Spaces:
Sleeping
Sleeping
File size: 8,184 Bytes
c3861d2 9a59367 c3861d2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 |
from flask import Flask, request, jsonify, send_file
from bs4 import BeautifulSoup
from newspaper import Article
from textblob import TextBlob
# from newsapi import NewsApiClient
from transformers import pipeline
import requests
from utils import *
import pandas as pd
import base64
import json
# import nest_asyncio
app = Flask(__name__)
# newsapi = NewsApiClient(api_key='YOUR_NEWS_API_KEY') # Replace with your API key
# @app.route('/analyze_news', methods=['GET'])
# def analyze_news():
def analyze_news(company, source):
company = company
source = source
# company = request.args.get('company')
# source = request.args.get('source')
if not company or not source:
return jsonify({"error": "Please provide a company name as a query parameter"}), 400
all_articles = []
output = {"Company": f"{company}", "Articles": all_articles}
overall_sentiment_count = 0
sentiment_count = {"POSITIVE": 0, "NEGATIVE": 0, "NEUTRAL": 0}
if source == "NewsOrg":
# Fetch articles from News API
# response = newsapi.get_everything(q=company, page_size=5, sort_by='publishedAt', language='en')
params = {"q":"tesla","apiKey":"7396bdb0bc0a42c5b5b0c9c5945d32fa", "pagesize":10, "sortBy": "publishedAt", "language":'en'}
articles = requests.get(url = "https://newsapi.org/v2/everything", params= params)
articles = json.loads(articles.text)
# results = []
# sentiment_count = {"POSITIVE": 0, "NEGATIVE": 0, "NEUTRAL": 0}
# print(f">>>>>>>>>>>>>>>>>>>>>{articles}")
for idx, article in enumerate(articles["articles"]):
# print(f">>>>>>>>>>>>>>>>>>>>>{article}")
url = article.get("url")
news_article = Article(url)
try:
news_article.download()
news_article.parse()
except:
continue
blob = TextBlob(news_article.text)
polarity = blob.sentiment.polarity
if polarity > 0.3:
sentiment = "POSITIVE"
overall_sentiment_count += 1
elif polarity < -0.3:
sentiment = "NEGATIVE"
overall_sentiment_count -= 1
else:
sentiment = "NEUTRAL"
# neutral_sentiment_count += 1
sentiment_count[sentiment] += 1
all_articles.append({
"Title": article.get("title"),
"Summary": article.get("description"),
"Sentiment": sentiment
})
output["Comparitive Sentiment Score"] = {
"Sentiment Distribution": sentiment_count
}
if overall_sentiment_count>0:
output["Final Sentiment Analysis"] = f"{company.capitalize()}'s lastest news is mostly positive. Potential stock growth expected."
elif overall_sentiment_count<0:
output["Final Sentiment Analysis"] = f"{company.capitalize()}'s lastest news is mostly negative. Potential stock decline expected."
else:
output["Final Sentiment Analysis"] = f"{company.capitalize()}'s lastest news is mostly neutral. Stocks going to stay stagnant for some time."
print(output)
print(f"{'>'*5} Starting text summarization.")
# return jsonify({
# "company": company,
# "sentiment_distribution": sentiment_count,
# "articles": results
# })
# df = pd.DataFrame(all_articles)
text_to_summarize = " ".join([d['Title'] + " " + d['Summary'] for d in all_articles[:5]])
summary_final = summarize_text(text_to_summarize)
audio_path = generate_hindi_tts(summary_final)
if audio_path:# and os.path.exists(audio_path):
# Convert audio file to base64
with open(audio_path, "rb") as f:
audio_base64 = base64.b64encode(f.read()).decode('utf-8')
output["Audio"] = audio_base64
return output
else:
return jsonify({"error": "Failed to generate audio"}), 500
elif source == "Yahoo News":
url = f"https://finance.yahoo.com/quote/{company}/news/"
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36 Edg/120.0.0.0'}
response = requests.get(url, headers=headers)
if response.status_code != 200:
print("Failed to fetch news articles")
return {}
paragraphs = []
titles = []
summaries = []
soup = BeautifulSoup(response.content, 'html.parser')
for news in soup.find_all("div", class_="holder yf-1napat3"):
title_all = news.find_all('h3', class_="clamp yf-82qtw3")
summary_all = news.find_all('p', class_="clamp yf-82qtw3")
for title, summary in zip(title_all, summary_all):
title_text = title.get_text()
summary_text = summary.get_text()
paragraph = title_text + ' ' + summary_text
titles.append(title_text)
summaries.append(summary_text)
paragraphs.append(paragraph)
# Analyze sentiment and prepare the output
for i, paragraph in enumerate(paragraphs):
sentiment = analyze_sentiment(paragraph)
if sentiment == "POSITIVE":
# positive_sentiment_count += 1
overall_sentiment_count += 1
elif sentiment == "NEGATIVE":
# negative_sentiment_count += 1
overall_sentiment_count -= 1
# else:
# neutral_sentiment_count += 1
# top_words =
sentiment_count[sentiment] += 1
article = {
"Title": titles[i],
"Summary": summaries[i],
"Sentiment": sentiment
}
all_articles.append(article)
output["Comparitive Sentiment Score"] = {
"Sentiment Distribution": sentiment_count
}
if overall_sentiment_count>0:
output["Final Sentiment Analysis"] = f"{company.capitalize()}'s lastest news is mostly positive. Potential stock growth expected."
elif overall_sentiment_count<0:
output["Final Sentiment Analysis"] = f"{company.capitalize()}'s lastest news is mostly negative. Potential stock decline expected."
else:
output["Final Sentiment Analysis"] = f"{company.capitalize()}'s lastest news is mostly neutral. Stocks going to stay stagnant for some time."
# df = pd.DataFrame(all_articles)
text_to_summarize = " ".join([d['Title'] + " " + d['summary'] for d in all_articles[:5]])
summary_final = summarize_text(text_to_summarize)
audio_path = generate_hindi_tts(summary_final)
if audio_path:# and os.path.exists(audio_path):
# Convert audio file to base64
with open(audio_path, "rb") as f:
audio_base64 = base64.b64encode(f.read()).decode('utf-8')
output["Audio"] = audio_base64
return output
else:
return jsonify({"error": "Failed to generate audio"}), 500
# df = pd.DataFrame(all_articles)
# text_to_summarize = " ".join([d['Title'] + " " + d['summary'] for d in article[:5]])
# summary_final = summarize_text(text_to_summarize)
# audio_path = generate_hindi_tts(summary_final)
# if audio_path:# and os.path.exists(audio_path):
# # Convert audio file to base64
# with open(audio_path, "rb") as f:
# audio_base64 = base64.b64encode(f.read()).decode('utf-8')
# output["Audio"] = audio_base64
# return output
# else:
# return jsonify({"error": "Failed to generate audio"}), 500
else:
return jsonify({"error": "Invalid source provided"}), 400
if __name__ == '__main__':
app.run(debug=True, port=8000)
|