Cara Membuat Scraper Data LinkedIn dengan Python (Panduan Mudah)

for job in jobs:
job_title = job.find('h3', class_='base-search-card__title').text.strip()
job_company = job.find('h4', class_='base-search-card__subtitle').text.strip()
job_location = job.find('span', class_='job-search-card__location').text.strip()
job_link = job.find('a', class_='base-card__full-link')('href')

file = open('linkedin-jobs.csv', 'a')
writer = csv.writer(file)
writer.writerow(('Title', 'Company', 'Location', 'Apply'))

writer.writerow((
job_title.encode('utf-8'),
job_company.encode('utf-8'),
job_location.encode('utf-8'),
job_link.encode('utf-8')
))

 else:
file.close()
print('File closed')

http://api.scraperapi.com?api_key={YOUR_API_KEY}&url=

linkedin_scraper('http://api.scraperapi.com?api_key=51e43be283e4db2a5afb62660xxxxxxx&url=https://www.linkedin.com/jobs-guest/jobs/api/seeMoreJobPostings/search?keywords=Product%20Management&location=San%20Francisco%20Bay%20Area&geoId=90000084&trk=public_jobs_jobs-search-bar_search-submit&position=1&pageNum=0&start=', 0)

import csv
import requests
from bs4 import BeautifulSoup

file = open('linkedin-jobs.csv', 'a')
writer = csv.writer(file)
writer.writerow(('Title', 'Company', 'Location', 'Apply'))

def linkedin_scraper(webpage, page_number):
next_page = webpage + str(page_number)
print(str(next_page))
response = requests.get(str(next_page))
soup = BeautifulSoup(response.content,'html.parser')

jobs = soup.find_all('div', class_='base-card relative w-full hover:no-underline focus:no-underline base-card--link base-search-card base-search-card--link job-search-card')
for job in jobs:
job_title = job.find('h3', class_='base-search-card__title').text.strip()
job_company = job.find('h4', class_='base-search-card__subtitle').text.strip()
job_location = job.find('span', class_='job-search-card__location').text.strip()
job_link = job.find('a', class_='base-card__full-link')('href')

writer.writerow((
job_title.encode('utf-8'),
job_company.encode('utf-8'),
job_location.encode('utf-8'),
job_link.encode('utf-8')
))

print('Data updated')

if page_number 

pip install selenium selenium-wire undetected-chromedriver beautifulsoup4 lxml webdriver-manager setuptools 

from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from time import sleep
import undetected_chromedriver as uc
from bs4 import BeautifulSoup
import csv

proxy_host="your_proxy_host"
proxy_port="your_proxy_port"
proxy_username="your_username"
proxy_password = 'your_password'

proxy_url = f'http://{proxy_username}:{proxy_password}@{proxy_host}:{proxy_port}'

seleniumwire_options = {
    'proxy': {
        'http': proxy_url,
        'https': proxy_url,
    },
    'verify_ssl': False,
}

linkedin_url="https://www.linkedin.com/search/results/people/?geoUrn=%5B%22103644278%22%2C%22102713980%22%5D&keywords=junior%20web%20developer&origin=FACETED_SEARCH"

# Initialize the undetected Chrome driver with proxy settings
driver = uc.Chrome(options=options, seleniumwire_options=seleniumwire_options)

# Go to the LinkedIn page
driver.get(linkedin_url)

options = Options()
options.add_argument("--disable-blink-features=AutomationControlled")
options.add_argument("--headless=new")

# Wait for the username and password fields to load and enter credentials
username_field = WebDriverWait(driver, 20).until(EC.presence_of_element_located((By.ID, 'username')))
username_field.send_keys('Linkedin_username')
password_field = driver.find_element(By.ID, 'password')
password_field.send_keys(‘Linkedin_password’)
login_button = driver.find_element(By.CSS_SELECTOR, '.login__form_action_container button')
login_button.click()

print("Sign In Successful...\n")

# Allow some time to bypass CAPTCHA if needed
sleep(10)

with open('linkedin_profiles.csv', 'w', newline="", encoding='utf-8') as csvfile:
    fieldnames = ('Name', 'Profile Link', 'Job Title', 'Location', 'Current Role')
    writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
    writer.writeheader()

for page_number in range(1, 6):
        page_url = linkedin_url + f"&page={page_number}"
        driver.get(page_url)
        print(f"Scraping page {page_number}...\n")

profiles = soup.find_all('li', class_='reusable-search__result-container')

name_tag = profile.find('span', {'aria-hidden': 'true'})
name = name_tag.get_text(strip=True) if name_tag else "LinkedIn Member"

profile_link_tag = profile.find('a', class_='app-aware-link', href=True)
profile_link = profile_link_tag('href') if profile_link_tag else "N/A"

job_title_tag = profile.find('div', class_='entity-result__primary-subtitle')
job_title = job_title_tag.get_text(strip=True) if job_title_tag else "N/A"

location_tag = profile.find('div', class_='entity-result__secondary-subtitle')
location = location_tag.get_text(strip=True) if location_tag else "N/A"

current_role = "N/A"
summary_p = profile.find('p', class_='entity-result__summary')
if summary_p:
    summary_text = summary_p.get_text(strip=True)
    if summary_text.startswith("Current:"):
        current_role = summary_text.replace("Current:", "").strip()

writer.writerow({
    'Name': name,
    'Profile Link': profile_link,
    'Job Title': job_title,
    'Location': location,
    'Current Role': current_role
})

print(f"Saved profile: {name}")

# Close the browser
driver.quit()

from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from time import sleep
import undetected_chromedriver as uc
from bs4 import BeautifulSoup
import csv

proxy_host="your_proxy_host"
proxy_port="your_proxy_port"
proxy_username="your_linkedin_email"
proxy_password = 'your_password'

# Construct the proxy URL
proxy_url = f'http://{proxy_username}:{proxy_password}@{proxy_host}:{proxy_port}'

# LinkedIn URL and credentials
linkedin_url="https://www.linkedin.com/search/results/people/?geoUrn=%5B%22103644278%22%2C%22102713980%22%5D&keywords=junior%20web%20developer&origin=FACETED_SEARCH"
username = "Your_linkedin_username"
password = "Your_linkedin_password"

# Setting Chrome options and proxy configuration for undetected_chromedriver
options = Options()
options.add_argument("--disable-blink-features=AutomationControlled")
options.add_argument("--headless=new") 


seleniumwire_options = {
    'proxy': {
        'http': proxy_url,
        'https': proxy_url,
    },
    'verify_ssl': False,
}

# Initialize the undetected Chrome driver with proxy settings
driver = uc.Chrome(options=options, seleniumwire_options=seleniumwire_options)

# Go to the LinkedIn page
driver.get(linkedin_url)

# Wait for the username and password fields to load and enter credentials
username_field = WebDriverWait(driver, 20).until(EC.presence_of_element_located((By.ID, 'username')))
username_field.send_keys(username)
password_field = driver.find_element(By.ID, 'password')
password_field.send_keys(password)
login_button = driver.find_element(By.CSS_SELECTOR, '.login__form_action_container button')
login_button.click()

print("Sign In Successful...\n")

sleep(10)

# Open a CSV file to write the data
with open('linkedin_profiles.csv', 'w', newline="", encoding='utf-8') as csvfile:
    fieldnames = ('Name', 'Profile Link', 'Job Title', 'Location', 'Current Role')
    writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
    writer.writeheader()  # Write the header row

    # Loop through the first 5 pages
    for page_number in range(1, 6):
        page_url = linkedin_url + f"&page={page_number}"
        driver.get(page_url)
        print(f"Scraping page {page_number}...\n")
        
        # Wait for the search results to load
        sleep(5) 

        # Locate and parse the profile details
        try:
            page_source = driver.page_source
            soup = BeautifulSoup(page_source, 'lxml')
            profiles = soup.find_all('li', class_='reusable-search__result-container')

            for profile in profiles:
                # name
                name_tag = profile.find('span', {'aria-hidden': 'true'})
                name = name_tag.get_text(strip=True) if name_tag else "LinkedIn Member"
                
                # profile link
                profile_link_tag = profile.find('a', class_='app-aware-link', href=True)
                profile_link = profile_link_tag('href') if profile_link_tag else "N/A"
                
                # job title 
                job_title_tag = profile.find('div', class_='entity-result__primary-subtitle')
                job_title = job_title_tag.get_text(strip=True) if job_title_tag else "N/A"
                
                # location
                location_tag = profile.find('div', class_='entity-result__secondary-subtitle')
                location = location_tag.get_text(strip=True) if location_tag else "N/A"
                
                # current (if any)
                current_role = "N/A"
                summary_p = profile.find('p', class_='entity-result__summary')
                if summary_p:
                    summary_text = summary_p.get_text(strip=True)
                    if summary_text.startswith("Current:"):
                        current_role = summary_text.replace("Current:", "").strip()
                
                # Write the extracted data to the CSV file
                writer.writerow({
                    'Name': name,
                    'Profile Link': profile_link,
                    'Job Title': job_title,
                    'Location': location,
                    'Current Role': current_role
                })
                
                print(f"Saved profile: {name}")

        except Exception as e:
            print(f"An error occurred on page {page_number}: {e}")

# Close the browser
driver.quit()

linkedin_url="https://www.linkedin.com/search/results/companies/?companyHqGeo=%5B%22103644278%22%5D&companySize=%5B%22C%22%5D&industryCompanyVertical=%5B%221594%22%5D&origin=FACETED_SEARCH&sid=G4U"

for page_number in range(1, 6):
    page_url = linkedin_url + f"&page={page_number}"
    driver.get(page_url)
    print(f"Scraping page {page_number}...\n")
    sleep(5)  # Adjust sleep time if necessary

page_source = driver.page_source
soup = BeautifulSoup(page_source, 'lxml')
company_listings = soup.find_all('li', class_='reusable-search__result-container')

name_tag = company_li.find('span', class_='entity-result__title-text')
company_name = name_tag.get_text(strip=True) if name_tag else "N/A"