Created
August 30, 2023 16:04
-
-
Save jancbeck/f749031aa4f65b5dead744620e650a4e to your computer and use it in GitHub Desktop.
Takes a Safari exported reading list JSON and converts to Pocket's export format
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from datetime import datetime | |
from bs4 import BeautifulSoup | |
# Create a BeautifulSoup object with the basic HTML structure | |
html_structure = ''' | |
<!DOCTYPE html> | |
<html> | |
<head> | |
<title>Reading List</title> | |
</head> | |
<body> | |
<h1>Unread</h1> | |
<ul id="unread_list"> | |
</ul> | |
<h1>Read</h1> | |
<ul id="read_list"> | |
</ul> | |
</body> | |
</html> | |
''' | |
soup = BeautifulSoup(html_structure, 'html.parser') | |
# Locate the ul elements for read and unread articles | |
unread_ul = soup.find(id='unread_list') | |
read_ul = soup.find(id='read_list') | |
# Convert JSON data to HTML | |
# Here, I'll assume that all articles are unread as there is no information in the JSON data to distinguish read from unread articles. | |
for article in reading_list_data: | |
# Extract necessary information | |
title = article.get('title', 'Unknown Title') | |
url = article.get('URLString', '#') | |
date_added = article.get('DateAdded', 'Unknown Date') | |
# Convert date to timestamp (assuming date is in 'YYYY-MM-DD HH:MM:SS' format) | |
try: | |
time_added = int(datetime.strptime(date_added, '%Y-%m-%d %H:%M:%S').timestamp()) | |
except Exception as e: | |
time_added = 0 | |
# Create a new list item with an embedded link | |
new_li = soup.new_tag('li') | |
new_a = soup.new_tag('a', href=url, time_added=str(time_added), tags='') | |
new_a.string = title | |
new_li.append(new_a) | |
# Append to the unread list (since we assumed all are unread) | |
unread_ul.append(new_li) | |
# Save the BeautifulSoup object as an HTML file | |
html_output_path = '/mnt/data/reading_list.html' | |
with open(html_output_path, 'w') as file: | |
file.write(str(soup)) | |
html_output_path |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment