!pip install python-docx
!pip install textract

# Reading a .docx File into a DataFrame
import pandas as pd
from docx import Document

def read_docx_to_dataframe(file_path):
    doc = Document(file_path)
    data = {'Text': [para.text for para in doc.paragraphs]}
    df = pd.DataFrame(data)
    return df

df = read_docx_to_dataframe('sample.docx')
print(df)

# Writing a DataFrame to a .docx File
import pandas as pd
from docx import Document

# Sample DataFrame
data = {
    'Name': ['Alice', 'Bob', 'Charlie'],
    'Age': [25, 30, 35],
    'City': ['New York', 'Los Angeles', 'Chicago']
}
df = pd.DataFrame(data)

def write_dataframe_to_docx(df, file_path):
    doc = Document()
    table = doc.add_table(rows=1, cols=len(df.columns))
    hdr_cells = table.rows[0].cells
    for i, column in enumerate(df.columns):
        hdr_cells[i].text = column
    for index, row in df.iterrows():
        row_cells = table.add_row().cells
        for i, value in enumerate(row):
            row_cells[i].text = str(value)
    doc.save(file_path)

write_dataframe_to_docx(df, 'output.docx')

# Reading a .doc File into a DataFrame
import pandas as pd
import textract

def read_doc_to_dataframe(file_path):
    text = textract.process(file_path).decode('utf-8')
    data = {'Text': text.split('\n')}
    df = pd.DataFrame(data)
    return df
df = read_doc_to_dataframe('sample.doc')
print(df)

# Writing a DataFrame to a .doc File
import pandas as pd
from docx import Document
import subprocess

def write_dataframe_to_docx(df, file_path):
    doc = Document()
    table = doc.add_table(rows=1, cols=len(df.columns))
    hdr_cells = table.rows[0].cells
    for i, column in enumerate(df.columns):
        hdr_cells[i].text = column

    for index, row in df.iterrows():
        row_cells = table.add_row().cells
        for i, value in enumerate(row):
            row_cells[i].text = str(value)
    doc.save(file_path)

def convert_docx_to_doc(docx_path, doc_path):
    subprocess.run(['libreoffice', '--headless', '--convert-to', 'doc', docx_path, '--outdir', '.'])
    subprocess.run(['mv', docx_path.replace('.docx', '.doc'), doc_path])

data = {
    'Name': ['Alice', 'Bob', 'Charlie'],
    'Age': [25, 30, 35],
    'City': ['New York', 'Los Angeles', 'Chicago']
}
df = pd.DataFrame(data)
write_dataframe_to_docx(df, 'output.docx')
convert_docx_to_doc('output.docx', 'output.doc')

# importing multiple documents docx into a dataframe
import os
import pandas as pd
from docx import Document

def read_docx(file_path):
    doc = Document(file_path)
    full_text = []
    for para in doc.paragraphs:
        full_text.append(para.text)
    return '\n'.join(full_text)

folder_path = 'path/to/your/folder'

documents = []
for filename in os.listdir(folder_path):
    if filename.endswith('.docx'):
        file_path = os.path.join(folder_path, filename)
        doc_text = read_docx(file_path)
        documents.append({'filename': filename, 'text': doc_text})
df = pd.DataFrame(documents)
print(df)