File size: 4,459 Bytes
09ebcd0
 
 
 
 
 
4409afe
1ac298a
09ebcd0
1d7a9d5
 
 
5947621
1d7a9d5
ed4ef14
5947621
4409afe
 
 
 
 
 
 
 
 
 
 
 
 
 
dac6155
4409afe
 
 
68a8b0c
ed4ef14
 
 
1d7a9d5
09ebcd0
 
 
f42fdaf
68a8b0c
f42fdaf
68a8b0c
09ebcd0
 
 
 
 
f42fdaf
09ebcd0
f42fdaf
68a8b0c
09ebcd0
dac6155
 
ab30506
68a8b0c
ed4ef14
 
 
 
 
 
 
 
 
 
 
ab30506
4409afe
ed4ef14
 
 
dac6155
68a8b0c
 
 
b659602
dac6155
b659602
 
 
 
 
 
dac6155
b659602
 
68a8b0c
09ebcd0
b659602
68a8b0c
ab30506
 
 
1d7a9d5
 
 
ad0f104
b659602
4409afe
ed4ef14
b659602
ad0f104
 
ab30506
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
import gradio as gr
import requests
from datetime import datetime, timedelta
import pycountry
import json

# NewsAPI key
API_KEY = "37d83e266422487b8b2e4cb6e1ff0aa6"

COUNTRY_CODES = "ae ar at au be bg br ca ch cn co cu cz de eg fr gb gr hk hu id ie il in it jp kr lt lv ma mx my ng nl no nz ph pl pt ro rs ru sa se sg si sk th tr tw ua us ve za".split()

COUNTRIES = {'all': 'All Countries'}
COUNTRIES.update({code: pycountry.countries.get(alpha_2=code.upper()).name for code in COUNTRY_CODES if pycountry.countries.get(alpha_2=code.upper())})

def get_news(keyword, article_count, country, extend_search=False):
    country_code = next((code for code, name in COUNTRIES.items() if name == country), 'all')
    
    if country_code == 'all':
        base_url = "https://newsapi.org/v2/everything"
        params = {
            'apiKey': API_KEY,
            'q': keyword,
            'language': 'en',
            'sortBy': 'publishedAt',
            'pageSize': article_count
        }
    else:
        base_url = "https://newsapi.org/v2/top-headlines"
        params = {
            'apiKey': API_KEY,
            'q': keyword,
            'country': country_code,
            'pageSize': article_count
        }
    
    if not extend_search:
        two_days_ago = (datetime.utcnow() - timedelta(hours=48)).isoformat()
        params['from'] = two_days_ago

    debug_info = f"API Request URL: {base_url}\n"
    debug_info += f"Parameters: {json.dumps(params, indent=2)}\n\n"

    try:
        response = requests.get(base_url, params=params, timeout=10)
        response.raise_for_status()
        news_data = response.json()

        debug_info += f"API Response Status: {response.status_code}\n"
        debug_info += f"API Response Headers: {json.dumps(dict(response.headers), indent=2)}\n\n"
        debug_info += f"API Response Body: {json.dumps(news_data, indent=2)}\n\n"

    except requests.RequestException as e:
        return f"<p style='color: red;'>Error fetching news: {str(e)}</p><pre>{debug_info}</pre>"

    if news_data['status'] != 'ok':
        return f"<p style='color: red;'>API Error: {news_data.get('message', 'Unknown error occurred')}</p><pre>{debug_info}</pre>"

    articles = news_data['articles']
    
    if not articles:
        if not extend_search:
            return get_news(keyword, article_count, country, extend_search=True)
        else:
            return (f"<p>No news found for the keyword '<strong>{keyword}</strong>' in {country}.<br>"
                    f"Suggestions:</p>"
                    f"<ul>"
                    f"<li>Try a different keyword</li>"
                    f"<li>Expand your search to all countries</li>"
                    f"<li>Increase the number of articles</li>"
                    f"</ul>"
                    f"<pre>{debug_info}</pre>")

    html_output = f"<h2>News results for '{keyword}' in {country}</h2>"
    if extend_search:
        html_output += "<p><em>Note: Search range was extended due to limited recent results.</em></p>"
    
    for article in articles:
        title = article['title']
        link = article['url']
        pub_date = datetime.strptime(article['publishedAt'], "%Y-%m-%dT%H:%M:%SZ")
        source = article.get('source', {}).get('name', 'Unknown Source')
        description = article.get('description', 'No description available')
        
        html_output += f"""
        <div style='margin-bottom: 20px; padding: 10px; border: 1px solid #ddd; border-radius: 5px;'>
            <h3><a href='{link}' target='_blank' style='text-decoration: none; color: #1a0dab;'>{title}</a></h3>
            <p style='color: #006621;'>{source}</p>
            <p style='color: #545454;'>{pub_date.strftime('%Y-%m-%d %H:%M:%S')}</p>
            <p>{description}</p>
        </div>
        """

    html_output += f"<details><summary>Debug Info</summary><pre>{debug_info}</pre></details>"
    return html_output

iface = gr.Interface(
    fn=get_news,
    inputs=[
        gr.Textbox(label="Enter keyword"),
        gr.Slider(minimum=10, maximum=100, step=10, value=10, label="Number of Articles"),
        gr.Dropdown(choices=list(COUNTRIES.values()), value="All Countries", label="Select Country")
    ],
    outputs=gr.HTML(),
    title="Enhanced Visual News Search",
    description="Search for news articles using NewsAPI. If recent results are limited, the search range will be automatically extended.",
    theme=gr.themes.Soft()
)

iface.launch()