<div role="rowheader">
  <a href="/owner/repo/tree/main/folder-name">folder-name</a>
</div>

3. ????? ??

3.1. ?? ??? ??

????? ??? ????? ????? ?? ??? ?????. ?? ??? ???? ???? ??? ??? ?? ?? ????? ???????.

import requests
from bs4 import BeautifulSoup
import time

def crawl_github_folder(url, depth=0, max_depth=3):
    """
    Recursively crawls a GitHub repository folder structure.

    Parameters:
    - url (str): URL of the GitHub folder to scrape.
    - depth (int): Current recursion depth.
    - max_depth (int): Maximum depth to recurse.
    """
    if depth > max_depth:
        return

    headers = {"User-Agent": "Mozilla/5.0"}
    response = requests.get(url, headers=headers)

    if response.status_code != 200:
        print(f"Failed to access {url} (Status code: {response.status_code})")
        return

    soup = BeautifulSoup(response.text, 'html.parser')

    # Extract folder and file links
    items = soup.select('div[role="rowheader"] a')

    for item in items:
        item_name = item.text.strip()
        item_url = f"https://github.com{item['href']}"

        if '/tree/' in item_url:
            print(f"{'  ' * depth}Folder: {item_name}")
            crawl_github_folder(item_url, depth + 1, max_depth)
        elif '/blob/' in item_url:
            print(f"{'  ' * depth}File: {item_name}")

# Example usage
if __name__ == "__main__":
    repo_url = "https://github.com/<owner>/<repo>/tree/<branch>/<folder>"
    crawl_github_folder(repo_url)

4. ?? ??

1. ?? ??: ??? ???? ???? ???? ????? ???? ??? ?????.
2. ?? ???:
   • ??(/tree/)? ???? ????? ?????.
   • ?? ?? ?? ??(/blob/)? ?????.
3. ????: ??? ?? ?? ??? ?????.
4. ?? ??: ?? ??(max_length)? ???? ??? ??? ?????.

5. ??? ??

??? ?? ??? ???? ??? ???? ????? ?? ???????. ?? ????, ?? ??, ?? ?? ?? ?? ???? ??? ???? ??? ????? ??? ????? ?????.

5.1. ?? ????

? ?? ??? ? ??? ??? ???? JSON ??? ?????.

   pip install requests beautifulsoup4

5.2. ?? ??

???? ?? ? ??? ?? HTML ??? ?? ??? ?? ?? ??? ?????.

<div role="rowheader">
  <a href="/owner/repo/tree/main/folder-name">folder-name</a>
</div>

5.3. ?? ??

GitHub? ?? ??? ????? ??? ?????.

import requests
from bs4 import BeautifulSoup
import time

def crawl_github_folder(url, depth=0, max_depth=3):
    """
    Recursively crawls a GitHub repository folder structure.

    Parameters:
    - url (str): URL of the GitHub folder to scrape.
    - depth (int): Current recursion depth.
    - max_depth (int): Maximum depth to recurse.
    """
    if depth > max_depth:
        return

    headers = {"User-Agent": "Mozilla/5.0"}
    response = requests.get(url, headers=headers)

    if response.status_code != 200:
        print(f"Failed to access {url} (Status code: {response.status_code})")
        return

    soup = BeautifulSoup(response.text, 'html.parser')

    # Extract folder and file links
    items = soup.select('div[role="rowheader"] a')

    for item in items:
        item_name = item.text.strip()
        item_url = f"https://github.com{item['href']}"

        if '/tree/' in item_url:
            print(f"{'  ' * depth}Folder: {item_name}")
            crawl_github_folder(item_url, depth + 1, max_depth)
        elif '/blob/' in item_url:
            print(f"{'  ' * depth}File: {item_name}")

# Example usage
if __name__ == "__main__":
    repo_url = "https://github.com/<owner>/<repo>/tree/<branch>/<folder>"
    crawl_github_folder(repo_url)

6. ??? ??

????? ??? ? ??? ????? ???? Shpetim Haxhiu? ??? ? ??? GitHub ???? ???? ?? ?? ??? ????? ?????.

• ?? ??: GitHub? ??? ??? ?????.
• ?? ???: ??? ???? ??? ???? GitHub ??? ?????.
• ??: ?? ???? ???? ???? ?? ??? ????.

7. ?? ??

?? ??? ??? ?? ????? ??? ????.

import json

def crawl_to_json(url, depth=0, max_depth=3):
    """Crawls and saves results as JSON."""
    result = {}

    if depth > max_depth:
        return result

    headers = {"User-Agent": "Mozilla/5.0"}
    response = requests.get(url, headers=headers)

    if response.status_code != 200:
        print(f"Failed to access {url}")
        return result

    soup = BeautifulSoup(response.text, 'html.parser')
    items = soup.select('div[role="rowheader"] a')

    for item in items:
        item_name = item.text.strip()
        item_url = f"https://github.com{item['href']}"

        if '/tree/' in item_url:
            result[item_name] = crawl_to_json(item_url, depth + 1, max_depth)
        elif '/blob/' in item_url:
            result[item_name] = "file"

    return result

if __name__ == "__main__":
    repo_url = "https://github.com/<owner>/<repo>/tree/<branch>/<folder>"
    structure = crawl_to_json(repo_url)

    with open("output.json", "w") as file:
        json.dump(structure, file, indent=2)

    print("Repository structure saved to output.json")

? ?? ???? ??? ??? GitHub ?? ???? ??? ? ????. ? ??? ??? ??? ????? ??? ?? ??? ?? ??? ? ????.

?? ??? ??? ?????! ??, ??? ???? ?? ?? ???:

• ???: shpetim.h@gmail.com
• LinkedIn: linkedin.com/in/shpetimhaxhiu
• GitHub: github.com/shpetimhaxhiu

? ??? ?? ????: API ?? GitHub ????? ?? ???? ?? ?????. ??? ??? PHP ??? ????? ?? ?? ??? ?????!