Bonjour @ScrapingExpert voici le sitemap, il n’est pas complet c’est juste pour donner une idée du truc. Pas complet parce que plus complexe que ce que j’ai fait, en effet les fiches ne sont pas toutes les mêmes selon l’activité mais en gros voilà .
{
"_id":"irmawork",
"startUrl":[
"https://www.irmawork.com/annuaire/recherche?q=&cible=organizations"
],
"selectors":[
{
"id":"ELEMENT",
"type":"SelectorElementScroll",
"parentSelectors":[
"_root"
],
"selector":"li.jss233",
"multiple":true,
"delay":"3000"
},
{
"id":"NOM",
"type":"SelectorText",
"parentSelectors":[
"ELEMENT"
],
"selector":"h6",
"multiple":false,
"regex":"",
"delay":0
},
{
"id":"Nombre d'activité",
"type":"SelectorText",
"parentSelectors":[
"ELEMENT"
],
"selector":"span.jss374",
"multiple":false,
"regex":"",
"delay":0
},
{
"id":"Domaine",
"type":"SelectorText",
"parentSelectors":[
"ELEMENT"
],
"selector":".jss179 span:nth-of-type(1)",
"multiple":false,
"regex":"[^Domaine: ].+",
"delay":0
},
{
"id":"Localisation",
"type":"SelectorText",
"parentSelectors":[
"ELEMENT"
],
"selector":"span.jss75:nth-of-type(2)",
"multiple":false,
"regex":"[^Localisation: ].+",
"delay":0
},
{
"id":"PLUS",
"type":"SelectorLink",
"parentSelectors":[
"ELEMENT"
],
"selector":"a",
"multiple":false,
"delay":0
},
{
"id":"Activité",
"type":"SelectorText",
"parentSelectors":[
"PLUS"
],
"selector":"div.jss404:nth-of-type(1) h5",
"multiple":false,
"regex":"",
"delay":0
},
{
"id":"Genre(s) musical(aux)",
"type":"SelectorText",
"parentSelectors":[
"PLUS"
],
"selector":"div.jss404:nth-of-type(1) p:nth-of-type(1)",
"multiple":false,
"regex":"[^Genre(s) musical(aux) : ].+",
"delay":0
},
{
"id":"Manager",
"type":"SelectorText",
"parentSelectors":[
"PLUS"
],
"selector":"p:nth-of-type(2)",
"multiple":false,
"regex":"[^Manager : ].+",
"delay":0
},
{
"id":"Tourneur",
"type":"SelectorText",
"parentSelectors":[
"PLUS"
],
"selector":"p:nth-of-type(3)",
"multiple":false,
"regex":"[^Tourneur : ].+",
"delay":0
},
{
"id":"Editeur",
"type":"SelectorText",
"parentSelectors":[
"PLUS"
],
"selector":"p:nth-of-type(4)",
"multiple":false,
"regex":"[^Éditeur : ].+",
"delay":0
},
{
"id":"Maison de disques",
"type":"SelectorText",
"parentSelectors":[
"PLUS"
],
"selector":"p:nth-of-type(5)",
"multiple":false,
"regex":"[^Maison de disques : ].+",
"delay":0
},
{
"id":"Promotion",
"type":"SelectorText",
"parentSelectors":[
"PLUS"
],
"selector":"p:nth-of-type(6)",
"multiple":false,
"regex":"[^Promotion : ].+",
"delay":0
},
{
"id":"Distinction et récompenses",
"type":"SelectorText",
"parentSelectors":[
"PLUS"
],
"selector":"p:nth-of-type(7)",
"multiple":false,
"regex":"[^Distinctions et récompenses : ].+",
"delay":0
},
{
"id":"Mise à jour",
"type":"SelectorText",
"parentSelectors":[
"PLUS"
],
"selector":"div:nth-of-type(5) p",
"multiple":false,
"regex":".+[^ - ©2019 Irma, tous droits réservés.]",
"delay":0
}
]
}
Et voici le screeshot du selector graph