84 lines
No EOL
3.3 KiB
Python
84 lines
No EOL
3.3 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Simple script to extract LinkedIn profiles using existing working pattern.
|
|
"""
|
|
import json
|
|
import os
|
|
import subprocess
|
|
from datetime import datetime, timezone
|
|
from pathlib import Path
|
|
|
|
def extract_profile_simple(linkedin_url: str, name: str, output_file: str, source_file: str, staff_id: str) -> bool:
|
|
"""Extract LinkedIn profile using existing working pattern."""
|
|
|
|
print(f"Extracting LinkedIn profile for: {name}")
|
|
|
|
# Use the exact command pattern that worked before
|
|
cmd = [
|
|
'python', 'scripts/extract_linkedin_profile_exa.py',
|
|
linkedin_url,
|
|
output_file,
|
|
'--source_file', source_file,
|
|
'--staff_id', staff_id
|
|
]
|
|
|
|
try:
|
|
result = subprocess.run(cmd, capture_output=True, text=True, timeout=120)
|
|
|
|
if result.returncode == 0:
|
|
print(f"✅ Successfully extracted profile for {name}")
|
|
return True
|
|
else:
|
|
print(f"❌ Failed to extract profile for {name}: {result.stderr}")
|
|
return False
|
|
|
|
except Exception as e:
|
|
print(f"❌ Exception extracting profile for {name}: {e}")
|
|
return False
|
|
|
|
def main():
|
|
"""Main function to extract specific LinkedIn profiles."""
|
|
|
|
# Define specific profiles to extract from Academiehuis Grote Kerk Zwolle
|
|
profiles = [
|
|
{
|
|
'linkedin_url': 'https://www.linkedin.com/in/anja-van-hoorn-657b66223',
|
|
'name': 'Anja van Hoorn',
|
|
'output_file': '/Users/kempersc/apps/glam/data/custodian/person/entity/anja-van-hoorn-657b66223_20251210T160000Z.json',
|
|
'source_file': '/Users/kempersc/apps/glam/data/custodian/person/affiliated/parsed/academiehuis-grote-kerk-zwolle_staff_20251210T155412Z.json',
|
|
'staff_id': 'academiehuis-grote-kerk-zwolle_staff_0001_anja_van_hoorn'
|
|
},
|
|
{
|
|
'linkedin_url': 'https://www.linkedin.com/in/inez-van-kleef',
|
|
'name': 'Inez van Kleef',
|
|
'output_file': '/Users/kempersc/apps/glam/data/custodian/person/entity/inez-van-kleef_20251210T160000Z.json',
|
|
'source_file': '/Users/kempersc/apps/glam/data/custodian/person/affiliated/parsed/academiehuis-grote-kerk-zwolle_staff_20251210T155412Z.json',
|
|
'staff_id': 'academiehuis-grote-kerk-zwolle_staff_0002_inez_van_kleef'
|
|
},
|
|
{
|
|
'linkedin_url': 'https://www.linkedin.com/in/marga-edens-a284175',
|
|
'name': 'Marga Edens',
|
|
'output_file': '/Users/kempersc/apps/glam/data/custodian/person/entity/marga-edens-a284175_20251210T160000Z.json',
|
|
'source_file': '/Users/kempersc/apps/glam/data/custodian/person/affiliated/parsed/academiehuis-grote-kerk-zwolle_staff_20251210T155412Z.json',
|
|
'staff_id': 'academiehuis-grote-kerk-zwolle_staff_0003_marga_edens'
|
|
}
|
|
]
|
|
|
|
success_count = 0
|
|
total_cost = 0.0
|
|
|
|
for profile in profiles:
|
|
if extract_profile_simple(**profile):
|
|
success_count += 1
|
|
total_cost += 0.001
|
|
# Delay between requests
|
|
import time
|
|
time.sleep(3)
|
|
|
|
print(f"\n📊 Extraction Summary:")
|
|
print(f"✅ Successfully processed: {success_count}")
|
|
print(f"💰 Total cost: ${total_cost:.3f}")
|
|
print(f"📁 Files saved to: /Users/kempersc/apps/glam/data/custodian/person/entity")
|
|
|
|
if __name__ == "__main__":
|
|
main() |