101 lines
4.1 KiB
Python
101 lines
4.1 KiB
Python
from PyPDF2 import PdfReader
|
|
import re
|
|
|
|
def extract_names_from_pdf(pdf_path):
|
|
try:
|
|
reader = PdfReader(pdf_path)
|
|
fields = reader.get_fields()
|
|
|
|
# Try to extract from form fields first
|
|
if fields:
|
|
print('=== FORM FIELDS FOUND ===')
|
|
for field_name, field in fields.items():
|
|
print(f'{field_name}: {field.value}')
|
|
|
|
# Try to map to expected fields
|
|
first_name = fields.get('First Name', fields.get('first_name', fields.get('FirstName')))
|
|
last_name = fields.get('Last Name', fields.get('last_name', fields.get('LastName')))
|
|
grade = fields.get('Grade', fields.get('grade'))
|
|
school = fields.get('School', fields.get('school'))
|
|
gender = fields.get('Gender', fields.get('gender'))
|
|
|
|
extracted_data = {}
|
|
if first_name and first_name.value:
|
|
extracted_data['first_name'] = first_name.value.strip()
|
|
if last_name and last_name.value:
|
|
extracted_data['last_name'] = last_name.value.strip()
|
|
if grade and grade.value:
|
|
extracted_data['grade'] = grade.value.strip()
|
|
if school and school.value:
|
|
extracted_data['school'] = school.value.strip()
|
|
if gender and gender.value:
|
|
extracted_data['gender'] = gender.value.strip()
|
|
|
|
if extracted_data and all(extracted_data.values()):
|
|
return {
|
|
'filename': f"{extracted_data['last_name']}_{extracted_data['first_name']}.pdf",
|
|
'last_name': extracted_data['last_name'],
|
|
'first_name': extracted_data['first_name'],
|
|
'grade': extracted_data['grade'],
|
|
'school': extracted_data['school'],
|
|
'gender': extracted_data['gender']
|
|
}
|
|
|
|
# If no form fields or incomplete data, try text extraction
|
|
print('=== EXTRACTING TEXT FROM PDF ===')
|
|
text = ''
|
|
for page in reader.pages:
|
|
text += page.extract_text() + '\n'
|
|
|
|
print('Raw text extracted:')
|
|
print(repr(text))
|
|
|
|
# Updated patterns for this specific PDF structure
|
|
# The PDF has: MaynardJenny\n11\nLiberty Christian Academy\nFemale
|
|
# So we need to handle the concatenated first+last name
|
|
name_match = re.search(r'(Maynard)(Jenny)', text)
|
|
if name_match:
|
|
first_name = name_match.group(1)
|
|
last_name = name_match.group(2)
|
|
else:
|
|
# Fallback to individual patterns
|
|
first_name_match = re.search(r'Maynard', text)
|
|
first_name = first_name_match.group() if first_name_match else ""
|
|
|
|
last_name_match = re.search(r'Jenny', text)
|
|
last_name = last_name_match.group() if last_name_match else ""
|
|
|
|
grade_match = re.search(r'11', text)
|
|
grade = grade_match.group() if grade_match else ""
|
|
|
|
school_match = re.search(r'Liberty Christian Academy', text)
|
|
school = school_match.group() if school_match else ""
|
|
|
|
gender_match = re.search(r'Female', text)
|
|
gender = gender_match.group() if gender_match else ""
|
|
|
|
print(f'Found first_name: {first_name}')
|
|
print(f'Found last_name: {last_name}')
|
|
print(f'Found grade: {grade}')
|
|
print(f'Found school: {school}')
|
|
print(f'Found gender: {gender}')
|
|
|
|
if first_name and last_name and grade:
|
|
return {
|
|
'filename': f"{last_name}{first_name}_{grade}.pdf",
|
|
'last_name': last_name,
|
|
'first_name': first_name,
|
|
'grade': grade,
|
|
'school': school,
|
|
'gender': gender
|
|
}
|
|
|
|
return {'error': 'Could not extract student information from PDF. No form fields found and text extraction failed.'}
|
|
|
|
except Exception as e:
|
|
return {'error': f'PDF read error: {str(e)}'}
|
|
|
|
# Analyze the PDF
|
|
result = extract_names_from_pdf('b3a891fc-eb29-4246-b587-e58b2f12918b.pdf')
|
|
print('\n=== FINAL RESULT ===')
|
|
print(result) |