Skip to content

Commit 7b52d3d

Browse files
janetleekimdviramontes
authored andcommitted
feat: al.com parser (#110)
* feat: al.com parser I think this is good but could you pls double check time zone on the date? Thanks * fix: date_published timezone
1 parent 15df584 commit 7b52d3d

File tree

4 files changed

+137
-0
lines changed

4 files changed

+137
-0
lines changed

fixtures/www.al.com/1482445422101.html

+3
Large diffs are not rendered by default.

src/extractors/custom/index.js

+1
Original file line numberDiff line numberDiff line change
@@ -51,6 +51,7 @@ export * from './uproxx.com';
5151
export * from './www.eonline.com';
5252
export * from './www.miamiherald.com';
5353
export * from './www.refinery29.com';
54+
export * from './www.al.com';
5455
export * from './www.thepennyhoarder.com';
5556
export * from './www.westernjournalism.com';
5657
export * from './fusion.net';
+46
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,46 @@
1+
export const WwwAlComExtractor = {
2+
domain: 'www.al.com',
3+
4+
title: {
5+
selectors: [
6+
['meta[name="title"]', 'value'],
7+
],
8+
},
9+
10+
author: {
11+
selectors: [
12+
['meta[name="article_author"]', 'value'],
13+
],
14+
},
15+
16+
date_published: {
17+
selectors: [
18+
['meta[name="article_date_original"]', 'value'],
19+
],
20+
timezone: 'EST',
21+
},
22+
23+
lead_image_url: {
24+
selectors: [
25+
['meta[name="og:image"]', 'value'],
26+
],
27+
},
28+
29+
content: {
30+
selectors: [
31+
'.entry-content',
32+
],
33+
34+
// Is there anything in the content you selected that needs transformed
35+
// before it's consumable content? E.g., unusual lazy loaded images
36+
transforms: {
37+
},
38+
39+
// Is there anything that is in the result that shouldn't be?
40+
// The clean selectors will remove anything that matches from
41+
// the result
42+
clean: [
43+
44+
],
45+
},
46+
};
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,87 @@
1+
import assert from 'assert';
2+
import fs from 'fs';
3+
import URL from 'url';
4+
import cheerio from 'cheerio';
5+
6+
import Mercury from 'mercury';
7+
import getExtractor from 'extractors/get-extractor';
8+
import { excerptContent } from 'utils/text';
9+
10+
describe('WwwAlComExtractor', () => {
11+
describe('initial test case', () => {
12+
let result;
13+
let url;
14+
beforeAll(() => {
15+
url =
16+
'http://www.al.com/news/birmingham/index.ssf/2016/12/two_arrested_in_multi-state_de.html#incart_river_home';
17+
const html =
18+
fs.readFileSync('./fixtures/www.al.com/1482445422101.html');
19+
result =
20+
Mercury.parse(url, html, { fallback: false });
21+
});
22+
23+
it('is selected properly', () => {
24+
// This test should be passing by default.
25+
// It sanity checks that the correct parser
26+
// is being selected for URLs from this domain
27+
const extractor = getExtractor(url);
28+
assert.equal(extractor.domain, URL.parse(url).hostname);
29+
});
30+
31+
it('returns the title', async () => {
32+
// To pass this test, fill out the title selector
33+
// in ./src/extractors/custom/www.al.com/index.js.
34+
const { title } = await result;
35+
36+
// Update these values with the expected values from
37+
// the article.
38+
assert.equal(title, 'Two arrested in multi-state debit card skimming scheme');
39+
});
40+
41+
it('returns the author', async () => {
42+
// To pass this test, fill out the author selector
43+
// in ./src/extractors/custom/www.al.com/index.js.
44+
const { author } = await result;
45+
46+
// Update these values with the expected values from
47+
// the article.
48+
assert.equal(author, 'Mike Cason | [email protected]');
49+
});
50+
51+
it('returns the date_published', async () => {
52+
// To pass this test, fill out the date_published selector
53+
// in ./src/extractors/custom/www.al.com/index.js.
54+
const { date_published } = await result;
55+
56+
// Update these values with the expected values from
57+
// the article.
58+
assert.equal(date_published, '2016-12-22T19:47:00.000Z');
59+
});
60+
61+
it('returns the lead_image_url', async () => {
62+
// To pass this test, fill out the lead_image_url selector
63+
// in ./src/extractors/custom/www.al.com/index.js.
64+
const { lead_image_url } = await result;
65+
66+
// Update these values with the expected values from
67+
// the article.
68+
assert.equal(lead_image_url, 'http://image.al.com/home/bama-media/width620/img/news_birmingham_impact/photo/21753198-standard.jpg');
69+
});
70+
71+
it('returns the content', async () => {
72+
// To pass this test, fill out the content selector
73+
// in ./src/extractors/custom/www.al.com/index.js.
74+
// You may also want to make use of the clean and transform
75+
// options.
76+
const { content } = await result;
77+
78+
const $ = cheerio.load(content || '');
79+
80+
const first13 = excerptContent($('*').first().text(), 13);
81+
82+
// Update these values with the expected values from
83+
// the article.
84+
assert.equal(first13, 'Jake Frith, special agent with the Alabama Attorney General\'s office, talks about an');
85+
});
86+
});
87+
});

0 commit comments

Comments
 (0)