linkedin-playwright-scraper 4.0.0__py3-none-any.whl

linkedin_playwright_scraper-4.0.0.dist-info/METADATA

@@ -0,0 +1,502 @@
+Metadata-Version: 2.4
+Name: linkedin-playwright-scraper
+Version: 4.0.0
+Summary: Async LinkedIn scraper for profiles, companies, jobs and feed — Playwright-based
+Project-URL: Homepage, https://github.com/vinzlac/linkedin_scraper
+Project-URL: Documentation, https://github.com/vinzlac/linkedin_scraper#readme
+Project-URL: Repository, https://github.com/vinzlac/linkedin_scraper
+Project-URL: Issues, https://github.com/vinzlac/linkedin_scraper/issues
+Author: Vincent Lacombe
+License: Apache 2.0
+License-File: LICENSE
+Keywords: async,feed,linkedin,mcp,playwright,profiles,scraper,scraping
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Internet :: WWW/HTTP :: Dynamic Content
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.9
+Requires-Dist: aiofiles>=23.0.0
+Requires-Dist: lxml>=5.0.0
+Requires-Dist: playwright>=1.40.0
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: python-dotenv>=1.0.0
+Requires-Dist: requests>=2.31.0
+Description-Content-Type: text/markdown
+
+# LinkedIn Scraper
+
+[![PyPI version](https://badge.fury.io/py/linkedin-scraper.svg)](https://badge.fury.io/py/linkedin-scraper)
+[![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)
+[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+
+Async LinkedIn scraper built with Playwright for extracting profile, company, and job data from LinkedIn.
+
+## ⚠️ Breaking Changes in v3.0.0
+
+**Version 3.0.0 introduces breaking changes and is NOT backwards compatible with previous versions.**
+
+### What Changed:
+- **Playwright instead of Selenium** - Complete rewrite using Playwright for better performance and reliability
+- **Async/await throughout** - All methods are now async and require `await`
+- **New package structure** - Imports have changed (e.g., `from linkedin_scraper import PersonScraper`)
+- **Updated data models** - Using Pydantic models instead of simple objects
+- **Different API** - Method signatures and return types have changed
+
+### Migration Guide:
+
+**Before (v2.x with Selenium):**
+```python
+from linkedin_scraper import Person
+
+person = Person("https://linkedin.com/in/username", driver=driver)
+print(person.name)
+```
+
+**After (v3.0+ with Playwright):**
+```python
+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())
+```
+
+**If you need the old Selenium-based version:**
+```bash
+pip install linkedin-scraper==2.11.2
+```
+## Quick Start (development)
+
+```bash
+git clone https://github.com/joeyism/linkedin_scraper.git
+cd linkedin_scraper
+
+# Install dependencies + Playwright browser
+just install
+
+# Create your LinkedIn session (manual login in browser)
+just session
+
+# Scrape a profile (slug or full URL)
+just run-person your-linkedin-slug
+
+# Scrape your feed
+just run-feed
+```
+
+Run `just` with no arguments to list all available commands.
+
+---
+
+---
+
+## Features
+
+- **Person Profiles** - Scrape comprehensive profile information
+  - Basic info (name, headline, location, about)
+  - Work experience with details
+  - Education history
+  - Skills and accomplishments
+  
+- **Company Pages** - Extract company information
+  - Company overview and details
+  - Industry and size
+  - Headquarters location
+  
+- **Company Posts** - Scrape posts from company pages
+  - Post content and text
+  - Reactions, comments, reposts counts
+  - Posted date and images
+
+- **Feed** - Scrape your authenticated LinkedIn feed
+  - Author name and profile URL
+  - Post content, date, reactions, comments, reposts
+  - Sponsored/promoted posts automatically filtered out
+
+- **Job Listings** - Scrape job postings
+  - Job details and requirements
+  - Company information
+  - Application links
+
+- **Async/Await** - Modern async Python with Playwright
+- **Type Safety** - Full Pydantic models for all data
+- **Progress Callbacks** - Track scraping progress
+- **Session Management** - Reuse authenticated sessions
+
+## Installation
+
+**From PyPI:**
+```bash
+pip install linkedin-playwright-scraper
+playwright install chromium
+```
+
+**From source (recommended for development):**
+```bash
+# Requires uv and just
+just install
+```
+
+## Quick Start
+
+### Basic Usage
+
+```python
+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())
+```
+
+### Company Scraping
+
+```python
+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())
+```
+
+### Job Scraping
+
+```python
+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())
+```
+
+### Company Posts Scraping
+
+```python
+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())
+```
+
+### Feed Scraping
+
+```python
+from linkedin_scraper import BrowserManager, FeedScraper
+
+async def scrape_feed():
+    async with BrowserManager(headless=False) as browser:
+        await browser.load_session("session.json")
+
+        scraper = FeedScraper(browser.page)
+        posts = await scraper.scrape(limit=20)
+
+        for post in posts:
+            print(f"Author: {post.author_name} ({post.author_url})")
+            print(f"Posted: {post.posted_date}")
+            print(f"Text: {post.text[:200]}...")
+            print(f"Reactions: {post.reactions_count}")
+            print("---")
+
+asyncio.run(scrape_feed())
+```
+
+Or via the command line:
+
+```bash
+just run-feed
+```
+
+## Authentication
+
+LinkedIn requires authentication. You need to create a session file first:
+
+### Option 1: Manual Login Script
+
+```python
+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())
+```
+
+### Option 2: Programmatic Login
+
+```python
+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())
+```
+
+## Progress Tracking
+
+Track scraping progress with callbacks:
+
+```python
+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())
+```
+
+### Custom Callbacks
+
+```python
+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}")
+```
+
+## Data Models
+
+All scraped data is returned as Pydantic models:
+
+### Person
+
+```python
+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]
+```
+
+### Company
+
+```python
+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
+```
+
+### Job
+
+```python
+class Job(BaseModel):
+    title: str
+    company: str
+    location: Optional[str]
+    description: Optional[str]
+    employment_type: Optional[str]
+    seniority_level: Optional[str]
+    linkedin_url: str
+```
+
+### Post
+
+```python
+class Post(BaseModel):
+    linkedin_url: Optional[str]
+    urn: Optional[str]
+    author_name: Optional[str]
+    author_url: 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]
+    video_url: Optional[str]
+    article_url: Optional[str]
+```
+
+## Advanced Usage
+
+### Browser Configuration
+
+```python
+browser = BrowserManager(
+    headless=False,  # Show browser window
+    slow_mo=100,     # Slow down operations (ms)
+    viewport={"width": 1920, "height": 1080},
+    user_agent="Custom User Agent"
+)
+```
+
+### Error Handling
+
+```python
+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")
+```
+
+## Best Practices
+
+1. **Rate Limiting** - Add delays between requests
+   ```python
+   import asyncio
+   await asyncio.sleep(2)  # 2 second delay
+   ```
+
+2. **Session Reuse** - Save and reuse sessions to avoid frequent logins
+
+3. **Error Handling** - Always handle exceptions (rate limits, auth errors, etc.)
+
+4. **Headless Mode** - Use `headless=False` during development, `True` for production
+
+5. **Respect LinkedIn** - Don't scrape aggressively, respect rate limits
+
+## Requirements
+
+- Python 3.9+
+- [uv](https://docs.astral.sh/uv/) (package manager)
+- [just](https://just.systems/) (task runner)
+- Playwright (installed automatically via `just install`)
+
+## License
+
+Apache License 2.0 - see [LICENSE](LICENSE) file for details.
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request.
+
+## Disclaimer
+
+This tool is for educational purposes only. Make sure to comply with LinkedIn's Terms of Service and use responsibly. The authors are not responsible for any misuse of this tool.
+
+## Links
+
+- [GitHub Repository](https://github.com/joeyism/linkedin_scraper)
+- [Issue Tracker](https://github.com/joeyism/linkedin_scraper/issues)
+- [PyPI Package](https://pypi.org/project/linkedin-scraper/)

linkedin_playwright_scraper-4.0.0.dist-info/RECORD

@@ -0,0 +1,26 @@
+linkedin_scraper/__init__.py,sha256=PiEZ1emaIBqXEyGZM0SPXFK1pUUZuverw09CJzFRa9U,2031
+linkedin_scraper/callbacks.py,sha256=5QynTionrIL-HWr9PvfHZjhOipx5tPDE7qXIXqzW29I,5119
+linkedin_scraper/core/__init__.py,sha256=4RX5Us0AEctZckkQH0dhW2oA6RxEjFwZKldTMy_sMJ0,1784
+linkedin_scraper/core/auth.py,sha256=g9B0kcgxW61f8sxhl5EqNswjWUSKpnUP4IPXt15fBqM,10652
+linkedin_scraper/core/browser.py,sha256=VoM2knGosmUSsAPQS82lyVUh_RIoASo-mLoxSV2mTy0,8715
+linkedin_scraper/core/exceptions.py,sha256=W_bFWxJOgmK_1Ug_jATwfN7DQzUVyx5407fH4VzUu00,979
+linkedin_scraper/core/permalink_cache.py,sha256=3bYGuKp4TeuvslAYO20RO2kaUXSxcIyvKgeby-Zr0-c,1624
+linkedin_scraper/core/rate_limit_guard.py,sha256=IadnB5AzRKIxCAp1fh6047sZVE41JNiDEUrJ0yywiT4,4240
+linkedin_scraper/core/utils.py,sha256=vdtVNbhM0t5_zpEFLotLeZzm8jbVZNmkalR2_opux-8,9629
+linkedin_scraper/models/__init__.py,sha256=C7LuNmnK1WpiIwrHq7A0-9b9LU3Xy_EiVI0nKMLPNKs,427
+linkedin_scraper/models/company.py,sha256=d-XMY3YaDk8Y4Tx8-g8Sp9UumBV5CVbfOvt4S9c73ZE,2500
+linkedin_scraper/models/job.py,sha256=_Z8XT8-OyIju0YbYesMjr_2hAmBSu_GjlUmsCobtJq0,1751
+linkedin_scraper/models/person.py,sha256=TfYmvefVNQS-o2wwy5_7o9tmG2uNZHUjhUAEv2qG4Pg,3641
+linkedin_scraper/models/post.py,sha256=cDNFUiwJlZbsC_6sF_fYIOHRRYuhzr9flkT62VmUWDc,2150
+linkedin_scraper/scrapers/__init__.py,sha256=3Ilgx4KnmY8YSwUK3slamuhkCmw7EbBvAmpcK-XxxBs,448
+linkedin_scraper/scrapers/base.py,sha256=wd6IHbYnenpLlMPdg2-vfDx7HHMIAnCCx5Jmpq7D980,8509
+linkedin_scraper/scrapers/company.py,sha256=ulHdUP-CrWiAfqaQ0GYE1OHhDmODwPMlFN2tT9g2gLA,8372
+linkedin_scraper/scrapers/company_posts.py,sha256=AibnAtKRp_CGgOEskrRkrrgrT0wvyUpwg2slownPyEk,13962
+linkedin_scraper/scrapers/feed.py,sha256=4IS6tdNBNOnTfmw7BND95RRc_gRw73-CoflpI-5yV_k,85000
+linkedin_scraper/scrapers/job.py,sha256=VylRclztwwURAXbqx8ZsNuWM5VV14YKQnV6os4BprS0,7631
+linkedin_scraper/scrapers/job_search.py,sha256=5aAPnPdLOAAJvwrb1M7IPOKmNP-loWKcmjjrvbsuGJA,4804
+linkedin_scraper/scrapers/person.py,sha256=MIbcDf75bORDmGeYhB_SAkL3SkoIP9BC7E1-CrVWujM,30047
+linkedin_playwright_scraper-4.0.0.dist-info/METADATA,sha256=DeoyQgFaXU7eupJrTWveyiNihxtsvcWEQHalgrZTHGU,13855
+linkedin_playwright_scraper-4.0.0.dist-info/WHEEL,sha256=lCkmxWfQsSc9CfIClYeavTdQeEX2toPqufh9gI35EQA,87
+linkedin_playwright_scraper-4.0.0.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+linkedin_playwright_scraper-4.0.0.dist-info/RECORD,,

linkedin_playwright_scraper-4.0.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.31.0
+Root-Is-Purelib: true
+Tag: py3-none-any