python实现pdf转word的例子
pdf转word的效果一般都很差，下面使用pdfminer和docx框架，前者用来读取pdf的文本内容，后者用来写到word文件中。仅作入门级参考。
例子如下：
例子如下：
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 |
#!/usr/bin/env python# coding=utf-8import sysimport osfrom binascii import b2a_hexfrom pdfminer.pdfparser import PDFParserfrom pdfminer.pdfdocument import PDFDocument, PDFNoOutlinesfrom pdfminer.pdfpage import PDFPagefrom pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreterfrom pdfminer.converter import PDFPageAggregatorfrom pdfminer.layout import LAParams, LTTextBox, LTTextLine, LTFigure, LTImage, LTCharfrom docx import Documentdef _parse_toc (doc): """With an open PDFDocument object, get the table of contents (toc) data [this is a higher-order function to be passed to with_pdf()]""" toc = [] try: outlines = doc.get_outlines() for (level,title,dest,a,se) in outlines: toc.append( (level, title) ) except PDFNoOutlines: pass return tocdef with_pdf (pdf_doc, fn, pdf_pwd, *args): """Open the pdf document, and apply the function, returning the results""" result = None try: # open the pdf file fp = open(pdf_doc, 'rb') # create a parser object associated with the file object parser = PDFParser(fp) # create a PDFDocument object that stores the document structure doc = PDFDocument(parser, pdf_pwd) # connect the parser and document objects parser.set_document(doc) # supply the password for initialization if doc.is_extractable: # apply the function and return the result result = fn(doc, *args) # close the pdf file fp.close() except IOError: # the file doesn't exist or similar problem pass return result def get_toc (pdf_doc, pdf_pwd=''): """Return the table of contents (toc), if any, for this pdf file""" return with_pdf(pdf_doc, _parse_toc, pdf_pwd) def write_file (folder, filename, filedata, flags='w'): """Write the file data to the folder and filename combination (flags: 'w' for write text, 'wb' for write binary, use 'a' instead of 'w' for append)""" result = False if os.path.isdir(folder): try: file_obj = open(os.path.join(folder, filename), flags) file_obj.write(filedata) file_obj.close() result = True except IOError: pass return resultdef determine_image_type (stream_first_4_bytes): """Find out the image file type based on the magic number comparison of the first 4 (or 2) bytes""" file_type = None bytes_as_hex = b2a_hex(stream_first_4_bytes) if bytes_as_hex.startswith('ffd8'): file_type = '.jpeg' elif bytes_as_hex == '89504e47': file_type = '.png' elif bytes_as_hex == '47494638': file_type = '.gif' elif bytes_as_hex.startswith('424d'): file_type = '.bmp' return file_typedef save_image (lt_image, page_number, images_folder): """Try to save the image data from this LTImage object, and return the file name, if successful""" result = None if lt_image.stream: file_stream = lt_image.stream.get_rawdata() if file_stream: file_ext = determine_image_type(file_stream[0:4]) if file_ext: file_name = ''.join([str(page_number), '_', lt_image.name, file_ext]) if write_file(images_folder, file_name, file_stream, flags='wb'): result = file_name return resultdef to_bytestring (s, enc='utf-8'): """Convert the given unicode string to a bytestring, using the standard encoding, unless it's already a bytestring""" if s: if isinstance(s, str): return s else: return s.encode(enc) def update_page_text_hash (h, lt_obj, pct=0.2): """Use the bbox x0,x1 values within pct% to produce lists of associated text within the hash""" x0 = lt_obj.bbox[0] x1 = lt_obj.bbox[2] key_found = False for k, v in h.items(): hash_x0 = k[0] if x0 >= (hash_x0 * (1.0-pct)) and (hash_x0 * (1.0+pct)) >= x0: hash_x1 = k[1] if x1 >= (hash_x1 * (1.0-pct)) and (hash_x1 * (1.0+pct)) >= x1: # the text inside this LT* object was positioned at the same # width as a prior series of text, so it belongs together key_found = True v.append(to_bytestring(lt_obj.get_text())) h[k] = v if not key_found: # the text, based on width, is a new series, # so it gets its own series (entry in the hash) h[(x0,x1)] = [to_bytestring(lt_obj.get_text())] return h def parse_lt_objs (lt_objs, page_number, images_folder, text=[]): """Iterate through the list of LT* objects and capture the text or image data contained in each""" text_content = [] page_text = {} ''''k=(x0, x1) of the bbox, v=list of text strings within that bbox width (physical column)''' for lt_obj in lt_objs: if isinstance(lt_obj, LTTextBox) or isinstance(lt_obj, LTTextLine): # text, so arrange is logically based on its column width page_text = update_page_text_hash(page_text, lt_obj) elif isinstance(lt_obj, LTImage): # an image, so save it to the designated folder, and note its place in the text saved_file = save_image(lt_obj, page_number, images_folder) if saved_file: # use html style <img /> tag to mark the position of the image within the text text_content.append('<img src="'+os.path.join(images_folder, saved_file)+'" />') else: pass #print >> sys.stderr, "error saving image on page", page_number, lt_obj.__repr__ elif isinstance(lt_obj, LTFigure): ''' LTFigure objects are containers for other LT* objects, so recurse through the children''' text_content.append(parse_lt_objs(lt_obj, page_number, images_folder, text_content)) for k, v in sorted([(key,value) for (key,value) in page_text.items()]): # sort the page_text hash by the keys (x0,x1 values of the bbox), # which produces a top-down, left-to-right sequence of related columns text_content.append(''.join(v)) return '\n'.join(text_content)def _parse_pages (doc, images_folder): """With an open PDFDocument object, get the pages and parse each one [this is a higher-order function to be passed to with_pdf()]""" rsrcmgr = PDFResourceManager() laparams = LAParams() device = PDFPageAggregator(rsrcmgr, laparams=laparams) interpreter = PDFPageInterpreter(rsrcmgr, device) text_content = [] for i, page in enumerate(PDFPage.create_pages(doc)): interpreter.process_page(page) # receive the LTPage object for this page layout = device.get_result() ''' layout is an LTPage object which may contain child objects like LTTextBox, LTFigure, LTImage, etc.''' objs = parse_lt_objs(layout, (i+1), images_folder) text_content.append(objs) return text_contentdef get_pages (pdf_doc, pdf_pwd='', images_folder='/tmp'): """Process each of the pages in this pdf file and return a list of strings representing the text found in each page""" return with_pdf(pdf_doc, _parse_pages, pdf_pwd, *tuple([images_folder]))def remove_control_characters(content): mpa = dict.fromkeys(range(32)) return content.translate(mpa)def write_text_to_word(doc, content, file_path): paragraph = doc.add_paragraph() paragraph.add_run(content) doc.save(file_path) if __name__ == '__main__': doc = Document() for page_content in get_pages('D:/pdf/test.pdf'): write_text_to_word(doc, unicode(page_content, "utf-8"), 'D:/pdf/test.docx') |
