Initial commit - Kindle Clippings Parser
🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
JoelShepard
510
main.py
Normal file
510
main.py
Normal file
@@ -0,0 +1,510 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Kindle Clippings to Markdown Converter
|
||||
|
||||
This script parses a "My Clippings.txt" file from Kindle and converts it
|
||||
to structured markdown files, creating a separate file for each book.
|
||||
Optionally uploads the results to a WebDAV server.
|
||||
"""
|
||||
|
||||
import re
|
||||
from collections import defaultdict
|
||||
from pathlib import Path
|
||||
import argparse
|
||||
import requests
|
||||
from requests.auth import HTTPBasicAuth
|
||||
import sys
|
||||
import os
|
||||
from xml.etree import ElementTree as ET
|
||||
from config import get_webdav_config
|
||||
|
||||
|
||||
def clean_title(title):
|
||||
"""Clean and normalize book title."""
|
||||
return title.strip().replace('\r', '').replace('\n', '')
|
||||
|
||||
|
||||
def extract_page_info(metadata_line):
|
||||
"""
|
||||
Extract page information from the metadata line.
|
||||
|
||||
Args:
|
||||
metadata_line (str): The line containing page and position info
|
||||
|
||||
Returns:
|
||||
str: Formatted page reference or empty string if not found
|
||||
"""
|
||||
metadata_line = metadata_line.lower()
|
||||
|
||||
# Look for page information
|
||||
page_match = re.search(r'pagina\s+(\d+)', metadata_line)
|
||||
if page_match:
|
||||
page_num = page_match.group(1)
|
||||
return f"(p. {page_num})"
|
||||
|
||||
# If no page found, look for position as fallback
|
||||
position_match = re.search(r'posizione\s+(\d+)', metadata_line)
|
||||
if position_match:
|
||||
position_num = position_match.group(1)
|
||||
return f"(pos. {position_num})"
|
||||
|
||||
return ""
|
||||
|
||||
|
||||
def sanitize_filename(filename):
|
||||
"""
|
||||
Sanitize filename by removing/replacing invalid characters while preserving spaces.
|
||||
|
||||
Args:
|
||||
filename (str): Original filename
|
||||
|
||||
Returns:
|
||||
str: Sanitized filename safe for filesystem with preserved spaces
|
||||
"""
|
||||
# Replace invalid filesystem characters with safe alternatives
|
||||
replacements = {
|
||||
'<': '⟨', # Mathematical left angle bracket
|
||||
'>': '⟩', # Mathematical right angle bracket
|
||||
':': '꞉', # Modifier letter colon
|
||||
'"': '"', # Right double quotation mark
|
||||
'/': '∕', # Division slash
|
||||
'\\': '∖', # Set minus
|
||||
'|': '❘', # Light vertical bar
|
||||
'?': '？', # Full-width question mark
|
||||
'*': '∗', # Asterisk operator
|
||||
}
|
||||
|
||||
# Apply character replacements
|
||||
for invalid_char, safe_char in replacements.items():
|
||||
filename = filename.replace(invalid_char, safe_char)
|
||||
|
||||
# Clean up multiple spaces but preserve single spaces
|
||||
filename = re.sub(r'\s+', ' ', filename.strip())
|
||||
|
||||
# Remove leading/trailing dots and spaces that could cause issues
|
||||
filename = filename.strip('. ')
|
||||
|
||||
# Limit length to avoid filesystem issues (keeping some margin for .md extension)
|
||||
if len(filename) > 200:
|
||||
filename = filename[:200].strip()
|
||||
|
||||
# Ensure filename is not empty and doesn't end with problematic characters
|
||||
if not filename or filename.endswith('.'):
|
||||
filename = filename.rstrip('.') or 'Untitled Book'
|
||||
|
||||
return filename
|
||||
|
||||
|
||||
def parse_clippings_file(file_path):
|
||||
"""
|
||||
Parse the My Clippings.txt file and extract book titles, citations, and page references.
|
||||
|
||||
Args:
|
||||
file_path (str): Path to the My Clippings.txt file
|
||||
|
||||
Returns:
|
||||
dict: Dictionary with book titles as keys and lists of (citation, page_ref) tuples as values
|
||||
"""
|
||||
try:
|
||||
with open(file_path, 'r', encoding='utf-8') as file:
|
||||
content = file.read()
|
||||
except UnicodeDecodeError:
|
||||
# Try with different encoding if UTF-8 fails
|
||||
with open(file_path, 'r', encoding='latin-1') as file:
|
||||
content = file.read()
|
||||
|
||||
# Split entries by the delimiter
|
||||
entries = content.split('==========')
|
||||
|
||||
# Dictionary to group citations by book title
|
||||
books = defaultdict(list)
|
||||
|
||||
for entry in entries:
|
||||
entry = entry.strip()
|
||||
if not entry:
|
||||
continue
|
||||
|
||||
# Split entry into lines and filter empty ones
|
||||
lines = [line.strip() for line in entry.split('\n') if line.strip()]
|
||||
|
||||
if len(lines) < 2:
|
||||
continue
|
||||
|
||||
# First line is the book title
|
||||
book_title = clean_title(lines[0])
|
||||
|
||||
# Second line contains metadata (page, position, etc.)
|
||||
metadata_line = lines[1]
|
||||
page_ref = extract_page_info(metadata_line)
|
||||
|
||||
# Third line onwards (if exists) contains the actual citation
|
||||
if len(lines) > 2:
|
||||
# Join all content lines (in case citation spans multiple lines)
|
||||
citation = ' '.join(lines[2:]).strip()
|
||||
|
||||
# Only add non-empty citations
|
||||
if citation and citation != '':
|
||||
# Check if it's a bookmark entry (no actual text content)
|
||||
meta_line = lines[1].lower()
|
||||
if 'segnalibro' in meta_line and len(citation) < 10:
|
||||
# Skip bookmark entries with very short or no text
|
||||
continue
|
||||
|
||||
books[book_title].append((citation, page_ref))
|
||||
|
||||
return dict(books)
|
||||
|
||||
|
||||
def generate_markdown_files(books_dict, output_dir="kindle_books"):
|
||||
"""
|
||||
Generate separate markdown files for each book with page references.
|
||||
|
||||
Args:
|
||||
books_dict (dict): Dictionary with book titles and (citation, page_ref) tuples
|
||||
output_dir (str): Directory to save markdown files
|
||||
|
||||
Returns:
|
||||
list: List of generated file paths
|
||||
"""
|
||||
# Create output directory if it doesn't exist
|
||||
output_path = Path(output_dir)
|
||||
output_path.mkdir(exist_ok=True)
|
||||
|
||||
generated_files = []
|
||||
|
||||
# Sort books alphabetically
|
||||
sorted_books = sorted(books_dict.items())
|
||||
|
||||
for book_title, citations_with_pages in sorted_books:
|
||||
if not citations_with_pages: # Skip books with no citations
|
||||
continue
|
||||
|
||||
# Create sanitized filename
|
||||
safe_filename = sanitize_filename(book_title)
|
||||
file_path = output_path / f"{safe_filename}.md"
|
||||
|
||||
# Generate markdown content for this book
|
||||
markdown_content = []
|
||||
|
||||
# Add each citation as a blockquote with page reference
|
||||
for citation, page_ref in citations_with_pages:
|
||||
# Clean up citation text
|
||||
citation = citation.replace('\r', '').replace('\n', ' ').strip()
|
||||
if citation:
|
||||
# Format the citation with page reference
|
||||
if page_ref:
|
||||
markdown_content.append(f"> {citation} {page_ref}\n")
|
||||
else:
|
||||
markdown_content.append(f"> {citation}\n")
|
||||
|
||||
# Write to file
|
||||
with open(file_path, 'w', encoding='utf-8') as f:
|
||||
f.write('\n'.join(markdown_content))
|
||||
|
||||
generated_files.append(str(file_path))
|
||||
print(f"Generated: {file_path}")
|
||||
|
||||
total_citations = sum(len(citations) for citations in books_dict.values())
|
||||
print(f"\nTotal books processed: {len(generated_files)}")
|
||||
print(f"Total citations: {total_citations}")
|
||||
print(f"Files saved in: {output_path.absolute()}")
|
||||
|
||||
return generated_files
|
||||
|
||||
|
||||
def get_webdav_directory_contents(base_url, auth):
|
||||
"""
|
||||
Get list of files in the WebDAV directory using PROPFIND request.
|
||||
|
||||
Args:
|
||||
base_url (str): WebDAV base URL
|
||||
auth: HTTPBasicAuth object
|
||||
|
||||
Returns:
|
||||
list: List of file URLs found in the directory
|
||||
"""
|
||||
try:
|
||||
# PROPFIND request to list directory contents
|
||||
headers = {
|
||||
'Depth': '1',
|
||||
'Content-Type': 'application/xml'
|
||||
}
|
||||
|
||||
# Basic PROPFIND body to get file names
|
||||
propfind_body = '''<?xml version="1.0" encoding="utf-8" ?>
|
||||
<D:propfind xmlns:D="DAV:">
|
||||
<D:prop>
|
||||
<D:displayname/>
|
||||
<D:resourcetype/>
|
||||
</D:prop>
|
||||
</D:propfind>'''
|
||||
|
||||
response = requests.request(
|
||||
'PROPFIND',
|
||||
base_url,
|
||||
data=propfind_body,
|
||||
headers=headers,
|
||||
auth=auth,
|
||||
timeout=30
|
||||
)
|
||||
|
||||
if response.status_code != 207: # WebDAV Multi-Status
|
||||
print(f"Warning: Could not list directory contents - Status: {response.status_code}")
|
||||
return []
|
||||
|
||||
# Parse the XML response
|
||||
root = ET.fromstring(response.text)
|
||||
file_urls = []
|
||||
|
||||
# Define namespaces
|
||||
namespaces = {'D': 'DAV:'}
|
||||
|
||||
for response_elem in root.findall('.//D:response', namespaces):
|
||||
href_elem = response_elem.find('D:href', namespaces)
|
||||
resourcetype_elem = response_elem.find('.//D:resourcetype', namespaces)
|
||||
|
||||
if href_elem is not None and resourcetype_elem is not None:
|
||||
href = href_elem.text
|
||||
# Skip directories (they contain D:collection element)
|
||||
collection_elem = resourcetype_elem.find('D:collection', namespaces)
|
||||
|
||||
if collection_elem is None and href: # It's a file, not a directory
|
||||
# Skip the base directory itself
|
||||
if not href.endswith('/'):
|
||||
file_urls.append(href)
|
||||
|
||||
return file_urls
|
||||
|
||||
except Exception as e:
|
||||
print(f"Error listing directory contents: {e}")
|
||||
return []
|
||||
|
||||
|
||||
def delete_webdav_file(file_url, auth):
|
||||
"""
|
||||
Delete a single file from WebDAV server.
|
||||
|
||||
Args:
|
||||
file_url (str): Full URL of the file to delete
|
||||
auth: HTTPBasicAuth object
|
||||
|
||||
Returns:
|
||||
bool: True if successful, False otherwise
|
||||
"""
|
||||
try:
|
||||
response = requests.delete(file_url, auth=auth, timeout=30)
|
||||
|
||||
if response.status_code in [200, 204, 404]: # 404 means already deleted
|
||||
return True
|
||||
else:
|
||||
print(f"Failed to delete {file_url} - Status: {response.status_code}")
|
||||
return False
|
||||
|
||||
except Exception as e:
|
||||
print(f"Error deleting {file_url}: {e}")
|
||||
return False
|
||||
|
||||
|
||||
def clear_webdav_directory():
|
||||
"""
|
||||
Clear all files from the WebDAV directory.
|
||||
|
||||
Returns:
|
||||
bool: True if successful, False otherwise
|
||||
"""
|
||||
# Get WebDAV configuration
|
||||
webdav_config = get_webdav_config()
|
||||
WEBDAV_BASE_URL = webdav_config['base_url']
|
||||
WEBDAV_USERNAME = webdav_config['username']
|
||||
WEBDAV_PASSWORD = webdav_config['password']
|
||||
|
||||
auth = HTTPBasicAuth(WEBDAV_USERNAME, WEBDAV_PASSWORD)
|
||||
|
||||
print("Clearing WebDAV directory...")
|
||||
|
||||
# Get list of existing files
|
||||
file_urls = get_webdav_directory_contents(WEBDAV_BASE_URL, auth)
|
||||
|
||||
if not file_urls:
|
||||
print("No files found in WebDAV directory (or could not list contents)")
|
||||
return True
|
||||
|
||||
print(f"Found {len(file_urls)} files to delete")
|
||||
|
||||
deleted_count = 0
|
||||
failed_count = 0
|
||||
|
||||
for file_url in file_urls:
|
||||
# Convert relative URL to absolute if needed
|
||||
if file_url.startswith('/'):
|
||||
# Extract the base domain from WEBDAV_BASE_URL
|
||||
from urllib.parse import urlparse
|
||||
parsed_base = urlparse(WEBDAV_BASE_URL)
|
||||
full_url = f"{parsed_base.scheme}://{parsed_base.netloc}{file_url}"
|
||||
else:
|
||||
full_url = file_url
|
||||
|
||||
# Extract filename for display
|
||||
filename = file_url.split('/')[-1]
|
||||
|
||||
if delete_webdav_file(full_url, auth):
|
||||
print(f"✓ Deleted: {filename}")
|
||||
deleted_count += 1
|
||||
else:
|
||||
print(f"✗ Failed to delete: {filename}")
|
||||
failed_count += 1
|
||||
|
||||
print(f"\nCleanup Summary:")
|
||||
print(f"✓ Files deleted: {deleted_count}")
|
||||
print(f"✗ Failed deletions: {failed_count}")
|
||||
|
||||
return failed_count == 0
|
||||
|
||||
|
||||
def upload_files_to_webdav(file_paths):
|
||||
"""
|
||||
Upload multiple files to WebDAV server using preconfigured settings.
|
||||
|
||||
Args:
|
||||
file_paths (list): List of local file paths to upload
|
||||
|
||||
Returns:
|
||||
tuple: (successful_uploads, failed_uploads)
|
||||
"""
|
||||
# Get WebDAV configuration
|
||||
webdav_config = get_webdav_config()
|
||||
WEBDAV_BASE_URL = webdav_config['base_url']
|
||||
WEBDAV_USERNAME = webdav_config['username']
|
||||
WEBDAV_PASSWORD = webdav_config['password']
|
||||
|
||||
successful_uploads = []
|
||||
failed_uploads = []
|
||||
|
||||
for file_path in file_paths:
|
||||
try:
|
||||
# Get the filename from the local path
|
||||
filename = Path(file_path).name
|
||||
|
||||
# Construct the full WebDAV URL including the filename
|
||||
webdav_file_url = f"{WEBDAV_BASE_URL}/{filename}"
|
||||
|
||||
# Read the file content
|
||||
with open(file_path, 'rb') as f:
|
||||
file_content = f.read()
|
||||
|
||||
# Prepare the request headers
|
||||
headers = {
|
||||
'Content-Type': 'text/markdown',
|
||||
'Content-Length': str(len(file_content))
|
||||
}
|
||||
|
||||
# Set up authentication
|
||||
auth = HTTPBasicAuth(WEBDAV_USERNAME, WEBDAV_PASSWORD)
|
||||
|
||||
print(f"Uploading: {filename}")
|
||||
|
||||
# Make the PUT request to upload the file
|
||||
response = requests.put(
|
||||
webdav_file_url,
|
||||
data=file_content,
|
||||
headers=headers,
|
||||
auth=auth,
|
||||
timeout=30
|
||||
)
|
||||
|
||||
if response.status_code in [200, 201, 204]:
|
||||
print(f"✓ Successfully uploaded: {filename}")
|
||||
successful_uploads.append(file_path)
|
||||
else:
|
||||
print(f"✗ Upload failed for {filename} - Status: {response.status_code}")
|
||||
print(f" Response: {response.text}")
|
||||
failed_uploads.append(file_path)
|
||||
|
||||
except requests.exceptions.RequestException as e:
|
||||
print(f"✗ Network error uploading {filename}: {e}")
|
||||
failed_uploads.append(file_path)
|
||||
except Exception as e:
|
||||
print(f"✗ Unexpected error uploading {filename}: {e}")
|
||||
failed_uploads.append(file_path)
|
||||
|
||||
return successful_uploads, failed_uploads
|
||||
|
||||
|
||||
def main():
|
||||
"""Main function to run the converter."""
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Convert Kindle My Clippings.txt to separate Markdown files for each book"
|
||||
)
|
||||
parser.add_argument(
|
||||
'input_file',
|
||||
nargs='?',
|
||||
default='My Clippings.txt',
|
||||
help='Path to the My Clippings.txt file (default: My Clippings.txt)'
|
||||
)
|
||||
parser.add_argument(
|
||||
'-d', '--output-dir',
|
||||
default='kindle_books',
|
||||
help='Output directory for markdown files (default: kindle_books)'
|
||||
)
|
||||
parser.add_argument(
|
||||
'--upload',
|
||||
action='store_true',
|
||||
help='Upload the markdown files to WebDAV server'
|
||||
)
|
||||
parser.add_argument(
|
||||
'--no-clear',
|
||||
action='store_true',
|
||||
help='Skip clearing WebDAV directory before upload (files will be added/overwritten)'
|
||||
)
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
# Check if input file exists
|
||||
input_path = Path(args.input_file)
|
||||
if not input_path.exists():
|
||||
print(f"Error: Input file '{args.input_file}' not found.")
|
||||
return 1
|
||||
|
||||
try:
|
||||
# Parse the clippings file
|
||||
print(f"Parsing {args.input_file}...")
|
||||
books = parse_clippings_file(args.input_file)
|
||||
|
||||
# Generate markdown files
|
||||
print("Generating markdown files...")
|
||||
generated_files = generate_markdown_files(books, args.output_dir)
|
||||
|
||||
if not generated_files:
|
||||
print("No books with citations found.")
|
||||
return 0
|
||||
|
||||
# Upload to WebDAV if requested
|
||||
if args.upload:
|
||||
# Clear WebDAV directory first (unless --no-clear is specified)
|
||||
if not args.no_clear:
|
||||
if not clear_webdav_directory():
|
||||
print("Warning: Some files could not be deleted from WebDAV directory.")
|
||||
print("Continuing with upload (files will be overwritten)...")
|
||||
print() # Empty line for better readability
|
||||
|
||||
print("Uploading to WebDAV server...")
|
||||
|
||||
successful, failed = upload_files_to_webdav(generated_files)
|
||||
|
||||
print(f"\nUpload Summary:")
|
||||
print(f"✓ Successful uploads: {len(successful)}")
|
||||
print(f"✗ Failed uploads: {len(failed)}")
|
||||
|
||||
if failed:
|
||||
print("Warning: Some files failed to upload.")
|
||||
return 1
|
||||
|
||||
return 0
|
||||
|
||||
except Exception as e:
|
||||
print(f"Error processing file: {e}")
|
||||
return 1
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
exit(main())
|
||||
Reference in New Issue
Block a user