import assert from 'assert' ;
import URL from 'url' ;
import cheerio from 'cheerio' ;
import Mercury from 'mercury' ;
import getExtractor from 'extractors/get-extractor' ;
import { excerptContent } from 'utils/text' ;
const fs = require ( 'fs' ) ;
describe ( 'IciRadioCanadaCaExtractor' , ( ) => {
describe ( 'initial test case' , ( ) => {
let result ;
let url ;
beforeAll ( ( ) => {
url =
'http://ici.radio-canada.ca/nouvelle/1022038/kpmg-comptables-fiscalite-impots-paradis-fiscaux-juge-bocock-cocktail' ;
const html = fs . readFileSync (
'./fixtures/ici.radio-canada.ca/1489433621634.html'
) ;
result = Mercury . parse ( url , { html , fallback : false } ) ;
} ) ;
it ( 'is selected properly' , ( ) => {
// This test should be passing by default.
// It sanity checks that the correct parser
// is being selected for URLs from this domain
const extractor = getExtractor ( url ) ;
assert . equal ( extractor . domain , URL . parse ( url ) . hostname ) ;
} ) ;
it ( 'returns the title' , async ( ) => {
// To pass this test, fill out the title selector
// in ./src/extractors/custom/ici.radio-canada.ca/index.js.
const { title } = await result ;
// Update these values with the expected values from
// the article.
assert . equal ( title , 'Affaire KPMG: un juge se récuse' ) ;
} ) ;
it ( 'returns the author' , async ( ) => {
// To pass this test, fill out the author selector
// in ./src/extractors/custom/ici.radio-canada.ca/index.js.
const { author } = await result ;
// Update these values with the expected values from
// the article.
assert . equal (
author ,
'Zone Justice et faits divers - ICI.Radio-Canada.ca'
) ;
} ) ;
it ( 'returns the date_published' , async ( ) => {
// To pass this test, fill out the date_published selector
// in ./src/extractors/custom/ici.radio-canada.ca/index.js.
const { date _published } = await result ;
// Update these values with the expected values from
// the article.
assert . equal ( date _published , '2017-03-13T23:18:00.000Z' ) ;
} ) ;
it ( 'returns the dek' , async ( ) => {
// To pass this test, fill out the dek selector
// in ./src/extractors/custom/ici.radio-canada.ca/index.js.
const { dek } = await result ;
// Update these values with the expected values from
// the article.
assert . equal (
dek ,
"Un juge de la cour de l'impôt se récuse d'un dossier mettant en cause un stratagème du cabinet comptable KPMG. Selon les émissions Enquête et the fifth estate, le juge Bocock avait participé à une soirée cocktail organisée par un cabinet d'avocats lié à l'affaire."
) ;
} ) ;
it ( 'returns the lead_image_url' , async ( ) => {
// To pass this test, fill out the lead_image_url selector
// in ./src/extractors/custom/ici.radio-canada.ca/index.js.
const { lead _image _url } = await result ;
// Update these values with the expected values from
// the article.
assert . equal (
lead _image _url ,
'https://images.radio-canada.ca/w_635,h_357/v1/ici-info/16x9/randall-bocock-juge.jpg'
) ;
} ) ;
it ( 'returns the content' , async ( ) => {
// To pass this test, fill out the content selector
// in ./src/extractors/custom/ici.radio-canada.ca/index.js.
// You may also want to make use of the clean and transform
// options.
const { content } = await result ;
const $ = cheerio . load ( content || '' ) ;
const first13 = excerptContent (
$ ( '*' )
. first ( )
. text ( ) ,
13
) ;
// Update these values with the expected values from
// the article.
assert . equal (
first13 ,
"Le juge Randall Bocock se retire d'une cause liée à KPMG Photo :"
) ;
} ) ;
} ) ;
} ) ;