feat: add money.cnn custom parser (#26)

* feat: add money.cnn custom parser

* added timezone to cnn custom parser
pull/25/head^2
Janet 8 years ago committed by Adam Pash
parent 6343946dd8
commit c4d72fb735

6
.gitignore vendored

@ -6,6 +6,6 @@ read
preview.html
preview.json
coverage
dist/mercury.test.js
dist/mercury.test.js.map
dist/mercury.test.web.js
dist/mercury_test.js
dist/mercury_test.js.map
dist/mercury_test.web.js

40
dist/mercury.js vendored

@ -2787,6 +2787,43 @@ var WwwWashingtonpostComExtractor = {
}
};
var MoneyCnnComExtractor = {
domain: 'money.cnn.com',
title: {
selectors: ['.article-title']
},
author: {
selectors: ['.byline a']
},
date_published: {
selectors: [['meta[name="date"]', 'value']]
},
dek: {
selectors: ['#storytext h2']
},
lead_image_url: {
selectors: [['meta[name="og:image"]', 'value']]
},
content: {
selectors: ['#storytext'],
// 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: ['.inStoryHeading']
}
};
var CustomExtractors = Object.freeze({
@ -2809,7 +2846,8 @@ var CustomExtractors = Object.freeze({
ApartmentTherapyExtractor: ApartmentTherapyExtractor,
MediumExtractor: MediumExtractor,
WwwTmzComExtractor: WwwTmzComExtractor,
WwwWashingtonpostComExtractor: WwwWashingtonpostComExtractor
WwwWashingtonpostComExtractor: WwwWashingtonpostComExtractor,
MoneyCnnComExtractor: MoneyCnnComExtractor
});
var Extractors = _Object$keys(CustomExtractors).reduce(function (acc, key) {

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

@ -17,7 +17,7 @@
"test:web": "./node_modules/karma/bin/karma start karma.conf.js",
"test:build": "cd ./scripts && jest check-build.test.js",
"test:build:web": "node ./scripts/proxy-browser-test.js",
"watch:test": "jest ./src --watch",
"watch:test": "jest --watch",
"generate-parser": "node ./dist/generate-custom-parser.js",
"add-contributor": "all-contributors add",
"generate-contributors": "all-contributors generate"

@ -5,7 +5,7 @@ var execSync = require('child_process').execSync
console.log('Rebuilding Mercury')
execSync('MERCURY_TEST_BUILD=true npm run build')
var Mercury = require('./dist/mercury.test')
var Mercury = require('./dist/mercury_test')
var url = process.argv[2]

@ -13,6 +13,6 @@ export default {
babel(babelOpts),
],
format: 'cjs',
dest: process.env.MERCURY_TEST_BUILD ? 'dist/mercury.test.js' : 'dist/mercury.js',
dest: process.env.MERCURY_TEST_BUILD ? 'dist/mercury_test.js' : 'dist/mercury.js',
sourceMap: true,
};

@ -26,6 +26,6 @@ export default {
],
format: 'iife',
moduleName: 'Mercury',
dest: process.env.MERCURY_TEST_BUILD ? 'dist/mercury.test.web.js' : 'dist/mercury.web.js',
dest: process.env.MERCURY_TEST_BUILD ? 'dist/mercury_test.web.js' : 'dist/mercury.web.js',
sourceMap: false,
};

@ -18,3 +18,4 @@ export * from './www.apartmenttherapy.com';
export * from './medium.com';
export * from './www.tmz.com';
export * from './www.washingtonpost.com';
export * from './money.cnn.com';

@ -0,0 +1,53 @@
export const MoneyCnnComExtractor = {
domain: 'money.cnn.com',
title: {
selectors: [
'.article-title',
],
},
author: {
selectors: [
'.byline a',
],
},
date_published: {
selectors: [
['meta[name="date"]', 'value'],
],
timezone: 'GMT',
},
dek: {
selectors: [
'#storytext h2',
],
},
lead_image_url: {
selectors: [
['meta[name="og:image"]', 'value'],
],
},
content: {
selectors: [
'#storytext',
],
// 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: [
'.inStoryHeading',
],
},
};

@ -0,0 +1,122 @@
import assert from 'assert';
import fs from 'fs';
import URL from 'url';
import cheerio from 'cheerio';
import Mercury from 'mercury';
import getExtractor from 'extractors/get-extractor';
import { excerptContent } from 'utils/text';
describe('MoneyCnnComExtractor', () => {
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 url =
'http://money.cnn.com/2016/11/29/news/ohare-workers-strike/index.html';
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/money.cnn.com/index.js.
const html =
fs.readFileSync('./fixtures/money.cnn.com/1480437611330.html');
const articleUrl =
'http://money.cnn.com/2016/11/29/news/ohare-workers-strike/index.html';
const { title } =
await Mercury.parse(articleUrl, html, { fallback: false });
// Update these values with the expected values from
// the article.
assert.equal(title, 'Hundreds of Chicago O\'Hare airport workers go on strike');
});
it('returns the author', async () => {
// To pass this test, fill out the author selector
// in ./src/extractors/custom/money.cnn.com/index.js.
const html =
fs.readFileSync('./fixtures/money.cnn.com/1480437611330.html');
const articleUrl =
'http://money.cnn.com/2016/11/29/news/ohare-workers-strike/index.html';
const { author } =
await Mercury.parse(articleUrl, html, { fallback: false });
// Update these values with the expected values from
// the article.
assert.equal(author, 'Julia Horowitz');
});
it('returns the date_published', async () => {
// To pass this test, fill out the date_published selector
// in ./src/extractors/custom/money.cnn.com/index.js.
const html =
fs.readFileSync('./fixtures/money.cnn.com/1480437611330.html');
const articleUrl =
'http://money.cnn.com/2016/11/29/news/ohare-workers-strike/index.html';
const { date_published } =
await Mercury.parse(articleUrl, html, { fallback: false });
// Update these values with the expected values from
// the article.
assert.equal(date_published, '2016-11-29T03:33:08.000Z');
});
it('returns the dek', async () => {
// To pass this test, fill out the dek selector
// in ./src/extractors/custom/money.cnn.com/index.js.
const html =
fs.readFileSync('./fixtures/money.cnn.com/1480437611330.html');
const articleUrl =
'http://money.cnn.com/2016/11/29/news/ohare-workers-strike/index.html';
const { dek } =
await Mercury.parse(articleUrl, html, { fallback: false });
// Update these values with the expected values from
// the article.
assert.equal(dek, 'Heads up, travelers: Hundreds of workers are striking at Chicago O\'Hare International Airport on Tuesday.');
});
it('returns the lead_image_url', async () => {
// To pass this test, fill out the lead_image_url selector
// in ./src/extractors/custom/money.cnn.com/index.js.
const html =
fs.readFileSync('./fixtures/money.cnn.com/1480437611330.html');
const articleUrl =
'http://money.cnn.com/2016/11/29/news/ohare-workers-strike/index.html';
const { lead_image_url } =
await Mercury.parse(articleUrl, html, { fallback: false });
// Update these values with the expected values from
// the article.
assert.equal(lead_image_url, 'http://i2.cdn.turner.com/money/dam/assets/161118102423-ohare-airport-strike-780x439.jpg');
});
it('returns the content', async () => {
// To pass this test, fill out the content selector
// in ./src/extractors/custom/money.cnn.com/index.js.
// You may also want to make use of the clean and transform
// options.
const html =
fs.readFileSync('./fixtures/money.cnn.com/1480437611330.html');
const url =
'http://money.cnn.com/2016/11/29/news/ohare-workers-strike/index.html';
const { content } =
await Mercury.parse(url, html, { fallback: false });
const $ = cheerio.load(content || '');
const first13 = excerptContent($('*').first().text(), 13);
// Update these values with the expected values from
// the article.
assert.equal(first13, 'Janitors, baggage handlers, cabin cleaners and wheelchair attendants are asking for a $15');
});
});
Loading…
Cancel
Save