Collection of python-docx hyperlink snippets

docx_hyperlink_snippets.py

import re
import docx
from docx.text.run import Run

def add_hyperlink_into_run(paragraph, run, url):
    """
    https://github.com/python-openxml/python-docx/issues/610#issuecomment-458289054
    """

    runs = paragraph.runs
    for i in range(len(runs)):
        if runs[i].text == run.text:
            break
    # --- This gets access to the document.xml.rels file and gets a new relation id value ---
    part = paragraph.part
    r_id = part.relate_to(
        url, docx.opc.constants.RELATIONSHIP_TYPE.HYPERLINK, is_external=True
    )
    # --- Create the w:hyperlink tag and add needed values ---
    hyperlink = docx.oxml.shared.OxmlElement('w:hyperlink')
    hyperlink.set(docx.oxml.shared.qn('r:id'), r_id, )
    hyperlink.append(run._r)
    paragraph._p.insert(i,hyperlink)
    run.font.color.rgb = docx.shared.RGBColor(0, 0, 255)
    


def add_hyperlink(paragraph, url, text, color, underline):
    """
    https://github.com/python-openxml/python-docx/issues/74#issuecomment-261169410
    
    A function that places a hyperlink within a paragraph object.

    :param paragraph: The paragraph we are adding the hyperlink to.
    :param url: A string containing the required url
    :param text: The text displayed for the url
    :return: The hyperlink object
    """

    # This gets access to the document.xml.rels file and gets a new relation id value
    part = paragraph.part
    r_id = part.relate_to(url, docx.opc.constants.RELATIONSHIP_TYPE.HYPERLINK, is_external=True)

    # Create the w:hyperlink tag and add needed values
    hyperlink = docx.oxml.shared.OxmlElement('w:hyperlink')
    hyperlink.set(docx.oxml.shared.qn('r:id'), r_id, )

    # Create a w:r element
    new_run = docx.oxml.shared.OxmlElement('w:r')

    # Create a new w:rPr element
    rPr = docx.oxml.shared.OxmlElement('w:rPr')

    # Add color if it is given
    if not color is None:
      c = docx.oxml.shared.OxmlElement('w:color')
      c.set(docx.oxml.shared.qn('w:val'), color)
      rPr.append(c)

    # Remove underlining if it is requested
    if not underline:
      u = docx.oxml.shared.OxmlElement('w:u')
      u.set(docx.oxml.shared.qn('w:val'), 'none')
      rPr.append(u)

    # Join all the xml elements together add add the required text to the w:r element
    new_run.append(rPr)
    new_run.text = text
    hyperlink.append(new_run)

    paragraph._p.append(hyperlink)

    return hyperlink

########################################################################################################################################
# https://github.com/python-openxml/python-docx/issues/610#issuecomment-458289054

# --- this document contains one paragraph and one run with the following text:
# --- "Please refer to document 1 (doc. 1). More testing sentences. "
doc = docx.Document('testing runs.docx')

# --- This is the pattern to match the string '(doc. #)'
pattern = "\(doc. [0-9]\)."


for paragraph in doc.paragraphs:
    for run in paragraph.runs:
        matches = re.findall(pattern, run.text)
        if matches:
            print("Found a match!")
            # --- this replaces the pattern we wrote above with nothing.
            run.text = re.sub(pattern, "", run.text) 
            # --- if there are more than one instances of '(doc. #)' in the run,
            # --- we want to replace all of them. This logic might not work perfectly
            # --- but it's a start.
            for match in matches: 
                new_run_element = paragraph._element._new_r()
                run._element.addnext(new_run_element)
                new_run = Run(new_run_element, run._parent)
                new_run.text = match + " "
                add_hyperlink_into_run(paragraph, new_run, "http://google.com")
                
doc.save('testing-runs-complete.docx')



########################################################################################################################################
# https://github.com/python-openxml/python-docx/issues/74#issuecomment-261169410

document = docx.Document()
p = document.add_paragraph()

#add a hyperlink with the normal formatting (blue underline)
hyperlink = add_hyperlink(p, 'http://www.google.com', 'Google', None, True)

#add a hyperlink with a custom color and no underline
hyperlink = add_hyperlink(p, 'http://www.google.com', 'Google', 'FF8822', False)

document.save('demo.docx')

########################################################################################################################################
# https://github.com/python-openxml/python-docx/issues/720

from docx.oxml.ns import qn  # ---for "qualified name", aka. Clark-notation tagname---

def remove_relationship_from_doc(doc, hyperlink):
  hyperlink_rel_id = hyperlink.get(qn("r:id"))
  document_part = document.part
  document_part.drop_rel(hyperlink_rel_id)


def remove_hyperlink_from_paragraph(doc, paragraph, remove_label=True):
  p = paragraph._p
  hyperlink = p.xpath("./w:hyperlink")[0]
  if remove_label:
    p.remove(hyperlink)
  else:
    label_r = p.xpath("./w:hyperlink/w:r")[0]
    hyperlink.add_previous(label_r)
  p.remove(hyperlink)
  remove_relationship_from_doc(doc, hyperlink)