Created
February 22, 2021 20:27
-
-
Save remylagerweij/c4ae393577766ce373e524d0f91d11a9 to your computer and use it in GitHub Desktop.
Scraping people from search results on LinkedIn
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
let people_list = []; | |
(function(){ | |
const person_naam = '.actor-name'; | |
const person_title = '.subline-level-1'; | |
const person_location = '.subline-level-2'; | |
const person_job_function = '.mt2.t-12.t-black--light.t-normal.search-result__snippets-black'; | |
function getAttribute(person, attribute){ | |
if (person.querySelector(attribute)) { | |
return person.querySelector(attribute).innerText; | |
} | |
return ""; | |
} | |
function splitJobAndCompany(person, attribute, job_or_company){ | |
if (!person.querySelector(attribute)) { | |
return "" | |
} | |
let temp_job = person.querySelector(attribute).innerText.split("bij"); | |
if (person.querySelector(attribute)) { | |
if (job_or_company == "job" && temp_job[0]) { | |
return temp_job[0].replace("Huidig: ", ""); | |
}; | |
if (job_or_company == "company" && temp_job[1]) { | |
return temp_job[1]; | |
}; | |
} | |
return ""; | |
}; | |
function getLinkedInUrl(person) { | |
if(person.querySelector('.search-result__result-link')) { | |
return person.querySelector('.search-result__result-link').href; | |
} | |
return ""; | |
} | |
function fetchPeople(){ | |
document.querySelectorAll('.search-result__info').forEach(function(person){ | |
person_data = { | |
"person_name": getAttribute(person, person_naam), | |
"person_title": getAttribute(person,person_title), | |
"person_location": getAttribute(person, person_location), | |
"person_function": splitJobAndCompany(person, person_job_function, "job"), | |
"person_company": splitJobAndCompany(person, person_job_function, "company"), | |
"person_linkedinurl": getLinkedInUrl(person) | |
} | |
people_list.push(person_data) | |
}); | |
// console.log(JSON.stringify(people_list)); | |
checkAndClickNext(); | |
} | |
function checkAndClickNext(){ | |
let pagination_button = document.querySelector('.artdeco-pagination .artdeco-pagination__button--next'); | |
if (!pagination_button.classList.contains("artdeco-button--disabled")) { | |
pagination_button.click() | |
setTimeout(function(){ | |
setTimeout(function(){ | |
window.scrollTo(0,document.body.scrollHeight); | |
setTimeout(function(){ | |
fetchPeople(); | |
}, 2000) | |
}, 2000); | |
}, 3000); | |
} else { | |
console.log(JSON.stringify(people_list)); | |
} | |
} | |
fetchPeople(); | |
}()) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment