Spaces:
Configuration error
Configuration error
Delete summarizer
Browse files- summarizer/README.md +0 -1
- summarizer/__pycache__/document_data.cpython-311.pyc +0 -0
- summarizer/__pycache__/load.cpython-311.pyc +0 -0
- summarizer/__pycache__/website_data.cpython-311.pyc +0 -0
- summarizer/app.py +0 -7
- summarizer/document_data.py +0 -19
- summarizer/load.py +0 -9
- summarizer/pages/document.py +0 -8
- summarizer/pages/text.py +0 -7
- summarizer/pages/url.py +0 -8
- summarizer/pages/video.py +0 -0
- summarizer/pages/youtube_video.py +0 -12
- summarizer/website_data.py +0 -40
summarizer/README.md
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
Summariser
|
|
|
|
summarizer/__pycache__/document_data.cpython-311.pyc
DELETED
Binary file (1.43 kB)
|
|
summarizer/__pycache__/load.cpython-311.pyc
DELETED
Binary file (811 Bytes)
|
|
summarizer/__pycache__/website_data.cpython-311.pyc
DELETED
Binary file (1.59 kB)
|
|
summarizer/app.py
DELETED
@@ -1,7 +0,0 @@
|
|
1 |
-
import streamlit as st
|
2 |
-
st.set_page_config(
|
3 |
-
page_title="Summarize EAZY",
|
4 |
-
page_icon="fav2.jpg",
|
5 |
-
layout="wide",
|
6 |
-
)
|
7 |
-
st.header("Welcome to the **SUMMARIZE EAZY**")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
summarizer/document_data.py
DELETED
@@ -1,19 +0,0 @@
|
|
1 |
-
import streamlit as st
|
2 |
-
from PyPDF2 import PdfReader
|
3 |
-
import docx2txt
|
4 |
-
def document_extract():
|
5 |
-
uploaded_file = st.file_uploader("Choose a file",accept_multiple_files=True)
|
6 |
-
content = """"""
|
7 |
-
if uploaded_file is not None:
|
8 |
-
for x in uploaded_file:
|
9 |
-
if(x.type=="application/vnd.openxmlformats-officedocument.wordprocessingml.document"):
|
10 |
-
content += docx2txt.process(x)
|
11 |
-
elif(x.type=="application/pdf"):
|
12 |
-
pdf_reader = PdfReader(x)
|
13 |
-
for page_num in range(len(pdf_reader.pages)):
|
14 |
-
content += pdf_reader.pages[page_num].extract_text()
|
15 |
-
elif(x.type=="text/plain"):
|
16 |
-
content = st.read(x)
|
17 |
-
else:
|
18 |
-
st.error("Please provide files of type **.docx**,**.pdf**,**.txt**")
|
19 |
-
return content
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
summarizer/load.py
DELETED
@@ -1,9 +0,0 @@
|
|
1 |
-
import pathlib
|
2 |
-
import textwrap
|
3 |
-
import google.generativeai as genai
|
4 |
-
def output(text):
|
5 |
-
response = model.generate_content("Summarize this and also don't make this too short "+text)
|
6 |
-
return response
|
7 |
-
GOOGLE_API_KEY="AIzaSyCgX2dUhfUNGZ1aSrjUIlXNfor1ylBdw7I"
|
8 |
-
genai.configure(api_key=GOOGLE_API_KEY)
|
9 |
-
model = genai.GenerativeModel('gemini-pro')
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
summarizer/pages/document.py
DELETED
@@ -1,8 +0,0 @@
|
|
1 |
-
import streamlit as st
|
2 |
-
import document_data
|
3 |
-
import load
|
4 |
-
data=document_data.document_extract()
|
5 |
-
if data:
|
6 |
-
response=(load.output(data))
|
7 |
-
for chunk in response:
|
8 |
-
st.write(chunk.text)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
summarizer/pages/text.py
DELETED
@@ -1,7 +0,0 @@
|
|
1 |
-
import load
|
2 |
-
import streamlit as st
|
3 |
-
text=st.text_input("Enter the text you want to summarize..")
|
4 |
-
if text:
|
5 |
-
response=(load.output(text))
|
6 |
-
for chunk in response:
|
7 |
-
st.write(chunk.text)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
summarizer/pages/url.py
DELETED
@@ -1,8 +0,0 @@
|
|
1 |
-
import streamlit as st
|
2 |
-
import load
|
3 |
-
import website_data
|
4 |
-
url=st.text_input("Enter the url",placeholder="URL....")
|
5 |
-
if url:
|
6 |
-
response=(load.output(website_data.scrape(url)))
|
7 |
-
for chunk in response:
|
8 |
-
st.write(chunk.text)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
summarizer/pages/video.py
DELETED
File without changes
|
summarizer/pages/youtube_video.py
DELETED
@@ -1,12 +0,0 @@
|
|
1 |
-
import streamlit as st
|
2 |
-
import load
|
3 |
-
from langchain_community.document_loaders import YoutubeLoader
|
4 |
-
url=st.text_input("Enter the url",placeholder="URL....")
|
5 |
-
if url:
|
6 |
-
loader = YoutubeLoader.from_youtube_url(
|
7 |
-
url, add_video_info=False
|
8 |
-
)
|
9 |
-
transcript=loader.load()
|
10 |
-
response=load.output(str(transcript))
|
11 |
-
for chunk in response:
|
12 |
-
st.write(chunk.text)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
summarizer/website_data.py
DELETED
@@ -1,40 +0,0 @@
|
|
1 |
-
import requests
|
2 |
-
from bs4 import BeautifulSoup
|
3 |
-
|
4 |
-
|
5 |
-
def scrape(url):
|
6 |
-
URL = url
|
7 |
-
headers = {'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.135 Safari/537.36 Edge/12.246"}
|
8 |
-
# Here the user agent is for Edge browser on windows 10. You can find your browser user agent from the above given link.
|
9 |
-
|
10 |
-
r = requests.get(url=URL, headers=headers)
|
11 |
-
if r.status_code ==200:
|
12 |
-
# print(r.content)
|
13 |
-
|
14 |
-
soup = BeautifulSoup(r.content, 'html.parser') # If this line causes an error, run 'pip install html5lib' or install html5lib
|
15 |
-
# print(soup.prettify())
|
16 |
-
# b = soup.find_all('p','ul li')
|
17 |
-
# for yy in b:
|
18 |
-
# print(yy.get_text())
|
19 |
-
flag = 0;
|
20 |
-
enter = """
|
21 |
-
"""
|
22 |
-
str = ""
|
23 |
-
body = soup.body.find_all()
|
24 |
-
for tag in body:
|
25 |
-
if tag.name=='p' or tag.name=='h1' or tag.name=='h2' or tag.name=='h3' :
|
26 |
-
str += tag.get_text()
|
27 |
-
str += enter
|
28 |
-
if tag.name=='p':
|
29 |
-
flag=1
|
30 |
-
|
31 |
-
elif (tag.name == 'ul' or tag.name=='ol') and flag==1:
|
32 |
-
liBody=tag.find_all('li')
|
33 |
-
for text in liBody:
|
34 |
-
str+=text.get_text()
|
35 |
-
str += enter
|
36 |
-
# print(str)
|
37 |
-
# print(soup.body.get_text())
|
38 |
-
return str
|
39 |
-
else:
|
40 |
-
return ""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|