Spaces:
Runtime error
Runtime error
File size: 8,932 Bytes
7498f2c | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 | """
LinkedIn Profile Data Extractor
Extracts user profile data and job listings from LinkedIn
"""
import os
import logging
import json
import re
from typing import Dict, Any, List, Optional
from datetime import datetime
import requests
logger = logging.getLogger(__name__)
class LinkedInProfileExtractor:
"""Extract and populate user data from LinkedIn"""
def __init__(self):
self.client_id = os.getenv('LINKEDIN_CLIENT_ID')
self.client_secret = os.getenv('LINKEDIN_CLIENT_SECRET')
self.access_token = None
def set_access_token(self, token: str):
"""Set the OAuth access token"""
self.access_token = token
def extract_profile_data(self, profile_url: Optional[str] = None) -> Dict[str, Any]:
"""
Extract profile data from LinkedIn
Note: Due to LinkedIn API restrictions, this provides a structure
that would be filled with actual data when proper API access is available
"""
# LinkedIn API v2 endpoints (requires OAuth 2.0)
if self.access_token:
try:
# Get basic profile
headers = {
'Authorization': f'Bearer {self.access_token}',
'X-Restli-Protocol-Version': '2.0.0'
}
# Get user profile
profile_response = requests.get(
'https://api.linkedin.com/v2/me',
headers=headers
)
# Get email
email_response = requests.get(
'https://api.linkedin.com/v2/emailAddress?q=members&projection=(elements*(handle~))',
headers=headers
)
if profile_response.status_code == 200:
profile = profile_response.json()
email_data = email_response.json() if email_response.status_code == 200 else {}
return self._parse_linkedin_response(profile, email_data)
except Exception as e:
logger.error(f"Error fetching LinkedIn profile: {e}")
# Return template structure for manual filling or mock data
return self._get_profile_template()
def _parse_linkedin_response(self, profile: Dict, email_data: Dict) -> Dict[str, Any]:
"""Parse LinkedIn API response into our standard format"""
extracted_data = {
'contact': {
'name': f"{profile.get('localizedFirstName', '')} {profile.get('localizedLastName', '')}".strip(),
'email': '',
'phone': '',
'linkedin': f"https://www.linkedin.com/in/{profile.get('vanityName', '')}",
'location': profile.get('localizedHeadline', '')
},
'summary': profile.get('summary', ''),
'headline': profile.get('localizedHeadline', ''),
'experience': [],
'education': [],
'skills': [],
'certifications': [],
'languages': [],
'projects': []
}
# Extract email
if email_data.get('elements'):
for element in email_data['elements']:
if 'handle~' in element:
extracted_data['contact']['email'] = element['handle~'].get('emailAddress', '')
break
# Note: Full experience, education, skills require additional API calls
# with specific permissions that are restricted in LinkedIn's current API
return extracted_data
def _get_profile_template(self) -> Dict[str, Any]:
"""Get a template structure for profile data"""
return {
'contact': {
'name': '',
'email': '',
'phone': '',
'linkedin': '',
'location': '',
'website': ''
},
'summary': '',
'headline': '',
'experience': [
{
'title': '',
'company': '',
'location': '',
'start_date': '',
'end_date': '',
'description': '',
'skills_used': []
}
],
'education': [
{
'degree': '',
'field': '',
'school': '',
'start_date': '',
'end_date': '',
'description': ''
}
],
'skills': [],
'certifications': [],
'languages': [],
'projects': [],
'recommendations': []
}
def search_jobs(self, keywords: str, location: str = '') -> List[Dict[str, Any]]:
"""
Search for jobs on LinkedIn
Note: LinkedIn Jobs API has strict limitations
"""
jobs = []
if self.access_token:
try:
# LinkedIn Jobs API is heavily restricted
# This is a placeholder for when proper access is available
headers = {
'Authorization': f'Bearer {self.access_token}',
'X-Restli-Protocol-Version': '2.0.0'
}
# Note: Actual job search API requires special partnership access
# Using mock structure for demonstration
pass
except Exception as e:
logger.error(f"Error searching LinkedIn jobs: {e}")
# Return mock data for demonstration
return self._get_mock_linkedin_jobs(keywords, location)
def _get_mock_linkedin_jobs(self, keywords: str, location: str) -> List[Dict[str, Any]]:
"""Get mock LinkedIn job data for demonstration"""
return [
{
'id': 'linkedin_job_1',
'title': f'Senior {keywords} Engineer',
'company': 'Tech Innovations Inc.',
'location': location or 'Remote',
'description': f'We are looking for a talented {keywords} engineer to join our team...',
'url': 'https://www.linkedin.com/jobs/view/123456',
'posted_date': datetime.now().isoformat(),
'salary': '$120,000 - $180,000',
'job_type': 'Full-time',
'experience_level': 'Senior',
'skills_required': [keywords, 'Python', 'AWS', 'Docker'],
'source': 'LinkedIn'
},
{
'id': 'linkedin_job_2',
'title': f'{keywords} Developer',
'company': 'Global Solutions Corp',
'location': location or 'Hybrid',
'description': f'Join our growing team as a {keywords} developer...',
'url': 'https://www.linkedin.com/jobs/view/789012',
'posted_date': datetime.now().isoformat(),
'salary': '$90,000 - $130,000',
'job_type': 'Full-time',
'experience_level': 'Mid-level',
'skills_required': [keywords, 'JavaScript', 'React', 'Node.js'],
'source': 'LinkedIn'
}
]
def auto_populate_from_linkedin(self, linkedin_url: str) -> Dict[str, Any]:
"""
Auto-populate user data from LinkedIn profile URL
This would scrape or use API to get data
"""
# Extract username from URL
username_match = re.search(r'linkedin\.com/in/([^/]+)', linkedin_url)
if not username_match:
logger.error(f"Invalid LinkedIn URL: {linkedin_url}")
return self._get_profile_template()
username = username_match.group(1)
# In production, this would use LinkedIn API or scraping
# For now, return template with username filled
template = self._get_profile_template()
template['contact']['linkedin'] = linkedin_url
template['contact']['name'] = username.replace('-', ' ').title()
# Add mock data for demonstration
template['summary'] = f"Experienced professional with expertise in various domains. LinkedIn: {username}"
template['skills'] = ['Leadership', 'Project Management', 'Strategic Planning', 'Team Building']
return template
# Singleton instance
linkedin_extractor = LinkedInProfileExtractor() |