Created
October 13, 2020 14:45
-
-
Save timokoola/8c364d72025683789f03511178da62bd to your computer and use it in GitHub Desktop.
Node.js snippet for quick json creation from scraped webpage (Chinese Grammar Wiki)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| const cheerio = require("cheerio"); | |
| const got = require("got"); | |
| const fs = require("fs"); | |
| const hsk3URL = | |
| "https://resources.allsetlearning.com/chinese/grammar/HSK_3_grammar_points"; | |
| (async () => { | |
| const response = await got(hsk3URL); | |
| const $ = cheerio.load(response.body); | |
| let result = []; | |
| let titles = { 0: "title", 1: "description", 2: "example" }; | |
| $("tr").map((i, el) => { | |
| let item = {}; | |
| $(el) | |
| .find("td") | |
| .map((j, el) => { | |
| let text = | |
| j == 2 ? $(el).text().trim().replace(/\s/g, "") : $(el).text().trim(); | |
| item[titles[j]] = text; | |
| let link = $(el).find("a").attr("href"); | |
| if (link) { | |
| item["link"] = `https://resources.allsetlearning.com${link}`; | |
| } | |
| }); | |
| if (item && item.title) { | |
| result.push(item); | |
| } | |
| }); | |
| let data = JSON.stringify(result); | |
| fs.writeFileSync("hsk3.json", data); | |
| })(); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment