78 | "Connection": "keep-alive", 79 | "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36 Edg/91.0.864.59", 80 | }, 81 | }) 82 | 83 | let ast = parse(html) 84 | 85 | // let body = search(ast, "body") 86 | 87 | let parser = getAll(ast.children, "parser") 88 | 89 | // console.log(browser, parser) 90 | let count = browser.length > parser.length ? browser.length : parser.length; 91 | for (let i = 0; i < count; i++) { 92 | // console.log(browser[i] ? browser[i].tag : "undefined", parser[i] ? parser[i].tag : "undefined") 93 | expect(browser[i].tag.toLowerCase()).toBe(parser[i].tag) 94 | // console.assert(browser[i].tag.toLowerCase() === parser[i].tag, `${browser[i] ? browser[i].tag : "undefined"}, ${parser[i] ? parser[i].tag : "undefined"}`) 95 | } 96 | }); -------------------------------------------------------------------------------- /test/test26.spec.ts: -------------------------------------------------------------------------------- 1 | import { test, expect } from '@playwright/test'; 2 | const request = require("request-promise") 3 | import { parse } from '../src/parser' 4 | 5 | function getAll(source, type) { 6 | let current = source; 7 | let res = [] 8 | let stack = Array.isArray(current) ? current : [current]; 9 | while (stack.length) { 10 | let top = stack.pop(); 11 | // console.log([top]) 12 | if (type === "browser") { 13 | if (top.nodeName === "#comment") { 14 | continue 15 | } 16 | if (top.nodeName === "#text" && /[\r\n]+/.test(top.data)) { 17 | continue 18 | } 19 | res.push({ tag: top.tagName ? top.tagName : "text", content: top.data }) 20 | } else if (type === "parser") { 21 | if (top.type === "comment") { 22 | continue 23 | } 24 | if (top.type === "text" && /[\r\n]+/.test(top.content)) { 25 | continue 26 | } 27 | res.push({ tag: top.tag ? top.tag : "text", content: top.content }) 28 | } 29 | if (top.childNodes) { 30 | stack.push(...top.childNodes) 31 | } else if (top.children) { 32 | stack.push(...top.children) 33 | } 34 | } 35 | return res 36 | } 37 | 38 | test('test26.html', async ({ page }) => { 39 | // encodeURIComponent 40 | let url = "http://127.0.0.1:3000/demo/test26.html" 41 | await page.goto(url, { 42 | referer: "", 43 | // timeout: 30, 44 | waitUntil: "domcontentloaded" 45 | }); 46 | 47 | await page.evaluateHandle(`document.body.classList.add("body")`) 48 | 49 | // const name = await page.innerText('title'); 50 | // expect(name).toBe('Document'); 51 | // const elementHandle = await page.$('body'); 52 | // console.log(elementHandle) 53 | // const bodyElement = elementHandle.asElement() 54 | // console.log(bodyElement) 55 | 56 | // const aHandle = await page.evaluateHandle('document'); 57 | // console.log(aHandle) 58 | 59 | // const aHandle = await page.evaluateHandle(() => document.body); 60 | // let doc = await aHandle.jsonValue() 61 | // console.log(doc) 62 | // const resultHandle = await page.evaluateHandle(body => body.innerHTML, aHandle); 63 | // const jsonValue = await resultHandle.jsonValue() 64 | // console.log(jsonValue); 65 | // await resultHandle.dispose(); 66 | 67 | const aHandle = await page.evaluateHandle(`(${getAll.toString()})(Array.from(document.childNodes),"browser")`); 68 | // console.log(aHandle) 69 | const browser: any = await aHandle.jsonValue() 70 | 71 | let html = await request({ 72 | method: "GET", 73 | uri: url, 74 | headers: { 75 | "Accept": "*/*", 76 | "Accept-Encoding": "deflate, br", 77 | "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6", 78 | "Connection": "keep-alive", 79 | "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36 Edg/91.0.864.59", 80 | }, 81 | }) 82 | 83 | let ast = parse(html) 84 | 85 | // let body = search(ast, "body") 86 | 87 | let parser = getAll(ast.children, "parser") 88 | 89 | // console.log(browser, parser) 90 | let count = browser.length > parser.length ? browser.length : parser.length; 91 | for (let i = 0; i < count; i++) { 92 | // console.log(browser[i] ? browser[i].tag : "undefined", parser[i] ? parser[i].tag : "undefined") 93 | expect(browser[i].tag.toLowerCase()).toBe(parser[i].tag) 94 | // console.assert(browser[i].tag.toLowerCase() === parser[i].tag, `${browser[i] ? browser[i].tag : "undefined"}, ${parser[i] ? parser[i].tag : "undefined"}`) 95 | } 96 | }); -------------------------------------------------------------------------------- /demo/test25.html: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | Document 8 | 9 | 10 | 11 | 12 | 13 | 18 | 24 | 25 | 26 | -------------------------------------------------------------------------------- /test/test24.spec.ts: -------------------------------------------------------------------------------- 1 | import { test, expect } from '@playwright/test'; 2 | import { webkit } from 'playwright' 3 | const request = require("request-promise") 4 | import { parse } from '../src/parser' 5 | 6 | function getAll(source, type) { 7 | let current = source; 8 | let res = [] 9 | let stack = Array.isArray(current) ? current : [current]; 10 | while (stack.length) { 11 | let top = stack.pop(); 12 | // console.log([top]) 13 | if (type === "browser") { 14 | if (top.nodeName === "#comment") { 15 | continue 16 | } 17 | if (top.nodeName === "#text" && /[\r\n]+/.test(top.data)) { 18 | continue 19 | } 20 | res.push({ tag: top.tagName ? top.tagName : "text", content: top.data }) 21 | } else if (type === "parser") { 22 | if (top.type === "comment") { 23 | continue 24 | } 25 | if (top.type === "text" && /[\r\n]+/.test(top.content)) { 26 | continue 27 | } 28 | res.push({ tag: top.tag ? top.tag : "text", content: top.content }) 29 | } 30 | if (top.childNodes) { 31 | stack.push(...top.childNodes) 32 | } else if (top.children) { 33 | stack.push(...top.children) 34 | } 35 | } 36 | return res 37 | } 38 | 39 | test('test24.html', async (/*{ page }*/) => { 40 | // encodeURIComponent 41 | let url = "http://127.0.0.1:3000/demo/test24.html" 42 | const web = await webkit.launch(); 43 | const context = await web.newContext({ 44 | javaScriptEnabled: false 45 | }); 46 | const newpage = await context.newPage(); 47 | await newpage.goto(url, { 48 | referer: "", 49 | // timeout: 30, 50 | waitUntil: "domcontentloaded" 51 | }); 52 | 53 | await newpage.evaluateHandle(`document.body.classList.add("body")`) 54 | 55 | // const name = await page.innerText('title'); 56 | // expect(name).toBe('Document'); 57 | // const elementHandle = await page.$('body'); 58 | // console.log(elementHandle) 59 | // const bodyElement = elementHandle.asElement() 60 | // console.log(bodyElement) 61 | 62 | // const aHandle = await page.evaluateHandle('document'); 63 | // console.log(aHandle) 64 | 65 | // const aHandle = await page.evaluateHandle(() => document.body); 66 | // let doc = await aHandle.jsonValue() 67 | // console.log(doc) 68 | // const resultHandle = await page.evaluateHandle(body => body.innerHTML, aHandle); 69 | // const jsonValue = await resultHandle.jsonValue() 70 | // console.log(jsonValue); 71 | // await resultHandle.dispose(); 72 | 73 | const aHandle = await newpage.evaluateHandle(`(${getAll.toString()})(Array.from(document.childNodes),"browser")`); 74 | // console.log(aHandle) 75 | const browser: any = await aHandle.jsonValue() 76 | 77 | let html = await request({ 78 | method: "GET", 79 | uri: url, 80 | headers: { 81 | "Accept": "*/*", 82 | "Accept-Encoding": "deflate, br", 83 | "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6", 84 | "Connection": "keep-alive", 85 | "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36 Edg/91.0.864.59", 86 | }, 87 | }) 88 | 89 | let ast = parse(html) 90 | 91 | // let body = search(ast, "body") 92 | 93 | let parser = getAll(ast.children, "parser") 94 | 95 | // console.log(browser, parser) 96 | let count = browser.length > parser.length ? browser.length : parser.length; 97 | for (let i = 0; i < count; i++) { 98 | // console.log(browser[i] ? browser[i].tag : "undefined", parser[i] ? parser[i].tag : "undefined") 99 | expect(browser[i].tag.toLowerCase()).toBe(parser[i].tag) 100 | // console.assert(browser[i].tag.toLowerCase() === parser[i].tag, `${browser[i] ? browser[i].tag : "undefined"}, ${parser[i] ? parser[i].tag : "undefined"}`) 101 | } 102 | }); -------------------------------------------------------------------------------- /demo/test31.html: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | Document 8 | 9 | 10 |

11 |

12 |

13 |

Found a problem with this page?

14 |

Source on GitHub
Report a problem with this content on 21 | GitHub
Want to fix the problem yourself? See 23 | our Contribution guide.

26 |

27 |

Last modified: Jul 9, 2021, 29 | by MDN contributors

30 | 49 |

50 |

51 | 52 | -------------------------------------------------------------------------------- /demo/test19.html: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | Document 8 | 9 | 10 |

11 |

12 |

>A federal appeals court has dealt the Obama administration yet another blow in its quest to keep at least 13 | some age restrictions on the sale of emergency contraceptive pills.

14 |

In a three-paragraph 16 | order, a three-judge panel for the United States Court of Appeals for the 2nd Circuit ruled that 17 | although the government's appeal of a lower 19 | court decision removing all age restrictions on morning-after pills is still pending, at least some 20 | medications must be made available over the counter immediately.

21 |

Specifically, the panel said that while the requirement for one-pill versions of the morning-after pill to be 22 | made available without age restrictions can be delayed while the appeal is considered, that is not the case 23 | for "two-pill variants," which include generic products Next Choice and other levonorgestral tablets.

26 |

Ironically, the FDA had sought to produce a compromise by approving 28 | in late April an over-the-counter version of Plan B 29 | One-Step, a one-pill version that would be available on pharmacy shelves but only to those 15 and 30 | over who are able to produce proper identification.

31 |

But Plan B One-Step costs 33 | in the neighborhood of $50, while the generic two-pill formulations cost about $20 to $35.

35 |

The saga of trying to move emergency contraception from a prescription-only to an over-the-counter product 36 | has been ongoing for more than a decade through two successive presidential administrations.

37 |

U.S. District Court Judge Edward Korman, who has overseen the case since 2005, has made it clear that he 38 | thinks the government has dragged its feet to the point of violating the law.

39 |

But few expected the New York-based appeals court to agree with Korman, even in part, by denying the 40 | government's request to stay his April 6 order while the appeal is being heard.

41 |

The government — via the Departments of Justice and Health and Human Services — had no immediate comment on 42 | the ruling. Representatives would say only that they were "reviewing the order" from the appeals court.

43 |

Those who have been pursuing the case, however, had a bit more to say.

44 |

"Today's decision from the 2nd Circuit marks an historic day for women's health," said Nancy Northup, 45 | president and CEO of the Center for Reproductive Rights, which 46 | has represented some of the plaintiffs in the lawsuit. "Finally, after more than a decade of politically 47 | motivated delays, women will no longer have to endure intrusive, onerous and medically unnecessary 48 | restrictions to get emergency contraception."

49 |

What happens next remains unclear. Some lawyers say the government might be able to appeal to the full 2nd 50 | Circuit. But more likely, if they insist on fighting, government attorneys would have to seek relief from 51 | the Supreme Court justice who oversees the 2nd Circuit — Ruth Bader Ginsburg.

52 |

54 |

55 |

56 |

57 |

58 | 59 | -------------------------------------------------------------------------------- /src/parser/Html.ts: -------------------------------------------------------------------------------- 1 | import { Lexer, TOKEN_EQUAL, TOKEN_LEFT_PAREN, TOKEN_NAME, TOKEN_QUOTE, TOKEN_RIGHT_PAREN, TOKEN_SELF_CLOSE, TOKEN_SINGLE_QUOTE } from "../lexer"; 2 | 3 | export interface Node { 4 | LineNum?: number, 5 | children?: Array, 6 | attr: Array, 7 | type?: string, 8 | tag?: string, 9 | selfClose?: boolean, 10 | parent?: any, 11 | } 12 | 13 | let temp = Symbol("temp") 14 | let nextSibling = temp 15 | 16 | export class Node { 17 | constructor() { 18 | this.children = [] 19 | this.attr = [] 20 | } 21 | get nextSibling() { 22 | if (nextSibling !== temp) return nextSibling 23 | if (!this.parent) return null 24 | let lengtn = this.parent.children.length 25 | let index = -1 26 | for (let item of this.parent.children) { 27 | index++ 28 | if (item === this) { 29 | break 30 | } 31 | } 32 | if (index + 1 > lengtn) { 33 | return null 34 | } 35 | return this.parent.children[index + 1] 36 | } 37 | 38 | set nextSibling(value: any) { 39 | nextSibling = value 40 | } 41 | } 42 | 43 | export function parseTag(lexer: Lexer) { 44 | return lexer.NextTokenIs(TOKEN_NAME).nowToken; // tag_name 45 | } 46 | 47 | export function parseName(lexer: Lexer, node: any) { 48 | let attrReg = /[^\s"'>/=[\u0000-\u001f]+/.exec(lexer.sourceCode) 49 | let name = "" 50 | if (attrReg) { 51 | name = attrReg[0] 52 | } 53 | if (name.includes("<")) { 54 | /* 55 | 57 | 58 |

Unlock all the features

25 | $2.99 26 |
27 | Monthly 28 | Annual Billing 29 |

30 |

31 | Upgrade Now 32 |

33 |

34 | 42 |

43 |

44 | 45 | 46 | 47 | 50 | 51 | 52 | 53 | 56 | 57 | 58 | 59 | 62 | 63 | 64 | 65 | 68 | 69 | 70 | 71 | 74 | 75 | 76 | 77 | 80 | 81 | 82 |

48 \| Pro Version Features: 49 \|
	54 \| Unlimited Words for non-stop Listening 55 \|
	60 \| Read Text in 27 Different Languages 61 \|
	66 \| Read Text at 21 Different Speed Settings 67 \|
	72 \| Autoplay Text - Fast and Easy 73 \|
	78 \| Automatic Language Detection 79 \|

contentText

101 | //

contentText

102 | // contentText 103 | //

contentText
||

contentText
104 | let stack = lexer.stack 105 | const length = stack.length 106 | if (isClose(lexer) && 107 | length >= 4 && 108 | stack[length - 2].tokenType === TOKEN_RIGHT_PAREN /*>*/ && 109 | stack[length - 3].tokenType === TOKEN_NAME /*name*/ && 110 | stack[length - 4].tokenType === TOKEN_LEFT_PAREN /*<*/ 111 | ) { 112 | // 118 | */ 119 | let script = ["", ""] 120 | if (script.includes(lexer.sourceCode.slice(0, script[0].length))) { 121 | return false 122 | } else { 123 | return true 124 | } 125 | } 126 | // noscript 127 | // if (lexer.stack[length - 3].token === "noscript") { 128 | // /* 129 | // 132 | // */ 133 | // let script = "" 134 | // if (lexer.sourceCode.slice(0, script.length) === script) { 135 | // return false 136 | // } else { 137 | // return true 138 | // } 139 | // } 140 | judgeEnd(lexer) 141 | } 142 | //

contentText

143 | //

contentText 144 | //

contentText

145 | //

contentText
146 | if (isClose(lexer) && 147 | length >= 4 && 148 | stack[length - 2].tokenType === TOKEN_RIGHT_PAREN /*>*/ && 149 | stack[length - 3].tokenType === TOKEN_NAME /*name*/ && 150 | stack[length - 4].tokenType === TOKEN_CLOSE /*contentText

155 | //
contentText 156 | //
contentText

157 | //
contentText
158 | 159 | if (isClose(lexer) && 160 | length >= 4 && 161 | stack[length - 2].tokenType === TOKEN_SELF_CLOSE /*self-close />
*/ && 162 | stack[length - 3].tokenType === TOKEN_NAME /*name*/ && 163 | stack[length - 4].tokenType === TOKEN_LEFT_PAREN /*<*/ 164 | ) { 165 | judgeEnd(lexer) 166 | } 167 | 168 | // contentText

169 | // contentText 170 | // contentText

171 | // contentText
172 | if (isClose(lexer) && 173 | stack[length - 2].tokenType === COMMENT /*COMMENT*/ 174 | ) { 175 | judgeEnd(lexer) 176 | } 177 | 178 | // contentText

179 | // contentText

180 | // contentText 181 | // contentText
182 | if (isClose(lexer) && 183 | stack[length - 2].tokenType === TOKEN_DTD /*DTD*/ 184 | ) { 185 | judgeEnd(lexer) 186 | } 187 | 188 | /*contentText

*/ 189 | /*contentText || */ 191 | /*contentText
*/ 192 | if (stack[length - 1].tokenType === TOKEN_CONTENT_TEXT /*contentText*/) { 193 | if ((lexer.sourceCode[0] === "<" && 194 | regexName.test(lexer.sourceCode[1])) /*contentText

*/ || 195 | lexer.sourceCode.slice(0, 2) === " || */ 197 | ) { 198 | return false 199 | } else { 200 | /*contentText
*/ 201 | if ((lexer.sourceCode[0] === "<" 202 | && regexName.test(lexer.sourceCode[1]))) { 203 | let parseRes = parseHtml(lexer) 204 | if (parseRes.selfClose) { 205 | return false 206 | } 207 | } 208 | return true 209 | } 210 | } 211 | 212 | 213 | // return true 214 | throw new Error(`not find contentEnd! at line ${lexer.GetLineNum()} ${lexer.sourceCode.slice(0, 100)}`) 215 | 216 | } 217 | 218 | export function parseText(lexer: Lexer) { 219 | lexer.hasCache = false 220 | let node = new Node() 221 | if (!lexer.check) { 222 | node.nextSibling = null 223 | } 224 | 225 | // lexer.isIgnored(); 226 | node.LineNum = lexer.GetLineNum() 227 | 228 | let content = "" 229 | while (contentEnd(lexer) && !lexer.isEmpty()) { 230 | if (lexer.nextSourceCodeIs("\r\n") || lexer.nextSourceCodeIs("\n\r")) { 231 | lexer.lineNum += 1 232 | content += lexer.sourceCode.slice(0, 2) 233 | lexer.skipSourceCode(2) 234 | } else { 235 | if (lexer.isNewLine(lexer.sourceCode[0])) { 236 | lexer.lineNum += 1 237 | content += lexer.sourceCode[0] 238 | lexer.skipSourceCode(1) 239 | } else { 240 | content += lexer.sourceCode[0] 241 | lexer.skipSourceCode(1) 242 | } 243 | } 244 | } 245 | 246 | if ( 247 | lexer.stack.length >= 3 && 248 | isSpecialTag({ tag: lexer.stack[lexer.stack.length - 3].token })) { 249 | let token = lexer.stack[lexer.stack.length - 3].token 250 | let tokenLen = ``.length 251 | if (lexer.sourceCode.slice(0, tokenLen) === ``) { 252 | lexer.skipSourceCode(2) 253 | let res = { lineNum: lexer.lineNum, tokenType: TOKEN_CLOSE, token: " lengtn) { 27 | return null; 28 | } 29 | return this.parent.children[index + 1]; 30 | } 31 | set nextSibling(value) { 32 | nextSibling = value; 33 | } 34 | } 35 | exports.Node = Node; 36 | function isClose(lexer) { 37 | const length = lexer.stack.length; 38 | const topTwo = length >= 2 ? lexer.stack[length - 2].tokenType : ""; 39 | const isTOKEN_DTD = topTwo === lexer_1.TOKEN_DTD; 40 | const isCOMMENT = topTwo === lexer_1.COMMENT; 41 | if (length >= 2 && 42 | (isTOKEN_DTD /*dtd*/ || 43 | isCOMMENT /*comment*/)) { 44 | return true; 45 | } 46 | if (length < 4) 47 | return false; 48 | const topThree = lexer.stack[length - 3].tokenType; 49 | const topFour = lexer.stack[length - 4].tokenType; 50 | const isTOKEN_RIGHT_PAREN = topTwo === lexer_1.TOKEN_RIGHT_PAREN; 51 | const isTOKEN_NAME = topThree === lexer_1.TOKEN_NAME; 52 | // 53 | let one = isTOKEN_RIGHT_PAREN /*>*/ && 54 | isTOKEN_NAME /*tag_name*/ && 55 | topFour === lexer_1.TOKEN_CLOSE /* 57 | let close = isTOKEN_RIGHT_PAREN /*>*/ && 58 | topThree === lexer_1.TOKEN_NAME /*tag_name*/ && 59 | topFour === lexer_1.TOKEN_LEFT_PAREN /*<*/; 60 | // /> 61 | let selfClose = topTwo === lexer_1.TOKEN_SELF_CLOSE; // />
62 | return one || close || selfClose; 63 | } 64 | exports.isClose = isClose; 65 | /* 66 | 提取出来的公共代码 67 | */ 68 | function judgeEnd(lexer) { 69 | if (lexer.sourceCode.slice(0, 2) === "*/ || 70 | lexer.sourceCode.slice(0, 2) === " || */) { 73 | return false; 74 | } 75 | else { 76 | /*在这里是什么特征看调用函数的注释部分contentText
*/ 77 | if ((lexer.sourceCode[0] === "<" 78 | && lexer_1.regexName.test(lexer.sourceCode[1]))) { 79 | let parseRes = Html_1.parseHtml(lexer); 80 | if (parseRes.selfClose) { 81 | return false; 82 | } 83 | } 84 | return true; 85 | } 86 | } 87 | function contentEnd(lexer) { 88 | //

contentText

89 | //

contentText

90 | // contentText 91 | //

contentText
||

contentText
92 | let stack = lexer.stack; 93 | const length = stack.length; 94 | if (isClose(lexer) && 95 | length >= 4 && 96 | stack[length - 2].tokenType === lexer_1.TOKEN_RIGHT_PAREN /*>*/ && 97 | stack[length - 3].tokenType === lexer_1.TOKEN_NAME /*name*/ && 98 | stack[length - 4].tokenType === lexer_1.TOKEN_LEFT_PAREN /*<*/) { 99 | // 105 | */ 106 | let script = ["", ""]; 107 | if (script.includes(lexer.sourceCode.slice(0, script[0].length))) { 108 | return false; 109 | } 110 | else { 111 | return true; 112 | } 113 | } 114 | // noscript 115 | // if (lexer.stack[length - 3].token === "noscript") { 116 | // /* 117 | // 120 | // */ 121 | // let script = "" 122 | // if (lexer.sourceCode.slice(0, script.length) === script) { 123 | // return false 124 | // } else { 125 | // return true 126 | // } 127 | // } 128 | judgeEnd(lexer); 129 | } 130 | //

contentText

131 | //

contentText 132 | //

contentText

133 | //

contentText
134 | if (isClose(lexer) && 135 | length >= 4 && 136 | stack[length - 2].tokenType === lexer_1.TOKEN_RIGHT_PAREN /*>*/ && 137 | stack[length - 3].tokenType === lexer_1.TOKEN_NAME /*name*/ && 138 | stack[length - 4].tokenType === lexer_1.TOKEN_CLOSE /*contentText

142 | //
contentText 143 | //
contentText

144 | //
contentText
145 | if (isClose(lexer) && 146 | length >= 4 && 147 | stack[length - 2].tokenType === lexer_1.TOKEN_SELF_CLOSE /*self-close />
*/ && 148 | stack[length - 3].tokenType === lexer_1.TOKEN_NAME /*name*/ && 149 | stack[length - 4].tokenType === lexer_1.TOKEN_LEFT_PAREN /*<*/) { 150 | judgeEnd(lexer); 151 | } 152 | // contentText

153 | // contentText 154 | // contentText

155 | // contentText
156 | if (isClose(lexer) && 157 | stack[length - 2].tokenType === lexer_1.COMMENT /*COMMENT*/) { 158 | judgeEnd(lexer); 159 | } 160 | // contentText

161 | // contentText

162 | // contentText 163 | // contentText
164 | if (isClose(lexer) && 165 | stack[length - 2].tokenType === lexer_1.TOKEN_DTD /*DTD*/) { 166 | judgeEnd(lexer); 167 | } 168 | /*contentText

*/ 169 | /*contentText || */ 171 | /*contentText
*/ 172 | if (stack[length - 1].tokenType === lexer_1.TOKEN_CONTENT_TEXT /*contentText*/) { 173 | if ((lexer.sourceCode[0] === "<" && 174 | lexer_1.regexName.test(lexer.sourceCode[1])) /*contentText

*/ || 175 | lexer.sourceCode.slice(0, 2) === " || */) { 177 | return false; 178 | } 179 | else { 180 | /*contentText
*/ 181 | if ((lexer.sourceCode[0] === "<" 182 | && lexer_1.regexName.test(lexer.sourceCode[1]))) { 183 | let parseRes = Html_1.parseHtml(lexer); 184 | if (parseRes.selfClose) { 185 | return false; 186 | } 187 | } 188 | return true; 189 | } 190 | } 191 | // return true 192 | throw new Error(`not find contentEnd! at line ${lexer.GetLineNum()} ${lexer.sourceCode.slice(0, 100)}`); 193 | } 194 | function parseText(lexer) { 195 | lexer.hasCache = false; 196 | let node = new Node(); 197 | if (!lexer.check) { 198 | node.nextSibling = null; 199 | } 200 | // lexer.isIgnored(); 201 | node.LineNum = lexer.GetLineNum(); 202 | let content = ""; 203 | while (contentEnd(lexer) && !lexer.isEmpty()) { 204 | if (lexer.nextSourceCodeIs("\r\n") || lexer.nextSourceCodeIs("\n\r")) { 205 | lexer.lineNum += 1; 206 | content += lexer.sourceCode.slice(0, 2); 207 | lexer.skipSourceCode(2); 208 | } 209 | else { 210 | if (lexer.isNewLine(lexer.sourceCode[0])) { 211 | lexer.lineNum += 1; 212 | content += lexer.sourceCode[0]; 213 | lexer.skipSourceCode(1); 214 | } 215 | else { 216 | content += lexer.sourceCode[0]; 217 | lexer.skipSourceCode(1); 218 | } 219 | } 220 | } 221 | if (lexer.stack.length >= 3 && 222 | tagClose_1.isSpecialTag({ tag: lexer.stack[lexer.stack.length - 3].token })) { 223 | let token = lexer.stack[lexer.stack.length - 3].token; 224 | let tokenLen = ``.length; 225 | if (lexer.sourceCode.slice(0, tokenLen) === ``) { 226 | lexer.skipSourceCode(2); 227 | let res = { lineNum: lexer.lineNum, tokenType: lexer_1.TOKEN_CLOSE, token: " 11 | 12 | 13 | 14 | 15 | 16 | Document 17 | 18 | 19 |

20 |

11{{res.value}}

21 |

22 | 23 | 24 | 25 | ``` 26 | 27 | ## AST 28 |

29 |

点击查看详情(Click to view details)

30 |


 31 | {
 32 |     "type": "root",
 33 |     "children": [
 34 |         {
 35 |             "type": "DTD",
 36 |             "LineNum": 1,
 37 |             "content": "DOCTYPE html"
 38 |         },
 39 |         {
 40 |             "content": "\r\n",
 41 |             "LineNum": 1,
 42 |             "type": "text"
 43 |         },
 44 |         {
 45 |             "children": [
 46 |                 {
 47 |                     "content": "\r\n",
 48 |                     "LineNum": 2,
 49 |                     "type": "text"
 50 |                 },
 51 |                 {
 52 |                     "children": [
 53 |                         {
 54 |                             "content": "\r\n    ",
 55 |                             "LineNum": 3,
 56 |                             "type": "text"
 57 |                         },
 58 |                         {
 59 |                             "children": [],
 60 |                             "attr": [
 61 |                                 {
 62 |                                     "name": "charset",
 63 |                                     "value": "UTF-8"
 64 |                                 }
 65 |                             ],
 66 |                             "LineNum": 4,
 67 |                             "type": "tag",
 68 |                             "tag": "meta"
 69 |                         },
 70 |                         {
 71 |                             "content": "\r\n    ",
 72 |                             "LineNum": 4,
 73 |                             "type": "text"
 74 |                         },
 75 |                         {
 76 |                             "children": [],
 77 |                             "attr": [
 78 |                                 {
 79 |                                     "name": "http-equiv",
 80 |                                     "value": "X-UA-Compatible"
 81 |                                 },
 82 |                                 {
 83 |                                     "name": "content",
 84 |                                     "value": "IE=edge"
 85 |                                 }
 86 |                             ],
 87 |                             "LineNum": 5,
 88 |                             "type": "tag",
 89 |                             "tag": "meta"
 90 |                         },
 91 |                         {
 92 |                             "content": "\r\n    ",
 93 |                             "LineNum": 5,
 94 |                             "type": "text"
 95 |                         },
 96 |                         {
 97 |                             "children": [],
 98 |                             "attr": [
 99 |                                 {
100 |                                     "name": "name",
101 |                                     "value": "viewport"
102 |                                 },
103 |                                 {
104 |                                     "name": "content",
105 |                                     "value": "width=device-width, initial-scale=1.0"
106 |                                 }
107 |                             ],
108 |                             "LineNum": 6,
109 |                             "type": "tag",
110 |                             "tag": "meta"
111 |                         },
112 |                         {
113 |                             "content": "\r\n    ",
114 |                             "LineNum": 6,
115 |                             "type": "text"
116 |                         },
117 |                         {
118 |                             "children": [
119 |                                 {
120 |                                     "content": "Document",
121 |                                     "LineNum": 7,
122 |                                     "type": "text"
123 |                                 }
124 |                             ],
125 |                             "attr": [],
126 |                             "LineNum": 7,
127 |                             "type": "tag",
128 |                             "tag": "title"
129 |                         },
130 |                         {
131 |                             "content": "\r\n",
132 |                             "LineNum": 7,
133 |                             "type": "text"
134 |                         }
135 |                     ],
136 |                     "attr": [],
137 |                     "LineNum": 3,
138 |                     "type": "tag",
139 |                     "tag": "head"
140 |                 },
141 |                 {
142 |                     "content": "\r\n",
143 |                     "LineNum": 8,
144 |                     "type": "text"
145 |                 },
146 |                 {
147 |                     "children": [
148 |                         {
149 |                             "content": "\r\n    ",
150 |                             "LineNum": 9,
151 |                             "type": "text"
152 |                         },
153 |                         {
154 |                             "children": [
155 |                                 {
156 |                                     "content": "\r\n        ",
157 |                                     "LineNum": 10,
158 |                                     "type": "text"
159 |                                 },
160 |                                 {
161 |                                     "children": [
162 |                                         {
163 |                                             "content": "11{{res.value}}",
164 |                                             "LineNum": 11,
165 |                                             "type": "text"
166 |                                         }
167 |                                     ],
168 |                                     "attr": [
169 |                                         {
170 |                                             "name": "v-if",
171 |                                             "value": "res.value"
172 |                                         },
173 |                                         {
174 |                                             "name": "name",
175 |                                             "value": "11"
176 |                                         },
177 |                                         {
178 |                                             "name": "@click",
179 |                                             "value": "tes"
180 |                                         }
181 |                                     ],
182 |                                     "LineNum": 11,
183 |                                     "type": "tag",
184 |                                     "tag": "h1"
185 |                                 },
186 |                                 {
187 |                                     "content": "\r\n    ",
188 |                                     "LineNum": 11,
189 |                                     "type": "text"
190 |                                 }
191 |                             ],
192 |                             "attr": [],
193 |                             "LineNum": 10,
194 |                             "type": "tag",
195 |                             "tag": "div"
196 |                         },
197 |                         {
198 |                             "content": "\r\n    ",
199 |                             "LineNum": 12,
200 |                             "type": "text"
201 |                         },
202 |                         {
203 |                             "children": [],
204 |                             "attr": [
205 |                                 {
206 |                                     "name": "href",
207 |                                     "value": "http://github.com/"
208 |                                 }
209 |                             ],
210 |                             "LineNum": 13,
211 |                             "type": "tag",
212 |                             "tag": "a"
213 |                         },
214 |                         {
215 |                             "content": "\r\n",
216 |                             "LineNum": 13,
217 |                             "type": "text"
218 |                         }
219 |                     ],
220 |                     "attr": [],
221 |                     "LineNum": 9,
222 |                     "type": "tag",
223 |                     "tag": "body"
224 |                 },
225 |                 {
226 |                     "content": "\r\n",
227 |                     "LineNum": 14,
228 |                     "type": "text"
229 |                 }
230 |             ],
231 |             "attr": [
232 |                 {
233 |                     "name": "lang",
234 |                     "value": "en"
235 |                 }
236 |             ],
237 |             "LineNum": 2,
238 |             "type": "tag",
239 |             "tag": "html"
240 |         }
241 |     ],
242 |     "LineNum": 1
243 | }
244 |

245 |

246 | 247 | ## 添加应用 248 | [查找节点](https://github.com/liulinboyi/HTMLParser-App/tree/main/platform) 249 | 250 | ## TIPS 251 | 252 | > 无运行时依赖 253 | 254 | 没有做到浏览器那样兼容性巨好，HTML写成啥样都不报错都会解析，我只解析了一部分奇葩写法~有的HTML写法太奇葩了，要兼容就需要更多的分支和处理，需要更多的精力就算了。 255 | 256 | ## 注意 257 | 258 | #### ~~tsc编译后无法加上.js后缀，导致无法使用module，所以在所有ts文件导入加上了js后缀~~ 259 | #### ~~https://segmentfault.com/q/1010000038671707~~ 260 | #### ~~[社区讨论](https://github.com/microsoft/TypeScript/issues/16577)~~ 261 | 262 | #### 已解决，写了个[脚本](./script/addSuffixJs.js)，将所有编译后的ES modules的导入导出部分加上了js后缀 263 | 264 | ## [测试](./test) 265 | #### 使用[playwright](https://github.com/microsoft/playwright.git)和浏览器生成的DOM结构做了对比，除了一些奇葩写法，其他基本没问题。 266 | -------------------------------------------------------------------------------- /dist/parser.js: -------------------------------------------------------------------------------- 1 | "use strict"; 2 | Object.defineProperty(exports, "__esModule", { value: true }); 3 | exports.parse = exports.Program = void 0; 4 | const lexer_1 = require("./lexer"); 5 | const Comment_1 = require("./parser/Comment"); 6 | const Directive_1 = require("./parser/Directive"); 7 | const DTD_1 = require("./parser/DTD"); 8 | const Html_1 = require("./parser/Html"); 9 | const parseText_1 = require("./parser/parseText"); 10 | const tagClose_1 = require("./parser/tagClose"); 11 | class Program { 12 | constructor() { 13 | this.type = 'root'; 14 | this.children = []; 15 | } 16 | } 17 | exports.Program = Program; 18 | // SourceCode ::= Statement+ 19 | function parseSourceCode(lexer, check) { 20 | let LineNum = lexer.GetLineNum(); 21 | let root = parseStatements(lexer, check); 22 | root.LineNum = LineNum; 23 | return root; 24 | } 25 | /** 26 | * 将children中的多余的text节点去除 27 | * @param children 28 | * @returns 29 | */ 30 | function filterText(children) { 31 | for (let start = 0; start < children.length; start++) { 32 | if (children[start].type === "text") { 33 | // 从实践中知道，如果有去除body后多余的text节点，则最多是两个取一个，所以有下面代码 34 | let i = start + 1; 35 | if (i < children.length && children[i].type === "text") { 36 | // 其中重要的特征就是，里面是只有\r\n和空格 37 | // 只要当前标签和下一个标签这两个标签，则一定会删除一个"空标签(只包含\r\n和空格)" 38 | if (!children[i].content.replace(/[\r\n]+/g, "").trim()) { 39 | children[i].delete = true; // 添加上delete属性，后面好处理 40 | } 41 | else { 42 | children[start].delete = true; // 添加上delete属性，后面好处理 43 | } 44 | } 45 | } 46 | } 47 | // 删除delete为true的标签 48 | return children.filter((item) => !item.delete); 49 | } 50 | // Statement 51 | function parseStatements(lexer, check) { 52 | if (check) { 53 | lexer.check = true; 54 | } 55 | let root = { 56 | type: "root", 57 | children: [], 58 | LineNum: 1 59 | }; 60 | let statements = [root]; 61 | let Block_level_elements = [ 62 | "address", 63 | "article", 64 | "aside", 65 | "audio", 66 | "blockquote", 67 | "canvas", 68 | "dd", 69 | // "div", 70 | "dl", 71 | "fieldset", 72 | "figcaption", 73 | "figure", 74 | "figcaption", 75 | "footer", 76 | "form", 77 | "header", 78 | "hgroup", 79 | "hr", 80 | "noscript", 81 | "ol", 82 | "output", 83 | "p", 84 | "pre", 85 | "section", 86 | "table", 87 | "tfoot", 88 | "ul", 89 | "video" 90 | ]; 91 | let inlInline_elementsine = [ 92 | "b", 93 | "big", 94 | "i", 95 | "small", 96 | "tt", 97 | "abbr", 98 | "acronym", 99 | "cite", 100 | "code", 101 | "dfn", 102 | "em", 103 | "kbd", 104 | "strong", 105 | "samp", 106 | "var", 107 | "a", 108 | "bdo", 109 | "br", 110 | "img", 111 | "map", 112 | "object", 113 | "q", 114 | "script", 115 | "span", 116 | "sub", 117 | "sup", 118 | "button", 119 | "input", 120 | "label", 121 | "select", 122 | "textarea" 123 | ]; 124 | let notInSelf = [ 125 | "a", 126 | "br", 127 | "img", 128 | "script", 129 | "button", 130 | "input", 131 | ]; 132 | // select 里面的select会消失 133 | // textarea 会解析成 134 | let body = null; 135 | let mainBodyFinished = false; 136 | let uniqueStack = []; 137 | // let mainBodyFinishedIsText = false 138 | // 先调用LookAhead一次，将GetNextToken的结果缓存 139 | while (!isSourceCodeEnd(lexer.LookAhead().tokenType)) { 140 | // if (lexer.GetLineNum() === 20) { 141 | // debugger 142 | // } 143 | let statement = {}; 144 | statement = parseStatement(lexer); 145 | // console.log(`at line ${lexer.GetLineNum()} ${lexer.sourceCode.slice(0, 30)}`) 146 | if (!statement) 147 | continue; 148 | let stack = statements; 149 | let s = statement; 150 | const length = stack.length - 1; 151 | if (s.type === "tag") { 152 | s.tag = s.tag.toLocaleLowerCase(); 153 | } 154 | if (!s.closeTag) { 155 | uniqueStack = []; 156 | if (notInSelf.includes(s.tag) && s.tag === stack[length].tag) { // 不能包含自己的元素 157 | stack.pop(); 158 | stack[stack.length - 1].children.push(s); 159 | stack.push(s); 160 | if (check) { 161 | s.parent = stack[stack.length - 1]; 162 | } 163 | continue; 164 | } 165 | // 处理多个body标签的问题 166 | // 如果mainBodyFinished位false，表示还未出现第一个body，并且当前起始标签是body，则寻找他的父节点，并将其赋值给body变量 167 | if (!mainBodyFinished && s.tag === "body" && !body) { 168 | // 寻找父节点 169 | let i = stack.length - 1; 170 | let parent = null; 171 | while (stack[i].type !== "tag" && i >= 0) { 172 | i--; 173 | } 174 | parent = i >= 0 ? stack[i] : null; 175 | // 找到的节点，赋值给body 176 | body = s; 177 | // 找到的父节点赋值给上面节点的parent属性，方便后续处理 178 | body.parent = parent; 179 | } 180 | stack[length].children.push(s); // 栈顶就是levalElement层级元素 181 | if (check) { 182 | s.parent = stack[length]; 183 | } 184 | if (s.type === "tag" && !s.selfClose && !tagClose_1.isSpecialTag(s)) { 185 | stack.push(s); 186 | // 处理多个body标签的问题 187 | // 如果已经出现过一个body标签并且现在这个起始标签还是body，则将其从栈中弹出，并且将其从栈顶的children中弹出 188 | if (mainBodyFinished && s.tag === "body") { 189 | stack.pop(); 190 | stack[length].children.pop(); 191 | if (check) { 192 | s.parent = null; 193 | } 194 | } 195 | } 196 | // 处理多个body标签的问题 197 | // 如果出现第一个body起始标签，则将mainBodyFinished置为true，方便在第一个body标签中再次出现body起始标签时将其忽略 198 | if (!mainBodyFinished && s.tag === "body") { 199 | mainBodyFinished = true; 200 | } 201 | } 202 | else { 203 | if (stack[length].tag !== s.tag) { 204 | uniqueStack.push(s); 205 | // 处理多个body标签的问题 206 | // 如果当前第一个body标签解析完成（mainBodyFinished），并且当前结束标签是body，则直接进行下次循环 207 | if (mainBodyFinished && s.tag === "body") { 208 | continue; 209 | } 210 | if (Block_level_elements.includes(s.tag)) { // 如果是块级元素会加入到levalElement层级元素当child 211 | stack[length].children.push(s); 212 | if (check) { 213 | s.parent = stack[length]; 214 | } 215 | } 216 | // 学习浏览器HTML解析，即使匹配不上也不报错，直接添加到levalElement层级元素当child 217 | console.warn(`${stack[length].tag} and ${s.tag} is not math! at line ${lexer.GetLineNum()} ${lexer.sourceCode.slice(0, 100)}`); 218 | // throw new Error(`${stack[length].tag} and ${s.tag} is not math! at line ${lexer.GetLineNum()} ${lexer.sourceCode.slice(0, 100)}`) 219 | } 220 | else { 221 | // 处理多个body标签的问题 222 | // 如果第一个body标签没有解析完成（mainBodyFinished），并且当前结束标签是body，则mainBodyFinished置为true 223 | if (!mainBodyFinished && s.tag === "body") { 224 | mainBodyFinished = true; 225 | } 226 | stack.pop(); 227 | if (uniqueStack.length > 0 && uniqueStack[uniqueStack.length - 1].tag === stack[stack.length - 1].tag) { 228 | uniqueStack.pop(); 229 | stack.pop(); 230 | } 231 | } 232 | } 233 | } 234 | // 处理多个body标签的问题 235 | // 找出body在父节点的索引 236 | let index = body && body.parent.children.findIndex((item) => item === body); 237 | // 从父节点下一个索引开始添加到第一个body中 238 | let real = index + 1; 239 | if (body) { 240 | for (let i = real; i < body.parent.children.length; i++) { 241 | if (body.parent.children[i].type === "tag") { 242 | body.parent.children[i].children = filterText(body.parent.children[i].children); 243 | } 244 | body.children.push(body.parent.children[i]); 245 | } 246 | let childrenLength = body.parent.children.length; 247 | for (let i = real; i < childrenLength; i++) { 248 | body.parent.children.pop(); 249 | } 250 | body.children = filterText(body.children); 251 | body.parent = null; 252 | } 253 | for (let i = 0; i < root.children.length; i++) { 254 | if (root.children[i].type === "DTD") { 255 | if (i - 1 >= 0 && root.children[i - 1].type === "text" && !root.children[i - 1].content.replace(/[\r\n]+/g, "").trim()) { 256 | root.children[i - 1].delete = true; 257 | } 258 | } 259 | if (root.children[i].tag === "html") { 260 | if (i - 1 >= 0 && root.children[i - 1].type === "text" && !root.children[i - 1].content.replace(/[\r\n]+/g, "").trim()) { 261 | root.children[i - 1].delete = true; 262 | } 263 | } 264 | if (check) { 265 | root.children[i].parent = null; 266 | } 267 | } 268 | root.children = root.children.filter((item) => !item.delete); 269 | return root; 270 | } 271 | function parseStatement(lexer) { 272 | // 向前看一个token并跳过 273 | lexer.LookAheadAndSkip(lexer_1.TOKEN_IGNORED); // skip if source code start with ignored token 274 | let look = lexer.LookAhead().tokenType; 275 | let flag = false; 276 | let top = lexer.stack[lexer.stack.length - 1]; 277 | if (top.tokenType === lexer_1.TOKEN_CONTENT_TEXT 278 | // isClose(lexer) && 279 | // top.tokenType !== TOKEN_LEFT_PAREN /*<*/ && 280 | // top.tokenType !== TOKEN_CLOSE /*, 13 | } 14 | 15 | export class Program { 16 | constructor() { 17 | this.type = 'root' 18 | this.children = [] 19 | } 20 | } 21 | 22 | 23 | // SourceCode ::= Statement+ 24 | function parseSourceCode(lexer: Lexer, check: boolean) { 25 | let LineNum = lexer.GetLineNum() 26 | let root = parseStatements(lexer, check) 27 | root.LineNum = LineNum 28 | return root 29 | } 30 | 31 | /** 32 | * 将children中的多余的text节点去除 33 | * @param children 34 | * @returns 35 | */ 36 | function filterText(children: any) { 37 | for (let start = 0; start < children.length; start++) { 38 | if (children[start].type === "text") { 39 | // 从实践中知道，如果有去除body后多余的text节点，则最多是两个取一个，所以有下面代码 40 | let i = start + 1 41 | if (i < children.length && children[i].type === "text") { 42 | // 其中重要的特征就是，里面是只有\r\n和空格 43 | // 只要当前标签和下一个标签这两个标签，则一定会删除一个"空标签(只包含\r\n和空格)" 44 | if (!children[i].content.replace(/[\r\n]+/g, "").trim()) { 45 | children[i].delete = true // 添加上delete属性，后面好处理 46 | } else { 47 | children[start].delete = true // 添加上delete属性，后面好处理 48 | } 49 | } 50 | } 51 | } 52 | // 删除delete为true的标签 53 | return children.filter((item: any) => !item.delete) 54 | } 55 | 56 | // Statement 57 | function parseStatements(lexer: Lexer, check: boolean) { 58 | 59 | if (check) { 60 | lexer.check = true 61 | } 62 | 63 | let root: any = { 64 | type: "root", 65 | children: [], 66 | LineNum: 1 67 | } 68 | 69 | let statements: Array = [root] 70 | 71 | let Block_level_elements = [ // 块级元素 72 | "address", 73 | "article", 74 | "aside", 75 | "audio", 76 | "blockquote", 77 | "canvas", 78 | "dd", 79 | // "div", 80 | "dl", 81 | "fieldset", 82 | "figcaption", 83 | "figure", 84 | "figcaption", 85 | "footer", 86 | "form", 87 | "header", 88 | "hgroup", 89 | "hr", 90 | "noscript", 91 | "ol", 92 | "output", 93 | "p", 94 | "pre", 95 | "section", 96 | "table", 97 | "tfoot", 98 | "ul", 99 | "video" 100 | ] 101 | 102 | let inlInline_elementsine = [ // 行内元素 103 | "b", 104 | "big", 105 | "i", 106 | "small", 107 | "tt", 108 | "abbr", 109 | "acronym", 110 | "cite", 111 | "code", 112 | "dfn", 113 | "em", 114 | "kbd", 115 | "strong", 116 | "samp", 117 | "var", 118 | "a", 119 | "bdo", 120 | "br", 121 | "img", 122 | "map", 123 | "object", 124 | "q", 125 | "script", 126 | "span", 127 | "sub", 128 | "sup", 129 | "button", 130 | "input", 131 | "label", 132 | "select", 133 | "textarea" 134 | ] 135 | 136 | let notInSelf = [ // 不能包含自己的元素 137 | "a", 138 | "br", 139 | "img", 140 | "script", 141 | "button", 142 | "input", 143 | ] 144 | // select 里面的select会消失 145 | // textarea 会解析成 146 | 147 | 148 | let body: any = null 149 | let mainBodyFinished = false 150 | let uniqueStack = [] 151 | // let mainBodyFinishedIsText = false 152 | // 先调用LookAhead一次，将GetNextToken的结果缓存 153 | while (!isSourceCodeEnd(lexer.LookAhead().tokenType)) { 154 | // if (lexer.GetLineNum() === 20) { 155 | // debugger 156 | // } 157 | let statement: any = {} 158 | statement = parseStatement(lexer) 159 | // console.log(`at line ${lexer.GetLineNum()} ${lexer.sourceCode.slice(0, 30)}`) 160 | if (!statement) continue 161 | let stack = statements; 162 | let s = statement; 163 | const length = stack.length - 1 164 | if (s.type === "tag") { 165 | s.tag = s.tag.toLocaleLowerCase() 166 | } 167 | if (!s.closeTag) { 168 | 169 | uniqueStack = [] 170 | if (notInSelf.includes(s.tag) && s.tag === stack[length].tag) { // 不能包含自己的元素 171 | stack.pop() 172 | stack[stack.length - 1].children.push(s) 173 | stack.push(s) 174 | if (check) { 175 | s.parent = stack[stack.length - 1] 176 | } 177 | continue 178 | } 179 | 180 | // 处理多个body标签的问题 181 | // 如果mainBodyFinished位false，表示还未出现第一个body，并且当前起始标签是body，则寻找他的父节点，并将其赋值给body变量 182 | if (!mainBodyFinished && s.tag === "body" && !body) { 183 | // 寻找父节点 184 | let i = stack.length - 1 185 | let parent = null 186 | while (stack[i].type !== "tag" && i >= 0) { 187 | i--; 188 | } 189 | parent = i >= 0 ? stack[i] : null; 190 | // 找到的节点，赋值给body 191 | body = s 192 | // 找到的父节点赋值给上面节点的parent属性，方便后续处理 193 | body.parent = parent 194 | } 195 | 196 | stack[length].children.push(s) // 栈顶就是levalElement层级元素 197 | if (check) { 198 | s.parent = stack[length] 199 | } 200 | if (s.type === "tag" && !s.selfClose && !isSpecialTag(s)) { 201 | stack.push(s) 202 | // 处理多个body标签的问题 203 | // 如果已经出现过一个body标签并且现在这个起始标签还是body，则将其从栈中弹出，并且将其从栈顶的children中弹出 204 | if (mainBodyFinished && s.tag === "body") { 205 | stack.pop() 206 | stack[length].children.pop() 207 | if (check) { 208 | s.parent = null 209 | } 210 | } 211 | } 212 | // 处理多个body标签的问题 213 | // 如果出现第一个body起始标签，则将mainBodyFinished置为true，方便在第一个body标签中再次出现body起始标签时将其忽略 214 | if (!mainBodyFinished && s.tag === "body") { 215 | mainBodyFinished = true 216 | } 217 | } else { 218 | if (stack[length].tag !== s.tag) { 219 | uniqueStack.push(s) 220 | // 处理多个body标签的问题 221 | // 如果当前第一个body标签解析完成（mainBodyFinished），并且当前结束标签是body，则直接进行下次循环 222 | if (mainBodyFinished && s.tag === "body") { 223 | continue 224 | } 225 | if (Block_level_elements.includes(s.tag)) { // 如果是块级元素会加入到levalElement层级元素当child 226 | stack[length].children.push(s) 227 | if (check) { 228 | s.parent = stack[length] 229 | } 230 | } 231 | // 学习浏览器HTML解析，即使匹配不上也不报错，直接添加到levalElement层级元素当child 232 | console.warn(`${stack[length].tag} and ${s.tag} is not math! at line ${lexer.GetLineNum()} ${lexer.sourceCode.slice(0, 100)}`) 233 | // throw new Error(`${stack[length].tag} and ${s.tag} is not math! at line ${lexer.GetLineNum()} ${lexer.sourceCode.slice(0, 100)}`) 234 | } else { 235 | // 处理多个body标签的问题 236 | // 如果第一个body标签没有解析完成（mainBodyFinished），并且当前结束标签是body，则mainBodyFinished置为true 237 | if (!mainBodyFinished && s.tag === "body") { 238 | mainBodyFinished = true 239 | } 240 | stack.pop() 241 | if (uniqueStack.length > 0 && uniqueStack[uniqueStack.length - 1].tag === stack[stack.length - 1].tag) { 242 | uniqueStack.pop() 243 | stack.pop() 244 | } 245 | } 246 | } 247 | } 248 | 249 | // 处理多个body标签的问题 250 | // 找出body在父节点的索引 251 | let index = body && body.parent.children.findIndex((item: any) => item === body) 252 | // 从父节点下一个索引开始添加到第一个body中 253 | let real = index + 1 254 | 255 | if (body) { 256 | 257 | for (let i = real; i < body.parent.children.length; i++) { 258 | if (body.parent.children[i].type === "tag") { 259 | body.parent.children[i].children = filterText(body.parent.children[i].children) 260 | } 261 | body.children.push(body.parent.children[i]) 262 | } 263 | 264 | let childrenLength = body.parent.children.length 265 | for (let i = real; i < childrenLength; i++) { 266 | body.parent.children.pop() 267 | } 268 | 269 | body.children = filterText(body.children) 270 | 271 | body.parent = null 272 | } 273 | 274 | 275 | for (let i = 0; i < root.children.length; i++) { 276 | if (root.children[i].type === "DTD") { 277 | if (i - 1 >= 0 && root.children[i - 1].type === "text" && !root.children[i - 1].content.replace(/[\r\n]+/g, "").trim()) { 278 | root.children[i - 1].delete = true 279 | } 280 | } 281 | if (root.children[i].tag === "html") { 282 | if (i - 1 >= 0 && root.children[i - 1].type === "text" && !root.children[i - 1].content.replace(/[\r\n]+/g, "").trim()) { 283 | root.children[i - 1].delete = true 284 | } 285 | } 286 | if (check) { 287 | root.children[i].parent = null 288 | } 289 | } 290 | 291 | root.children = root.children.filter((item: any) => !item.delete) 292 | 293 | return root 294 | } 295 | 296 | function parseStatement(lexer: Lexer) { 297 | // 向前看一个token并跳过 298 | lexer.LookAheadAndSkip(TOKEN_IGNORED) // skip if source code start with ignored token 299 | let look = lexer.LookAhead().tokenType 300 | let flag = false 301 | let top = lexer.stack[lexer.stack.length - 1] 302 | if ( 303 | top.tokenType === TOKEN_CONTENT_TEXT 304 | // isClose(lexer) && 305 | // top.tokenType !== TOKEN_LEFT_PAREN /*<*/ && 306 | // top.tokenType !== TOKEN_CLOSE /* 2 | 3 | 4 | 5 | 6 | 7 | Document 8 | 9 | 10 | 385 | 386 | -------------------------------------------------------------------------------- /dist/lexer.js: -------------------------------------------------------------------------------- 1 | "use strict"; 2 | Object.defineProperty(exports, "__esModule", { value: true }); 3 | exports.NewLexer = exports.Lexer = exports.tokenNameMap = exports.keywords = exports.regexName = exports.SourceCharacter = exports.DIRECTIVE = exports.COMMENT = exports.INTERGER = exports.TOKEN_IGNORED = exports.TOKEN_NAME = exports.TOKEN_SELF_CLOSE = exports.TOKEN_DTD = exports.TOKEN_CLOSE = exports.TOKEN_CONTENT_TEXT = exports.TOKEN_DUOQUOTE = exports.TOKEN_LEFT_LINE = exports.TOKEN_SINGLE_QUOTE = exports.TOKEN_QUOTE = exports.TOKEN_EQUAL = exports.TOKEN_RIGHT_PAREN = exports.TOKEN_TAG_NAME = exports.TOKEN_LEFT_PAREN = exports.TOKEN_EOF = exports.Tokens = void 0; 4 | // token const 5 | var Tokens; 6 | (function (Tokens) { 7 | Tokens[Tokens["TOKEN_EOF"] = 0] = "TOKEN_EOF"; 8 | Tokens[Tokens["TOKEN_LEFT_PAREN"] = 1] = "TOKEN_LEFT_PAREN"; 9 | Tokens[Tokens["TOKEN_TAG_NAME"] = 2] = "TOKEN_TAG_NAME"; 10 | Tokens[Tokens["TOKEN_RIGHT_PAREN"] = 3] = "TOKEN_RIGHT_PAREN"; 11 | Tokens[Tokens["TOKEN_EQUAL"] = 4] = "TOKEN_EQUAL"; 12 | Tokens[Tokens["TOKEN_QUOTE"] = 5] = "TOKEN_QUOTE"; 13 | Tokens[Tokens["TOKEN_SINGLE_QUOTE"] = 6] = "TOKEN_SINGLE_QUOTE"; 14 | Tokens[Tokens["TOKEN_LEFT_LINE"] = 7] = "TOKEN_LEFT_LINE"; 15 | Tokens[Tokens["TOKEN_DUOQUOTE"] = 8] = "TOKEN_DUOQUOTE"; 16 | Tokens[Tokens["TOKEN_CONTENT_TEXT"] = 9] = "TOKEN_CONTENT_TEXT"; 17 | Tokens[Tokens["TOKEN_CLOSE"] = 10] = "TOKEN_CLOSE"; 18 | Tokens[Tokens["TOKEN_DTD"] = 11] = "TOKEN_DTD"; 19 | Tokens[Tokens["TOKEN_SELF_CLOSE"] = 12] = "TOKEN_SELF_CLOSE"; 20 | Tokens[Tokens["TOKEN_NAME"] = 13] = "TOKEN_NAME"; 21 | Tokens[Tokens["TOKEN_IGNORED"] = 14] = "TOKEN_IGNORED"; 22 | Tokens[Tokens["INTERGER"] = 15] = "INTERGER"; 23 | Tokens[Tokens["COMMENT"] = 16] = "COMMENT"; 24 | Tokens[Tokens["DIRECTIVE"] = 17] = "DIRECTIVE"; 25 | Tokens[Tokens["SourceCharacter"] = 18] = "SourceCharacter"; 26 | })(Tokens = exports.Tokens || (exports.Tokens = {})); 27 | exports.TOKEN_EOF = Tokens.TOKEN_EOF, exports.TOKEN_LEFT_PAREN = Tokens.TOKEN_LEFT_PAREN, exports.TOKEN_TAG_NAME = Tokens.TOKEN_TAG_NAME, exports.TOKEN_RIGHT_PAREN = Tokens.TOKEN_RIGHT_PAREN, exports.TOKEN_EQUAL = Tokens.TOKEN_EQUAL, exports.TOKEN_QUOTE = Tokens.TOKEN_QUOTE, exports.TOKEN_SINGLE_QUOTE = Tokens.TOKEN_SINGLE_QUOTE, exports.TOKEN_LEFT_LINE = Tokens.TOKEN_LEFT_LINE, exports.TOKEN_DUOQUOTE = Tokens.TOKEN_DUOQUOTE, exports.TOKEN_CONTENT_TEXT = Tokens.TOKEN_CONTENT_TEXT, exports.TOKEN_CLOSE = Tokens.TOKEN_CLOSE, exports.TOKEN_DTD = Tokens.TOKEN_DTD, exports.TOKEN_SELF_CLOSE = Tokens.TOKEN_SELF_CLOSE, exports.TOKEN_NAME = Tokens.TOKEN_NAME, exports.TOKEN_IGNORED = Tokens.TOKEN_IGNORED, exports.INTERGER = Tokens.INTERGER, exports.COMMENT = Tokens.COMMENT, exports.DIRECTIVE = Tokens.DIRECTIVE, exports.SourceCharacter = Tokens.SourceCharacter; 28 | // regex match patterns 29 | exports.regexName = /^[a-zA-z]+[0-9]*([-_:']*[a-zA-z0-9]*)*/; 30 | // 关键字 31 | exports.keywords = {}; 32 | exports.tokenNameMap = { 33 | [exports.TOKEN_EOF]: "EOF", 34 | [exports.TOKEN_LEFT_PAREN]: "<", 35 | [exports.TOKEN_TAG_NAME]: "tagNmae", 36 | [exports.TOKEN_RIGHT_PAREN]: ">", 37 | [exports.TOKEN_EQUAL]: "=", 38 | [exports.TOKEN_QUOTE]: "\"", 39 | [exports.TOKEN_SINGLE_QUOTE]: "'", 40 | [exports.TOKEN_LEFT_LINE]: "/", 41 | [exports.TOKEN_DUOQUOTE]: "\"\"", 42 | [exports.TOKEN_CONTENT_TEXT]: "ContentText", 43 | [exports.TOKEN_CLOSE]: "close", 44 | [exports.TOKEN_DTD]: "dtd", 45 | [exports.TOKEN_SELF_CLOSE]: "self-close", 46 | [exports.TOKEN_NAME]: "Name", 47 | [exports.TOKEN_IGNORED]: "Ignored", 48 | [exports.INTERGER]: "INTERGER", 49 | [exports.COMMENT]: "COMMENT", 50 | [exports.DIRECTIVE]: "DIRECTIVE", 51 | [exports.SourceCharacter]: "SourceCharacter", 52 | }; 53 | class Lexer { 54 | constructor(sourceCode, lineNum, nextToken, nextTokenType, nextTokenLineNum) { 55 | this.sourceCode = sourceCode; 56 | this.lineNum = lineNum; 57 | this.nextToken = nextToken; 58 | this.nextTokenType = nextTokenType; 59 | this.nextTokenLineNum = nextTokenLineNum; 60 | this.hasCache = false; 61 | this.stack = []; 62 | } 63 | get judgeIsContent() { 64 | const length = this.stack.length - 1; 65 | return this.stack[length].tokenType === exports.TOKEN_RIGHT_PAREN /*>*/ || 66 | this.stack[length].tokenType === exports.TOKEN_SELF_CLOSE /*/>
*/ || 67 | this.stack[length].tokenType === exports.TOKEN_DTD /*dtd*/ || 68 | this.stack[length].tokenType === exports.COMMENT /**/ || 69 | this.stack[length].tokenType === exports.TOKEN_CONTENT_TEXT; /*ContentText*/ 70 | } 71 | get isContentText() { 72 | if (this.stack.length < 1) { 73 | if (this.sourceCode[0] === "<") { 74 | return false; 75 | } 76 | return true; 77 | } 78 | let origin = this.sourceCode; 79 | // while (this.stack.length > 10) { 80 | // this.stack.shift() 81 | // } 82 | if (this.judgeIsContent) { 83 | // this.isIgnored() 84 | //

48 \| Pro Version Features: 49 \|
	54 \| Unlimited Words for non-stop Listening 55 \|
	60 \| Read Text in 27 Different Languages 61 \|
	66 \| Read Text at 21 Different Speed Settings 67 \|
	72 \| Autoplay Text - Fast and Easy 73 \|
	78 \| Automatic Language Detection 79 \|

11{{res.value}}

11{{res.value}}

11{{res.value}}

11{{res.value}}

More In News

11{{res.value}}