old-svevijesti/pyth/get_articles.py

from bs4 import BeautifulSoup
import requests
from urllib.parse import urljoin
from openai import OpenAI 
import os
from langchain_openai import OpenAIEmbeddings
from db_management import (insert_data ,is_similar_data ,get_all_links,cleansing )
import json
from dotenv import load_dotenv
import tiktoken
from json_repair import repair_json

load_dotenv()
cleansing()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")

client = OpenAI()
embeddings = OpenAIEmbeddings()

dlinks = ['https://klix.ba', 'https://srpskainfo.com', 'https://bljesak.info','https://www.index.hr', 'https://avaz.ba', 'https://www.telegraf.rs', 'https://www.blic.rs', 'https://www.vijesti.me','https://dnevnik.hr','https://24sata.hr']
headers = {'User-Agent': 'Mozilla/5.0 (Linux; Android 5.1.1; SM-G928X Build/LMY47X) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.83 Mobile Safari/537.36'}

def num_tokens_from_string(string: str, model="gpt-3.5-turbo") -> int:
    encoding = tiktoken.encoding_for_model(model)
    return len(encoding.encode(string))

def slice_text_at_2k_tokens(text):
    encoding_name = "gpt-3.5-turbo"
    max_tokens = 1950
    encoding = tiktoken.encoding_for_model(encoding_name)
    tokens = encoding.encode(text)
    if len(tokens) <= max_tokens:
        return [text] 
    sliced_tokens = tokens[:max_tokens]
    sliced_text = encoding.decode(sliced_tokens)
    return sliced_text

def slice_title_if_needed(text):
    encoding_name = "gpt-3.5-turbo"
    max_tokens = 100
    encoding = tiktoken.encoding_for_model(encoding_name)
    tokens = encoding.encode(text)
    if len(tokens) <= max_tokens:
        return [text] 
    sliced_tokens = tokens[:max_tokens]
    sliced_text = encoding.decode(sliced_tokens)
    return sliced_text

def replace_with_spaces(text):
    allowed_chars = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyzČčĆćDždžĐ𩹮ž0123456789 "
    cleaned_text = ''.join(char if char in allowed_chars else ' ' for char in text)
    return cleaned_text

def fix_links(links_set):
    modified_links = set()
    for link in links_set:
        if "www" in link:
            modified_link = link.replace("www.", "")
            modified_links.add(modified_link)
        else:
            modified_links.add(link)
    return modified_links

total_links = set()
collected_news = set()

def get_article_links(url, already_checked):
    response = requests.get(url,headers)
    if response.status_code == 200:
        soup = BeautifulSoup(response.text, 'html.parser')
        articles = soup.find_all('article')
        link_store = []

        for article in articles:
            links = article.find_all('a', href=True)
            for link in links:
                link_value = urljoin(url, link['href'])
                if link_value not in already_checked:
                    link_store.append(link_value)
                    already_checked.add(link_value)
        return link_store

already_checked = set()

for dlink in dlinks:
    temp_links = get_article_links(dlink, already_checked)
    if temp_links:
        total_links.update(temp_links)
final_links = {item for item in total_links if item}

db_links = set(get_all_links())
new_links = final_links - db_links
final_links = new_links
final_links = set(final_links)
final_links = fix_links(final_links)

if __name__ == '__main__':
 
    for link in final_links:
        if link not in db_links:
            print(f"Processing link: {link}")
            db_links.add(link)

            response = requests.get(link,headers)
            soup = BeautifulSoup(response.text, 'html.parser')

            titles = soup.find_all(['h2', 'h1','h3'])
            title_text = ' '.join([title.get_text(strip=True) for title in titles])

            texts = soup.find_all(['p'])
            text_text = ' '.join([text.get_text(strip=True) for text in texts])

            text_text = text_text
            title_text = title_text
    
            title_text = replace_with_spaces(title_text)

            text_text = slice_text_at_2k_tokens(text_text)
            text_text = replace_with_spaces(str(text_text))

            ttk = num_tokens_from_string(text_text)

            category_options = ['politics','business','sport','magazine','scitech']

            category_translation = {
                 'politics': 'Politika',
                 'business': 'Biznis',
                 'sport': 'Sport',
                 'magazine': 'Magazin',
                 'scitech': 'Nauka i tehnologija',
                 'other': 'Ostalo',
                }

            if ttk > 1900:
                title_text = slice_title_if_needed(title_text)
            try:
                completion = client.chat.completions.create(
                model="gpt-3.5-turbo",
                messages=[
                    {"role": "system", "content": "Data analytic, Journalist and News reporter"},
                    {"role": "user", "content": rf"Extract relevant information from the following input: Title: {title_text}, Text: {text_text}. Remove any non-news element related to the current text and title and remove 'FOTO' and 'VIDEO' from title and text, from {category_options} select category in wich that news belong,  and provide the cleaned data make sure that its on Bosnian language and valid JSON object with 'title' field, 'category' and 'content' field."}
                ])
                generated_text = completion.choices[0].message.content

                generated_text = repair_json(generated_text)

                response_data = json.loads(generated_text)
                title = response_data["title"]
                predicted_category = response_data["category"]
                text = response_data["content"]

                if predicted_category.lower() in category_options:
                    category = predicted_category.lower()
                else:
                    category = 'other'

                category = category_translation.get(category, category.capitalize())

                vector = embeddings.embed_query(generated_text)

                print(f"Category: {category}")
        
                if not is_similar_data(title, text, link, vector, threshold=0.98):
                    similar_d = "NO"
                    insert_data(title, text, link, vector,similar_d,category)

            except Exception as e:
                print(f"Error in completion: {e}")
                continue