## hpr3596 :: Extracting text, tables and images from docx files using Python

 Tools to extract data from docx files:

docx2txt
python-docx2txt
python-docx

Code Snippets
text = docx2txt.process(src, img_dest)
with open("data.txt", "wt") as f:
    f.write(text)

document = docx.Document(src)
tables = document.tables
data = []
for table in tables:
    table_data = []
    for row in table.rows:
        row_data = []
        for cell in row.cells:
            row_data.append(cell.text)
        table_data.append(row_data)
    data.append(table_table)

for i, table in enumerate(tables):
    with open(f"{i}.csv", "wt") as f:
        writer = csv.writer(f)
        writer.writerows(table)

