Spaces:
Runtime error
Runtime error
Commit
·
dc9d537
1
Parent(s):
210a212
Create App.py
Browse files
App.py
ADDED
@@ -0,0 +1,133 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
from PIL import Image
|
3 |
+
from bs4 import BeautifulSoup as soup
|
4 |
+
from urllib.request import urlopen
|
5 |
+
from newspaper import Article
|
6 |
+
import io
|
7 |
+
import nltk
|
8 |
+
nltk.download('punkt')
|
9 |
+
|
10 |
+
st.set_page_config(page_title='NewsAgora🇧🇷: Um Portal de Notícias Resumidas📰', page_icon='./Meta/newspaper.ico')
|
11 |
+
|
12 |
+
|
13 |
+
def fetch_news_search_topic(topic):
|
14 |
+
site = 'https://news.google.com/rss?hl=pt-BR&gl=BR&ceid=BR:pt'.format(topic)
|
15 |
+
op = urlopen(site) # Open that site
|
16 |
+
rd = op.read() # read data from site
|
17 |
+
op.close() # close the object
|
18 |
+
sp_page = soup(rd, 'xml') # scrapping data from site
|
19 |
+
news_list = sp_page.find_all('item') # finding news
|
20 |
+
return news_list
|
21 |
+
|
22 |
+
|
23 |
+
def fetch_top_news():
|
24 |
+
site = 'https://news.google.com/rss?hl=pt-BR&gl=BR&ceid=BR:pt'
|
25 |
+
op = urlopen(site) # Open that site
|
26 |
+
rd = op.read() # read data from site
|
27 |
+
op.close() # close the object
|
28 |
+
sp_page = soup(rd, 'xml') # scrapping data from site
|
29 |
+
news_list = sp_page.find_all('item') # finding news
|
30 |
+
return news_list
|
31 |
+
|
32 |
+
|
33 |
+
def fetch_category_news(topic):
|
34 |
+
site = 'https://news.google.com/news/rss/headlines/section/topic/{}?hl=pt-BR&gl=BR&ceid=BR:pt'.format(topic)
|
35 |
+
op = urlopen(site) # Open that site
|
36 |
+
rd = op.read() # read data from site
|
37 |
+
op.close() # close the object
|
38 |
+
sp_page = soup(rd, 'xml') # scrapping data from site
|
39 |
+
news_list = sp_page.find_all('item') # finding news
|
40 |
+
return news_list
|
41 |
+
|
42 |
+
|
43 |
+
def fetch_news_poster(poster_link):
|
44 |
+
try:
|
45 |
+
u = urlopen(poster_link)
|
46 |
+
raw_data = u.read()
|
47 |
+
image = Image.open(io.BytesIO(raw_data))
|
48 |
+
st.image(image, use_column_width=True)
|
49 |
+
except:
|
50 |
+
image = Image.open('./Meta/no_image.jpg')
|
51 |
+
st.image(image, use_column_width=True)
|
52 |
+
|
53 |
+
|
54 |
+
def display_news(list_of_news, news_quantity):
|
55 |
+
c = 0
|
56 |
+
for news in list_of_news:
|
57 |
+
c += 1
|
58 |
+
# st.markdown(f"({c})[ {news.title.text}]({news.link.text})")
|
59 |
+
st.write('**({}) {}**'.format(c, news.title.text))
|
60 |
+
news_data = Article(news.link.text)
|
61 |
+
try:
|
62 |
+
news_data.download()
|
63 |
+
news_data.parse()
|
64 |
+
news_data.nlp()
|
65 |
+
except Exception as e:
|
66 |
+
st.error(e)
|
67 |
+
fetch_news_poster(news_data.top_image)
|
68 |
+
with st.expander(news.title.text):
|
69 |
+
st.markdown(
|
70 |
+
'''<h6 style='text-align: justify;'>{}"</h6>'''.format(news_data.summary),
|
71 |
+
unsafe_allow_html=True)
|
72 |
+
st.markdown("[Read more at {}...]({})".format(news.source.text, news.link.text))
|
73 |
+
st.success("Published Date: " + news.pubDate.text)
|
74 |
+
if c >= news_quantity:
|
75 |
+
break
|
76 |
+
|
77 |
+
|
78 |
+
def run():
|
79 |
+
st.title("NewsAgora🇧🇷: Um Portal de Notícias Resumidas📰")
|
80 |
+
image = Image.open('./Meta/newspaper.png')
|
81 |
+
|
82 |
+
col1, col2, col3 = st.columns([3, 5, 3])
|
83 |
+
|
84 |
+
with col1:
|
85 |
+
st.write("")
|
86 |
+
|
87 |
+
with col2:
|
88 |
+
st.image(image, use_column_width=False)
|
89 |
+
|
90 |
+
with col3:
|
91 |
+
st.write("")
|
92 |
+
category = ['--Selecione--', 'Notícias em Alta🔥', 'Tópicos Favoritos💙', 'Buscar Tópico🔍']
|
93 |
+
cat_op = st.selectbox('Selecione a categoria', category)
|
94 |
+
if cat_op == category[0]:
|
95 |
+
st.warning('Por favor, selecione uma opção!')
|
96 |
+
elif cat_op == category[1]:
|
97 |
+
st.subheader("✅ Aqui estão as notícias em alta para você")
|
98 |
+
no_of_news = st.slider('Número de notícias:', min_value=5, max_value=15, step=1)
|
99 |
+
news_list = fetch_top_news()
|
100 |
+
display_news(news_list, no_of_news)
|
101 |
+
elif cat_op == category[2]:
|
102 |
+
av_topics = ['Choose Topic', 'WORLD', 'NATION', 'BUSINESS', 'TECHNOLOGY', 'ENTERTAINMENT', 'SPORTS', 'SCIENCE',
|
103 |
+
'HEALTH']
|
104 |
+
st.subheader("Escolha seu tópico favorito")
|
105 |
+
chosen_topic = st.selectbox("Escolha seu tópico favorito", av_topics)
|
106 |
+
if chosen_topic == av_topics[0]:
|
107 |
+
st.warning("Por favor, escolha um tópico")
|
108 |
+
else:
|
109 |
+
no_of_news = st.slider('Número de notícias:', min_value=5, max_value=15, step=1)
|
110 |
+
news_list = fetch_category_news(chosen_topic)
|
111 |
+
if news_list:
|
112 |
+
st.subheader("✅ Aqui estão algumas notícias de {} para você".format(chosen_topic))
|
113 |
+
display_news(news_list, no_of_news)
|
114 |
+
else:
|
115 |
+
st.error("Nenhuma notícia encontrada para {}".format(chosen_topic))
|
116 |
+
|
117 |
+
elif cat_op == category[3]:
|
118 |
+
user_topic = st.text_input("Digite seu tópico🔍")
|
119 |
+
no_of_news = st.slider('Número de notícias:', min_value=5, max_value=15, step=1)
|
120 |
+
|
121 |
+
if st.button("Search") and user_topic != '':
|
122 |
+
user_topic_pr = user_topic.replace(' ', '')
|
123 |
+
news_list = fetch_news_search_topic(topic=user_topic_pr)
|
124 |
+
if news_list:
|
125 |
+
st.subheader("✅ Aqui estão algumas notícias de {} para você".format(user_topic.capitalize()))
|
126 |
+
display_news(news_list, no_of_news)
|
127 |
+
else:
|
128 |
+
st.error("Nenhuma notícia encontrada para {}".format(user_topic))
|
129 |
+
else:
|
130 |
+
st.warning("Por favor, escreva o nome do tópico para pesquisar🔍")
|
131 |
+
|
132 |
+
|
133 |
+
run()
|