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
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
|
import logger from "@remember/shared/logger";
import {
LinkCrawlerQueue,
OpenAIQueue,
ZCrawlLinkRequest,
queueConnectionDetails,
zCrawlLinkRequestSchema,
} from "@remember/shared/queues";
import { Worker } from "bullmq";
import { Job } from "bullmq";
import { prisma } from "@remember/db";
import { Browser } from "puppeteer";
import puppeteer from "puppeteer-extra";
import StealthPlugin from "puppeteer-extra-plugin-stealth";
import metascraper from "metascraper";
import metascraperDescription from "metascraper-description";
import metascraperImage from "metascraper-image";
import metascraperLogo from "metascraper-logo-favicon";
import metascraperTitle from "metascraper-title";
import metascraperUrl from "metascraper-url";
import metascraperTwitter from "metascraper-twitter";
import metascraperReadability from "metascraper-readability";
import { Mutex } from "async-mutex";
import assert from "assert";
const metascraperParser = metascraper([
metascraperReadability(),
metascraperTitle(),
metascraperDescription(),
metascraperTwitter(),
metascraperImage(),
metascraperLogo(),
metascraperUrl(),
]);
let browser: Browser | undefined;
// Guards the interactions with the browser instance.
// This is needed given that most of the browser APIs are async.
const browserMutex = new Mutex();
async function launchBrowser() {
browser = undefined;
await browserMutex.runExclusive(async () => {
browser = await puppeteer.launch({ headless: true });
browser.on("disconnected", async () => {
logger.info(
"The puppeteer browser got disconnected. Will attempt to launch it again.",
);
await launchBrowser();
});
});
}
export class CrawlerWorker {
static async build() {
puppeteer.use(StealthPlugin());
await launchBrowser();
logger.info("Starting crawler worker ...");
const worker = new Worker<ZCrawlLinkRequest, void>(
LinkCrawlerQueue.name,
runCrawler,
{
connection: queueConnectionDetails,
autorun: false,
},
);
worker.on("completed", (job) => {
const jobId = job?.id || "unknown";
logger.info(`[Crawler][${jobId}] Completed successfully`);
});
worker.on("failed", (job, error) => {
const jobId = job?.id || "unknown";
logger.error(`[Crawler][${jobId}] Crawling job failed: ${error}`);
});
return worker;
}
}
async function getBookmarkUrl(bookmarkId: string) {
const bookmark = await prisma.bookmarkedLink.findUnique({
where: { id: bookmarkId },
});
if (!bookmark) {
throw new Error("The bookmark either doesn't exist or not a link");
}
return bookmark.url;
}
async function crawlPage(url: string) {
assert(browser);
const context = await browser.createBrowserContext();
try {
const page = await context.newPage();
await page.goto(url, {
timeout: 10000, // 10 seconds
waitUntil: "networkidle2",
});
const htmlContent = await page.content();
return htmlContent;
} finally {
await context.close();
}
}
async function runCrawler(job: Job<ZCrawlLinkRequest, void>) {
const jobId = job.id || "unknown";
const request = zCrawlLinkRequestSchema.safeParse(job.data);
if (!request.success) {
logger.error(
`[Crawler][${jobId}] Got malformed job request: ${request.error.toString()}`,
);
return;
}
const { bookmarkId } = request.data;
const url = await getBookmarkUrl(bookmarkId);
logger.info(
`[Crawler][${jobId}] Will crawl "${url}" for link with id "${bookmarkId}"`,
);
// TODO(IMPORTANT): Run security validations on the input URL (e.g. deny localhost, etc)
const htmlContent = await crawlPage(url);
const meta = await metascraperParser({
url,
html: htmlContent,
});
await prisma.bookmarkedLink.update({
where: {
id: bookmarkId,
},
data: {
title: meta.title,
description: meta.description,
imageUrl: meta.image,
favicon: meta.logo,
crawledAt: new Date(),
},
});
// Enqueue openai job
OpenAIQueue.add("openai", {
bookmarkId,
});
}
|
