Internship

JibinCB/authors.py

@@ -0,0 +1,23 @@
+import pypdf
+import spacy
+nlp = spacy.load("en_core_web_sm")
+
+def extract_names_from_pdf(pdf_path):
+    names = []
+    with open(pdf_path, "rb") as pdf_file:
+        pdf_reader = pypdf.PdfReader(pdf_file)
+        page = pdf_reader.pages[0]
+        text = page.extract_text()
+        doc = nlp(text)
+        for ent in doc.ents:
+            if ent.label_ == "PERSON":
+                names.append(ent.text)
+    return names
+
+# Example usage
+def authors():
+    pdf_path = "paper1.pdf"
+    names_list = extract_names_from_pdf(pdf_path)
+    return(names_list)
+
+

JibinCB/main.py

@@ -0,0 +1,17 @@
+import pandas as pd
+from summary import summary_of_pdf
+from authors import authors
+from title_of_pdf import title
+# Load the existing Excel file into a DataFrame
+
+# Sample new data
+new_data = [
+    {'Title': title(), 'Authors': authors(), 'Summary': summary_of_pdf()}
+]
+df = pd.DataFrame(new_data)
+# Append new data to the DataFrame
+# for item in new_data:
+#     df = df.append(item, ignore_index=True)
+
+# Save the updated DataFrame to Excel
+df.to_excel('sample.xlsx', index=False)

JibinCB/summary.py

@@ -0,0 +1,36 @@
+import pypdf
+from sumy.nlp.tokenizers import Tokenizer
+from sumy.parsers.plaintext import PlaintextParser
+from sumy.summarizers.lsa import LsaSummarizer
+from sumy.nlp.stemmers import Stemmer
+from sumy.utils import get_stop_words
+
+LANGUAGE = "english"
+
+
+def extract_text_from_pdf(pdf_path):
+    text = ""
+    with open(pdf_path, "rb") as pdf_file:
+        pdf_reader = pypdf.PdfReader(pdf_file)
+        for page_num in range(len(pdf_reader.pages)):
+            page = pdf_reader.pages[page_num]
+            text += page.extract_text()
+    return text
+
+
+def summarize_text(text, sentences_count=20):
+    parser = PlaintextParser.from_string(text, Tokenizer(LANGUAGE))
+    stemmer = Stemmer(LANGUAGE)
+    summarizer = LsaSummarizer(stemmer)
+    summarizer.stop_words = get_stop_words(LANGUAGE)
+    sentences = summarizer(parser.document, sentences_count)
+    summary = " ".join(str(sentence) for sentence in sentences)
+    return summary
+
+
+# Example usage
+def summary_of_pdf():
+    pdf_path = "paper1.pdf"
+    pdf_text = extract_text_from_pdf(pdf_path)
+    summary_text = summarize_text(pdf_text)
+    return(summary_text)

JibinCB/title_of_pdf.py

@@ -0,0 +1,19 @@
+import pypdf
+import re
+
+# Open the PDF file
+def title():
+    pdf_file = open('paper1.pdf', 'rb')
+
+    # Initialize PDF reader
+    pdf_reader = pypdf.PdfReader(pdf_file)
+
+    # Extract text from the first page
+    first_page = pdf_reader.get_page(0)
+    pdf_text_first_page = first_page.extract_text(0)
+    pdf_file.close()
+
+    fully_capitalized_text = re.findall(r'\b[A-Z\s\.\-]+\b', pdf_text_first_page)
+
+    title = fully_capitalized_text[0].strip()
+    return(title)