Infrastructure/ghost
0
Fork 0
mirror of https://github.com/TryGhost/Ghost.git synced 2025-04-15 03:01:37 -05:00
Code Issues Activity

🐛 Fixed embed/bookmark retrieval for sites that require cookies during redirects

Browse source 
no issue

- known failing case was Medium. Some *.medium.com articles triggered redirects but without cookies being stored/sent across the redirect requests it would cause an infinite redirect loop and we'd abort after 10 redirects
- use `got`'s [cookie support](https://github.com/sindresorhus/got/tree/v9.6.0#cookies) via `tough-cookie` so that we can create bookmark cards for medium.com and other sites with similar problems
This commit is contained in:
Kevin Ansfield 2020-06-17 10:03:36 +01:00
parent 32dd4574af
commit 4537ccd329
3 changed files with 20 additions and 5 deletions
core/server/api/canary
oembed.js
package.jsonyarn.lock

11
core/server/api/canary/oembed.js
View file

@ -3,6 +3,7 @@ const {extract, hasProvider} = require('oembed-parser');
const Promise = require('bluebird');
const cheerio = require('cheerio');
const _ = require('lodash');
const {CookieJar} = require('tough-cookie');
const config = require('../../../shared/config');
const {i18n} = require('../../lib/common');
const externalRequest = require('../../lib/request-external');
@ -23,7 +24,8 @@ async function fetchBookmarkData(url, html) {
try {
if (!html) {
const response = await externalRequest(url);
const cookieJar = new CookieJar();
const response = await externalRequest(url, {cookieJar});
html = response.body;
}
scraperResponse = await metascraper({html, url});
@ -132,10 +134,12 @@ function fetchOembedData(_url) {
// url not in oembed list so fetch it in case it's a redirect or has a
// <link rel="alternate" type="application/json+oembed"> element
const cookieJar = new CookieJar();
return externalRequest(url, {
method: 'GET',
timeout: 2 * 1000,
followRedirect: true
followRedirect: true,
cookieJar
}).then((pageResponse) => {
// url changed after fetch, see if we were redirected to a known oembed
if (pageResponse.url !== url) {
@ -164,7 +168,8 @@ function fetchOembedData(_url) {
method: 'GET',
json: true,
timeout: 2 * 1000,
followRedirect: true
followRedirect: true,
cookieJar
}).then((oembedResponse) => {
// validate the fetched json against the oembed spec to avoid
// leaking non-oembed responses

1
package.json
View file

@ -127,6 +127,7 @@
"rss": "1.2.2",
"sanitize-html": "1.26.0",
"semver": "7.3.2",
"tough-cookie": "4.0.0",
"uuid": "8.1.0",
"validator": "6.3.0",
"xml": "1.0.1"

13
yarn.lock
View file

@ -7718,7 +7718,7 @@ pseudomap@^1.0.1, pseudomap@^1.0.2:
resolved "https://registry.yarnpkg.com/pseudomap/-/pseudomap-1.0.2.tgz#f052a28da70e618917ef0a8ac34c1ae5a68286b3"
integrity sha1-8FKijacOYYkX7wqKw0wa5aaChrM=
psl@^1.1.24:
psl@^1.1.24, psl@^1.1.33:
version "1.8.0"
resolved "https://registry.yarnpkg.com/psl/-/psl-1.8.0.tgz#9326f8bcfb013adcc005fdff056acce020e51c24"
integrity sha512-RIdOzyoavK+hA18OGGWDqUTsCLhtA7IcZ/6NCs4fFJaHBDab+pDDmDIByWFRQJq2Cd7r1OoQxBGKOaztq+hjIQ==
@ -9332,6 +9332,15 @@ toidentifier@1.0.0:
resolved "https://registry.yarnpkg.com/toidentifier/-/toidentifier-1.0.0.tgz#7e1be3470f1e77948bc43d94a3c8f4d7752ba553"
integrity sha512-yaOH/Pk/VEhBWWTlhI+qXxDFXlejDGcQipMlyxda9nthulaxLZUNcUqFxokp0vcYnvteJln5FNQDRrxj3YcbVw==
tough-cookie@4.0.0:
version "4.0.0"
resolved "https://registry.yarnpkg.com/tough-cookie/-/tough-cookie-4.0.0.tgz#d822234eeca882f991f0f908824ad2622ddbece4"
integrity sha512-tHdtEpQCMrc1YLrMaqXXcj6AxhYi/xgit6mZu1+EDWUn+qhUf8wMQoFIy9NXuq23zAwtcB0t/MjACGR18pcRbg==
dependencies:
psl "^1.1.33"
punycode "^2.1.1"
universalify "^0.1.2"
tough-cookie@^2.3.3, tough-cookie@~2.5.0:
version "2.5.0"
resolved "https://registry.yarnpkg.com/tough-cookie/-/tough-cookie-2.5.0.tgz#cd9fb2a0aa1d5a12b473bd9fb96fa3dcff65ade2"
@ -9605,7 +9614,7 @@ unist-util-visit@^2.0.0:
unist-util-is "^4.0.0"
unist-util-visit-parents "^3.0.0"
universalify@^0.1.0:
universalify@^0.1.0, universalify@^0.1.2:
version "0.1.2"
resolved "https://registry.yarnpkg.com/universalify/-/universalify-0.1.2.tgz#b646f69be3942dabcecc9d6639c80dc105efaa66"
integrity sha512-rBJeI5CXAlmy1pV+617WB9J63U6XcazHHF2f2dbJix4XzpUF0RS3Zbj0FGIOCAva5P/d/GBOYaACQ1w+0azUkg==