url = require('url')
{ HTMLPage } = require('webcrawler/src/html_page')
loadMock = _.memoize (fileName) ->
fs.readFileSync(path.join(__dirname, '..', 'mocks', fileName), 'utf8')
pageWithBody = (body) -> """
#{body}
"""
pageWithHead = (head) -> """
#{head}
"""
describe 'HTMLPage', ->
before ->
@fourLinks = {
url: 'http://localhost:8080/mocks/four_links.html'
body: loadMock('four_links.html')
}
it 'should exist', ->
expect(HTMLPage).to.exist
describe 'constructor', ->
describe '@request', ->
integ 'should resolve promise for https://gocardless.com', ->
HTMLPage.request(url: 'https://gocardless.com').then (page) ->
expect(page).to.be.ok
integ 'should reject for https://dashboard.gocardless.com/api/user', ->
expect(HTMLPage.request({
url: 'https://dashboard.gocardless.com/api/user'
}))
.to.be.rejected
describe '#new', ->
it 'should successfully new', ->
expect(new HTMLPage(@fourLinks)).to.be.ok
describe 'method', ->
before -> @mockUrl = 'http://domain.com'
describe '#resolveLink', ->
before -> @page = new HTMLPage(url: @mockUrl)
it 'should resolve relative link', ->
expect(@page.resolveLink('/relative_page.html'))
.to.equal "#{@page.url}/relative_page.html"
it 'should remove query params', ->
expect(@page.resolveLink('/relative_page.html?hello=5'))
.to.equal "#{@page.url}/relative_page.html"
it 'should leave absolute urls untouched', ->
expect(@page.resolveLink('http://google.com'))
.to.equal 'http://google.com'
it 'should remove trailing slash', ->
expect(@page.resolveLink('http://google.com'))
.to.equal 'http://google.com'
describe '#parseStaticAssets', ->
it 'should return an array', ->
page = new HTMLPage(url: @mockUrl)
expect(page.parseStaticAssets()).to.be.an.array
context 'for specific tag', ->
before -> @expectMock = (page, resource) ->
expect(page.parseStaticAssets()).to.eql [
url.resolve(@mockUrl, resource)
]
it 'should detect 
', ->
@expectMock new HTMLPage({
url: @mockUrl
body: pageWithBody('
')
}), 'image.jpg'
it 'should detect