ফেসবুক পোস্ট থেকে ওয়ার্ডপ্রেস ব্লগ

[
    {
      "timestamp": 1722342460,
      "data": [
        {
          "post": ""
        },
        {
          
        }
      ]
    },
    {
      "timestamp": 1722182695,
      "attachments": [
        {
          "data": [
            {
              "media": {
                "uri": "",
                "creation_timestamp": 1722182683,
                "media_metadata": {
                  "photo_metadata": {
                    "exif_data": [
                      {
                        "upload_ip": "",
                        "taken_timestamp": 1722182695
                      }
                    ]
                  }
                },
                "title": "Timeline photos",
                "description": " ",
                "backup_uri": ""
              }
            }
          ]
        }
      ],
      "data": [
        {
          "post": " "
        },
        {
        }
      ]
    }
  ]

import json

# Function to decode Latin-encoded data to UTF-8
def decode_latin_encoded_text(text):
    try:
        return text.encode('latin1').decode('utf-8')
    except UnicodeEncodeError:
        return text  # Return the original text if encoding/decoding fails

# Load JSON data from the input file
input_file_path = 'your_facebook_post.json'  # Replace with the path to your input JSON file
output_file_path = 'output.json'  # Path to save the new JSON file

with open(input_file_path, 'r', encoding='utf-8') as f:
    data = json.load(f)

# Iterate through the JSON data and decode Latin-encoded fields
for item in data:
    if 'data' in item:
        for entry in item['data']:
            if 'post' in entry:
                entry['post'] = decode_latin_encoded_text(entry['post'])
    
    if 'attachments' in item:
        for attachment in item['attachments']:
            for media_data in attachment.get('data', []):
                if 'media' in media_data:
                    if 'description' in media_data['media']:
                        media_data['media']['description'] = decode_latin_encoded_text(media_data['media']['description'])

# Save the modified data to a new JSON file
with open(output_file_path, 'w', encoding='utf-8') as f:
    json.dump(data, f, ensure_ascii=False, indent=4)

print(f"New JSON file with decoded text saved to {output_file_path}")

import json
import base64
import requests
import os
from datetime import datetime

# Replace these with your WordPress site URL and user credentials
WORDPRESS_API_URL = 'http://hello.local/wp-json/wp/v2'
USERNAME = 'admin'
PASSWORD = 'cYQE 4rqwr 0VOq 344 Mq3O P7Ug'  # Generated from WordPress

# Load JSON data from the file
with open('your_facebook_data.json', 'r', encoding='utf-8') as f:
    data = json.load(f)


# File to store processed post titles
processed_posts_file = 'processed_posts.txt'
processed_media_file = 'processed_media.txt'

# Load processed items into sets
if os.path.exists(processed_posts_file):
    with open(processed_posts_file, 'r', encoding='utf-8') as f:
        processed_posts = set(f.read().splitlines())
else:
    processed_posts = set()

if os.path.exists(processed_media_file):
    with open(processed_media_file, 'r', encoding='utf-8') as f:
        processed_media = set(f.read().splitlines())
else:
    processed_media = set()


# Function to log processed post titles
def log_processed_post(title):
    with open(processed_posts_file, 'a', encoding='utf-8') as f:
        f.write(title + '\n')
    processed_posts.add(title)


# Function to log processed media
def log_processed_media(filename):
    with open(processed_media_file, 'a', encoding='utf-8') as f:
        f.write(filename + '\n')
    processed_media.add(filename)


# Check if a post or media file has already been processed
def is_post_processed(title):
    return title in processed_posts


def is_media_processed(filename):
    return filename in processed_media


# Encode the username and password for Basic Auth
auth_str = f"{USERNAME}:{PASSWORD}"
auth_bytes = base64.b64encode(auth_str.encode('utf-8'))
auth_header = f"Basic {auth_bytes.decode('utf-8')}"

# Counter for the number of posts created
post_counter = 0


# Function to check if the file is an image (skip video files)
def is_image_file(filename):
    image_extensions = ['.jpg', '.jpeg', '.png', '.gif']
    return any(filename.lower().endswith(ext) for ext in image_extensions)

# Function to convert a Unix timestamp to the WordPress REST API date format
def convert_timestamp_to_wp_date(timestamp):
    dt_object = datetime.fromtimestamp(timestamp)
    return dt_object.strftime('%Y-%m-%dT%H:%M:%S')


# Function to upload an image from a local directory and get its URL
def upload_image_from_local_path(file_path, media_description):
    # Skip the file if it's not an image
    if not is_image_file(file_path):
        print(f"Skipping non-image file: {file_path}")
        return None

    headers = {
        'Authorization': auth_header
    }

    # Ensure the file exists
    if os.path.exists(file_path):
        with open(file_path, 'rb') as image_file:
            files = {
                'file': (os.path.basename(file_path), image_file, 'image/jpeg'),  # Adjust MIME type if necessary
                'description': (None, media_description),
            }

            # Upload the image to WordPress
            response = requests.post(f'{WORDPRESS_API_URL}/media', headers=headers, files=files)

            if response.status_code == 201:
                print(f"Uploaded {file_path} successfully.")
                return response.json().get('source_url')
            else:
                print(f"Failed to upload {file_path}: {response.status_code}, {response.text}")
                return None
    else:
        print(f"File not found: {file_path}")
        return None


# Function to create a post on WordPress
def create_post(title, content, timestamp=None, image_url=None):
    title.replace("\n", " ")

    if title in processed_posts:
        print(f"Post '{title}' already processed. Skipping.")
        return  # Skip if the post was already processed

    global post_counter
    headers = {
        'Authorization': auth_header,
        'Content-Type': 'application/json'
    }
    post_data = {
        'title': title,
        'content': content,
        'status': 'publish'  # Change to 'draft' if you want to review before publishing
    }

    if timestamp:
        post_date = convert_timestamp_to_wp_date(timestamp)
        post_data['date'] = post_date  # Publish with a specific date

    if image_url:
        post_data['content'] += f'<img src="{image_url}" alt="{title}" />'

    response = requests.post(f'{WORDPRESS_API_URL}/posts', headers=headers, json=post_data)

    if response.status_code == 201:
        post_counter += 1
        print(f"[{post_counter}] Post '{title}' created successfully.")
        log_processed_post(title)  # log the title  
    else:
        print(f"Failed to create post '{title}': {response.status_code}, {response.text}")


# Iterate through the JSON data and handle posts and media
local_media_directory = ''  # Replace with the path to your local directory

for item in data:

    if 'attachments' in item:
        for attachment in item['attachments']:
            for media_data in attachment.get('data', []):
                if 'media' in media_data:
                    media_filename = media_data['media'].get('uri', '')

                    if media_filename in processed_media:
                        print(f"Media '{media_filename}' already processed media list. Skipping.")
                        continue  # Skip if the media was already processed

                    file_path = os.path.join(local_media_directory, media_filename)
                    media_description = media_data['media'].get('description', 'Media Post').encode('latin1').decode(
                        'utf-8')

                    # skip the post if it is smaller than 20 word
                    if len(media_description.split()) < 20:
                        continue

                    post_title = media_description[:40] + "..." if len(media_description) > 40 else media_description
                    post_timestamp = item.get('timestamp')  # Get the timestamp for media posts

                    # Upload image from local path and create a post with the uploaded image URL
                    uploaded_image_url = upload_image_from_local_path(file_path, media_description)

                    if uploaded_image_url:
                        create_post(post_title, media_description, post_timestamp, uploaded_image_url)
                        # log the media name 
                        log_processed_media(media_filename)
                        break  # Break to prevent creating multiple posts from the same item
                else:
                    # Continue the outer loop if no media post was created
                    continue

                break  # Exit 'attachments' processing if a post was created        
    elif 'data' in item:
        for entry in item['data']:
            if 'post' in entry:
                post_text = entry['post'].encode('latin1').decode('utf-8')

                # skip the post if it is smaller than 20 word
                if len(post_text.split()) < 20:
                    continue
                post_title = post_text[:40] + "..." if len(post_text) > 40 else post_text
                post_timestamp = item.get('timestamp')  # Get the timestamp from the item
                create_post(post_title, post_text, post_timestamp)
                break  # Exit 'data' processing after creating a post               

print("Script execution completed.")

WORDPRESS_API_URL = 'http://hello.local/wp-json/wp/v2'
USERNAME = 'admin'
PASSWORD = 'cYQE 4rqwr 0VOq 344 Mq3O P7Ug'  # Generated from WordPress

python upload.py

with open('your_facebook_data.json', 'r', encoding='utf-8') as f:
    data = json.load(f)

if len(media_description.split()) < 20:
    continue

if len(post_text.split()) < 20:
    continue

    # Skip the file if it's not an image
    if not is_image_file(file_path):
        print(f"Skipping non-image file: {file_path}")
        return None

https://public-api.wordpress.com/oauth2/authorize?client_id=YOUR_CLIENT_ID&redirect_uri=YOUR_REDIRECT_URI&response_type=code&scope=YOUR_SCOPES

https://public-api.wordpress.com/oauth2/authorize?client_id=12345&redirect_uri=http://hello.local&response_type=code&scope=global

import requests

# Replace these values with your actual credentials
client_id = '12345'
client_secret = 'App Client Secret'
auth_code = 'Rty6D2334RTYu9'
redirect_uri = 'http://hello.local'

# Prepare the data for the token request
data = {
    'client_id': client_id,
    'client_secret': client_secret,
    'code': auth_code,
    'redirect_uri': redirect_uri,
    'grant_type': 'authorization_code'
}

# Send the POST request
response = requests.post('https://public-api.wordpress.com/oauth2/token', data=data)

# Print the response
if response.status_code == 200:
    token_info = response.json()
    access_token = token_info['access_token']
    print("Access Token:", access_token)
else:
    print("Failed to get access token:", response.status_code, response.text)

https://public-api.wordpress.com/wp/v2/sites/example.wordpress.com

import json
import base64
import requests
import os
from datetime import datetime

# Replace these with your WordPress site URL and user credentials
WORDPRESS_API_URL = 'https://public-api.wordpress.com/wp/v2/sites/example.wordpress.com'
access_token = "YOUR_ACCESS_TOKEN"

# Load JSON data from the file
with open('facebook_post_data.json', 'r', encoding='utf-8') as f:
    data = json.load(f)

# File to store processed post titles
processed_posts_file = 'processed_posts.txt'
processed_media_file = 'processed_media.txt'

# Load processed items into sets
if os.path.exists(processed_posts_file):
    with open(processed_posts_file, 'r', encoding='utf-8') as f:
        processed_posts = set(f.read().splitlines())
else:
    processed_posts = set()

if os.path.exists(processed_media_file):
    with open(processed_media_file, 'r', encoding='utf-8') as f:
        processed_media = set(f.read().splitlines())
else:
    processed_media = set()


# Function to log processed post titles
def log_processed_post(title):
    with open(processed_posts_file, 'a', encoding='utf-8') as f:
        f.write(title + '\n')
    processed_posts.add(title)


# Function to log processed media
def log_processed_media(filename):
    with open(processed_media_file, 'a', encoding='utf-8') as f:
        f.write(filename + '\n')
    processed_media.add(filename)


# Check if a post or media file has already been processed
def is_post_processed(title):
    return title in processed_posts


def is_media_processed(filename):
    return filename in processed_media


# Counter for the number of posts created
post_counter = 0


# Function to check if the file is an image (skip video files)
def is_image_file(filename):
    image_extensions = ['.jpg', '.jpeg', '.png', '.gif']
    return any(filename.lower().endswith(ext) for ext in image_extensions)


# Function to convert a Unix timestamp to the WordPress REST API date format
def convert_timestamp_to_wp_date(timestamp):
    dt_object = datetime.fromtimestamp(timestamp)
    return dt_object.strftime('%Y-%m-%dT%H:%M:%S')


# Function to upload an image from a local directory and get its URL
def upload_image_from_local_path(file_path, media_description):
    # Skip the file if it's not an image
    if not is_image_file(file_path):
        print(f"Skipping non-image file: {file_path}")
        return None

    headers = {
        'Authorization': f'Bearer {access_token}'
    }

    # Ensure the file exists
    if os.path.exists(file_path):
        with open(file_path, 'rb') as image_file:
            files = {
                'file': (os.path.basename(file_path), image_file, 'image/jpeg'),  # Adjust MIME type if necessary
                'description': (None, media_description),
            }

            # Upload the image to WordPress
            response = requests.post(f'{WORDPRESS_API_URL}/media', headers=headers, files=files)

            if response.status_code == 201:
                print(f"Uploaded {file_path} successfully.")
                return response.json().get('source_url')
            else:
                print(f"Failed to upload {file_path}: {response.status_code}, {response.text}")
                return None
    else:
        print(f"File not found: {file_path}")
        return None


# Function to create a post on WordPress
def create_post(title, content, timestamp=None, image_url=None):
    headers = {
        'Authorization': f'Bearer {access_token}',
        'Content-Type': 'application/json'
    }

    title.replace("\n", " ")

    if title in processed_posts:
        print(f"Post '{title}' already processed. Skipping.")
        return  # Skip if the post was already processed

    global post_counter

    post_data = {
        'title': title,
        'content': content,
        'status': 'publish'  # Change to 'draft' if you want to review before publishing
    }

    if timestamp:
        post_date = convert_timestamp_to_wp_date(timestamp)
        post_data['date'] = post_date  # Publish with a specific date

    if image_url:
        post_data['content'] += f'<img src="{image_url}" alt="{title}" />'

    response = requests.post(f'{WORDPRESS_API_URL}/posts', headers=headers, json=post_data)

    if response.status_code == 201:
        post_counter += 1
        print(f"[{post_counter}] Post '{title}' created successfully.")
        log_processed_post(title)  # log the title  
    else:
        print(f"Failed to create post '{title}': {response.status_code}, {response.text}")


# Iterate through the JSON data and handle posts and media
local_media_directory = ''  # Replace with the path to your local directory

for item in data:

    if 'attachments' in item:
        for attachment in item['attachments']:
            for media_data in attachment.get('data', []):
                if 'media' in media_data:
                    media_filename = media_data['media'].get('uri', '')

                    if media_filename in processed_media:
                        print(f"Media '{media_filename}' already processed media list. Skipping.")
                        continue  # Skip if the media was already processed

                    file_path = os.path.join(local_media_directory, media_filename)
                    media_description = media_data['media'].get('description', 'Media Post').encode('latin1').decode(
                        'utf-8')

                    # skip the post if it is smaller than 20 word
                    if len(media_description.split()) < 20:
                        continue

                    post_title = media_description[:40] + "..." if len(media_description) > 40 else media_description
                    post_timestamp = item.get('timestamp')  # Get the timestamp for media posts

                    # Upload image from local path and create a post with the uploaded image URL
                    uploaded_image_url = upload_image_from_local_path(file_path, media_description)

                    if uploaded_image_url:
                        create_post(post_title, media_description, post_timestamp, uploaded_image_url)
                        # log the media name 
                        log_processed_media(media_filename)
                        break  # Break to prevent creating multiple posts from the same item
                else:
                    # Continue the outer loop if no media post was created
                    continue

                break  # Exit 'attachments' processing if a post was created        
    elif 'data' in item:
        for entry in item['data']:
            if 'post' in entry:
                post_text = entry['post'].encode('latin1').decode('utf-8')

                # skip the post if it is smaller than 20 word
                if len(post_text.split()) < 20:
                    continue
                post_title = post_text[:40] + "..." if len(post_text) > 40 else post_text
                post_timestamp = item.get('timestamp')  # Get the timestamp from the item
                create_post(post_title, post_text, post_timestamp)
                break  # Exit 'data' processing after creating a post               

print("Script execution completed.")