| 1 | { tmpdir } = require 'os'
|
| 2 | { join } = require 'path'
|
| 3 | endl = require '../src/index'
|
| 4 |
|
| 5 | waitTime = 20000
|
| 6 | urls = [
|
| 7 | 'http://dogancelik.com'
|
| 8 | 'http://lame.buanzo.org/'
|
| 9 | 'https://github.com/request/request/archive/master.zip'
|
| 10 | 'http://codecguide.com/download_k-lite_codec_pack_mega.htm'
|
| 11 | ]
|
| 12 |
|
| 13 | describe 'endl test #1', ->
|
| 14 | @timeout waitTime
|
| 15 |
|
| 16 | it 'should load page', (done) ->
|
| 17 | extractorInstance = endl.page(urls[0])
|
| 18 | extractorInstance._scraper.onStatusCode (code) ->
|
| 19 | code.should.be.equal 200
|
| 20 | done()
|
| 21 |
|
| 22 | it 'should find element', (done) ->
|
| 23 | extractorInstance = endl.page(urls[0])
|
| 24 | extractorInstance.find '#gif', (container) ->
|
| 25 | container._getAttr('alt').should.be.equal ':3'
|
| 26 | done()
|
| 27 |
|
| 28 | it 'should download src', (done) ->
|
| 29 | extractorInstance = endl.page(urls[0])
|
| 30 | containerPromise = extractorInstance.find('#gif')
|
| 31 | containerPromise.then((container) ->
|
| 32 | attrInstance = container.attr('src')
|
| 33 | attrInstance.download {filenameMode: {predefined: 'gif.gif'}, directory: tmpdir()}, -> done()
|
| 34 | )
|
| 35 |
|
| 36 | describe 'endl test #2', ->
|
| 37 | @timeout waitTime
|
| 38 |
|
| 39 | qsa = 'a[href^="http://lame.buanzo.org/Lame_"]'
|
| 40 | downloadOpts = {pageUrlAsReferrer: true, directory: tmpdir(), filenameMode: { urlBasename: true }}
|
| 41 |
|
| 42 | it 'should download', (done) ->
|
| 43 | endl.page(urls[1])
|
| 44 | .find(qsa)
|
| 45 | .then (container) ->
|
| 46 | container.download downloadOpts, -> done()
|
| 47 |
|
| 48 | it 'should download all files with .all', (done) ->
|
| 49 | i = 0
|
| 50 | endl.page(urls[1])
|
| 51 | .find(qsa)
|
| 52 | .then (container) ->
|
| 53 | container.all().forEach (attr) ->
|
| 54 | attr.download downloadOpts, ->
|
| 55 | i++
|
| 56 | done() if i == 4
|
| 57 |
|
| 58 | describe 'endl test #3', ->
|
| 59 | @timeout waitTime
|
| 60 |
|
| 61 | it 'should download and unzip', (done) ->
|
| 62 | endl.file(urls[2])
|
| 63 | .download({pageUrlAsReferrer: true, filenameMode: { contentDisposition: true }, directory: tmpdir()})
|
| 64 | .extract {to: join(tmpdir(), '/unzip'), cd: 'request-master', fileGlob: '*.js', maintainEntryPath: false}, (extracted) ->
|
| 65 | if extracted.length == 0 then throw new Error('Zip is empty?')
|
| 66 | done()
|
| 67 |
|
| 68 | describe 'endl test #4', ->
|
| 69 |
|
| 70 | it 'should use previousUrl', (done) ->
|
| 71 | endl.page(urls[3])
|
| 72 | .find('a[href^="http://www.majorgeeks.com/"]')
|
| 73 | .then (container) ->
|
| 74 | container.page({ pageUrlAsReferrer: true })
|
| 75 | .find('a[href*="getmirror/k_lite_mega_codec_pack"]',
|
| 76 | (container) ->
|
| 77 | referer = container._scraper.scraper.response.request.headers.referer
|
| 78 | if referer == urls[3]
|
| 79 | done()
|
| 80 | else
|
| 81 | throw new Error "Referrer is not initial URL: #{referer}"
|
| 82 | )
|
| 83 |
|
| 84 | describe 'endl test #5', ->
|
| 85 | @timeout waitTime
|
| 86 |
|
| 87 | it 'should parse json', (done) ->
|
| 88 | endl.load(join(__dirname, 'test.json'), null, -> done())
|