Skip to content

Instantly share code, notes, and snippets.

Embed
What would you like to do?
Sitemap to extract job details based on a job and location from Indeed using webscraper.io chrome extension
{
"_id":"indeed",
"startUrl":[
"https://www.indeed.com/jobs?q=accountant&l=Los+Angeles,+CA&rbl=Anaheim,+CA&jlid=a05ccab40146becb&jt=fulltime"
],
"selectors":[
{
"id":"listings",
"type":"SelectorElement",
"parentSelectors":[
"_root",
"next"
],
"selector":"div.jobsearch-SerpJobCard:nth-of-type(n)",
"multiple":true,
"delay":0
},
{
"id":"link",
"type":"SelectorLink",
"parentSelectors":[
"listings"
],
"selector":"a.jobtitle",
"multiple":false,
"delay":0
},
{
"id":"job_title",
"type":"SelectorText",
"parentSelectors":[
"link"
],
"selector":"h3.icl-u-xs-mb--xs",
"multiple":false,
"regex":"",
"delay":0
},
{
"id":"company",
"type":"SelectorText",
"parentSelectors":[
"link"
],
"selector":"div.icl-u-lg-mr--sm:nth-of-type(1)",
"multiple":false,
"regex":"",
"delay":0
},
{
"id":"rating",
"type":"SelectorElementAttribute",
"parentSelectors":[
"link"
],
"selector":"a.icl-Ratings-starsCountWrapper",
"multiple":false,
"extractAttribute":"aria-label",
"delay":0
},
{
"id":"next",
"type":"SelectorLink",
"parentSelectors":[
"_root",
"next"
],
"selector":"div.pagination a:last-of-type",
"multiple":false,
"delay":0
},
{
"id":"reviews",
"type":"SelectorText",
"parentSelectors":[
"link"
],
"selector":"a.icl-Ratings-starsCountWrapper div.icl-Ratings-count",
"multiple":false,
"regex":"[^reviews]+",
"delay":0
},
{
"id":"location",
"type":"SelectorText",
"parentSelectors":[
"link"
],
"selector":"div.jobsearch-InlineCompanyRating",
"multiple":false,
"regex":"(?<=\\-)\\\\s(.)",
"delay":0
},
{
"id":"job_description",
"type":"SelectorText",
"parentSelectors":[
"link"
],
"selector":"div.jobsearch-JobComponent-description > div",
"multiple":false,
"regex":"",
"delay":0
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment