python read word in a paragraph, table, FIG.

To read text, drawings, tables, extract information

Import docx
 Import ZipFile
 Import OS
 Import the shutil 

'' ' to read the text of the word ' ''
 DEF gettxt (): 
    File = docx.Document ( " gao.docx " )
     Print ( " the number of paragraphs: " + STR (len (File .paragraphs))) # number of paragraphs 13, each section of the transport isolated 
    
    # output each piece of content 
    # for para in file.paragraphs: 
    #      Print (para.text) 
    
    # output numbered paragraphs and paragraphs of 
    for I in Range ( len (file.paragraphs)):
         IFlen (file.paragraphs [I] .text.replace ( '  ' , '' ))>. 4 :
             Print ( " first " + STR (I) + " of content is: " + file.paragraphs [I] .text ) 


            
'' ' to read the word in the table ' '' 
 DEF GetTable (): 
    DOC = docx.Document ( ' word.docx ' )
     for table in doc.tables:   # through all forms 
        Print ( ' ---- the table- ----- ')
        for row intable.rows:   # traversing all table rows 
            # row_str = '\ t'.join ([cell.text for Cell in row.cells]) line of data # 
            # Print row_str 
            for Cell in row.cells:
                 Print (cell.text , ' \ T ' ) '' 'file information acquisition decompression' ''


 DEF the getinfo (the wordfile): 
    F = zipfile.ZipFile (the wordfile, ' R & lt ' )
     for filename in f.namelist (): 
        f.extract (filename ) 
        Print (filename) 
        
'' ' 
information after decompressed output: 
the _rels / 
the _rels /.rels
customXml/rels
customXml/_rels/
customXML / the _rels / item1.xml.rels 
customXML / the _rels / item2.xml.rels 
customXML / item1.xml 
customXML / item2.xml 
customXML / itemProps1.xml 
customXML / itemProps2.xml 
docProps / 
docProps / app.xml 
docProps / core.xml 
docProps / Custom.xml 
docProps / Thumbnail.wmf 
Word / 
Word / the _rels / 
Word / the _rels / document.xml.rels 
Word / the document.xml 
Word / fontTable.xml 
Word / Media / 
Word / Media / image1.jpeg 
Word / Numbering. XML 
Word / the settings.xml 
Word / the styles.xml 
Word / Theme / 
Word / Theme / theme1.xml 
'' ' 





' '' 
------ FIG obtain:
word文档的路径 
ZIP archive path 
provisional decompression path tmp
Finally, the need to preserve store_path path 
'' ' 
DEF getpic (path, zip_path, tmp_path, store_path):
     ' '' 
    : param path: source file 
    : param zip_path: docx rename ZIP 
    : param tmp_path: transit Pictures folder 
    : param store_path : Finally save the results of a folder (created manually) 
    : return: 
    '' ' 
    ' '' ============= docx file will rename the zip file ======== ============ '' ' 
    os.rename (path, zip_path) 
    # decompress 
    f = zipfile.ZipFile (zip_path, ' r ' )
     # will extract and save images 
    for File in f.namelist (): 
        f.extract (File,tmp_path) 
    #Releasing the zip file 
    f.close ()
     '' ' ============= to restore files from the zip docx docx ================= === '' ' 
    os.rename (zip_path, path) 
    # get the cache folder picture list 
    PIC = os.listdir (os.path.join (tmp_path, ' Word / Media ' ))
     ' '' ==== ========= copy pictures to a folder on the final ==================== '' ' 
    for i in PIC:
         # according to the word path generating image name 
        NEW_NAME = path.replace ( ' \\ ' , ' _ ' ) 
        NEW_NAME = new_name.replace ( ' :', '' ) + ' _ ' + I 
        shutil.copy (the os.path.join (tmp_path + ' / Word / Media ' , I), the os.path.join (store_path, NEW_NAME))
     '' ' ======= ====== delete cache file folder to store the file in a ==================== '' ' 
    for I in the os.listdir (tmp_path):
         # If the folder is deleted 
        IF os.path.isdir (os.path.join (tmp_path, i)): 
            shutil.rmtree (os.path.join (tmp_path, i)) 

    
            

IF  __name__ == ' __main__ ' :
     # source file 
    path = R & lt 'E: \ dogcat \ extract pictures \ log.docx ' 
    # docx rename ZIP 
    zip_path = r ' E: \ dogcat \ extract pictures \ log.zip ' 
    # transit Pictures folder 
    tmp_path = r ' E: \ dogcat \ extract pictures \ tmp ' 
    # finally save the results of a folder 
    store_path = r ' E: \ dogcat \ extract pictures \ test ' 
    m = getpic (path, zip_path, tmp_path, store_path)

 

 

 

As for processing doc docx files directly into a dump file on it

DEF docTTTTTdocx (DOC_NAME, docx_name):     the try :
         # is first converted into doc docx 
        Word = client.Dispatch ( " the Word.Application " ) 
        doc = word.Documents.Open (DOC_NAME)
         # parameters represents 16 to convert doc docx 
        doc .SaveAs (docx_name, 16 ) 
        doc.close () 
        word.Quit () 
    the except :
         Pass

 

 

reference:

https://blog.csdn.net/qq_40925239/article/details/83279957

https://blog.csdn.net/qq_15969343/article/details/81673970