Merge pull request #13 from postlight/feat-apartmenttherapy-parser

feat: Add custom extrator for Apartment Therapy
pull/14/head
Adam Pash 8 years ago committed by GitHub
commit 94321111e9

61
dist/mercury.js vendored

@ -1034,6 +1034,64 @@ var BroadwayWorldExtractor = {
}
};
// Rename CustomExtractor
// to fit your publication
// (e.g., NYTimesExtractor)
var ApartmentTherapyExtractor = {
domain: 'www.apartmenttherapy.com',
title: {
selectors: ['h1.headline']
},
author: {
selectors: ['.PostByline__name']
},
content: {
selectors: ['div.post__content'],
// Is there anything in the content you selected that needs transformed
// before it's consumable content? E.g., unusual lazy loaded images
transforms: {
'div[data-render-react-id="images/LazyPicture"]': function divDataRenderReactIdImagesLazyPicture($node, $) {
var data = JSON.parse($node.attr('data-props'));
var src = data.sources[0].src;
var $img = $('<img />').attr('src', src);
$node.replaceWith($img);
}
},
// Is there anything that is in the result that shouldn't be?
// The clean selectors will remove anything that matches from
// the result
clean: []
},
date_published: {
selectors: [['.PostByline__timestamp[datetime]', 'datetime']]
},
lead_image_url: {
selectors: [['meta[name="og:image"]', 'value']]
},
dek: {
selectors: [['meta[name=description]', 'value']]
},
next_page_url: {
selectors: [
// enter selectors
]
},
excerpt: {
selectors: [
// enter selectors
]
}
};
var Extractors = {
'nymag.com': NYMagExtractor,
'blogspot.com': BloggerExtractor,
@ -1050,7 +1108,8 @@ var Extractors = {
'www.littlethings.com': LittleThingsExtractor,
'www.politico.com': PoliticoExtractor,
'deadspin.com': DeadspinExtractor,
'www.broadwayworld.com': BroadwayWorldExtractor
'www.broadwayworld.com': BroadwayWorldExtractor,
'www.apartmenttherapy.com': ApartmentTherapyExtractor
};
// Spacer images to be removed

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

@ -14,6 +14,7 @@ import { LittleThingsExtractor } from './custom/www.littlethings.com';
import { PoliticoExtractor } from './custom/www.politico.com';
import { DeadspinExtractor } from './custom/deadspin.com';
import { BroadwayWorldExtractor } from './custom/www.broadwayworld.com';
import { ApartmentTherapyExtractor } from './custom/www.apartmenttherapy.com';
const Extractors = {
'nymag.com': NYMagExtractor,
@ -32,6 +33,7 @@ const Extractors = {
'www.politico.com': PoliticoExtractor,
'deadspin.com': DeadspinExtractor,
'www.broadwayworld.com': BroadwayWorldExtractor,
'www.apartmenttherapy.com': ApartmentTherapyExtractor,
};
export default Extractors;

@ -0,0 +1,71 @@
// Rename CustomExtractor
// to fit your publication
// (e.g., NYTimesExtractor)
export const ApartmentTherapyExtractor = {
domain: 'www.apartmenttherapy.com',
title: {
selectors: [
'h1.headline',
],
},
author: {
selectors: [
'.PostByline__name',
],
},
content: {
selectors: [
'div.post__content',
],
// Is there anything in the content you selected that needs transformed
// before it's consumable content? E.g., unusual lazy loaded images
transforms: {
'div[data-render-react-id="images/LazyPicture"]': ($node, $) => {
const data = JSON.parse($node.attr('data-props'));
const { src } = data.sources[0];
const $img = $('<img />').attr('src', src);
$node.replaceWith($img);
},
},
// Is there anything that is in the result that shouldn't be?
// The clean selectors will remove anything that matches from
// the result
clean: [
],
},
date_published: {
selectors: [
['.PostByline__timestamp[datetime]', 'datetime'],
],
},
lead_image_url: {
selectors: [
['meta[name="og:image"]', 'value'],
],
},
dek: {
selectors: [
['meta[name=description]', 'value'],
],
},
next_page_url: {
selectors: [
// enter selectors
],
},
excerpt: {
selectors: [
// enter selectors
],
},
};

@ -0,0 +1,130 @@
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';
// Rename CustomExtractor
describe('CustomExtractor', () => {
it('is selected properly', () => {
// To pass this test, rename your extractor in
// ./src/extractors/custom/www.apartmenttherapy.com/index.js
// (e.g., CustomExtractor => NYTimesExtractor)
// then add your new extractor to
// src/extractors/all.js
const url =
'http://www.apartmenttherapy.com/a-light-filled-la-loft-236564';
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.apartmenttherapy.com/index.js.
const html =
fs.readFileSync('./fixtures/www.apartmenttherapy.com/1476396697639.html');
const articleUrl =
'http://www.apartmenttherapy.com/a-light-filled-la-loft-236564';
const { title } =
await Mercury.parse(articleUrl, html, { fallback: false });
// Update these values with the expected values from
// the article.
assert.equal(title, 'A Light Filled LA Loft');
});
it('returns the author', async () => {
// To pass this test, fill out the author selector
// in ./src/extractors/custom/www.apartmenttherapy.com/index.js.
const html =
fs.readFileSync('./fixtures/www.apartmenttherapy.com/1476396697639.html');
const articleUrl =
'http://www.apartmenttherapy.com/a-light-filled-la-loft-236564';
const { author } =
await Mercury.parse(articleUrl, html, { fallback: false });
// Update these values with the expected values from
// the article.
assert.equal(author, 'Apartment Therapy Submissions');
});
it('returns the date_published', async () => {
// To pass this test, fill out the date_published selector
// in ./src/extractors/custom/www.apartmenttherapy.com/index.js.
const html =
fs.readFileSync('./fixtures/www.apartmenttherapy.com/1476396697639.html');
const articleUrl =
'http://www.apartmenttherapy.com/a-light-filled-la-loft-236564';
const { date_published } =
await Mercury.parse(articleUrl, html, { fallback: false });
// Update these values with the expected values from
// the article.
assert.equal(date_published, '2016-10-13T21:00:00.000Z');
});
it('returns the dek', async () => {
// To pass this test, fill out the dek selector
// in ./src/extractors/custom/www.apartmenttherapy.com/index.js.
const html =
fs.readFileSync('./fixtures/www.apartmenttherapy.com/1476396697639.html');
const articleUrl =
'http://www.apartmenttherapy.com/a-light-filled-la-loft-236564';
const { dek } =
await Mercury.parse(articleUrl, html, { fallback: false });
// Update these values with the expected values from
// the article.
assert.equal(dek, "Name: Ashley Location: Downtown — Los Angeles, California Welcome to our sunny and spacious downtown home located in the in the heart of Downtown LA's Historic Core. Inside you'll find a 1,300 square foot bi-level ground unit with loft (only three of its kind!) that offers an unparalleled, refined industrial, modern aesthetic.");
});
it('returns the lead_image_url', async () => {
// To pass this test, fill out the lead_image_url selector
// in ./src/extractors/custom/www.apartmenttherapy.com/index.js.
const html =
fs.readFileSync('./fixtures/www.apartmenttherapy.com/1476396697639.html');
const articleUrl =
'http://www.apartmenttherapy.com/a-light-filled-la-loft-236564';
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://atmedia.imgix.net/9332fdca908b1fcc5c9a6891b458820718239950?w=1500&fit=max');
});
it('returns the content', async () => {
// To pass this test, fill out the content selector
// in ./src/extractors/custom/www.apartmenttherapy.com/index.js.
// You may also want to make use of the clean and transform
// options.
const html =
fs.readFileSync('./fixtures/www.apartmenttherapy.com/1476396697639.html');
const url =
'http://www.apartmenttherapy.com/a-light-filled-la-loft-236564';
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, 'Name: Ashley Location: Downtown — Los Angeles, California Welcome to our sunny and');
});
});
Loading…
Cancel
Save