feat: remove obsolete custom extractors (#712)
parent
4981355628
commit
7b68bcd94c
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@ -1,34 +0,0 @@
|
||||
export const WwwCinemablendComExtractor = {
|
||||
domain: 'www.cinemablend.com',
|
||||
|
||||
title: {
|
||||
selectors: ['.story_title'],
|
||||
},
|
||||
|
||||
author: {
|
||||
selectors: ['.author'],
|
||||
},
|
||||
|
||||
date_published: {
|
||||
selectors: [['meta[name="article:published_time"]', 'value']],
|
||||
|
||||
timezone: 'EST',
|
||||
},
|
||||
|
||||
lead_image_url: {
|
||||
selectors: [['meta[name="og:image"]', 'value']],
|
||||
},
|
||||
|
||||
content: {
|
||||
selectors: ['div#wrap_left_content'],
|
||||
|
||||
// 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: [],
|
||||
},
|
||||
};
|
@ -1,102 +0,0 @@
|
||||
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('WwwCinemablendComExtractor', () => {
|
||||
describe('initial test case', () => {
|
||||
let result;
|
||||
let url;
|
||||
beforeAll(() => {
|
||||
url =
|
||||
'http://www.cinemablend.com/news/1602870/to-3d-or-not-to-3d-buy-the-right-passengers-ticket';
|
||||
const html = fs.readFileSync(
|
||||
'./fixtures/www.cinemablend.com/1482432215722.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.cinemablend.com/index.js.
|
||||
const { title } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(
|
||||
title,
|
||||
'To 3D Or Not To 3D: Buy The Right Passengers Ticket'
|
||||
);
|
||||
});
|
||||
|
||||
it('returns the author', async () => {
|
||||
// To pass this test, fill out the author selector
|
||||
// in ./src/extractors/custom/www.cinemablend.com/index.js.
|
||||
const { author } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(author, 'Mike Reyes');
|
||||
});
|
||||
|
||||
it('returns the date_published', async () => {
|
||||
// To pass this test, fill out the date_published selector
|
||||
// in ./src/extractors/custom/www.cinemablend.com/index.js.
|
||||
const { date_published } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(date_published, '2016-12-22T02:46:48.000Z');
|
||||
});
|
||||
|
||||
it('returns the lead_image_url', async () => {
|
||||
// To pass this test, fill out the lead_image_url selector
|
||||
// in ./src/extractors/custom/www.cinemablend.com/index.js.
|
||||
const { lead_image_url } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(
|
||||
lead_image_url,
|
||||
'http://img.cinemablend.com/quill/6/a/4/e/4/0/6a4e40e4aad46eb7b27810ce5a9fccff01c03c19.jpg'
|
||||
);
|
||||
});
|
||||
|
||||
it('returns the content', async () => {
|
||||
// To pass this test, fill out the content selector
|
||||
// in ./src/extractors/custom/www.cinemablend.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,
|
||||
'What happens when you put two beautiful people together in the black of'
|
||||
);
|
||||
});
|
||||
});
|
||||
});
|
@ -1,33 +0,0 @@
|
||||
export const WwwHowtogeekComExtractor = {
|
||||
domain: 'www.howtogeek.com',
|
||||
|
||||
title: {
|
||||
selectors: ['title'],
|
||||
},
|
||||
|
||||
author: {
|
||||
selectors: ['#authorinfobox a'],
|
||||
},
|
||||
|
||||
date_published: {
|
||||
selectors: ['#authorinfobox + div li'],
|
||||
timezone: 'GMT',
|
||||
},
|
||||
|
||||
lead_image_url: {
|
||||
selectors: [['meta[name="og:image"]', 'value']],
|
||||
},
|
||||
|
||||
content: {
|
||||
selectors: ['.thecontent'],
|
||||
|
||||
// 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: [],
|
||||
},
|
||||
};
|
@ -1,102 +0,0 @@
|
||||
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('WwwHowtogeekComExtractor', () => {
|
||||
describe('initial test case', () => {
|
||||
let result;
|
||||
let url;
|
||||
beforeAll(() => {
|
||||
url =
|
||||
'http://www.howtogeek.com/282568/amazon-echo-vs.-google-home-which-one-should-you-buy/';
|
||||
const html = fs.readFileSync(
|
||||
'./fixtures/www.howtogeek.com/1482438125052.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.howtogeek.com/index.js.
|
||||
const { title } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(
|
||||
title,
|
||||
'Amazon Echo vs. Google Home: Which One Should You Buy?'
|
||||
);
|
||||
});
|
||||
|
||||
it('returns the author', async () => {
|
||||
// To pass this test, fill out the author selector
|
||||
// in ./src/extractors/custom/www.howtogeek.com/index.js.
|
||||
const { author } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(author, 'Craig Lloyd');
|
||||
});
|
||||
|
||||
it('returns the date_published', async () => {
|
||||
// To pass this test, fill out the date_published selector
|
||||
// in ./src/extractors/custom/www.rawstory.com/index.js.
|
||||
const { date_published } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(date_published, '2016-12-10T00:00:00.000Z');
|
||||
});
|
||||
|
||||
it('returns the lead_image_url', async () => {
|
||||
// To pass this test, fill out the lead_image_url selector
|
||||
// in ./src/extractors/custom/www.howtogeek.com/index.js.
|
||||
const { lead_image_url } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(
|
||||
lead_image_url,
|
||||
'http://www.howtogeek.com/thumbcache/280/160/2c80a158f6eb69883931148a7dc900a0/wp-content/uploads/2016/11/2016-11-29_0011-650x301.jpg'
|
||||
);
|
||||
});
|
||||
|
||||
it('returns the content', async () => {
|
||||
// To pass this test, fill out the content selector
|
||||
// in ./src/extractors/custom/www.howtogeek.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,
|
||||
'Amazon blew the industry wide open with its release of the Echo back'
|
||||
);
|
||||
});
|
||||
});
|
||||
});
|
@ -1,34 +0,0 @@
|
||||
export const WwwNjComExtractor = {
|
||||
domain: 'www.nj.com',
|
||||
|
||||
title: {
|
||||
selectors: [['meta[name="title"]', 'value']],
|
||||
},
|
||||
|
||||
author: {
|
||||
selectors: [['meta[name="article_author"]', 'value']],
|
||||
},
|
||||
|
||||
date_published: {
|
||||
selectors: [['meta[name="article_date_original"]', 'value']],
|
||||
|
||||
timezone: 'America/New_York',
|
||||
},
|
||||
|
||||
lead_image_url: {
|
||||
selectors: [['meta[name="og:image"]', 'value']],
|
||||
},
|
||||
|
||||
content: {
|
||||
selectors: ['.entry-content'],
|
||||
|
||||
// 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: [],
|
||||
},
|
||||
};
|
@ -1,100 +0,0 @@
|
||||
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('WwwNjComExtractor', () => {
|
||||
describe('initial test case', () => {
|
||||
let result;
|
||||
let url;
|
||||
beforeAll(() => {
|
||||
url =
|
||||
'http://www.nj.com/essex/index.ssf/2016/12/man_sentenced_for_stealing_millions_from_nj_atms_i.html#incart_river_home';
|
||||
const html = fs.readFileSync('./fixtures/www.nj.com/1481666201503.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.nj.com/index.js.
|
||||
const { title } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(
|
||||
title,
|
||||
'Man sentenced for stealing millions in elaborate N.J. ATM skimming scheme'
|
||||
);
|
||||
});
|
||||
|
||||
it('returns the author', async () => {
|
||||
// To pass this test, fill out the author selector
|
||||
// in ./src/extractors/custom/www.nj.com/index.js.
|
||||
const { author } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(author, 'Rajeev Dhir | NJ Advance Media for NJ.com');
|
||||
});
|
||||
|
||||
it('returns the date_published', async () => {
|
||||
// To pass this test, fill out the date_published selector
|
||||
// in ./src/extractors/custom/www.nj.com/index.js.
|
||||
const { date_published } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(date_published, '2016-12-13T21:51:00.000Z');
|
||||
});
|
||||
|
||||
it('returns the lead_image_url', async () => {
|
||||
// To pass this test, fill out the lead_image_url selector
|
||||
// in ./src/extractors/custom/www.nj.com/index.js.
|
||||
const { lead_image_url } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(
|
||||
lead_image_url,
|
||||
'http://image.nj.com/home/njo-media/width620/img/njcom_photos/photo/2016/12/08/21671718-large.png'
|
||||
);
|
||||
});
|
||||
|
||||
it('returns the content', async () => {
|
||||
// To pass this test, fill out the content selector
|
||||
// in ./src/extractors/custom/www.nj.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,
|
||||
'NEWARK -- A Romanian native was sentenced to 57 months on Tuesday for'
|
||||
);
|
||||
});
|
||||
});
|
||||
});
|
Loading…
Reference in New Issue