Skip to content

Fix relative resources in redirected page #242

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Sep 28, 2017
Merged

Fix relative resources in redirected page #242

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
98f56a9
Add test
s0ph1e Sep 27, 2017
f9b4ce9
Fix comparing urls
s0ph1e Sep 27, 2017
7ef0d4a
Add test
s0ph1e Sep 27, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 6 additions & 2 deletions lib/utils/index.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
const url = require('url');
const path = require('path');
const Promise = require('bluebird');
const normalizeUrl = require('normalize-url');
const normalize = require('normalize-url');
const htmlEntities = require('he');
const _ = require('lodash');
const typeByMime = require('../config/resource-type-by-mime');
Expand Down Expand Up @@ -66,7 +66,7 @@ function getFilenameFromUrl (u) {
* @returns {string} path
*/
function getFilepathFromUrl (u) {
var nu = normalizeUrl(u);
const nu = normalizeUrl(u, {removeTrailingSlash: true});
return getPathnameFromUrl(nu).substring(1);
}

Expand Down Expand Up @@ -109,6 +109,10 @@ function waitAllFulfilled (promises) {
}));
}

function normalizeUrl (u, opts) {
return normalize(u, extend({removeTrailingSlash: false}, opts));
}

function urlsEqual (url1, url2) {
return normalizeUrl(url1) === normalizeUrl(url2);
}
Expand Down
12 changes: 12 additions & 0 deletions test/functional/redirect/mocks/relative-resources-about.html
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>About</title>
<link rel="stylesheet" type="text/css" href="/style.css"/> <!-- /style.css -->
<link rel="stylesheet" type="text/css" href="style.css"/> <!-- /about/style.css -->
</head>
<body>

</body>
</html>
11 changes: 11 additions & 0 deletions test/functional/redirect/mocks/relative-resources-index.html
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>Index</title>
<link rel="stylesheet" type="text/css" href="style.css"/>
</head>
<body>
<a href="/about">About</a>
</body>
</html>
58 changes: 52 additions & 6 deletions test/functional/redirect/redirect.test.js
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,11 +1,14 @@
'use strict';

require('should');
var nock = require('nock');
var fs = require('fs-extra');
var sinon = require('sinon');
var Scraper = require('../../../lib/scraper');
const nock = require('nock');
const fs = require('fs-extra');
const sinon = require('sinon');
const Scraper = require('../../../lib/scraper');
const scrape = require('../../../index');

var testDirname = __dirname + '/.tmp';
var mockDirname = __dirname + '/mocks';
const testDirname = __dirname + '/.tmp';
const mockDirname = __dirname + '/mocks';

describe('Functional redirects', function() {

Expand Down Expand Up @@ -60,4 +63,47 @@ describe('Functional redirects', function() {
fs.readFileSync(testDirname + '/true-page.html').toString().should.be.eql('true page 1');
});
});

it('should correctly handle relative source in redirected page', () => {
const options = {
urls: [
{ url: 'http://example.com', filename: 'index.html'}
],
directory: testDirname,
subdirectories: [
{ directory: 'css', extensions: ['.css'] }
],
maxRecursiveDepth: 1,
sources: [
{selector: 'link', attr: 'href'},
{selector: 'a', attr: 'href'}
]
};

nock('http://example.com/').get('/').replyWithFile(200, mockDirname + '/relative-resources-index.html');
nock('http://example.com/').get('/about').reply(301, '', {'Location': 'http://example.com/about/'});
nock('http://example.com/').get('/about/').replyWithFile(200, mockDirname + '/relative-resources-about.html', {'content-type': 'text/html'});
nock('http://example.com/').get('/style.css').reply(200, 'style.css');
nock('http://example.com/').get('/about/style.css').reply(200, 'about/style.css');

return scrape(options).then(function() {
fs.existsSync(testDirname + '/index.html').should.be.eql(true);
fs.existsSync(testDirname + '/about.html').should.be.eql(true);
fs.existsSync(testDirname + '/css/style.css').should.be.eql(true);
fs.existsSync(testDirname + '/css/style_1.css').should.be.eql(true);

const style = fs.readFileSync(testDirname + '/css/style.css').toString();
style.should.be.eql('style.css');

const style_1 = fs.readFileSync(testDirname + '/css/style_1.css').toString();
style_1.should.be.eql('about/style.css');

const index = fs.readFileSync(testDirname + '/index.html').toString();
index.should.containEql('<link rel="stylesheet" type="text/css" href="css/style.css">');

const about = fs.readFileSync(testDirname + '/about.html').toString();
about.should.containEql('<link rel="stylesheet" type="text/css" href="css/style.css">');
about.should.containEql('<link rel="stylesheet" type="text/css" href="css/style_1.css">');
});
});
});
6 changes: 6 additions & 0 deletions test/unit/utils/utils-test.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -220,4 +220,10 @@ describe('Utils', function () {
should(utils.decodeHtmlEntities('?a=1&amp;v=2')).be.eql('?a=1&v=2');
});
});

describe('#urlsEqual', () => {
it('should return false for /path and /path/', function() {
should(utils.urlsEqual('http://example.com/path', 'http://example.com/path/')).be.eql(false);
});
})
});