-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathcrawl.js
More file actions
87 lines (75 loc) · 2.28 KB
/
Copy pathcrawl.js
File metadata and controls
87 lines (75 loc) · 2.28 KB
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
const{JSDOM} = require('jsdom')
async function crawlPage(baseURL, currentURL, pages){
const baseURLObj = new URL(baseURL)
const currentURLObj = new URL(currentURL)
if (baseURLObj.hostname !== currentURLObj.hostname){
return pages
}
const normalizedCurrentURL = normalizeURL(currentURL)
if(pages[normalizedCurrentURL] > 0){
pages[normalizedCurrentURL]++
return pages
}
pages[normalizedCurrentURL] = 1
console.log(`actively crawling: ${currentURL}`);
try {
const resp = await fetch(currentURL)
if(resp.status > 399){
console.log(`error in fetch with status code: ${resp.status} on page: ${currentURL}`)
return pages
}
const contentType = resp.headers.get("content-type")
if (!contentType.includes("text/html")) {
console.log(
`non html response, content type: ${contentType}, on page: ${currentURL}`
)
return pages
}
const htmlBody = await resp.text()
const nextURLs = getURLsFromHTML(htmlBody, baseURL)
for(const nextURL of nextURLs){
pages = await crawlPage(baseURL, nextURL, pages)
}
} catch (err) {
console.log(`error in fetch: ${err.message}, on page: ${currentURL} `)
}
return pages
}
function getURLsFromHTML(htmlBody, baseURL) {
const urls = []
const dom = new JSDOM(htmlBody)
const linkElements = dom.window.document.querySelectorAll('a')
for (const linkElement of linkElements){
if(linkElement.href.slice(0,1) === '/'){
// relative
try {
const urlObj = new URL(`${baseURL}${linkElement.href}`)
urls.push(urlObj.href)
} catch (err) {
console.log(`error with relative url: ${err.message}`)
}
} else {
// absolute
try {
const urlObj = new URL(linkElement.href)
urls.push(urlObj.href)
} catch (err) {
console.log(`error with absolute url: ${err.message}`)
}
}
}
return urls
}
function normalizeURL(urlString) {
const urlObj = new URL(urlString)
const hostPath = `${urlObj.hostname}${urlObj.pathname}`
if(hostPath.length > 0 && hostPath.slice(-1) === '/'){
return hostPath.slice(0,-1)
}
return hostPath
}
module.exports = {
normalizeURL,
getURLsFromHTML,
crawlPage
}