Extract content from URI

[alonePanda]

Hi everyone,

I am trying to integrate obsidian with anki and would like to get entire content of uri
obsidian://adv-uri?vault=prep&filepath=3.1%20Economics%2FAIM%2FW1D4.md&heading=Q1, this would fetch the entire content under heading Q1

obsidian://adv-uri?vault=prep&filepath=3.1%20Economics%2FAIM%2FW1D4.md&block=s6dd1j

this would get me content under block s6dd1j.

I would like to write this in python or go and based on uri extract the content and update it in anki

Thanks in advance.
Have a nice day

[alonePanda]

Hacked together this quick script, let me know if you are able to improve upon this

import os
import re
import sys
import urllib.parse

# Update this to your specific vault path
VAULT_PATH = "PATH_TO_YOUR_VAULT"


def fetch_content_from_obsidian(uri):
    print(f"Received URI: {uri}")

    # Parse the URI
    match = re.match(
        r"obsidian://adv-uri\?vault=(.+)&filepath=(.+)&(heading|block)=(.+)",
        uri,
    )
    if not match:
        raise ValueError("Invalid URI format")

    vault, filepath, type, identifier = match.groups()
    print(f"Parsed vault: {vault}")
    print(f"Parsed filepath: {filepath}")
    print(f"Parsed type: {type}")
    print(f"Parsed identifier: {identifier}")

    # Decode the URL-encoded filepath
    filepath = urllib.parse.unquote(filepath)
    print(f"Decoded filepath: {filepath}")

    # Construct the full path to the file
    full_path = os.path.join(VAULT_PATH, filepath)
    print(f"Constructed full path: {full_path}")

    content = ""
    try:
        with open(full_path, "r") as file:
            lines = file.readlines()
            print(f"Read {len(lines)} lines from file")

            if type == "heading":
                start_collecting = False
                target_heading_level = None
                heading_pattern = re.compile(r"^(#{1,6})\s+(.*)")
                for line in lines:
                    match = heading_pattern.match(line.strip())
                    if match:
                        heading_level = len(match.group(1))
                        heading_text = match.group(2)
                        if start_collecting:
                            if heading_level <= target_heading_level:
                                print(
                                    "Reached next main heading, stopping collection"
                                )
                                break
                        if heading_text == identifier:
                            print(f"Found heading: {identifier}")
                            target_heading_level = heading_level
                            start_collecting = True
                    if start_collecting:
                        content += line

            elif type == "block":
                block_id = re.compile(r"\^[a-zA-Z0-9]+")
                list_pattern = re.compile(r"^\s*[-*]\s+")
                start_collecting = False
                for line in lines:
                    if block_id.search(line) and identifier in line:
                        print(f"Found block ID: {identifier}")
                        content = line
                        start_collecting = True
                        continue
                    if start_collecting:
                        if list_pattern.match(line) or line.strip() == "":
                            content += line
                        else:
                            break

    except FileNotFoundError:
        raise FileNotFoundError(f"File not found: {full_path}")
    except PermissionError:
        raise PermissionError(f"Permission denied: {full_path}")

    print(f"Collected content: {content}")
    return content


if __name__ == "__main__":
    if len(sys.argv) != 2:
        print("Usage: python script.py <obsidian-uri>")
        sys.exit(1)

    uri = sys.argv[1]
    content = fetch_content_from_obsidian(uri)
    print(f"Final content: {content}")