python-pptx-utils

change-text-font.py

# https://github.com/scanny/python-pptx/issues/281
paragraph = text_frame.paragraphs[0]
paragraph.text = text
font = paragraph.font
font.color.rgb = RGBColor(...)

get-all-shape-text.py

# https://stackoverflow.com/questions/51701626/how-to-extract-text-from-a-text-shape-within-a-group-shape-in-powerpoint-using

from pptx.enum.shapes import MSO_SHAPE_TYPE

for slide in prs.slides:
    # ---only operate on group shapes---
    group_shapes = [
        shp for shp in slide.shapes
        if shp.shape_type == MSO_SHAPE_TYPE.GROUP
    ]
    for group_shape in group_shapes:
        for shape in group_shape.shapes:
            if shape.has_text_frame:
                print(shape.text)
 
 # ----
from pptx.shapes.group import GroupShape
from pptx import Presentation

prs = Presentation(pptx_file)

textrun=[]
for slide in prs.slides:
    for shape in slide.shapes:
        pass

def checkrecursivelyfortext(shpthissetofshapes,textrun):
    for shape in shpthissetofshapes:
        if shape.shape_type == MSO_SHAPE_TYPE.GROUP:
            textrun=checkrecursivelyfortext(shape.shapes,textrun)
        else:
            if hasattr(shape, "text"):
                print(shape.text)
                textrun.append(shape.text)
    return textrun

# 1
def extract(filename, **kwargs):
    presentation = Presentation(filename)
    text_runs = []

    for slide in presentation.slides:
        for shape in slide.shapes:
            if not shape.has_text_frame:
                continue

            for paragraph in shape.text_frame.paragraphs:
                for run in paragraph.runs:
                    text_runs.append(run.text)

    return '\n\n'.join(text_runs)

search_and_replace.py

# https://github.com/scanny/python-pptx/issues/285
def replace_paragraph_text_retaining_initial_formatting(paragraph, new_text):
    p = paragraph._p  # the lxml element containing the `<a:p>` paragraph element
    # remove all but the first run
    for idx, run in enumerate(paragraph.runs):
        if idx == 0:
            continue
        p.remove(run._r)
    paragraph.runs[0].text = new_text

paragraph = textframe.paragraph[0]  # or wherever you get the paragraph from
new_text = 'foobar'
replace_paragraph_text_retaining_initial_formatting(paragraph, new_text)


# https://stackoverflow.com/questions/37924808/python-pptx-power-point-find-and-replace-text-ctrl-h
def search_and_replace(search_str, repl_str, input, output):
    """"search and replace text in PowerPoint while preserving formatting"""
    #Useful Links ;)
    #https://stackoverflow.com/questions/37924808/python-pptx-power-point-find-and-replace-text-ctrl-h
    #https://stackoverflow.com/questions/45247042/how-to-keep-original-text-formatting-of-text-with-python-powerpoint
    from pptx import Presentation
    prs = Presentation(input)
    for slide in prs.slides:
        for shape in slide.shapes:
            if shape.has_text_frame:
                if(shape.text.find(search_str))!=-1:
                    text_frame = shape.text_frame
                    cur_text = text_frame.paragraphs[0].runs[0].text
                    new_text = cur_text.replace(str(search_str), str(repl_str))
                    text_frame.paragraphs[0].runs[0].text = new_text
    prs.save(output)

# 
prs = Presentation('blah.pptx')

# To get shapes in your slides
slides = [slide for slide in prs.slides]
shapes = []
for slide in slides:
    for shape in slide.shapes:
        shapes.append(shape)

def replace_text(self, replacements: dict, shapes: List):
    """Takes dict of {match: replacement, ... } and replaces all matches.
    Currently not implemented for charts or graphics.
    """
    for shape in shapes:
        for match, replacement in replacements.items():
            if shape.has_text_frame:
                if (shape.text.find(match)) != -1:
                    text_frame = shape.text_frame
                    for paragraph in text_frame.paragraphs:
                        for run in paragraph.runs:
                            cur_text = run.text
                            new_text = cur_text.replace(str(match), str(replacement))
                            run.text = new_text
            if shape.has_table:
                for row in shape.table.rows:
                    for cell in row.cells:
                        if match in cell.text:
                            new_text = cell.text.replace(match, replacement)
                            cell.text = new_text

replace_text({'string to replace': 'replacement text'}, shapes)