Fixes #22 adding User-Agent request header to bypass Incapsula protection of OSRS hiscore pages

This commit is contained in:
molo-pl
2021-01-12 15:37:19 +01:00
parent 0f68c1995c
commit cf8a4cc26e
4 changed files with 43 additions and 10 deletions

View File

@@ -37,7 +37,8 @@
"homepage": "https://github.com/maxswa/osrs-json-hiscores#readme", "homepage": "https://github.com/maxswa/osrs-json-hiscores#readme",
"dependencies": { "dependencies": {
"axios": "^0.21.1", "axios": "^0.21.1",
"jsdom": "^16.3.0" "jsdom": "^16.3.0",
"useragent-generator": "^1.1.0"
}, },
"devDependencies": { "devDependencies": {
"@types/jest": "^24.0.14", "@types/jest": "^24.0.14",

View File

@@ -1,4 +1,3 @@
import axios from 'axios';
import { import {
Player, Player,
Activity, Activity,
@@ -26,6 +25,7 @@ import {
numberFromElement, numberFromElement,
rsnFromElement, rsnFromElement,
getActivityPageURL, getActivityPageURL,
httpGet,
BOSSES, BOSSES,
} from './utils'; } from './utils';
import { JSDOM } from 'jsdom'; import { JSDOM } from 'jsdom';
@@ -39,12 +39,12 @@ export async function getStats(rsn: string): Promise<Player> {
throw Error('RSN must be between 1 and 12 characters'); throw Error('RSN must be between 1 and 12 characters');
} }
const mainRes = await axios(getStatsURL('main', rsn)); const mainRes = await httpGet(getStatsURL('main', rsn));
if (mainRes.status === 200) { if (mainRes.status === 200) {
const otherResponses = await Promise.all([ const otherResponses = await Promise.all([
axios(getStatsURL('ironman', rsn)).catch(err => err), httpGet(getStatsURL('ironman', rsn)).catch(err => err),
axios(getStatsURL('hardcore', rsn)).catch(err => err), httpGet(getStatsURL('hardcore', rsn)).catch(err => err),
axios(getStatsURL('ultimate', rsn)).catch(err => err), httpGet(getStatsURL('ultimate', rsn)).catch(err => err),
getRSNFormat(rsn).catch(() => undefined), getRSNFormat(rsn).catch(() => undefined),
]); ]);
@@ -120,7 +120,7 @@ export async function getStatsByGamemode(
} else if (!GAMEMODES.includes(mode)) { } else if (!GAMEMODES.includes(mode)) {
throw Error('Invalid game mode'); throw Error('Invalid game mode');
} }
const response = await axios(getStatsURL(mode, rsn)); const response = await httpGet(getStatsURL(mode, rsn));
if (response.status !== 200) { if (response.status !== 200) {
throw Error('Player not found'); throw Error('Player not found');
} }
@@ -143,7 +143,7 @@ export async function getSkillPage(
} }
const url = getSkillPageURL(mode, skill, page); const url = getSkillPageURL(mode, skill, page);
const response = await axios(url); const response = await httpGet(url);
const dom = new JSDOM(response.data); const dom = new JSDOM(response.data);
const playersHTML = dom.window.document.querySelectorAll( const playersHTML = dom.window.document.querySelectorAll(
'.personal-hiscores__row' '.personal-hiscores__row'
@@ -183,7 +183,7 @@ export async function getActivityPage(
} }
const url = getActivityPageURL(mode, activity, page); const url = getActivityPageURL(mode, activity, page);
const response = await axios(url); const response = await httpGet(url);
const dom = new JSDOM(response.data); const dom = new JSDOM(response.data);
const playersHTML = dom.window.document.querySelectorAll( const playersHTML = dom.window.document.querySelectorAll(
'.personal-hiscores__row' '.personal-hiscores__row'
@@ -218,7 +218,7 @@ export async function getRSNFormat(rsn: string): Promise<string> {
const url = getPlayerTableURL('main', rsn); const url = getPlayerTableURL('main', rsn);
try { try {
const response = await axios(url); const response = await httpGet(url);
const dom = new JSDOM(response.data); const dom = new JSDOM(response.data);
const spans = dom.window.document.querySelectorAll( const spans = dom.window.document.querySelectorAll(
'span[style="color:#AA0022;"]' 'span[style="color:#AA0022;"]'

View File

@@ -1,3 +1,4 @@
import axios from 'axios';
import { Gamemode, SkillName, ActivityName } from '../types'; import { Gamemode, SkillName, ActivityName } from '../types';
import { import {
GAMEMODE_URL, GAMEMODE_URL,
@@ -6,6 +7,7 @@ import {
SKILLS, SKILLS,
ACTIVITIES, ACTIVITIES,
} from './constants'; } from './constants';
const ua = require('useragent-generator');
export const getStatsURL = (gamemode: Gamemode, rsn: string) => export const getStatsURL = (gamemode: Gamemode, rsn: string) =>
`${GAMEMODE_URL[gamemode]}${STATS_URL}${encodeURIComponent(rsn)}`; `${GAMEMODE_URL[gamemode]}${STATS_URL}${encodeURIComponent(rsn)}`;
@@ -45,3 +47,12 @@ export const rsnFromElement = (el: Element | null) => {
const { innerHTML } = el || {}; const { innerHTML } = el || {};
return innerHTML?.replace(/\uFFFD/g, ' ') || ''; return innerHTML?.replace(/\uFFFD/g, ' ') || '';
}; };
export const httpGet = (url: string) => {
return axios.get(url, {
headers: {
// without User-Agent header requests may be rejected by DDoS protection mechanism
'User-Agent': ua.firefox(80)
}
});
};

View File

@@ -3528,6 +3528,11 @@ normalize-url@^4.1.0:
resolved "https://registry.yarnpkg.com/normalize-url/-/normalize-url-4.5.0.tgz#453354087e6ca96957bd8f5baf753f5982142129" resolved "https://registry.yarnpkg.com/normalize-url/-/normalize-url-4.5.0.tgz#453354087e6ca96957bd8f5baf753f5982142129"
integrity sha512-2s47yzUxdexf1OhyRi4Em83iQk0aPvwTddtFz4hnSSw9dCEsLEGf6SwIO8ss/19S9iBb5sJaOuTvTGDeZI00BQ== integrity sha512-2s47yzUxdexf1OhyRi4Em83iQk0aPvwTddtFz4hnSSw9dCEsLEGf6SwIO8ss/19S9iBb5sJaOuTvTGDeZI00BQ==
normalize-version@^1.0.5:
version "1.0.5"
resolved "https://registry.yarnpkg.com/normalize-version/-/normalize-version-1.0.5.tgz#a6a2b9002dc6fa2e5f15ec2f0b2c0284fb499712"
integrity sha1-pqK5AC3G+i5fFewvCywChPtJlxI=
np@^5.0.3: np@^5.0.3:
version "5.2.1" version "5.2.1"
resolved "https://registry.yarnpkg.com/np/-/np-5.2.1.tgz#037bc41a6702fa20ec002fc24f36ebeaa2b318a2" resolved "https://registry.yarnpkg.com/np/-/np-5.2.1.tgz#037bc41a6702fa20ec002fc24f36ebeaa2b318a2"
@@ -4337,6 +4342,13 @@ scoped-regex@^2.0.0:
resolved "https://registry.yarnpkg.com/scoped-regex/-/scoped-regex-2.1.0.tgz#7b9be845d81fd9d21d1ec97c61a0b7cf86d2015f" resolved "https://registry.yarnpkg.com/scoped-regex/-/scoped-regex-2.1.0.tgz#7b9be845d81fd9d21d1ec97c61a0b7cf86d2015f"
integrity sha512-g3WxHrqSWCZHGHlSrF51VXFdjImhwvH8ZO/pryFH56Qi0cDsZfylQa/t0jCzVQFNbNvM00HfHjkDPEuarKDSWQ== integrity sha512-g3WxHrqSWCZHGHlSrF51VXFdjImhwvH8ZO/pryFH56Qi0cDsZfylQa/t0jCzVQFNbNvM00HfHjkDPEuarKDSWQ==
semver-closest@^0.1.0:
version "0.1.2"
resolved "https://registry.yarnpkg.com/semver-closest/-/semver-closest-0.1.2.tgz#ede8d4d5fb04303bb0c334fff69d288cce7fc7db"
integrity sha512-Q6qk0bPNlK5zG62mWFC8L0Qc6OJX76XRWxiPgZyrh98IZTL3HPErgUlPfCyrAPsHVpU+YP4lf5Mz+LzpId91Og==
dependencies:
semver "^5.4.1"
semver-diff@^2.0.0: semver-diff@^2.0.0:
version "2.1.0" version "2.1.0"
resolved "https://registry.yarnpkg.com/semver-diff/-/semver-diff-2.1.0.tgz#4bbb8437c8d37e4b0cf1a68fd726ec6d645d6d36" resolved "https://registry.yarnpkg.com/semver-diff/-/semver-diff-2.1.0.tgz#4bbb8437c8d37e4b0cf1a68fd726ec6d645d6d36"
@@ -5063,6 +5075,15 @@ use@^3.1.0:
resolved "https://registry.yarnpkg.com/use/-/use-3.1.1.tgz#d50c8cac79a19fbc20f2911f56eb973f4e10070f" resolved "https://registry.yarnpkg.com/use/-/use-3.1.1.tgz#d50c8cac79a19fbc20f2911f56eb973f4e10070f"
integrity sha512-cwESVXlO3url9YWlFW/TA9cshCEhtu7IKJ/p5soJ/gGpj7vbvFrAY/eIioQ6Dw23KjZhYgiIo8HOs1nQ2vr/oQ== integrity sha512-cwESVXlO3url9YWlFW/TA9cshCEhtu7IKJ/p5soJ/gGpj7vbvFrAY/eIioQ6Dw23KjZhYgiIo8HOs1nQ2vr/oQ==
useragent-generator@^1.1.0:
version "1.1.0"
resolved "https://registry.yarnpkg.com/useragent-generator/-/useragent-generator-1.1.0.tgz#acf38287432a17980cf3cd1759ed33709abae762"
integrity sha1-rPOCh0MqF5gM880XWe0zcJq652I=
dependencies:
normalize-version "^1.0.5"
semver "^5.4.1"
semver-closest "^0.1.0"
util.promisify@^1.0.0: util.promisify@^1.0.0:
version "1.0.1" version "1.0.1"
resolved "https://registry.yarnpkg.com/util.promisify/-/util.promisify-1.0.1.tgz#6baf7774b80eeb0f7520d8b81d07982a59abbaee" resolved "https://registry.yarnpkg.com/util.promisify/-/util.promisify-1.0.1.tgz#6baf7774b80eeb0f7520d8b81d07982a59abbaee"