Last active
January 27, 2023 15:13
-
-
Save CrossEye/7f1b66570ba6e6df3fe0de686cbd1983 to your computer and use it in GitHub Desktop.
Simple crawler
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
// https://stackoverflow.com/a/75251817 | |
// crawl :: ((a -> Promise b), (b -> [a]), (b -> c), ((Map a c) -> d), Int?) -> [a] -> Promise d | |
const crawl = (search, extract, convert, collect, simul = 1) => async (inits) => { | |
const toCheck = new Set (inits) | |
const found = new Map () | |
while (toCheck .size !== 0) { | |
const nextBlock = [...toCheck .values ()] .slice (0, simul) | |
const results = await Promise .all (nextBlock .map ((x) => search (x))) | |
results .forEach ((res, i) => { | |
const key = nextBlock [i] | |
found .set (key, convert (res)) | |
const newVals = extract (res) | |
newVals .forEach ((val) => found .has (val) || toCheck .add (val)) | |
toCheck .delete (key) | |
}) | |
} | |
return collect (found) | |
} | |
// Exmaple code | |
const get = ((data) => (id) => console .log (`Getting ${id}`) || | |
new Promise ((res, rej) => setTimeout (() => res (data [id]), 1000)) | |
)({ // don't look for any structure here. The fruits were more fun than "a", "b", "c", ... | |
1: {val: ['Apples', 'Apricots'], kids: [3, 5]}, | |
2: {val: ['Bananas', 'Boysenberries', 'Blackberries', 'Blueberries'], kids: [3, 4]}, | |
3: {val: ['Cherries', 'Cantaloupes', 'Clementines'], kids: []}, | |
4: {val: ['Dates', 'Dewberries', 'Dragon Fruit'], kids: [1, 4, 5]}, | |
5: {val: ['Elderberries', 'Eggfruit'], kids: [2]}, | |
6: {val: ['Fig', 'Farkleberries'], kids: [6, 7]}, | |
7: {val: ['Grapefruit', 'Grapes', 'Gooseberries', 'Guava'], kids: []}, | |
}) | |
const findFruit = crawl ( | |
get, | |
(x) => x .kids, | |
(x) => x .val, | |
(m) => [... m .values ()], | |
3 | |
) | |
findFruit ([1]) // or, say, [1, 6] | |
.then (letters => console .log ('Results:', letters)) | |
.catch (err => console .log (`Error: ${err}`)) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment