# On Windows, install with: pip install pypdf
from pypdf import PdfReader, PdfWriter

# Example 1: Open a PDF file for reading
reader = PdfReader('sample.pdf')

# Example 2: Count the number of pages
num_pages = len(reader.pages)
print('Number of pages:', num_pages)

# Example 3: Extract text from the first page
page = reader.pages[0]
text = page.extract_text()
print('First page text:')
print(text)

# Example 4: Merge two PDF files
writer = PdfWriter()
for file_name in ['sample.pdf', 'second.pdf']:
    input_pdf = PdfReader(file_name)
    for page in input_pdf.pages:
        writer.add_page(page)
writer.write('merged.pdf')

# Example 5: Split a PDF into single-page files
for page_num, page in enumerate(reader.pages):
    writer = PdfWriter()
    writer.add_page(page)
    output_name = f'page_{page_num + 1}.pdf'
    writer.write(output_name)

# Example 6: Add metadata to a PDF
writer = PdfWriter()
for page in reader.pages:
    writer.add_page(page)
writer.add_metadata({'/Title': 'My Custom PDF', '/Author': 'YouTube Demo'})
writer.write('metadata_sample.pdf')

# Example 7: Decrypting an encrypted PDF (Intermediate)
protected_reader = PdfReader('protected.pdf')
if protected_reader.is_encrypted:
    protected_reader.decrypt('mypassword')
    text = protected_reader.pages[0].extract_text()
    print('Decrypted page 1 text:')
    print(text)

# Example 8: Rotate a page clockwise by 90 degrees
from copy import deepcopy
writer = PdfWriter()
rotated_page = deepcopy(reader.pages[0])
rotated_page.rotate(90)
writer.add_page(rotated_page)
writer.write('rotated.pdf')

# Example 9: Extracting all text from a PDF (Intermediate)
all_text = ''
for page in reader.pages:
    page_text = page.extract_text()
    if page_text:
        all_text += page_text + '\n'
print('All PDF text:')
print(all_text)

# Example 10: Copy only odd pages to a new PDF (Intermediate)
writer = PdfWriter()
for page_num, page in enumerate(reader.pages):
    if page_num % 2 == 0:
        writer.add_page(page)
writer.write('odd_pages.pdf')

# Example 11: Extract PDF meta data (Intermediate)
meta = reader.metadata
for key, value in meta.items():
    print(f'{key}: {value}')

# Example 12: Add password protection to a PDF (Advanced)
writer = PdfWriter()
for page in reader.pages:
    writer.add_page(page)
writer.encrypt('mypassword')
writer.write('protected_out.pdf')

# Example 13: Linearizing a PDF for fast web view (Advanced)
# PyPDF cannot fully linearize PDFs, but we can optimize structure.
writer = PdfWriter()
for page in reader.pages:
    writer.add_page(page)
writer.write('linearized_sample.pdf')

# Example 14: Catch missing file errors (Error Handling)
try:
    missing_reader = PdfReader('missing.pdf')
except FileNotFoundError:
    print('File missing.pdf not found! Check the file name.')

# Example 15: Warn when extracting text returns None (Error Handling)
page = reader.pages[0]
text = page.extract_text()
if text is None:
    print('No text extracted. This page may be scanned or image-only.')
else:
    print('Text:', text)

# Example 16: Always close writers for best practice
writer = PdfWriter()
for page in reader.pages:
    writer.add_page(page)
with open('best_practice.pdf', 'wb') as out_file:
    writer.write(out_file)

# Example 17: Check for encryption before extracting text (Best Practice)
if reader.is_encrypted:
    print('PDF is encrypted! Cannot extract text without the password.')
else:
    text = reader.pages[0].extract_text()
    print('Extracted text:', text)

# Example 18: Get total size of all PDF outputs (Common Pattern)
import os
total_size = 0
for name in ['merged.pdf', 'best_practice.pdf', 'odd_pages.pdf']:
    if os.path.exists(name):
        total_size += os.path.getsize(name)
print('Total size in bytes:', total_size)

# Example 19: Tiny Mini-Project: Combine only first pages of several PDFs
import glob
writer = PdfWriter()
for pdf_file in glob.glob('*.pdf'):
    try:
        pdf = PdfReader(pdf_file)
        first_page = pdf.pages[0]
        writer.add_page(first_page)
        print(f'Added first page from {pdf_file}')
    except Exception as e:
        print(f'Cannot add {pdf_file}:', e)
writer.write('first_pages_collection.pdf')