Hugging Face's logo

Spaces:
Gabesantos1007
/
NewsAgora
Runtime error

App Files Community
NewsAgora
File size: 5,089 Bytes 
dc9d537
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34d6871
dc9d537
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3945651
dc9d537
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
import streamlit as st
from PIL import Image
from bs4 import BeautifulSoup as soup
from urllib.request import urlopen
from newspaper import Article
import io
import nltk
nltk.download('punkt')

st.set_page_config(page_title='NewsAgora🇧🇷: Um Portal de Notícias Resumidas📰', page_icon='./Meta/newspaper.ico')


def fetch_news_search_topic(topic):
    site = 'https://news.google.com/rss?hl=pt-BR&gl=BR&ceid=BR:pt'.format(topic) 
    op = urlopen(site)  # Open that site
    rd = op.read()  # read data from site
    op.close()  # close the object
    sp_page = soup(rd, 'xml')  # scrapping data from site
    news_list = sp_page.find_all('item')  # finding news
    return news_list


def fetch_top_news():
    site = 'https://news.google.com/rss?hl=pt-BR&gl=BR&ceid=BR:pt'
    op = urlopen(site)  # Open that site
    rd = op.read()  # read data from site
    op.close()  # close the object
    sp_page = soup(rd, 'xml')  # scrapping data from site
    news_list = sp_page.find_all('item')  # finding news
    return news_list


def fetch_category_news(topic):
    site = 'https://news.google.com/news/rss/headlines/section/topic/{}?hl=pt-BR&gl=BR&ceid=BR:pt'.format(topic)
    op = urlopen(site)  # Open that site
    rd = op.read()  # read data from site
    op.close()  # close the object
    sp_page = soup(rd, 'xml')  # scrapping data from site
    news_list = sp_page.find_all('item')  # finding news
    return news_list


def fetch_news_poster(poster_link):
    try:
        u = urlopen(poster_link)
        raw_data = u.read()
        image = Image.open(io.BytesIO(raw_data))
        st.image(image, use_column_width=True)
    except:
        image = Image.open('no_image.jpg')
        st.image(image, use_column_width=True)


def display_news(list_of_news, news_quantity):
    c = 0
    for news in list_of_news:
        c += 1
        # st.markdown(f"({c})[ {news.title.text}]({news.link.text})")
        st.write('**({}) {}**'.format(c, news.title.text))
        news_data = Article(news.link.text)
        try:
            news_data.download()
            news_data.parse()
            news_data.nlp()
        except Exception as e:
            st.error(e)
        fetch_news_poster(news_data.top_image)
        with st.expander(news.title.text):
            st.markdown(
                '''<h6 style='text-align: justify;'>{}"</h6>'''.format(news_data.summary),
                unsafe_allow_html=True)
            st.markdown("[Read more at {}...]({})".format(news.source.text, news.link.text))
        st.success("Published Date: " + news.pubDate.text)
        if c >= news_quantity:
            break


def run():
    st.title("NewsAgora🇧🇷: Um Portal de Notícias Resumidas📰")
    image = Image.open('newspaper.png')

    col1, col2, col3 = st.columns([3, 5, 3])

    with col1:
        st.write("")

    with col2:
        st.image(image, use_column_width=False)

    with col3:
        st.write("")
    category = ['--Selecione--', 'Notícias em Alta🔥', 'Tópicos Favoritos💙', 'Buscar Tópico🔍']
    cat_op = st.selectbox('Selecione a categoria', category)
    if cat_op == category[0]:
        st.warning('Por favor, selecione uma opção!')
    elif cat_op == category[1]:
        st.subheader("✅ Aqui estão as notícias em alta para você")
        no_of_news = st.slider('Número de notícias:', min_value=5, max_value=15, step=1)
        news_list = fetch_top_news()
        display_news(news_list, no_of_news)
    elif cat_op == category[2]:
        av_topics = ['Choose Topic', 'WORLD', 'NATION', 'BUSINESS', 'TECHNOLOGY', 'ENTERTAINMENT', 'SPORTS', 'SCIENCE',
                     'HEALTH']
        st.subheader("Escolha seu tópico favorito")
        chosen_topic = st.selectbox("Escolha seu tópico favorito", av_topics)
        if chosen_topic == av_topics[0]:
            st.warning("Por favor, escolha um tópico")
        else:
            no_of_news = st.slider('Número de notícias:', min_value=5, max_value=15, step=1)
            news_list = fetch_category_news(chosen_topic)
            if news_list:
                st.subheader("✅ Aqui estão algumas notícias de {} para você".format(chosen_topic))
                display_news(news_list, no_of_news)
            else:
                st.error("Nenhuma notícia encontrada para {}".format(chosen_topic))

    elif cat_op == category[3]:
        user_topic = st.text_input("Digite seu tópico🔍")
        no_of_news = st.slider('Número de notícias:', min_value=5, max_value=15, step=1)

        if st.button("Search") and user_topic != '':
            user_topic_pr = user_topic.replace(' ', '')
            news_list = fetch_news_search_topic(topic=user_topic_pr)
            if news_list:
                st.subheader("✅ Aqui estão algumas notícias de {} para você".format(user_topic.capitalize()))
                display_news(news_list, no_of_news)
            else:
                st.error("Nenhuma notícia encontrada para {}".format(user_topic))
        else:
            st.warning("Por favor, escreva o nome do tópico para pesquisar🔍")


run()