Read word document in Python

getworddoc.py

!pip3 install python-docx -q
import docx2txt

# replace following line with location of your .docx file
wordfile = "your word document.docx"

# get the contents of the word document
def getDocxContent(filename):
    doc = docx.Document(filename)
    fullText = ""
    for para in doc.paragraphs:
        fullText += para.text
    return fullText

doc_content = getDocxContent(wordfile)


# Extracting paragraph text
doc = docx.Document(wordfile)
doc.paragraphs[0].text

# Extraction text from different sections
sections = doc.sections
len(doc.sections)
for section in sections:
     print(section.start_type)

# get headings
def iter_headings(paragraphs):
    for paragraph in paragraphs:
        print(paragraph.style.name)
        if paragraph.style.name.startswith('Heading'):
            yield paragraph

for heading in iter_headings(doc.paragraphs[1:100]):
    print(heading.text)