import os from PIL import Image import cv2 import anthropic import requests from dotenv import load_dotenv import pytesseract import tempfile import ssl import instaloader import pandas as pd from sklearn.feature_extraction.text import TfidfVectorizer import numpy as np from requests.auth import HTTPBasicAuth import mimetypes import os from PIL import Image import cv2 import anthropic from wordpress_xmlrpc import Client, WordPressPost from wordpress_xmlrpc.methods.posts import NewPost from wordpress_xmlrpc.compat import xmlrpc_client from dotenv import load_dotenv import pytesseract import tempfile import base64 from instascrape import Profile, Post import requests from io import BytesIO import time import json import requests import traceback from urllib.parse import urlparse import os import openpyxl from openai import OpenAI import ast import kw_search import os from PIL import Image import os from urllib.parse import urlparse import json import delete_files # Define a function to create schema for each post def create_schema(title, media_url_arr, blog_url): # Extract image URLs image_urls = list(media_url_arr) ## make sure it is a list # Organizatio details organization = ( { "@type": "Organization", "name": "Farmonaut", "url": "https://farmonaut.com", "sameAs": [ "https://www.facebook.com/farmonaut", "https://twitter.com/farmonaut", "https://www.linkedin.com/company/farmonaut", "https://www.instagram.com/farmonaut", # Add other social media links as necessary ], }, ) breadcrumbs = create_breadcrumbs_fromURL(urlparse(blog_url)) return { "@context": "https://schema.org", "@type": "Article", "headline": title, "image": image_urls, "author": organization, "breadcrumb": breadcrumbs, } def create_breadcrumbs_fromURL(parsed_url): # Split the path into segments path_segments = parsed_url.path.strip("/").split("/") # Split by '/' # Construct breadcrumb items breadcrumbs = {"@type": "BreadcrumbList", "itemListElement": []} # Add the home item breadcrumbs["itemListElement"].append( { "@type": "ListItem", "position": 1, "name": "Home", "item": f"{parsed_url.scheme}://{parsed_url.netloc}/", # Base URL } ) # Add items for each segment in the path for position, segment in enumerate(path_segments, start=2): # Start at position 2 breadcrumb_item = { "@type": "ListItem", "position": position, "name": segment.replace( "-", " " ).title(), # Convert hyphens to spaces and capitalize "item": f"{parsed_url.scheme}://{parsed_url.netloc}/{'/'.join(path_segments[:position-1])}", # Construct the URL up to this segment } breadcrumbs["itemListElement"].append(breadcrumb_item) return breadcrumbs def get_last_part(file_path): return os.path.basename(file_path) def convert_png_to_jpg(file_path): # Check if the file exists and is a PNG if not os.path.isfile(file_path) or not file_path.lower().endswith('.png'): raise ValueError("The provided file is not a valid PNG file.") # Open the PNG image with Image.open(file_path) as img: # Get the file name without extension file_name = os.path.splitext(file_path)[0] # Convert to RGB if the image has an alpha channel if img.mode in ('RGBA', 'LA') or (img.mode == 'P' and 'transparency' in img.info): img = img.convert('RGB') # Save as JPG jpg_path = f"{file_name}.jpg" img.save(jpg_path, 'JPEG') # Remove the original PNG file os.remove(file_path) print(f"Converted {file_path} to {jpg_path} and removed the original PNG.") # Example usage # convert_png_to_jpg('path/to/your/image.png') api_key = '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' api_key = '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' client = OpenAI( api_key = api_key ) import os import shutil import ast import openpyxl from difflib import SequenceMatcher import pandas as pd from fuzzywuzzy import fuzz import requests from requests.auth import HTTPBasicAuth import json import requests from requests.auth import HTTPBasicAuth import json import html import re from requests.auth import HTTPBasicAuth from PIL import Image from PIL import Image def add_watermark(main_image_path, watermark_path): # Open the main image main_image = Image.open(main_image_path).convert('RGBA') # Open the watermark image watermark = Image.open(watermark_path).convert('RGBA') # Calculate the new size for the watermark new_height = int(main_image.height * 0.1) aspect_ratio = watermark.width / watermark.height new_width = int(new_height * aspect_ratio) # Resize the watermark watermark = watermark.resize((new_width, new_height), Image.LANCZOS) # Calculate the position for the watermark (bottom right) #position = (main_image.width - watermark.width, main_image.height - watermark.height) position = (main_image.width - watermark.width, 0) # Create a new transparent image the same size as the main image transparent = Image.new('RGBA', main_image.size, (0,0,0,0)) # Paste the watermark onto the transparent image transparent.paste(watermark, position, watermark) # Combine the main image with the watermark output = Image.alpha_composite(main_image, transparent) # Convert back to the original mode if it wasn't RGBA original_image = Image.open(main_image_path) if original_image.mode != 'RGBA': output = output.convert(original_image.mode) # Save the result, overwriting the original image output.save(main_image_path) print(f"Watermark added to {main_image_path}") # Example usage: # add_watermark('path/to/main/image.jpg', 'path/to/watermark/image.png') # Example usage: # add_watermark('path/to/main/image.jpg', 'path/to/watermark/image.png') def normalize_title(title): # Decode HTML entities decoded = html.unescape(title) # Remove any remaining HTML tags no_html = re.sub('<[^<]+?>', '', decoded) # Convert to lowercase and remove non-alphanumeric characters return re.sub(r'[^a-z0-9]', '', no_html.lower()) def publish_or_update_wordpress_post(site_url, username, password, post_data): # WordPress REST API endpoints posts_url = f"{site_url}/wp-json/wp/v2/posts" # Set up authentication auth = HTTPBasicAuth(username, password) # Check if the API is accessible try: response = requests.get(f"{site_url}/wp-json", auth=auth) response.raise_for_status() except requests.exceptions.RequestException as e: raise Exception(f"Failed to access WordPress API: {str(e)}") # Check if a post with the same title exists # existing_post = check_existing_post_by_title(site_url, auth, post_data['title']) # if existing_post: # # Update existing post # update_url = f"{posts_url}/{existing_post['id']}" # post_data['id'] = existing_post['id'] # response = requests.post(update_url, json=post_data, auth=auth) # else: # Create new post response = requests.post(posts_url, json=post_data, auth=auth) if response.status_code in [200, 201]: return response.json() else: raise Exception(f"Failed to publish/update post: {response.text}") def check_existing_post_by_title(site_url, auth, title): # URL encode the title encoded_title = requests.utils.quote(title) # print(encoded_title) search_url = f"{site_url}/wp-json/wp/v2/posts?search={encoded_title}" # print(search_url) response = requests.get(search_url, auth=auth) title = normalize_title(title) if response.status_code == 200: # print('existing post found') posts = response.json() for post in posts: rendered_title = normalize_title(post['title']['rendered'].lower()) # print(post['title']['rendered'].lower()) # print(title.lower()) # print(rendered_title, title) if rendered_title == title: print('post found', rendered_title) return post return None #try: # result = publish_or_update_wordpress_post(site_url, username, password, post_data) # print("Post published/updated successfully:", result['link']) #except Exception as e: # print("Error:", str(e)) def replace_keywords(excel_file, sheet_name, keyword_array): # Read the Excel sheet df = pd.read_excel(excel_file, sheet_name=sheet_name) # Ensure the column with keywords is named 'Keywords' if 'Keywords' not in df.columns: raise ValueError("Excel sheet must have a 'Keywords' column") # Get the list of keywords from the Excel sheet excel_keywords = df['Keywords'].tolist() # Function to find the best match for a keyword def find_best_match(keyword): best_match = max(excel_keywords, key=lambda x: fuzz.ratio(keyword.lower(), str(x).lower())) return best_match if fuzz.ratio(keyword.lower(), str(best_match).lower()) > 70 else keyword # Replace keywords in the array with best matches replaced_keywords = [find_best_match(keyword) for keyword in keyword_array] return replaced_keywords def match_keywords(excel_path, sheet_name, text, column_letter='A'): # Open the Excel workbook and select the specified sheet workbook = openpyxl.load_workbook(excel_path) sheet = workbook[sheet_name] # Read keywords/phrases from the Excel sheet keywords = [cell.value for cell in sheet[column_letter] if cell.value] # Function to calculate similarity ratio def similarity(a, b): return SequenceMatcher(None, a.lower(), b.lower()).ratio() # Calculate similarity scores for each keyword/phrase scores = [(keyword, max(similarity(keyword, word) for word in text.split())) for keyword in keywords] # Sort by similarity score in descending order and get top 5 top_matches = sorted(scores, key=lambda x: x[1], reverse=True)[:5] # Return only the keywords/phrases, not the scores return [match[0] for match in top_matches] def remove_common_elements(array1, array2): return [x for x in array1 if x not in set(array2)] def remove_keyphrases_from_excel(file_path, keyphrases, output_path=None): # Load the workbook wb = openpyxl.load_workbook(file_path) # Iterate through all sheets for sheet in wb.worksheets: # Iterate through all cells in the sheet for row in sheet.iter_rows(): for cell in row: if cell.value: # Convert cell value to string cell_value = str(cell.value) # Check if any keyphrase is in the cell value for phrase in keyphrases: if phrase in cell_value: # Remove the keyphrase cell_value = cell_value.replace(phrase, '') # Update the cell value cell.value = cell_value if cell_value.strip() else None # Save the modified workbook if output_path: wb.save(output_path) else: wb.save(file_path) print("Keyphrases removed successfully.") def read_array_from_file(file_path): # Open the text file in read mode with open(file_path, 'r') as file: # Read the content of the file content = file.read() # Use ast.literal_eval to safely evaluate the string representation of the array array = ast.literal_eval(content) return array def remove_all_files_in_folder(folder_path): # Check if the folder exists if not os.path.exists(folder_path): #print(f"The folder {folder_path} does not exist.") return # Iterate over all files in the folder and remove them for filename in os.listdir(folder_path): file_path = os.path.join(folder_path, filename) try: # Check if it's a file (not a folder) and remove it if os.path.isfile(file_path): os.remove(file_path) elif os.path.isdir(file_path): # If it's a directory, remove the directory and its contents shutil.rmtree(file_path) except Exception as e: print(f"Error deleting {file_path}: {e}") print(f"All files and directories in {folder_path} have been removed.") def call_openai(prompt, temperature, max_tokens, tmp): #prompt = "Farmonaut wants to classify this google search query into only one of the following categories: a. Precision Agriculture, b. API/ Development, c. Traceability, d. Plantation, e. Unrelated, f. pests, diseases and weeds, g. irrigation, h. yield forecast, i. area estimation and crop identification, j. geotagging, k. fertilizers and soil health, l. Satellite/GIS/Remote Sensing, m. agri-tech startup/ company, n. agriculture content, o. not worth doing SEO. Answer only one category (without category alphabet). Google search query to classify: " + google_query #prompt = "Classify whether this google search query is related or unrelated to what Farmonaut does. Strictly answer RELATED OR UNRELATED : " + google_query completion = client.chat.completions.create( model="gpt-4o-mini-2024-07-18", messages=[ {"role": "system", "content": "You are a expert in SEO and a representative of Farmonaut."}, {"role": "user", "content": prompt} ], max_tokens=max_tokens, temperature=temperature ) return completion.choices[0].message.content def save_to_file(file_name, content): with open(file_name, 'w') as file: file.write(content) print(f"Content saved to {file_name}") def string_to_array(string): # Use ast.literal_eval to safely evaluate the string as a list try: array = ast.literal_eval(string) # print(array) except: array = string return array def get_first_column_values(file_path, sheet_name=None): # Load the workbook workbook = openpyxl.load_workbook(file_path, data_only=True) # If a sheet name is specified, load that sheet, otherwise use the active sheet sheet = workbook[sheet_name] if sheet_name else workbook.active # Get all the values from the first column (Column A) first_column_values = [] for cell in sheet['A']: # Convert cell value to string and append to list, handle empty cells first_column_values.append(str(cell.value) if cell.value is not None else "") return first_column_values # Example usage: # file_path = 'your_file.xlsx' # values = get_first_column_values(file_path, 'Sheet1') # print(values) def get_file_extension(url): # Parse the URL parsed_url = urlparse(url) # Get the path component of the URL path = parsed_url.path # Extract the file extension file_extension = os.path.splitext(path)[1] # Return the extension (without the dot) or an empty string if there's no extension return file_extension[1:] if file_extension else "" # posts = list(posts) ssl._create_default_https_context = ssl._create_unverified_context # Load environment variables load_dotenv() # Instagram session id (you need to get this from your browser after logging in to Instagram) SESSIONID = os.getenv("INSTAGRAM_SESSIONID") # Headers for Instagram requests headers = { "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.74 Safari/537.36 Edg/79.0.309.43", "cookie": f'sessionid={SESSIONID};' } # Initialize Instaloader L = instaloader.Instaloader() #L.login('himanshujain4578', 'harish@4321') L.post_metadata_txt_pattern = "" L.download_geotags = False L.save_metadata = False L.save_metadata_json = False L.download_comments = False # Anthropic API key (replace with your actual key) #anthropic_api_key = os.getenv("ANTHROPIC_API_KEY") # WordPress credentials wp_url = "https://www.farmonaut.com" wp_username = "ankuromar296" wp_password = "Tjat A2hz 9XMv pXJi YbV0 GR8o" def generate_blog_post(content, keywords_array, blog_tones_and_themes, youtube_videos, farmonaut_info, yoast_guidelines2, wp_url, wp_username, wp_password, gpt_mini, gpt_main, interval, done_posts): try: prompt = f'Output YES if the provided text is related to any of the following a. advertisement, b. meat, c. animals, d. mentions pakistan, palestine, north korea or iran. Only answer YES OR NO. Text: {content}' is_advertisement = call_openai(prompt, 0, 100, gpt_mini) print(is_advertisement) if "yes" in is_advertisement.lower(): # time.sleep(interval) return # Skip processing if content is not suitable prompt = f''' Task: Refine a keyword array. Input: {keywords_array} Instructions: 1. Review the provided keyword array. 2. Process the keywords as follows: a. Remove unnecessary terms, including: - Company names (except Farmonaut) - Person names - Beef, Slaughter, Meat, Pork etc. b. Mandatorily retain all the keywords of locations, cities, states, countries c. Mandatorily retain all the keywords related to general agriculture, farming, farm machinery, harvest, fertilizers, farm inputs, irrigation, pest, disease, weeds, gis, forestry, traceability, soil, technology, consumer, employment, finance, insurance, law, real estate topics d. For compound words lacking spaces: - Add appropriate spacing - Reassess relevance after spacing e. Retain relevant abbreviations/acronyms 3. Output format: - Return only the refined array of keywords - Do not include any explanatory text or commentary Note: Don't include any new keyword which is not a part of the original input keyword array.''' keywords_array = call_genai(prompt, 1, 1500) keywords_array = string_to_array(keywords_array) prompt = f'Summarize the content of this blog text in 500 words: {content}' blog_summary = call_openai(prompt, 1, 2000, gpt_mini) prompt = f'''Task: Generate SEO keyphrases for a website content. Input: - Keywords: {keywords_array} - Reference Text: {blog_summary} Instructions: 1. Analyze the provided content text. 2. Identify up to 10 high-ranking SEO keyphrases based on the following criteria: - Relevant to the content's main topics - Likely to have high search volume - Do not include any company names (including Farmonaut) - Do not include any individual names - Do not include anything related to Beef, Slaughter, Meat, Pork etc. - Include a mix of short-tail and long-tail keyphrases - Ensure keyphrases are grammatically correct and make sense in context 3. Output format: - Return results as an array of strings - Each keyphrase should be its own element in the array - Do not include any explanatory text or commentary - If fewer than 10 suitable keyphrases are found, include only those that meet the criteria Example output format: ["keyphrase 1", "keyphrase 2", "keyphrase 3", ...] Note: Prioritize quality and relevance over quantity.''' keyphrases = call_genai(prompt, 1, 4000) prompt = f'Identify the best tone and theme from the provided array for the content given below. Answer in less than 50 words. blog_tones_and_themes_array: {blog_tones_and_themes} , content: {content}' tone_and_theme = call_openai(prompt, 1, 200, gpt_mini) prompt = f'''Task: Generate an SEO-optimized blog title for Farmonaut. Inputs: - Keywords: {keywords_array} - Key phrases: {keyphrases} - Summary: {blog_summary} - Tone and Theme: {tone_and_theme} Instructions: 1. Analyze the provided keywords, key phrases, tone and theme. 2. Create a single, compelling blog title that: - Incorporates 1-3 of the most relevant keywords, key phrases, tone and theme - Is optimized for search engine ranking - Accurately reflects the likely content of the blog - Is concise (preferably 150 characters, not exceeding 200) - Uses power words or emotional triggers if appropriate - Clearly communicates value to the reader - Do not include anything related to Beef, Slaughter, Meat, Pork etc. - Do not include any person names, company names (except Farmonaut) - Mandatorily Localize it if location names are available in keywords. 3. Language consideration: - If the keywords/phrases are not in English, craft the title in that specific language 4. Output format: - Return only the suggested title - Do not include any explanatory text, quotation marks, or additional commentary''' title = call_genai(prompt, 1, 200) print(title) prompt = f'''Task: Generate an SEO-optimized blog summary. Inputs: - Keywords: {keywords_array} - Key phrases: {keyphrases} - Reference Text: {blog_summary} Instructions: 1. Create a 150-word summary that: - Incorporates the most relevant keywords and key phrases naturally - Provides a clear overview of the blog's main topics - Is optimized for search engine ranking - Do not include any person names, company names (except Farmonaut) - Farmonaut is not an online marketplace. Keep this in mind while writing the summary - Do not include anything related to Beef, Slaughter, Meat, Pork etc. - Engages the reader and encourages them to read the full blog - Tone and Theme: {tone_and_theme} - Highlights the value or insights the reader will gain 2. SEO Optimization: - Include 2-3 of the most important keywords in the first sentence - Distribute other keywords and phrases throughout the summary - Ensure the summary reads naturally, avoiding keyword stuffing 3. Language consideration: - If the keywords/phrases are not in English, write the summary in that specific language 4. Structure: - Open with a hook or compelling statement - Briefly outline the main points or sections of the blog - Close with a teaser or call-to-action to read the full article 5. Output format: - Provide only the 150-word summary - Do not include any additional text, explanations, or metadata ''' caption = call_genai(prompt, 1, 500) post_data = { 'caption': caption, 'media': [] } prompt = f'''Make 2 interesting short quantitative trivia statements up to 20 words each based upon these: - title: {title} - information: {caption} - tone and theme: {tone_and_theme} - exclude: don't make trivia about benefits of drones and IoTs Output Format: - [trivia1, trivia2]''' trivias = call_genai(prompt, 0, 500) prompt = f'''Identify 4 videos from this array which are in the format [(title, video_id)] which best match this content: {content}. Strictly return the response in this format [(title1, video_id1), (title2, video_id2),...]. Video Array: {youtube_videos}. ''' suggested_videos = call_openai(prompt, 0, 500, gpt_main) prompt = f'''Task: Recommend an optimal table type for Farmonaut's SEO blog. Inputs: - Title: {title} - Context: {caption} - Tone and Theme: {tone_and_theme} Instructions: 1. Analyze the provided inputs to understand the blog's focus. 2. Suggest a table type that: - Enhances reader understanding of the content - Aligns with SEO best practices 3. Table recommendation criteria: - Clarity: Easily understood by target audience - Relevance: Directly relates to blog content - Using only estimated values while adding any quantitative data 4. Language consideration: - Use the same language as the provided inputs 5. Output format: - Provide a 150-word description of the recommended table - Focus on table type, key columns/rows - Do not include any additional text or explanations Note: Prioritize a table suggestion that adds substantive value to the blog.''' table_info = call_genai(prompt, 1, 500) prompt = f''' Task: Suggest two SEO-optimizing AI image descriptions (DALL-E 3) for an SEO-optimized blog. Inputs: a. Keywords: {keywords_array} b. Title: {title} c. Context: {caption} d. KeyPhrases: {keyphrases} e. Tone and Theme: {tone_and_theme} Instructions: 1. Analyze the provided inputs to understand the blog's theme and focus. 2. Create two distinct image descriptions that: - Strongly relate to the blog's content - Incorporate relevant keywords naturally - Enhance SEO potential and reader engagement - Are highly detailed and realistic - Avoid depicting specific individuals or people from the Middle East and India - Don't depict drones and IoT Devices in the images Image description criteria: - Relevance: Directly supports blog content - Vividness: Uses rich, descriptive language for clarity - SEO value: Incorporates 2-3 key terms from the provided keywords - Uniqueness: Each image should highlight different aspects of the topic - Realism: Emphasize realistic, practical scenarios Output format: [ "Detailed description of first image, incorporating relevant keywords and focusing on a key aspect of the blog topic.", "Detailed description of second image, highlighting a different facet of the blog content or technologies, using appropriate keywords." ] Note: Focus on creating descriptions that would result in images that add significant value to the blog post while optimizing for search engines. Ensure descriptions are distinct from each other and highly relevant to the content. DO NOT OUTPUT ANY OTHER TEXT WITH THE RESPONSE. ''' image_descriptions = call_genai(prompt, 1, 1000) image_descriptions = string_to_array(image_descriptions) media_url_arr = [] for image_description in image_descriptions: try: media_url_arr.append(ai_image_url(image_description)) except Exception: print(traceback.format_exc()) media_info = process_media2(media_url_arr, title) if media_info: post_data['media'].extend(media_info) post_data['featured_media'] = media_info[0]['id'] if media_info else None stripe_html = ''' ''' prompt = f''' Create a comprehensive blog post of at least 3500 words on the following topic: - title: {title} - context: {caption} - summary: {blog_summary} Key requirements: - Tone and Theme: {tone_and_theme} - Use HTML formatting including ,

,

, , ,
    ,
      ,
      , and

      tags where appropriate - Write in a first-person plural format (we, us, our, ours) - Include and naturally incorporate as many of these keywords: {keywords_array} - Include these key phrases: {keyphrases} - Write in the language of keywords/phrases if they are not in English - Mandatorily localize the content if location names are available in keywords - Base Farmonaut-specific information solely on this context: {farmonaut_info} - Do not include case studies, success stories, or any hallucinated information about Farmonaut - Add all the images from this JSON object: {post_data['media']} with border-radius:16px, box-shadow: 10px 10px 15px, cursor: pointer. These images should open https://farmonaut.com/app_redirect when clicked. All images should be placed within 75% content of the blog. - Embed the playable YouTube videos available in the format [('video_title', 'video_id')]: {suggested_videos}. Create the full YouTube video URL: https://youtube.com/watch?v=video_id from the video_id. Uniformly add these videos within top 75% content of the blog. width: 100%, height: 500px, border-radius: 16px, box-shadow: 10px 10px 15px. - Add a beautifully formatted table based on this context: {table_info} - Add these trivias at the top and middle of the blog post: {trivias}. Make the trivia text bold, italic, within double-quotes, font-size: 50px, line-height: 50px, color: #034d5c - Add links: - App Button Image: https://farmonaut.com/Images/web_app_button.png, Link on this button: https://farmonaut.com/app_redirect, height: 80px - API: https://sat.farmonaut.com/api - API Developer Docs: https://farmonaut.com/farmonaut-satellite-weather-api-developer-docs/ - Android App Button Image: https://farmonaut.com/wp-content/uploads/2020/01/get_it_on_google_play.png, Link on this Button: https://play.google.com/store/apps/details?id=com.farmonaut.android, height: 80px - iOS App Button Image: https://farmonaut.com/wp-content/uploads/2020/01/available_on_app_store.png, Link on this Button: https://apps.apple.com/in/app/farmonaut/id1489095847, height: 80px - Earn With Farmonaut: Link https://farmonaut.com/affiliate-program, YouTube Video URL: https://www.youtube.com/watch?v=QydYrdtPBP0, Summary about this program: Earn 20% recurring commission with Farmonaut's affiliate program by sharing your promo code and helping farmers save 10%. Onboard 10 Elite farmers monthly to earn a minimum of $148,000 annually—start now and grow your income! Formatting: Make the text bold and larger than blog text size. - Distribute these links within top 75% content of the blog with bold font - Add this custom HTML for Farmonaut subscriptions: {stripe_html} - Add an FAQ section - Use bullet points and subheadings (font color: #034d5c) to improve readability - Make the content mobile responsive Additional guidelines: - Do not mention any partnership or collaboration of any sort with anyone in the blog - Achieve Flesch Reading Ease Score of at least 60 - Provide detailed explanations and examples - Ensure all content is factual and based on provided information - Organize information logically with clear transitions between sections - Use varied sentence structures and vocabulary for engaging reading - Farmonaut is not an: a. Online marketplace b. Manufacturer/seller of farm inputs or farm machinery c. Regulatory body Keep this in mind while writing the summary - Mandatorily implement all the latest SEO guidelines provided by Yoast SEO: {yoast_guidelines2} Please generate the blog post based on these requirements, ensuring it's well-structured and at least 3500 words long.''' blog_content = call_genai(prompt, 1, 8000) category_ids = { "south-america": 580, "asia": 579, "africa": 578, "united-kingdom": 577, "canada": 576, "europe": 575, "australia": 574, "blogs": 5, "news": 573, "case_study": 546, "area_estimation": 542, "remote_sensing": 9, "precision_farming": 548, "api_development": 572, "usa": 561 } prompt = f'Based upon this title: {title}, and caption: {caption} , identify the best category id in which this title fits in: {category_ids}. Strictly only return the integer value as the response' category_id = call_genai(prompt, 0, 5) try: category_id = int(category_id) except ValueError: category_id = 5 # Default category post_data['title'] = title post_data['content'] = blog_content post_data['status'] = 'publish' post_data['excerpt'] = caption post_data['comment_status'] = 'open' post_data['categories'] = [category_id] prompt = f"Can you convert this text into a URL slug. Don't output any other text. Text to convert to URL slug: {title}" slug = call_genai(prompt, 0, 500).strip() try: schema_media = [post_data['media'][0]['url'], post_data['media'][1]['url']] except Exception: print(traceback.format_exc()) schema_media = media_url_arr structured_schema_script = (f'') post_data["content"] = structured_schema_script + blog_content publish_or_update_wordpress_post(wp_url, wp_username, wp_password, post_data) save_to_file('posts_done.txt', str(done_posts)) print('done') time.sleep(interval) except Exception: print(traceback.format_exc()) time.sleep(70) remove_all_files_in_folder('insta_files') def remove_keywords(selected_keywords, excel_file, sheet_name, keyword_column, num_keywords=5): # Read the Excel sheet df = pd.read_excel(excel_file, sheet_name=sheet_name) # Ensure the keyword column exists if keyword_column not in df.columns: raise ValueError(f"Column '{keyword_column}' not found in the Excel sheet.") # Remove the selected keywords from the DataFrame df = df[~df[keyword_column].isin(selected_keywords)] # Save the updated DataFrame back to the Excel file df.to_excel(excel_file, sheet_name=sheet_name, index=False) def select_and_remove_keywords(text, excel_file, sheet_name, keyword_column, num_keywords=5): # Read the Excel sheet df = pd.read_excel(excel_file, sheet_name=sheet_name) # Ensure the keyword column exists if keyword_column not in df.columns: raise ValueError(f"Column '{keyword_column}' not found in the Excel sheet.") # Get the list of keywords keywords = df[keyword_column].tolist() # Create a TF-IDF vectorizer vectorizer = TfidfVectorizer() # Ensure text and keywords are strings text = str(text) if isinstance(text, dict) else text keywords = [str(keyword) if isinstance(keyword, dict) else keyword for keyword in keywords] # Fit the vectorizer on the text and transform the keywords tfidf_matrix = vectorizer.fit_transform([text] + keywords) # Calculate cosine similarity between the text and each keyword cosine_similarities = (tfidf_matrix * tfidf_matrix.T).toarray()[0][1:] # Get the indices of the top num_keywords similar keywords top_indices = np.argsort(cosine_similarities)[-num_keywords:][::-1] # Select the top keywords selected_keywords = [keywords[i] for i in top_indices] # Remove the selected keywords from the DataFrame df = df[~df[keyword_column].isin(selected_keywords)] # Save the updated DataFrame back to the Excel file df.to_excel(excel_file, sheet_name=sheet_name, index=False) return selected_keywords # Existing functions remain the same # (select_and_remove_keywords, get_instagram_posts, extract_text_from_image, extract_text_from_video, generate_blog_content) def call_genai(prompt, temperature, max_tokens): client = anthropic.Anthropic( # defaults to os.environ.get("ANTHROPIC_API_KEY") api_key="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", ) message = client.messages.create( model="claude-3-5-sonnet-20240620", max_tokens=max_tokens, temperature=temperature, system = "You are an SEO expert, a gis/ remote sensing expert, an agriculture and horticulture scientist, and a representative of Farmonaut (farmonaut.com).", messages=[ {"role": "user", "content": prompt} ] ) #print(message) return message.content[0].text def upload_media_to_wordpress(file_path, title): endpoint = f"{wp_url}/wp-json/wp/v2/media" auth = HTTPBasicAuth(wp_username, wp_password) mime_type, _ = mimetypes.guess_type(file_path) media_data = { 'alt_text':title, 'caption':title, 'description':title } upload_name = f"{title}_{os.path.basename(file_path)}" with open(file_path, 'rb') as file: files = {'file': (upload_name, file, mime_type)} #files = {'file': (os.path.basename(file_path), file, mime_type)} response = requests.post(endpoint, files=files, auth=auth, json = media_data) if response.status_code == 201: return response.json()['id'], response.json()['source_url'] else: print(f"Failed to upload media. Status code: {response.status_code}") print(f"Response: {response.text}") return None, None def extract_text_from_video(video_path): video = cv2.VideoCapture(video_path) fps = int(video.get(cv2.CAP_PROP_FPS)) frame_count = int(video.get(cv2.CAP_PROP_FRAME_COUNT)) duration = frame_count / fps text = "" for i in range(0, int(duration), 1): video.set(cv2.CAP_PROP_POS_MSEC, i * 1000) success, frame = video.read() if not success: break gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) frame_text = pytesseract.image_to_string(gray) text += frame_text + "\n" video.release() return text def process_media2(media_url_arr, title): #print(media_url_arr) media_info = [] media_num = 0 folder_name = 'insta_files' for url in media_url_arr: #print(url) media_num = media_num + 1 file_path = folder_name + '/' + str(media_num) + '.' + str(get_file_extension(url)) try: response = requests.get(url, stream=True) except: print(traceback.format_exc()) response = None if response is None: continue os.makedirs(os.path.dirname(file_path), exist_ok=True) if response.status_code == 200: with open(file_path, 'wb') as file: for chunk in response.iter_content(chunk_size=8192): if chunk: file.write(chunk) print(f"File downloaded successfully: {file_path}") add_watermark(file_path, 'watermark.jpg') convert_png_to_jpg(file_path) else: print(f"Failed to download file. Status code: {response.status_code}") # with tempfile.TemporaryDirectory() as tmpdir: # for media_url in media_url_arr: # L.download_post(post, target=tmpdir) media_files = os.listdir(folder_name) for file in media_files: file_path = os.path.join(folder_name, file) media_id, media_url = upload_media_to_wordpress(file_path, title) if media_id and media_url: media_info.append({ 'type': 'image', 'text': title, 'id': media_id, 'url': media_url }) else: continue # Skip files that are neither videos nor images return media_info def extract_text_from_image(image_path): image = Image.open(image_path) text = pytesseract.image_to_string(image) return text import pandas as pd import ast def get_keyword_arrays(file_path): # Read the Excel file into a DataFrame df = pd.read_excel(file_path, usecols=['Keywords']) # Iterate through each row and convert the string representation of the list into an actual list for keywords in df['Keywords']: try: # Safely evaluate the string to convert it into a list keyword_array = ast.literal_eval(keywords) yield keyword_array except (ValueError, SyntaxError): # Handle cases where the string is not a valid list format print(f"Invalid format for keywords: {keywords}") yield [] def ai_image_url(prompt): #print(prompt) response = client.images.generate( model="dall-e-3", prompt=prompt, size="1024x1024", quality="standard", n=1, ) image_url = response.data[0].url return image_url def main(): total_count, good_count, bad_count = 0,0,0 # posts_done = ['C_kYH2NJURr', 'C_aMTxcN0Vs', 'C_TJJ_MN2jD', 'C_P35JyyIVW', 'C-_8t2MvV--', 'C-mgOBuR_pU'] posts_done = [] posts_failed = [] #posts = get_instagram_posts(instagram_username) #posts = posts['data']['xdt_api__v1__feed__user_timeline_graphql_connection']['edges'] farmonaut_info = ''' Farmonaut is a pioneering agricultural technology company that offers advanced, satellite-based farm management solutions via android, iOS, web/browser App, and API. Its mission is to make precision agriculture affordable and accessible to farmers worldwide by integrating innovative technology and data-driven insights into traditional farming practices. Farmonaut's platform provides valuable services such as real-time crop health monitoring, AI-based advisory systems, blockchain-based traceability, and resource management tools. Here's a comprehensive overview of its technologies, business model, target audience, and value proposition. 1. Technologies Farmonaut leverages a blend of satellite imagery, artificial intelligence (AI), blockchain, and machine learning to address various agricultural challenges. Satellite-Based Crop Health Monitoring: Farmonaut uses multispectral satellite images to monitor crop health, providing farmers with insights into vegetation health (NDVI), soil moisture levels, and other critical metrics. This data helps farmers make informed decisions about irrigation, fertilizer usage, and pest management, ultimately optimizing crop yields and reducing resource wastage​( Farmonaut )​( Farmonaut ). Jeevn AI Advisory System: This AI-driven personalized farm advisory tool delivers real-time insights, weather forecasts, and expert crop management strategies to farmers. Jeevn AI analyzes satellite data and other inputs to generate customized advice, improving farm productivity and efficiency​( Farmonaut ). Blockchain-Based Product Traceability: By integrating blockchain technology, Farmonaut enables traceability solutions for various industries, particularly agriculture. Blockchain ensures that every stage of the product's journey, from farm to consumer, is transparent and secure, thereby enhancing trust and reducing fraud in supply chains​( Farmonaut ). Fleet and Resource Management: Farmonaut provides tools for fleet management, enabling agribusinesses to manage their logistics more efficiently. This helps reduce operational costs by optimizing vehicle usage, ensuring safety, and improving the overall management of agricultural machinery​( Farmonaut ). Carbon Footprinting: To help agribusinesses monitor and reduce their environmental impact, Farmonaut offers carbon footprint tracking. This feature provides real-time data on emissions, allowing businesses to take steps towards sustainability and compliance with environmental regulations​( Farmonaut )​( Farmonaut ). 2. Business Model Farmonaut operates on a subscription-based model, offering various packages that cater to individual farmers, cooperatives, agribusinesses, and government institutions. The company provides flexible pricing tiers depending on the number of hectares monitored and the frequency of satellite data updates. Their platform is accessible through web and mobile apps, making it easy for users to track and manage their farms from anywhere​( Farmonaut ). The business also extends its services through APIs, enabling developers and businesses to integrate Farmonaut’s satellite and weather data into their own systems. This API access broadens the company’s revenue streams and encourages collaboration with other agritech companies and agricultural research organizations​( Farmonaut ). Additionally, Farmonaut partners with financial institutions to provide satellite-based verification for crop loans and insurance, reducing the likelihood of fraud and improving access to financing for farmers​( Farmonaut )​( Farmonaut ). 3. Target Audience Farmonaut’s solutions are tailored for a wide range of users in the agricultural ecosystem: Individual Farmers: The platform offers individual farmers access to precise, real-time data on their crops. This allows them to make better decisions regarding crop health, pest management, and resource allocation. Small and medium-sized farms can particularly benefit from these affordable precision farming solutions​( Farmonaut ). Agribusinesses: Large-scale agribusinesses use Farmonaut for plantation management, fleet tracking, and resource optimization. These businesses can manage vast farming operations more efficiently by leveraging satellite monitoring and AI-driven insights​( Farmonaut ). Governments and NGOs: Farmonaut works with government agencies and non-governmental organizations (NGOs) to improve agricultural productivity, implement large-scale farm monitoring programs, and support sustainable farming initiatives. Governments also use Farmonaut's tools for crop area and yield estimation, especially in policy and subsidy distribution​( Farmonaut ). Financial Institutions: By providing satellite-based verification of farms, Farmonaut helps banks and insurance companies streamline crop loan approvals and reduce fraudulent claims in agricultural insurance​( Farmonaut )​( Farmonaut ). Corporate Clients: Companies, especially in sectors like textile and food, use Farmonaut's blockchain-based traceability solutions to ensure the authenticity and transparency of their supply chains. This strengthens consumer trust and enhances the brand's reputation​( Farmonaut ). 4. Value Proposition and Benefits Farmonaut’s key value propositions include: Cost-Effective Precision Agriculture: Farmonaut democratizes access to precision agriculture by offering affordable services for real-time crop monitoring and farm management. Unlike traditional precision farming tools that require expensive hardware, Farmonaut relies on satellite imagery, making it a more economical solution for farmers of all scales​( Farmonaut ). Increased Farm Productivity: By providing real-time data on crop health, soil moisture, and weather patterns, Farmonaut allows farmers to make informed decisions that optimize their resources. This leads to better crop yields, reduced input costs, and minimized crop losses​( Farmonaut ). Sustainability: Through features like carbon footprint tracking and efficient resource management, Farmonaut promotes sustainable farming practices. This is crucial in today’s agriculture, where there is growing pressure to reduce environmental impact while increasing food production​( Farmonaut ). Transparency and Trust: Farmonaut’s blockchain-based traceability solution ensures transparency in supply chains, particularly for corporate clients in agriculture and related sectors. By offering verifiable data on product origin and journey, the system helps build consumer trust​( Farmonaut ). Access to Financing: Farmonaut's partnerships with financial institutions provide farmers with satellite-based verification for loans and insurance. This improves access to financing while reducing the risks for lenders​( Farmonaut )​( Farmonaut ). Scalability: The platform is highly scalable, serving clients from smallholder farmers to large agribusinesses and government bodies. Its modular design allows users to choose the services they need and scale them up as their operations grow​( Farmonaut ). Conclusion Farmonaut stands out in the agritech space by offering a comprehensive suite of tools that combine satellite technology, AI, and blockchain to meet the diverse needs of modern agriculture. Whether it's precision farming, supply chain transparency, or sustainability, Farmonaut is at the forefront of the agricultural revolution, making it easier for farmers and agribusinesses to thrive in an increasingly data-driven world. By lowering the cost barrier and providing advanced solutions, Farmonaut continues to empower farmers, improve productivity, and promote sustainable agricultural practices globally. ''' yoast_guidelines = { "yoastSEOGuidelines": { "contentOptimization": [ { "guideline": "Use focus keyword in the first paragraph", "description": "Include your main keyword in the opening of your content." }, { "guideline": "Use focus keyword in the title", "description": "Include your main keyword in the page title, preferably at the beginning." }, { "guideline": "Use focus keyword in the URL", "description": "Include your main keyword in the page URL." }, { "guideline": "Use focus keyword in headings", "description": "Include your main keyword in at least one subheading (H2, H3, etc.)." }, { "guideline": "Keyword density", "description": "Maintain a keyword density between 0.5% and 2.5%." }, { "guideline": "Content length", "description": "Write at least 300 words for regular posts and pages." }, { "guideline": "Use internal links", "description": "Include internal links to other relevant pages on your website." }, { "guideline": "Use external links", "description": "Include outbound links to authoritative sources when appropriate." }, { "guideline": "Use images", "description": "Include at least one image with alt text containing the focus keyword." } ], "readability": [ { "guideline": "Use short paragraphs", "description": "Keep paragraphs to 150 words or less." }, { "guideline": "Use subheadings", "description": "Break up text with descriptive subheadings (H2, H3, etc.)." }, { "guideline": "Use transition words", "description": "Use transition words to improve content flow." }, { "guideline": "Vary sentence length", "description": "Mix short and long sentences for better readability." }, { "guideline": "Use Flesch Reading Ease score", "description": "Aim for a score of 60-70 for general audience content." } ] } } yoast_guidelines2 = { "content": { "focusKeyword": { "firstParagraph": "Include in opening", "title": "Include, preferably at start", "url": "Include in page URL", "headings": "Use in at least one subheading", "density": "0.5% - 2.5%" }, "length": "300+ words for posts/pages", "links": { "internal": "Include relevant internal links", "external": "Link to authoritative sources" }, "images": "Use with keyword in alt text" }, "readability": { "paragraphs": "Max 150 words", "subheadings": "Use to break up text", "transitionWords": "Improve content flow", "sentenceLength": "Mix short and long", "activeVoice": "Use in 90%+ of sentences", "fleschScore": "Aim for 60-70" } } blog_tones_and_themes = { "tones": [ {"name": "Informative", "description": "Neutral, objective, and educational."}, {"name": "Conversational", "description": "Friendly, engaging, and informal."}, {"name": "Persuasive", "description": "Assertive, convincing, and motivational."}, {"name": "Inspirational", "description": "Uplifting, motivational, and positive."}, {"name": "Humorous", "description": "Light-hearted, witty, and entertaining."}, {"name": "Serious/Professional", "description": "Formal, authoritative, and professional."} ], "themes": [ {"name": "Technology & Innovation", "description": "Focus on latest tech advancements and impacts."}, {"name": "Sustainability & Environment", "description": "Environmentally friendly and sustainable living."}, {"name": "Personal Growth & Development", "description": "Focus on self-improvement and productivity."}, {"name": "Industry Trends & News", "description": "Covering latest industry trends and news."}, {"name": "Case Studies & Success Stories", "description": "Showcasing examples of success."}, {"name": "Guides and How-tos", "description": "Step-by-step guides to accomplish tasks."}, {"name": "Problem-Solving", "description": "Addressing problems and providing solutions."}, {"name": "Lifestyle & Culture", "description": "Focusing on cultural and lifestyle aspects."}, {"name": "Health & Wellness", "description": "Topics related to physical or societal health."}, {"name": "Business & Entrepreneurship", "description": "Insights, tips, and strategies for businesses."}, {"name": "Finance & Investment", "description": "Advice on financial planning, budgeting, or investments."}, {"name": "Social Issues & Advocacy", "description": "Discussing social causes or movements."}, {"name": "Food & Cooking", "description": "Recipes, cooking tips, or food culture exploration."}, {"name": "Education & Learning", "description": "Tips for learning new skills, or education-related content."} ] } categories_obj = { "580":"south-america", "579": "asia", "578":"africa", "577":"united-kingdom", "576":"canada", "575":"europe", "574":"australia", "5":"blogs", "573":"news", "546":"case-study", "542":"area-estimation", "9":"remote-sensing", "548":"precision-farming", "572":"api-development", "561": "usa" } youtube_videos = f''' [('Farmonaut App Tutorial: How to Add & Map Fields Easily', 'https://youtube.com/watch?v=I3PZXJZE9as'), ("How Farmonaut's Satellite Technology is Revolutionizing Land Use in Agriculture", 'https://youtube.com/watch?v=B9K9IW0gy2Q'), ("Discover Farmonaut's Advanced Agri Solutions: Precision Crop Area Estimation - Egypt Case Study", 'https://youtube.com/watch?v=Fn5gY7QtFjo'), ('Unlocking Soil Organic Carbon: The Secret to Sustainable Farming with Farmonaut', 'https://youtube.com/watch?v=GEWF0ite050'), ("Explore Farmonaut's Advanced Crop Monitoring & Yield Prediction", 'https://youtube.com/watch?v=5wMEg-u5XdU'), ('Farmonaut Agro Admin App: Revolutionizing Large-Scale Farm Management', 'https://youtube.com/watch?v=iPg6X_s9Seo'), ('Satellite & AI Based Automated Tree Detection For Precise Counting and Location Mapping', 'https://youtube.com/watch?v=kB_V4JAlA1M'), ('Farmonaut Automated Detection of Alternate Wet and Dry Farming Phases', 'https://youtube.com/watch?v=GnXN51pte0E'), ('Welcome to the Future of Farming with JEEVN AI | AI Based Personalized Farm Advisory', 'https://youtube.com/watch?v=QkqWbooLh6s'), ('Transform Your Farming Experience with Farmonaut!', 'https://youtube.com/watch?v=i0w1z6FNxZQ'), ('WhatsApp Tutorial: Step-by-Step Guide to Connect Your Farm to Our Satellite Monitoring System', 'https://youtube.com/watch?v=XFLtA8zR96s'), ('Visualizing Farms with Satellite Data using iFrame for Farmonaut API Users', 'https://youtube.com/watch?v=J4HeFUJgwvk'), ('Integrate Weather Data Using Farmonaut API | Comprehensive Tutorial', 'https://youtube.com/watch?v=WgCHVXNDHNY'), ('How to Add and Remove Languages for Satellite Reports | Farmonaut API Tutorial', 'https://youtube.com/watch?v=-MRAf8_YX8E'), ('How to Check API Usage, Expired Farms, and Calculate Farm Area | Farmonaut API Tutorial', 'https://youtube.com/watch?v=sNZd4oxY7Zc'), ('How to Add a Field Using iFrame for Satellite Monitoring | Step-by-Step Tutorial', 'https://youtube.com/watch?v=S073EeIF3Xc'), ('How to Interpret Satellite Data for Agriculture | Tutorial | Farmonaut Mobile Apps', 'https://youtube.com/watch?v=OnsYwixc8_E'), ('How To Create An API Account | Farmonaut API Video Tutorial', 'https://youtube.com/watch?v=RpBlJ86Xgv4'), ("Farmonaut's Web App Tutorial: Comprehensive Guide for Interpreting Satellite Data", 'https://youtube.com/watch?v=e4BLMuWUAdU'), ('How to Retrieve Farm Data | Farmonaut API Tutorial', 'https://youtube.com/watch?v=OnuwHnpey0k'), ('Pause Resume or Extend Farm Satellite Monitoring - Farmonaut API Tutorial', 'https://youtube.com/watch?v=zBHE7mn0zT0'), ('Manage Your Farms with Ease Using Our APIs!', 'https://youtube.com/watch?v=kDWPl2hQpKI'), ('How to Check Consolidated Farm Report | Farmonaut Mobile Apps', 'https://youtube.com/watch?v=srbBgKp-MjQ'), ('How to Add Farm For Satellite Monitoring | Farmonaut Mobile Apps', 'https://youtube.com/watch?v=IVApjPza55M'), ('How To Check Detailed Satellite Report Of Your Farm - Farmonaut Mobile Apps', 'https://youtube.com/watch?v=wbHASbTJXvM'), ('How to Pause, Resume or Delete Field From Your Account | Farmonaut Mobile Apps', 'https://youtube.com/watch?v=9hBzyyWKWJA'), ('How To Check The Satellite Data - Farmonaut Mobile Apps', 'https://youtube.com/watch?v=pPcmGOmYyTc'), ("Tutorial for Farmonaut's Web App For Satellite Monitoring", 'https://youtube.com/watch?v=3erGO8xjDQY'), ('Celebrating 5 Years of Innovation in Agriculture with Farmonaut! | Farmonaut Turns 5', 'https://youtube.com/watch?v=oHFNO8LckLY'), ('Farmonaut: Cultivating Innovation in Agriculture | Year in Review 2023', 'https://youtube.com/watch?v=vRX9G9JALwc'), ("Farmonaut's Tech Advancements in Q3", 'https://youtube.com/watch?v=eNd8xCq30wc'), ("Farmonaut's Remarkable Half-Year Achievements 2023!", 'https://youtube.com/watch?v=12A8B_7uC-A'), ("Farmonaut®'s Traceability solution for Honey is going live with Dabur", 'https://youtube.com/watch?v=nU3Probs-Lk'), ('Farmonaut | Connect Your Farms With Satellites in Just 2 Minutes Using WhatsApp', 'https://youtube.com/watch?v=1MPp5ung6cI'), ("Farmonaut's Remarkable Q3 2023 Milestones in Agricultural Sector", 'https://youtube.com/watch?v=wrbn85x8bLE'), ('Satellite based WhatsApp advisory for Farmers by Farmonaut', 'https://youtube.com/watch?v=WhUG8rnrmFo'), ('Farmonaut Tutorial: Farm Mapping As a User of Smartphone Apps (Android and iOS)', 'https://youtube.com/watch?v=gRoPvQslDYc'), ('Farmonaut - STEI Foundation Africa Collaboration', 'https://youtube.com/watch?v=a-3k7TY0vzw'), ("Farmonaut's August Milestones", 'https://youtube.com/watch?v=8Hw6BlE6NFQ'), ('RADER & FARMONAUT partner for Africa Green Impact (AGI) in Central Africa & Nigeria.', 'https://youtube.com/watch?v=OD78p4IZmMQ'), ('Farmonaut®: Milestones Achieved in July 2023', 'https://youtube.com/watch?v=OuBK52GDS5g'), ('Farmonaut Satellite Monitoring Whitelabel Solutions', 'https://youtube.com/watch?v=zvlJp__of-g'), ("Farmonaut Spotlight - Q'2 - Part 2", 'https://youtube.com/watch?v=TpwEolFOgGw'), ('Farmonaut Farm Mapping Tutorial - Mobile App', 'https://youtube.com/watch?v=Uw0HzdJF6Q8'), ('Farmonaut Covered By Radix AI: Leveraging Remote Sensing and Machine Learning for a Greener Future', 'https://youtube.com/watch?v=tiB5zJ4IRu0'), ("Coromandel's My Gromor App offers satellite-based farm advice via Farmonaut to farmers", 'https://youtube.com/watch?v=LCtgELI95tA'), ("My Gromor App Brings Satellite-Powered Farm Advisory Services to India's Farmers via Farmonaut", 'https://youtube.com/watch?v=WYm1FQXUTN8'), ('Farmonaut® | 90-95% Accuracy in Organic Carbon Data From Farmonaut', 'https://youtube.com/watch?v=GuWKnuqnX0k'), ('JEEVN AI Tutorial | How to Use JEEVN AI For Generating Farm Advisory', 'https://youtube.com/watch?v=RNRN8ODo46k'), ('Introducing JEEVN AI | An AI Tool For Personalized Farm Advise', 'https://youtube.com/watch?v=25PjLwECtDo'), ('Farmonaut | How to Compare images', 'https://youtube.com/watch?v=n6KEWZClihg'), ('Farmonaut Web app | Satellite Based Crop monitoring', 'https://youtube.com/watch?v=tD7cC-dI-Yc'), ('Farmonaut Tutorial | How to Download Weather Data', 'https://youtube.com/watch?v=Azm0ajcUWng'), ('Farmonaut | How to Generate Time Lapse', 'https://youtube.com/watch?v=YSwP9iq5OXs'), ('Farmonaut Introduction - Large Scale Usage For Businesses and Governments', 'https://youtube.com/watch?v=aYUVo5u9YvE'), ('Farmonaut Introduction - English', 'https://youtube.com/watch?v=-RSqvtJ1SIE'), ('Farmonaut For Crop Area Estimation', 'https://youtube.com/watch?v=3PUPMR5Kfi4'), ('Farmonaut WhatsApp Based Satellite Advisory | 90% + Engagement Rate', 'https://youtube.com/watch?v=urSEO6KVkXM'), ('Farmonaut For Admins Tutorial Video', 'https://youtube.com/watch?v=YliR45N9B9Q'), ('Farmonaut API Video Tutorial - How To Make API Account', 'https://youtube.com/watch?v=tM8UlkbX4cI'), ('Introducing WhatsApp Based Satellite Advisory', 'https://youtube.com/watch?v=Z1ZdiKtnzgo'), ('Farmonaut | Cost Effective Blockchain Based Traceability Solutions for Textile and Fashion Industry', 'https://youtube.com/watch?v=fKOKe2fKI7A'), ('Mapping of Cotton in Maharashtra, Coriander in Rajasthan, Sugarcane in Karnataka, Banana in WB', 'https://youtube.com/watch?v=4sRXUNEgiIQ'), ('Coriander Farm Mapping Going on in Rajasthan', 'https://youtube.com/watch?v=6wy45OcgC6g'), ('Farmonaut Wishes Everyone A Very Happy Diwali!', 'https://youtube.com/watch?v=B4xF1hFvf3o'), ('Farmonaut For Crop Area Estimation', 'https://youtube.com/watch?v=RuN6nZKJV3U'), ('Farmonaut For Admins Tutorial Video', 'https://youtube.com/watch?v=jAQIOleOOBg'), ('Farmonaut Web App | Search For Farms Visited Yesterday By Satellites | Track Polygon Mapping Process', 'https://youtube.com/watch?v=FOWVebnTbOo'), ('Farmonaut For Oil Palm Plantation', 'https://youtube.com/watch?v=gSwG2pXbBLk'), ('Farmonaut® | Making Farming Better With Satellite Data', 'https://youtube.com/watch?v=DuYxCOxgl7w'), ('Farmonaut Has Received Ramaiah-Evolute Star Startup Award', 'https://youtube.com/watch?v=PAgKVOlTtd4'), ('Farmonaut Large Scale Field Mapping & Satellite Based Farm Monitoring | How To Get Started', 'https://youtube.com/watch?v=k1qdCCf-3Kw'), ('The Role of Artificial Intelligence in Agriculture - Farmonaut | Agritecture | Joyce Hunter', 'https://youtube.com/watch?v=YPZJ62YQsZY')] ''' try: done_posts = read_array_from_file('posts_done.txt') except: print(traceback.format_exc()) done_posts = [] #for temp_post in done_posts: # is_this_a_festival_post = "no" # if temp_post not in posts_done: # posts_done.append(temp_post) post_num = 0 main_folder = 'blogs' gpt_mini = "gpt-4o-mini-2024-07-18" gpt_main = "o1-preview" interval = 1800 while True: for root_folder in os.listdir(main_folder): root_path = f'{main_folder}/{root_folder}' for folder_name in os.listdir(root_path): #print(folder_name) file_count = 0 folder_path = f'{main_folder}/{root_folder}/{folder_name}'# os.path.join(root_folder, folder_name) if "usa" not in str(folder_path): continue if os.path.isdir(folder_path): for file_name in os.listdir(folder_path): #print(file_name) # print(folder_path, file_name) file_count = file_count +1 if 'jpg' in str(file_name): continue if file_name.endswith('.json'): file_path = os.path.join(folder_path, file_name) with open(file_path, 'r') as file: try: data = json.load(file) slug = data.get('slug', 'No slug found') content = data.get('content', 'No content found') if 'eudr' not in content.lower(): continue keywords = kw_search.extract_keywords(content,150) keywords_array = [] for keyword, frequency in keywords: keywords_array.append(keyword) #for post in posts: # post_num = post_num + 1 # print(done_posts) if str(file_name) in str(done_posts): continue if len(keywords_array) < 20: done_posts.append(file_path) save_to_file('posts_done.txt', str(done_posts)) continue print(folder_path, file_name) generate_blog_post(content, keywords_array, blog_tones_and_themes, youtube_videos, farmonaut_info, yoast_guidelines2, wp_url, wp_username, wp_password, gpt_mini, gpt_main, interval, done_posts) except: print(traceback.format_exc()) time.sleep(1) main()