blob: 8d33deddd25739918b6afbcce1f9a064cf388fca (
plain)
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
|
'use strict'
const MAX_DOWNLOAD_ATTEMPTS = 5
const fetch = require('node-fetch')
const { getHTMLLinks } = require('./crawl-links')
function crawl(absURL, attempts = 0) {
return fetch(absURL)
.then(res => res.text().then(text => playlistifyParse(text, absURL)), err => {
console.error('Failed to download: ' + absURL)
if (attempts < MAX_DOWNLOAD_ATTEMPTS) {
console.error(
'Trying again. Attempt ' + (attempts + 1) +
'/' + MAX_DOWNLOAD_ATTEMPTS + '...'
)
return crawl(absURL, attempts + 1)
} else {
console.error(
'We\'ve hit the download attempt limit (' +
MAX_DOWNLOAD_ATTEMPTS + '). Giving up on ' +
'this path.'
)
throw 'FAILED_DOWNLOAD'
}
})
.catch(error => {
if (error === 'FAILED_DOWNLOAD') {
// Debug logging for this is already handled above.
return []
} else {
throw error
}
})
}
function playlistifyParse(text, absURL) {
const links = getHTMLLinks(text)
const verbose = process.argv.includes('--verbose')
return Promise.all(links.map(link => {
const [ title, href ] = link
if (href.endsWith('/')) {
// It's a directory!
if (verbose) console.log('[Dir] ' + absURL + href)
return crawl(absURL + href)
.then(res => [title, res])
} else {
// It's a file!
if (verbose) console.log('[File] ' + absURL + href)
return Promise.resolve([title, absURL + href])
}
}))
}
if (process.argv.length === 2) {
console.log('Usage: crawl-recursive http://example.com/example/path')
} else {
let url = process.argv[2]
if (!(url.endsWith('/'))) {
url = url + '/'
}
crawl(url)
.then(res => console.log(JSON.stringify(res, null, 2)))
.catch(err => console.error(err))
}
|
