python - 从 powerpoint 文件中分离文本提取时遇到问题

Question

我有一个从 PowerPoint 中提取文本的函数。然而，输出是一个大列表中所有 Powerpoint 文件的所有文本。如何分离文本，以便最终为我提取的两个 powerpoint 文件提供两个文本列表？

text_runs = []

def pptx_collect(x):
    for file in pptx_files:
        prs = Presentation(file)
        for slide in prs.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(text_runs)

def Powerpoint(pptx_files):
        for name in pptx_files:
                #print(name)
                IP_list = (pptx_collect(name))
                for item in IP_list:
                        #print(item)
                    keyword = re.findall(inp,item)
                    keyword1 = re.findall(inp1,item)
                    keyword2 = re.findall(word_search,item)
                #print(ip_test)
                file_dict['keyword'].append(keyword+keyword1+keyword2)
                file_dict['name'].append(name.name[0:])
                file_dict['created'].append(time.ctime(name.stat().st_ctime))
                file_dict['modified'].append(time.ctime(name.stat().st_mtime))
                file_dict['path'].append(name)
                file_dict["content"].append(IP_list) #<--- This is where the 
                                                            #problem is.
                #print(file_dict)
        return(file_dict)
Powerpoint(pptx_files)

我得到的输出是:

['Billy’s ', 'pii', 'Just a test', '04/15/1991', '04.15.1991', '234-23-6456-billys ', 'SSN', 'Address: 58 bonnie ', 'rd', ', 'mass 07037', 'Text from second 2 ', 'Text from second ', 'powerpoint', ' ', '(second page)',  'Text from second 2 ', 'Text from second ', 'powerpoint', ' ', '(second page)', 'FOUO Test', 'Secret', 'This is a test to check ', 'for keywords']

我想要得到:

['Billy’s ', 'pii', 'Just a test', '04/15/1991', '04.15.1991', '234-23-6456-billys ', 'SSN', 'Address: 58 bonnie ', 'rd', ', Boston, mass 07037', 'Text from second 2 '] 

['Text from second ', 'powerpoint', ' ', '(second page)',  'Text from second 2 ', 'Text from second ', 'powerpoint', ' ', '(second page)', 'FOUO Test', 'Secret', 'This is a test to check ', 'for keywords']

Answer 1

pptx_collect() 函数会遍历所有文件。试试这个:

def pptx_collect(x):
    prs = Presentation(x)
    for slide in prs.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(text_runs)