兩行Python代碼實現pdf轉word功能
一、安裝依賴包
pip install --index https://pypi.mirrors.ustc.edu.cn/simple/ python-office
二、pdf轉word
2.1 代碼實現
import office office.pdf.pdf2docx(file_path = 'test.pdf')
運行過程如下:
[1/4] Opening document…
[INFO] [2/4] Analyzing document…
[WARNING] 'created' timestamp seems very low; regarding as unix timestamp
[WARNING] 'modified' timestamp seems very low; regarding as unix timestamp
[WARNING] 'created' timestamp seems very low; regarding as unix timestamp
[WARNING] 'modified' timestamp seems very low; regarding as unix timestamp
[INFO] [3/4] Parsing pages…
[INFO] (1/9) Page 1
[INFO] (2/9) Page 2
[INFO] (3/9) Page 3
[INFO] (4/9) Page 4
[INFO] (5/9) Page 5
[INFO] (6/9) Page 6
[INFO] (7/9) Page 7
[INFO] (8/9) Page 8
[INFO] (9/9) Page 9
[INFO] [4/4] Creating pages…
[INFO] (1/9) Page 1
[INFO] (2/9) Page 2
[INFO] (3/9) Page 3
[INFO] (4/9) Page 4
[INFO] (5/9) Page 5
[INFO] (6/9) Page 6
[INFO] (7/9) Page 7
[INFO] (8/9) Page 8
[INFO] (9/9) Page 9
[INFO] Terminated in 1.30s.
Process finished with exit code 0
2.2 pdf內容
2.3 轉換後的word
由上可見,效果還不錯。
補充
除瞭上文的辦法,小編還為大傢整理瞭更多Python實現的PDF轉Word方法,需要的可以參考一下
方法一:
import os from configparser import ConfigParser from io import StringIO from io import open from concurrent.futures import ProcessPoolExecutor from pdfminer.pdfinterp import PDFResourceManager from pdfminer.pdfinterp import process_pdf from pdfminer.converter import TextConverter from pdfminer.layout import LAParams from docx import Document def read_from_pdf(file_path): with open(file_path, 'rb') as file: resource_manager = PDFResourceManager() return_str = StringIO() lap_params = LAParams() device = TextConverter( resource_manager, return_str, laparams=lap_params) process_pdf(resource_manager, device, file) device.close() content = return_str.getvalue() return_str.close() return content def save_text_to_word(content, file_path): doc = Document() for line in content.split('\n'): paragraph = doc.add_paragraph() paragraph.add_run(remove_control_characters(line)) doc.save(file_path) def remove_control_characters(content): mpa = dict.fromkeys(range(32)) return content.translate(mpa) def pdf_to_word(pdf_file_path, word_file_path): content = read_from_pdf(pdf_file_path) save_text_to_word(content, word_file_path) def main(): config_parser = ConfigParser() config_parser.read('config.cfg') config = config_parser['default'] tasks = [] with ProcessPoolExecutor(max_workers=int(config['max_worker'])) as executor: for file in os.listdir(config['pdf_folder']): extension_name = os.path.splitext(file)[1] if extension_name != '.pdf': continue file_name = os.path.splitext(file)[0] pdf_file = config['pdf_folder'] + '/' + file word_file = config['word_folder'] + '/' + file_name + '.docx' print('正在處理: ', file) result = executor.submit(pdf_to_word, pdf_file, word_file) tasks.append(result) while True: exit_flag = True for task in tasks: if not task.done(): exit_flag = False if exit_flag: print('完成') exit(0) if __name__ == '__main__': main()
方法二:
加密過的PDF轉word
#-*- coding: UTF-8 -*- #!/usr/bin/python #-*- coding: utf-8 -*- import sys import importlib importlib.reload(sys) from pdfminer.pdfparser import PDFParser,PDFDocument from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter from pdfminer.converter import PDFPageAggregator from pdfminer.layout import * from pdfminer.pdfinterp import PDFTextExtractionNotAllowed import os #設置工作目錄文件夾 os.chdir(r'c:/users/dicey/desktop/codes/pdf-docx') #解析pdf文件函數 def parse(pdf_path): fp = open('diya.pdf', 'rb') # 以二進制讀模式打開 # 用文件對象來創建一個pdf文檔分析器 parser = PDFParser(fp) # 創建一個PDF文檔 doc = PDFDocument() # 連接分析器 與文檔對象 parser.set_document(doc) doc.set_parser(parser) # 提供初始化密碼 # 如果沒有密碼 就創建一個空的字符串 doc.initialize() # 檢測文檔是否提供txt轉換,不提供就忽略 if not doc.is_extractable: raise PDFTextExtractionNotAllowed else: # 創建PDf 資源管理器 來管理共享資源 rsrcmgr = PDFResourceManager() # 創建一個PDF設備對象 laparams = LAParams() device = PDFPageAggregator(rsrcmgr, laparams=laparams) # 創建一個PDF解釋器對象 interpreter = PDFPageInterpreter(rsrcmgr, device) # 用來計數頁面,圖片,曲線,figure,水平文本框等對象的數量 num_page, num_image, num_curve, num_figure, num_TextBoxHorizontal = 0, 0, 0, 0, 0 # 循環遍歷列表,每次處理一個page的內容 for page in doc.get_pages(): # doc.get_pages() 獲取page列表 num_page += 1 # 頁面增一 interpreter.process_page(page) # 接受該頁面的LTPage對象 layout = device.get_result() for x in layout: if isinstance(x,LTImage): # 圖片對象 num_image += 1 if isinstance(x,LTCurve): # 曲線對象 num_curve += 1 if isinstance(x,LTFigure): # figure對象 num_figure += 1 if isinstance(x, LTTextBoxHorizontal): # 獲取文本內容 num_TextBoxHorizontal += 1 # 水平文本框對象增一 # 保存文本內容 with open(r'test2.doc', 'a',encoding='utf-8') as f: #生成doc文件的文件名及路徑 results = x.get_text() f.write(results) f.write('\n') print('對象數量:\n','頁面數:%s\n'%num_page,'圖片數:%s\n'%num_image,'曲線數:%s\n'%num_curve,'水平文本框:%s\n' %num_TextBoxHorizontal) if __name__ == '__main__': pdf_path = r'diya.pdf' #pdf文件路徑及文件名 parse(pdf_path)
到此這篇關於兩行Python代碼實現pdf轉word功能的文章就介紹到這瞭,更多相關Python實現pdf轉word內容請搜索WalkonNet以前的文章或繼續瀏覽下面的相關文章希望大傢以後多多支持WalkonNet!
推薦閱讀:
- python解析PDF程序代碼
- python 實現存儲數據到txt和pdf文檔及亂碼問題的解決
- 詳解用Python把PDF轉為Word方法總結
- Python 操作pdf pdfplumber讀取PDF寫入Exce
- 6個Python辦公黑科技,助你提升工作效率