feat: add netease extractor

dist/mercury.js

@@ -6139,6 +6139,35 @@ var SpektrumExtractor = {
   }
 };
 
+var Www163ComExtractor = {
+  domain: 'www.163.com',
+  title: {
+    selectors: [['meta[property="og:title"]', 'content'], '.post_title']
+  },
+  author: {
+    selectors: [['meta[name="author"]', 'content'], ['meta[property="article:author"]', 'content'], '.post_author']
+  },
+  date_published: {
+    selectors: [['meta[property="article:published_time"]', 'content']]
+  },
+  dek: {
+    selectors: []
+  },
+  lead_image_url: {
+    selectors: ['p.f_center img']
+  },
+  content: {
+    selectors: ['.post_body'],
+    // Is there anything in the content you selected that needs transformed
+    // before it's consumable content? E.g., unusual lazy loaded images
+    transforms: {},
+    // Is there anything that is in the result that shouldn't be?
+    // The clean selectors will remove anything that matches from
+    // the result
+    clean: []
+  }
+};
+
 
 
 var CustomExtractors = /*#__PURE__*/Object.freeze({
@@ -6285,7 +6314,8 @@ var CustomExtractors = /*#__PURE__*/Object.freeze({
   WwwEngadgetComExtractor: WwwEngadgetComExtractor,
   ArstechnicaComExtractor: ArstechnicaComExtractor,
   WwwNdtvComExtractor: WwwNdtvComExtractor,
-  SpektrumExtractor: SpektrumExtractor
+  SpektrumExtractor: SpektrumExtractor,
+  Www163ComExtractor: Www163ComExtractor
 });
 
 var Extractors = _Object$keys(CustomExtractors).reduce(function (acc, key) {

src/extractors/custom/index.js

@@ -142,3 +142,4 @@ export * from './www.engadget.com';
 export * from './arstechnica.com';
 export * from './www.ndtv.com';
 export * from './www.spektrum.de';
+export * from './www.163.com';

src/extractors/custom/www.163.com/index.js

@@ -0,0 +1,40 @@
+export const Www163ComExtractor = {
+  domain: 'www.163.com',
+
+  title: {
+    selectors: [['meta[property="og:title"]', 'content'], '.post_title'],
+  },
+
+  author: {
+    selectors: [
+      ['meta[name="author"]', 'content'],
+      ['meta[property="article:author"]', 'content'],
+      '.post_author',
+    ],
+  },
+
+  date_published: {
+    selectors: [['meta[property="article:published_time"]', 'content']],
+  },
+
+  dek: {
+    selectors: [],
+  },
+
+  lead_image_url: {
+    selectors: ['p.f_center img'],
+  },
+
+  content: {
+    selectors: ['.post_body'],
+
+    // Is there anything in the content you selected that needs transformed
+    // before it's consumable content? E.g., unusual lazy loaded images
+    transforms: {},
+
+    // Is there anything that is in the result that shouldn't be?
+    // The clean selectors will remove anything that matches from
+    // the result
+    clean: [],
+  },
+};

src/extractors/custom/www.163.com/index.test.js

@@ -0,0 +1,65 @@
+import assert from 'assert';
+import URL from 'url';
+// import cheerio from 'cheerio';
+
+import Mercury from 'mercury';
+import getExtractor from 'extractors/get-extractor';
+// import { excerptContent } from 'utils/text';
+
+const fs = require('fs');
+
+describe('Www163ComExtractor', () => {
+  describe('initial test case', () => {
+    let result;
+    let url;
+    beforeAll(() => {
+      url = 'https://www.163.com/dy/article/GA1LTCMN051480KF.html';
+      const html = fs.readFileSync('./fixtures/www.163.com/1660814937204.html');
+      result = Mercury.parse(url, { html, fallback: false });
+    });
+
+    it('is selected properly', () => {
+      // This test should be passing by default.
+      // It sanity checks that the correct parser
+      // is being selected for URLs from this domain
+      const extractor = getExtractor(url);
+      assert.equal(extractor.domain, URL.parse(url).hostname);
+    });
+
+    it('returns the title', async () => {
+      // To pass this test, fill out the title selector
+      // in ./src/extractors/custom/www.163.com/index.js.
+      const { title } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(
+        title,
+        `破解难题！西安交大团队开发出高密度固态储氢材料：安全可控，稳定释氢`
+      );
+    });
+
+    it('returns the date_published', async () => {
+      // To pass this test, fill out the date_published selector
+      // in ./src/extractors/custom/www.163.com/index.js.
+      const { date_published } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(date_published, `2021-05-15T03:36:10.000Z`);
+    });
+
+    it('returns the lead_image_url', async () => {
+      // To pass this test, fill out the lead_image_url selector
+      // in ./src/extractors/custom/www.163.com/index.js.
+      const { lead_image_url } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(
+        lead_image_url,
+        'https://nimg.ws.126.net/?url=http%3A%2F%2Fdingyue.ws.126.net%2F2021%2F0515%2F8b37ab4aj00qt4q08003qc000hs00b2g.jpg&thumbnail=660x2147483647&quality=80&type=jpg'
+      );
+    });
+  });
+});