blob: 9e469e3e614c84a78f9d68bdd84922cfd481295b (
plain) (
blame)
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
|
import { ACTIVITY_PUB, JOB_REQUEST_TIMEOUT, WEBSERVER } from '../../initializers/constants'
import { doRequest } from '../../helpers/requests'
import { logger } from '../../helpers/logger'
import * as Bluebird from 'bluebird'
import { ActivityPubOrderedCollection } from '../../../shared/models/activitypub'
import { parse } from 'url'
type HandlerFunction<T> = (items: T[]) => (Promise<any> | Bluebird<any>)
type CleanerFunction = (startedDate: Date) => (Promise<any> | Bluebird<any>)
async function crawlCollectionPage <T> (uri: string, handler: HandlerFunction<T>, cleaner?: CleanerFunction) {
logger.info('Crawling ActivityPub data on %s.', uri)
const options = {
method: 'GET',
uri,
json: true,
activityPub: true,
timeout: JOB_REQUEST_TIMEOUT
}
const startDate = new Date()
const response = await doRequest<ActivityPubOrderedCollection<T>>(options)
const firstBody = response.body
let limit = ACTIVITY_PUB.FETCH_PAGE_LIMIT
let i = 0
let nextLink = firstBody.first
while (nextLink && i < limit) {
let body: any
if (typeof nextLink === 'string') {
// Don't crawl ourselves
const remoteHost = parse(nextLink).host
if (remoteHost === WEBSERVER.HOST) continue
options.uri = nextLink
const res = await doRequest<ActivityPubOrderedCollection<T>>(options)
body = res.body
} else {
// nextLink is already the object we want
body = nextLink
}
nextLink = body.next
i++
if (Array.isArray(body.orderedItems)) {
const items = body.orderedItems
logger.info('Processing %i ActivityPub items for %s.', items.length, options.uri)
await handler(items)
}
}
if (cleaner) await cleaner(startDate)
}
export {
crawlCollectionPage
}
|
