Upload 4 files

.gitignore

@@ -0,0 +1,152 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintainted in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

app.py

@@ -0,0 +1,77 @@
+import spacy
+from spacy.lang.en.stop_words import STOP_WORDS
+from string import punctuation
+from spacy import tokens
+import streamlit as st
+from heapq import nlargest
+import subprocess
+subprocess.run("pip3 install PyPDF2".split())
+subprocess.run("python3 -m spacy download en_core_web_sm".split())
+import PyPDF2
+from utils import (
+    clean_text,
+    fetch_article_text,
+    preprocess_text_for_abstractive_summarization,
+    read_text_from_file,
+)
+#---------------------Pre-Requiste------------------------#
+stopwords = STOP_WORDS
+punctuation = punctuation + '\n'
+
+
+
+if __name__=="__main__":
+    st.title("Text Summarizer 📝")
+    st.subheader("Creator: Shreyas Dixit")
+    
+    n = st.sidebar.slider('Summarization %',10,90,step=10)
+    n = n/100
+    type=st.selectbox('Pick one', ['PDF','Text'])
+    if type=="PDF":
+        #Upload file
+        uploaded_file = st.file_uploader("Choose a file",type=['pdf','txt','docx'])
+        text = read_text_from_file(uploaded_file)
+        # FileName = uploaded_file.name
+        # if uploaded_file is not None:
+        #     pdfFileObj = open("{FileName}", 'rb') 
+        #     pdfReader = PyPDF2.PdfFileReader(pdfFileObj) 
+        #     pageObj = pdfReader.getPage(0) 
+        #     text = (pageObj.extractText()) 
+        #     pdfFileObj.close() 
+    elif type=="Text": 
+        #Text
+        text=st.text_area("Input text !")
+
+    if st.button('Summarize'):
+        nlp = spacy.load('en_core_web_sm')
+        doc = nlp(text)
+        #Word tokenization
+        tokens = [tokens.text for tokens in doc]
+        word_frquency = {}
+        for word in doc:
+            if word.text.lower() not in stopwords:
+                if word.text.lower() not in punctuation:
+                    if word.text not in word_frquency.keys():
+                        word_frquency[word.text] = 1
+                    else:
+                        word_frquency[word.text] += 1
+        #Normalize the values
+        max_word = max(word_frquency.values())
+        for word in word_frquency.keys():
+            word_frquency[word] = word_frquency[word]/max_word
+        #Sentence Tokenization
+        sentence_token = [sent for sent in doc.sents]
+        sentence_score = {}
+        for sent in sentence_token:
+            for word in sent:
+                if word.text.lower() in word_frquency.keys():
+                    if sent not in sentence_score.keys():
+                        sentence_score[sent] = word_frquency[word.text.lower()]
+                    else:
+                        sentence_score[sent] += word_frquency[word.text.lower()]
+        #Creating a Summary
+        select_length = int(len(sentence_token)*n)
+        summary = nlargest(select_length,sentence_score,key = sentence_score.get)
+        summary = [word.text for word in summary]
+        summary = ' '.join(summary)
+        st.markdown(summary)

requirements.txt

@@ -0,0 +1,5 @@
+heapq-max==0.21
+spacy==2.2.4
+spacy-loggers==1.0.2
+streamlit==1.9.0
+PyPDF2

utils.py

@@ -0,0 +1,138 @@
+import re
+import requests
+import docx2txt
+from io import StringIO
+import PyPDF2
+from PyPDF2 import PdfFileReader
+
+from bs4 import BeautifulSoup
+from nltk.tokenize import sent_tokenize
+
+emoji_pattern = re.compile(
+    "["
+    u"\U0001F600-\U0001F64F"  # emoticons
+    u"\U0001F300-\U0001F5FF"  # symbols & pictographs
+    u"\U0001F680-\U0001F6FF"  # transport & map symbols
+    u"\U0001F1E0-\U0001F1FF"  # flags (iOS)
+    u"\U00002702-\U000027B0"
+    u"\U000024C2-\U0001F251"
+    "]+",
+    flags=re.UNICODE,
+)
+
+
+def clean_text(x):
+    # x = x.lower()  # lowercase
+    x = x.encode("ascii", "ignore").decode()  # unicode
+    x = re.sub(r"https*\S+", " ", x)  # url
+    x = re.sub(r"@\S+", " ", x)  # mentions
+    x = re.sub(r"#\S+", " ", x)  # hastags
+    # x = x.replace("'", "")  # remove ticks
+    # x = re.sub("[%s]" % re.escape(string.punctuation), " ", x)  # punctuation
+    # x = re.sub(r"\w*\d+\w*", "", x)  # numbers
+    x = re.sub(r"\s{2,}", " ", x)  # over spaces
+    x = emoji_pattern.sub(r"", x)  # emojis
+    x = re.sub("[^.,!?A-Za-z0-9]+", " ", x)  # special charachters except .,!?
+
+    return x
+
+
+def fetch_article_text(url: str):
+
+    r = requests.get(url)
+    soup = BeautifulSoup(r.text, "html.parser")
+    results = soup.find_all(["h1", "p"])
+    text = [result.text for result in results]
+    ARTICLE = " ".join(text)
+    ARTICLE = ARTICLE.replace(".", ".<eos>")
+    ARTICLE = ARTICLE.replace("!", "!<eos>")
+    ARTICLE = ARTICLE.replace("?", "?<eos>")
+    sentences = ARTICLE.split("<eos>")
+    current_chunk = 0
+    chunks = []
+    for sentence in sentences:
+        if len(chunks) == current_chunk + 1:
+            if len(chunks[current_chunk]) + len(sentence.split(" ")) <= 500:
+                chunks[current_chunk].extend(sentence.split(" "))
+            else:
+                current_chunk += 1
+                chunks.append(sentence.split(" "))
+        else:
+            print(current_chunk)
+            chunks.append(sentence.split(" "))
+
+    for chunk_id in range(len(chunks)):
+        chunks[chunk_id] = " ".join(chunks[chunk_id])
+
+    return ARTICLE, chunks
+
+
+def preprocess_text_for_abstractive_summarization(tokenizer, text):
+    sentences = sent_tokenize(text)
+
+    # initialize
+    length = 0
+    chunk = ""
+    chunks = []
+    count = -1
+    for sentence in sentences:
+        count += 1
+        combined_length = (
+            len(tokenizer.tokenize(sentence)) + length
+        )  # add the no. of sentence tokens to the length counter
+
+        if combined_length <= tokenizer.max_len_single_sentence:  # if it doesn't exceed
+            chunk += sentence + " "  # add the sentence to the chunk
+            length = combined_length  # update the length counter
+
+            # if it is the last sentence
+            if count == len(sentences) - 1:
+                chunks.append(chunk.strip())  # save the chunk
+
+        else:
+            chunks.append(chunk.strip())  # save the chunk
+
+            # reset
+            length = 0
+            chunk = ""
+
+            # take care of the overflow sentence
+            chunk += sentence + " "
+            length = len(tokenizer.tokenize(sentence))
+
+    return chunks
+
+
+def read_pdf(file):
+    pdfReader = PdfFileReader(file)
+    count = pdfReader.numPages
+    all_page_text = ""
+    for i in range(count):
+        page = pdfReader.getPage(i)
+        all_page_text += page.extractText()
+
+    return all_page_text
+
+
+def read_text_from_file(file):
+
+    # read text file
+    if file.type == "text/plain":
+        # To convert to a string based IO:
+        stringio = StringIO(file.getvalue().decode("utf-8"))
+
+        # To read file as string:
+        file_content = stringio.read()
+
+    # read pdf file
+    elif file.type == "application/pdf":
+        file_content = read_pdf(file)
+
+    # read docx file
+    elif (
+        file.type
+        == "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
+    ):
+        file_content = docx2txt.process(file)
+
+    return file_content