1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
|
import {extractHtmlMeta} from '../../src/lib/link-meta/html'
import {exampleComHtml} from './__mocks__/exampleComHtml'
import {youtubeHTML} from './__mocks__/youtubeHtml'
import {tiktokHtml} from './__mocks__/tiktokHtml'
import {youtubeChannelHtml} from './__mocks__/youtubeChannelHtml'
describe('extractHtmlMeta', () => {
const cases = [
['', {}],
['nothing', {}],
['<title>title</title>', {title: 'title'}],
['<title> aSd!@#AC </title>', {title: 'aSd!@#AC'}],
['<title>\n title\n </title>', {title: 'title'}],
['<meta name="title" content="meta title">', {title: 'meta title'}],
[
'<meta name="description" content="meta description">',
{description: 'meta description'},
],
['<meta property="og:title" content="og title">', {title: 'og title'}],
[
'<meta property="og:description" content="og description">',
{description: 'og description'},
],
[
'<meta property="og:image" content="https://ogimage.com/foo.png">',
{image: 'https://ogimage.com/foo.png'},
],
[
'<meta property="twitter:title" content="twitter title">',
{title: 'twitter title'},
],
[
'<meta property="twitter:description" content="twitter description">',
{description: 'twitter description'},
],
[
'<meta property="twitter:image" content="https://twitterimage.com/foo.png">',
{image: 'https://twitterimage.com/foo.png'},
],
['<meta\n name="title"\n content="meta title"\n>', {title: 'meta title'}],
]
it.each(cases)(
'given the html tag %p, returns %p',
// @ts-ignore not worth fixing -prf
(input, expectedResult) => {
const output = extractHtmlMeta({html: input as string, hostname: ''})
expect(output).toEqual(expectedResult)
},
)
it('extracts title and description from a generic HTML page', () => {
const input = exampleComHtml
const expectedOutput = {
title: 'Example Domain',
description: 'An example website',
}
const output = extractHtmlMeta({html: input, hostname: 'example.com'})
expect(output).toEqual(expectedOutput)
})
it('extracts title and description from a Tiktok HTML page', () => {
const input = tiktokHtml
const expectedOutput = {
title:
'Coca-Cola and Mentos! Super Reaction! #cocacola #mentos #reaction #bal... | TikTok',
description:
'5.5M Likes, 20.8K Comments. TikTok video from Power Vision Tests (@_powervision_): "Coca-Cola and Mentos! Super Reaction! #cocacola #mentos #reaction #balloon #sciencemoment #scienceexperiment #experiment #test #amazing #pvexp". оригинальный звук - Power Vision Tests.',
}
const output = extractHtmlMeta({html: input, hostname: 'tiktok.com'})
expect(output).toEqual(expectedOutput)
})
it('extracts title and description from a generic youtube page', () => {
const input = youtubeHTML
const expectedOutput = {
title: 'HD Video (1080p) with Relaxing Music of Native American Shamans',
description:
'Stunning HD Video ( 1080p ) of Patagonian Nature with Relaxing Native American Shamanic Music. HD footage used from ',
image: 'https://i.ytimg.com/vi/x6UITRjhijI/sddefault.jpg',
}
const output = extractHtmlMeta({html: input, hostname: 'youtube.com'})
expect(output).toEqual(expectedOutput)
})
it('extracts avatar from a youtube channel', () => {
const input = youtubeChannelHtml
const expectedOutput = {
title: 'penguinz0',
description:
'Clips channel: https://www.youtube.com/channel/UC4EQHfzIbkL_Skit_iKt1aA\n\nTwitter: https://twitter.com/MoistCr1TiKaL\n\nInstagram: https://www.instagram.com/bigmoistcr1tikal/?hl=en\n\nTwitch: https://www.twitch.tv/moistcr1tikal\n\nSnapchat: Hugecharles\n\nTik Tok: Hugecharles\n\nI don't have any other public accounts.',
image:
'https://yt3.googleusercontent.com/ytc/AL5GRJWOhJOuUC6C2b7gP-5D2q6ypXbcOOckyAE1En4RUQ=s176-c-k-c0x00ffffff-no-rj',
}
const output = extractHtmlMeta({html: input, hostname: 'youtube.com'})
expect(output).toEqual(expectedOutput)
})
it('extracts username from the url a twitter profile page', () => {
const expectedOutput = {
title: '@bluesky on Twitter',
}
const output = extractHtmlMeta({
html: '',
hostname: 'twitter.com',
pathname: '/bluesky',
})
expect(output).toEqual(expectedOutput)
})
it('extracts username from the url a tweet', () => {
const expectedOutput = {
title: 'Tweet by @bluesky',
}
const output = extractHtmlMeta({
html: '',
hostname: 'twitter.com',
pathname: '/bluesky/status/1582437529969917953',
})
expect(output).toEqual(expectedOutput)
})
it("does not extract username from the url when it's not a tweet or profile page", () => {
const expectedOutput = {
title: 'Twitter',
}
const output = extractHtmlMeta({
html: '',
hostname: 'twitter.com',
pathname: '/i/articles/follows/-1675653703?time_window=24',
})
expect(output).toEqual(expectedOutput)
})
})
|
