joeyism/linkedin_scraper

from linkedin_scraper import Person

person = Person("https://linkedin.com/in/username", driver=driver)
print(person.name)

import asyncio
from linkedin_scraper import BrowserManager, PersonScraper

async def main():
    async with BrowserManager() as browser:
        await browser.load_session("session.json")
        scraper = PersonScraper(browser.page)
        person = await scraper.scrape("https://linkedin.com/in/username")
        print(person.name)

asyncio.run(main())

pip install linkedin-scraper==2.11.2

git clone https://github.com/joeyism/linkedin_scraper.git
cd linkedin_scraper
pip3 install -e .

python3 samples/create_session.py
python3 samples/scrape_company.py
python3 samples/scrape_person.py

pip install linkedin-scraper

playwright install chromium

import asyncio
from linkedin_scraper import BrowserManager, PersonScraper

async def main():
    # Initialize browser
    async with BrowserManager(headless=False) as browser:
        # Load authenticated session
        await browser.load_session("session.json")
        
        # Create scraper
        scraper = PersonScraper(browser.page)
        
        # Scrape a profile
        person = await scraper.scrape("https://linkedin.com/in/williamhgates/")
        
        # Access data
        print(f"Name: {person.name}")
        print(f"Headline: {person.headline}")
        print(f"Location: {person.location}")
        print(f"Experiences: {len(person.experiences)}")
        print(f"Education: {len(person.educations)}")

asyncio.run(main())

from linkedin_scraper import CompanyScraper

async def scrape_company():
    async with BrowserManager(headless=False) as browser:
        await browser.load_session("session.json")
        
        scraper = CompanyScraper(browser.page)
        company = await scraper.scrape("https://linkedin.com/company/microsoft/")
        
        print(f"Company: {company.name}")
        print(f"Industry: {company.industry}")
        print(f"Size: {company.company_size}")
        print(f"About: {company.about_us[:200]}...")

asyncio.run(scrape_company())

from linkedin_scraper import JobSearchScraper

async def search_jobs():
    async with BrowserManager(headless=False) as browser:
        await browser.load_session("session.json")
        
        scraper = JobSearchScraper(browser.page)
        jobs = await scraper.search(
            keywords="Python Developer",
            location="San Francisco",
            limit=10
        )
        
        for job in jobs:
            print(f"{job.title} at {job.company}")
            print(f"Location: {job.location}")
            print(f"Link: {job.linkedin_url}")
            print("---")

asyncio.run(search_jobs())

from linkedin_scraper import BrowserManager, CompanyPostsScraper

async def scrape_company_posts():
    async with BrowserManager(headless=False) as browser:
        await browser.load_session("session.json")
        
        scraper = CompanyPostsScraper(browser.page)
        posts = await scraper.scrape(
            "https://linkedin.com/company/microsoft/",
            limit=10
        )
        
        for post in posts:
            print(f"Posted: {post.posted_date}")
            print(f"Text: {post.text[:200]}...")
            print(f"Reactions: {post.reactions_count}")
            print(f"Comments: {post.comments_count}")
            print(f"URL: {post.linkedin_url}")
            print("---")

asyncio.run(scrape_company_posts())

from linkedin_scraper import BrowserManager, wait_for_manual_login

async def create_session():
    async with BrowserManager(headless=False) as browser:
        # Navigate to LinkedIn
        await browser.page.goto("https://www.linkedin.com/login")
        
        # Wait for manual login (opens browser)
        print("Please log in to LinkedIn...")
        await wait_for_manual_login(browser.page, timeout=300)
        
        # Save session
        await browser.save_session("session.json")
        print("✓ Session saved!")

asyncio.run(create_session())

from linkedin_scraper import BrowserManager, login_with_credentials
import os

async def login():
    async with BrowserManager(headless=False) as browser:
        # Login with credentials
        await login_with_credentials(
            browser.page,
            username=os.getenv("LINKEDIN_EMAIL"),
            password=os.getenv("LINKEDIN_PASSWORD")
        )
        
        # Save session for reuse
        await browser.save_session("session.json")

asyncio.run(login())

from linkedin_scraper import ConsoleCallback, PersonScraper

async def scrape_with_progress():
    callback = ConsoleCallback()  # Prints progress to console
    
    async with BrowserManager(headless=False) as browser:
        await browser.load_session("session.json")
        
        scraper = PersonScraper(browser.page, callback=callback)
        person = await scraper.scrape("https://linkedin.com/in/williamhgates/")

asyncio.run(scrape_with_progress())

from linkedin_scraper import ProgressCallback

class MyCallback(ProgressCallback):
    async def on_start(self, scraper_type: str, url: str):
        print(f"Starting {scraper_type} scraping: {url}")
    
    async def on_progress(self, message: str, percent: int):
        print(f"[{percent}%] {message}")
    
    async def on_complete(self, scraper_type: str, url: str):
        print(f"Completed {scraper_type}: {url}")
    
    async def on_error(self, error: Exception):
        print(f"Error: {error}")

class Person(BaseModel):
    name: str
    headline: Optional[str]
    location: Optional[str]
    about: Optional[str]
    linkedin_url: str
    experiences: List[Experience]
    educations: List[Education]
    skills: List[str]
    accomplishments: Optional[Accomplishment]

class Company(BaseModel):
    name: str
    industry: Optional[str]
    company_size: Optional[str]
    headquarters: Optional[str]
    founded: Optional[str]
    specialties: List[str]
    about: Optional[str]
    linkedin_url: str

class Job(BaseModel):
    title: str
    company: str
    location: Optional[str]
    description: Optional[str]
    employment_type: Optional[str]
    seniority_level: Optional[str]
    linkedin_url: str

class Post(BaseModel):
    linkedin_url: Optional[str]
    urn: Optional[str]
    text: Optional[str]
    posted_date: Optional[str]
    reactions_count: Optional[int]
    comments_count: Optional[int]
    reposts_count: Optional[int]
    image_urls: List[str]

browser = BrowserManager(
    headless=False,  # Show browser window
    slow_mo=100,     # Slow down operations (ms)
    viewport={"width": 1920, "height": 1080},
    user_agent="Custom User Agent"
)

from linkedin_scraper import (
    AuthenticationError,
    RateLimitError,
    ProfileNotFoundError
)

try:
    person = await scraper.scrape(url)
except AuthenticationError:
    print("Not logged in - session expired")
except RateLimitError:
    print("Rate limited by LinkedIn")
except ProfileNotFoundError:
    print("Profile not found or private")