feat: Times of India extractor (#503)
* Adding custom parser for Times of India * moved transforms to clean The transforms were just working as cleans. Moved things around as per recommendations. Co-authored-by: Postlight Bot <adam.pash+postlight-bot@postlight.com>pull/624/head^2
parent
c15f4f5c3e
commit
30d6f472ee
File diff suppressed because one or more lines are too long
@ -0,0 +1,31 @@
|
||||
export const TimesofindiaIndiatimesComExtractor = {
|
||||
domain: 'timesofindia.indiatimes.com',
|
||||
|
||||
title: {
|
||||
selectors: ['h1'],
|
||||
},
|
||||
|
||||
extend: {
|
||||
reporter: {
|
||||
selectors: ['div.byline'],
|
||||
transforms: {},
|
||||
},
|
||||
},
|
||||
|
||||
date_published: {
|
||||
selectors: ['.byline'],
|
||||
format: 'MMM D, YYYY, HH:mm z',
|
||||
timezone: 'Asia/Kolkata',
|
||||
},
|
||||
|
||||
lead_image_url: {
|
||||
selectors: [['meta[name="og:image"]', 'value']],
|
||||
},
|
||||
|
||||
content: {
|
||||
selectors: ['div.contentwrapper:has(section)'],
|
||||
defaultCleaner: false,
|
||||
|
||||
clean: ['section', 'h1', '.byline', '.img_cptn'],
|
||||
},
|
||||
};
|
@ -0,0 +1,102 @@
|
||||
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('TimesofindiaIndiatimesComExtractor', () => {
|
||||
describe('initial test case', () => {
|
||||
let result;
|
||||
let url;
|
||||
beforeAll(() => {
|
||||
url =
|
||||
'https://timesofindia.indiatimes.com/india/china-snubs-imran-says-resolve-jk-bilaterally/articleshow/71496416.cms';
|
||||
const html = fs.readFileSync(
|
||||
'./fixtures/timesofindia.indiatimes.com/1570663350014.html'
|
||||
);
|
||||
result = Mercury.parse(url, { html, fallback: true });
|
||||
});
|
||||
|
||||
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/timesofindia.indiatimes.com/index.js.
|
||||
const { title } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(
|
||||
title,
|
||||
`China snubs Imran Khan, says resolve J&K bilaterally`
|
||||
);
|
||||
});
|
||||
|
||||
it('returns the author', async () => {
|
||||
// To pass this test, fill out the author selector
|
||||
// in ./src/extractors/custom/timesofindia.indiatimes.com/index.js.
|
||||
const { author } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(author, `Saibal Dasgupta`);
|
||||
});
|
||||
|
||||
it('returns the date_published', async () => {
|
||||
// To pass this test, fill out the date_published selector
|
||||
// in ./src/extractors/custom/timesofindia.indiatimes.com/index.js.
|
||||
const { date_published } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(date_published, '2019-10-09T05:35:00.000Z');
|
||||
});
|
||||
|
||||
it('returns the lead_image_url', async () => {
|
||||
// To pass this test, fill out the lead_image_url selector
|
||||
// in ./src/extractors/custom/timesofindia.indiatimes.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://static.toiimg.com/thumb/msid-71496420,width-1070,height-580,imgsize-83878,resizemode-6,overlay-toi_sw,pt-32,y_pad-40/photo.jpg`
|
||||
);
|
||||
});
|
||||
|
||||
it('returns the content', async () => {
|
||||
// To pass this test, fill out the content selector
|
||||
// in ./src/extractors/custom/timesofindia.indiatimes.com/index.js.
|
||||
// You may also want to make use of the clean and transform
|
||||
// options.
|
||||
const { content } = await result;
|
||||
|
||||
const $ = cheerio.load(content || '');
|
||||
|
||||
const first13 = excerptContent(
|
||||
$('*')
|
||||
.first()
|
||||
.text(),
|
||||
13
|
||||
);
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(
|
||||
first13,
|
||||
'BEIJING: In what is being seen as a snub to the visiting Pakistan'
|
||||
);
|
||||
});
|
||||
});
|
||||
});
|
Loading…
Reference in New Issue