Add a new custom extractor for www.abendblatt.de (#559)
* Add custom extractor for www.abendblatt.de * update Co-authored-by: Marco Wiedemeyer <marco.wiedemeyer@ottogroup.com> Co-authored-by: John Holdun <john@johnholdun.com>pull/570/head
parent
6014016283
commit
d0c78911e6
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,91 @@
|
||||
/* eslint-disable no-nested-ternary */
|
||||
/* eslint-disable no-unused-expressions */
|
||||
export const WwwAbendblattDeExtractor = {
|
||||
domain: 'www.abendblatt.de',
|
||||
|
||||
title: {
|
||||
selectors: ['h2.article__header__headline'],
|
||||
},
|
||||
|
||||
author: {
|
||||
selectors: ['span.author-info__name-text'],
|
||||
},
|
||||
|
||||
date_published: {
|
||||
selectors: [['time.article__header__date', 'datetime']],
|
||||
},
|
||||
|
||||
dek: {
|
||||
selectors: ["span[itemprop='description']"],
|
||||
},
|
||||
|
||||
lead_image_url: {
|
||||
selectors: [["meta[name='og:image']", 'value']],
|
||||
},
|
||||
|
||||
content: {
|
||||
selectors: ['div.article__body'],
|
||||
|
||||
// Is there anything in the content you selected that needs transformed
|
||||
// before it's consumable content? E.g., unusual lazy loaded images
|
||||
transforms: {
|
||||
p: $node => {
|
||||
if (!$node.hasClass('obfuscated')) return null;
|
||||
let o = '';
|
||||
let n = 0;
|
||||
for (let i = $node.text(); n < i.length; n += 1) {
|
||||
const r = i.charCodeAt(n);
|
||||
r === 177
|
||||
? (o += '%')
|
||||
: r === 178
|
||||
? (o += '!')
|
||||
: r === 180
|
||||
? (o += ';')
|
||||
: r === 181
|
||||
? (o += '=')
|
||||
: r === 32
|
||||
? (o += ' ')
|
||||
: r === 10
|
||||
? (o += '\n')
|
||||
: r > 33 && (o += String.fromCharCode(r - 1));
|
||||
}
|
||||
|
||||
$node.html(o);
|
||||
$node.removeClass('obfuscated');
|
||||
$node.addClass('deobfuscated');
|
||||
return null;
|
||||
},
|
||||
div: $node => {
|
||||
if (!$node.hasClass('obfuscated')) return null;
|
||||
let o = '';
|
||||
let n = 0;
|
||||
for (let i = $node.text(); n < i.length; n += 1) {
|
||||
const r = i.charCodeAt(n);
|
||||
r === 177
|
||||
? (o += '%')
|
||||
: r === 178
|
||||
? (o += '!')
|
||||
: r === 180
|
||||
? (o += ';')
|
||||
: r === 181
|
||||
? (o += '=')
|
||||
: r === 32
|
||||
? (o += ' ')
|
||||
: r === 10
|
||||
? (o += '\n')
|
||||
: r > 33 && (o += String.fromCharCode(r - 1));
|
||||
}
|
||||
|
||||
$node.html(o);
|
||||
$node.removeClass('obfuscated');
|
||||
$node.addClass('deobfuscated');
|
||||
return null;
|
||||
},
|
||||
},
|
||||
|
||||
// Is there anything that is in the result that shouldn't be?
|
||||
// The clean selectors will remove anything that matches from
|
||||
// the result
|
||||
clean: [],
|
||||
},
|
||||
};
|
@ -0,0 +1,112 @@
|
||||
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('WwwAbendblattDeExtractor', () => {
|
||||
describe('initial test case', () => {
|
||||
let result;
|
||||
let url;
|
||||
beforeAll(() => {
|
||||
url =
|
||||
'https://www.abendblatt.de/wirtschaft/article229123092/Hamburg-Grossmarkt-Obst-Gemuese-Mangos-Papayas-Fruechte-Preise-Corona.html';
|
||||
const html = fs.readFileSync(
|
||||
'./fixtures/www.abendblatt.de/1589525587379.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.abendblatt.de/index.js.
|
||||
const { title } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(title, `Warum Mangos und Papayas jetzt teurer sind`);
|
||||
});
|
||||
|
||||
it('returns the author', async () => {
|
||||
// To pass this test, fill out the author selector
|
||||
// in ./src/extractors/custom/www.abendblatt.de/index.js.
|
||||
const { author } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(author, 'Melanie Wassink');
|
||||
});
|
||||
|
||||
it('returns the date_published', async () => {
|
||||
// To pass this test, fill out the date_published selector
|
||||
// in ./src/extractors/custom/www.abendblatt.de/index.js.
|
||||
const { date_published } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(date_published, '2020-05-15T05:11:00.000Z');
|
||||
});
|
||||
|
||||
it('returns the dek', async () => {
|
||||
// To pass this test, fill out the dek selector
|
||||
// in ./src/extractors/custom/www.abendblatt.de/index.js.
|
||||
const { dek } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(
|
||||
dek,
|
||||
'Obst wird auch in Corona-Zeiten weltweit transportiert. Doch es gibt Probleme, wie ein Besuch auf dem Hamburger Großmarkt zeigt'
|
||||
);
|
||||
});
|
||||
|
||||
it('returns the lead_image_url', async () => {
|
||||
// To pass this test, fill out the lead_image_url selector
|
||||
// in ./src/extractors/custom/www.abendblatt.de/index.js.
|
||||
const { lead_image_url } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(
|
||||
lead_image_url,
|
||||
`https://img.abendblatt.de/img/wirtschaft/crop229123088/9271097785-w820-cv16_9-q85-fnov-fpi227770079-fpotr/Fruchtgrossmarkt.jpg`
|
||||
);
|
||||
});
|
||||
|
||||
it('returns the content', async () => {
|
||||
// To pass this test, fill out the content selector
|
||||
// in ./src/extractors/custom/www.abendblatt.de/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,
|
||||
'Hamburg. Gabi Eutemüller und Eliane Steinmeyer stehen in einer Halle auf dem Gelände'
|
||||
);
|
||||
});
|
||||
});
|
||||
});
|
Loading…
Reference in New Issue