WIP000.1- AI content writer

pseo_main.py

@@ -7,9 +7,12 @@ Allows the user to specify various parameters for blog generation without needin
 
 import sys
 import os
+import re
 import argparse
 import requests
 from loguru import logger
+import csv
+import json
 
 # Logger configuration
 logger.remove()
@@ -17,6 +20,8 @@ logger.add(sys.stdout, colorize=True, format="<level>{level}</level>|<green>{fil
 
 # Importing custom functions
 from lib.get_text_response import generate_detailed_blog, generate_youtube_blog
+from lib.main_youtube_research_blog import generate_youtube_research_blog
+from lib.main_keywords_to_blog import generate_keyword_blog
 
 
 def parse_arguments():
@@ -25,9 +30,8 @@ def parse_arguments():
     Returns:
         argparse.Namespace: Parsed arguments.
     """
-
     parser = argparse.ArgumentParser(description="Generate blogs based on user input.")
-    parser.add_argument("--num_blogs", type=int, default=5, help="Number of blogs to generate (default: 5).")
+    parser.add_argument("--csv", type=str, help="Provide path csv file. Check the template csv for example.")
     parser.add_argument("--keywords", type=str, help="Keywords for blog generation.")
     parser.add_argument("--niche", action='store_true', default=False, help="Flag to generate niche blogs (default: False).")
     parser.add_argument("--num_subtopics", type=int, default=6, help="Number of subtopics per blog (default: 6).")
@@ -59,7 +63,7 @@ def main():
         args = parse_arguments()
         logger.info("Fetch and Validate Openai key.")
         # Validate user input
-        if not args.keywords and not args.youtube_urls:
+        if not args.keywords and not args.youtube_urls and not args.csv:
             raise ValueError("Either --keywords or --youtube_urls must be provided.")
 
         # Validate OpenAI API key
@@ -72,17 +76,80 @@ def main():
         # Handle blog generation based on input
         if args.youtube_urls:
             yt_urls = args.youtube_urls.split(",")
-            logger.info(f"Generating blogs from YouTube URLs: {yt_urls}")
-            generate_youtube_blog(yt_urls)
+            valid_urls = [url for url in yt_urls if is_valid_url(url)]
+            quoted_strings = [url for url in yt_urls if not is_valid_url(url)]
+
+            if valid_urls:
+                logger.info(f"Generating blogs from YouTube URLs: {valid_urls}")
+                generate_youtube_blog(valid_urls)
+            if quoted_strings:
+                logger.info(f"Do youtube research and write blogs for: {quoted_strings}")
+                generate_youtube_research_blog(quoted_strings)
+
         elif args.keywords:
             logger.info(f"Generating {args.num_blogs} blogs on '{args.keywords}' with {args.num_subtopics} subtopics.")
-            generate_detailed_blog(args.num_blogs, args.keywords, args.niche,
-                    args.num_subtopics, args.wordpress, args.output_format)
+            #generate_detailed_blog(args.num_blogs, args.keywords, args.niche,
+            #        args.num_subtopics, args.wordpress, args.output_format)
+            keyword_list = args.keywords.split(",")
+            generate_keyword_blog(keyword_list)
 
+        elif args.csv:
+            try:
+                data = read_csv_to_json(args.csv)
+                logger.info(f"Generating blogs from csv file: {json.dumps(data, indent=4)}")
+                for item in data:
+                    keyword_list = [item['keyword']]
+                    generate_keyword_blog(keyword_list, item['URL'])
+            except Exception as err:
+                logger.error(f"Failed to generate blogs the CSV file:{err}")
+                sys.exit(1)
+            
     except Exception as e:
         logger.error(f"An error occurred: {e}")
         sys.exit(1)
 
 
+def read_csv_to_json(file_path):
+    # Initialize a list to store JSON objects
+    json_data = []
+
+    try:
+        # Read the CSV file
+        with open(file_path, newline='', encoding='utf-8') as csvfile:
+            reader = csv.DictReader(csvfile)
+
+            # Iterate over each row and convert it to a JSON object
+            for row in reader:
+                json_data.append(row)
+
+        return json_data
+    except Exception as err:
+        logger.error(f"Failed to read the CSV file:{err}")
+        sys.exit(1)
+
+
+def is_valid_url(url):
+    """
+    Check if the given string is a valid URL.
+
+    Args:
+        url (str): String to check.
+
+    Returns:
+        bool: True if the string is a valid URL, False otherwise.
+    """
+    # Regular expression to check for a valid URL
+    url_pattern = re.compile(     
+        r'^(?:http|ftp)s?://'  # http:// or https://
+        r'(?:(?:[A-Z0-9](?:[A-Z0-9-]{0,61}[A-Z0-9])?\.)+(?:[A-Z]{2,6}\.?|[A-Z0-9-]{2,}\.?)|'  # domain...
+        r'localhost|'  # localhost...
+        r'\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}|'  # ...or ipv4
+        r'\[?[A-F0-9]*:[A-F0-9:]+\]?)'  # ...or ipv6
+        r'(?::\d+)?'  # optional port
+        r'(?:/?|[/?]\S+)$', re.IGNORECASE)
+
+    return re.match(url_pattern, url) is not None
+
+
 if __name__ == "__main__":
     main()