From b186d7ae68c6e4e6f9b891291c3e29242e6ced0a Mon Sep 17 00:00:00 2001 From: myfreeer Date: Sat, 5 Dec 2020 18:52:51 +0800 Subject: [PATCH] mdn: skip incorrectly parsed url --- src/mdn/process-url/skip-process.ts | 18 +++++++++++++++--- test/mdn/process-url/skip-process.spec.ts | 5 +++++ 2 files changed, 20 insertions(+), 3 deletions(-) diff --git a/src/mdn/process-url/skip-process.ts b/src/mdn/process-url/skip-process.ts index 4dcb08b1..907b0913 100644 --- a/src/mdn/process-url/skip-process.ts +++ b/src/mdn/process-url/skip-process.ts @@ -1,4 +1,7 @@ -import {skipExternal as skipExternalLogger} from 'website-scrap-engine/lib/logger/logger'; +import { + skipExternal as skipExternalLogger, + error as errorLogger +} from 'website-scrap-engine/lib/logger/logger'; import URI from 'urijs'; import { downloadableHosts } from './consts'; import {Resource} from 'website-scrap-engine/lib/resource'; @@ -42,9 +45,18 @@ export const skipProcess = ( } const uri = URI(url), host = uri.host(); if (host && !downloadableHosts[host]) { - skipExternalLogger.debug('skipped external link', host, url, parent && parent.url); + skipExternalLogger.debug('skipped external link', host, url, parent?.url); return; } + // incorrectly parsed url + // localhost:3000 + // from https://developer.mozilla.org/zh-CN/docs/Learn/Tools_and_testing/ + // Client-side_JavaScript_frameworks/React_getting_started + if (uri.is('absolute') && !host) { + errorLogger.info('skipped incorrectly parsed url', url, parent?.url); + return; + } + const path = uri.path(); if (path.startsWith('/presentations/') || // very large file @@ -54,7 +66,7 @@ export const skipProcess = ( path.startsWith('/files/5243/IconsCommunications_20130401.psd') || path.startsWith('/files/5245/IconsSettings_20130415.psd') || path.startsWith('/files/5247/IconsPrimaryAction_20130501.psd')) { - skipExternalLogger.debug('skipped link to large file', url, parent && parent.url); + skipExternalLogger.debug('skipped link to large file', url, parent?.url); return; } return url; diff --git a/test/mdn/process-url/skip-process.spec.ts b/test/mdn/process-url/skip-process.spec.ts index 96ff1709..0b59a49b 100644 --- a/test/mdn/process-url/skip-process.spec.ts +++ b/test/mdn/process-url/skip-process.spec.ts @@ -60,4 +60,9 @@ describe('skip-process', function () { expect(skipProcess('http://www.mozilla.org/favicon.ico', null, null)) .toBe('https://developer.mozilla.org/static/img/favicon32.png'); }); + + test('skip incorrectly-parsed url', () => { + // https://developer.mozilla.org/zh-CN/docs/Learn/Tools_and_testing/Client-side_JavaScript_frameworks/React_getting_started + exceptSkipped('localhost:3000'); + }); });