标签:layout laparams python rsrcmgr pdfminer device pdf import txt
# -*- coding: utf-8 -*- # from pdfminer.pdfparser import PDFParser # from pdfminer.pdfdocument import PDFDocument # from pdfminer.pdfpage import PDFPage # from pdfminer.pdfpage import PDFTextExtractionNotAllowed # from pdfminer.pdfinterp import PDFResourceManager # from pdfminer.pdfinterp import PDFPageInterpreter # from pdfminer.pdfdevice import PDFDevice # from pdfminer.layout import * # from pdfminer.converter import PDFPageAggregator # import os # # os.chdir(r'F:\test') # fp = open('s.pdf', 'rb') # #来创建一个pdf文档分析器 # parser = PDFParser(fp) # #创建一个PDF文档对象存储文档结构 # document = PDFDocument(parser) # # 检查文件是否允许文本提取 # if not document.is_extractable: # raise PDFTextExtractionNotAllowed # else: # # 创建一个PDF资源管理器对象来存储共赏资源 # rsrcmgr=PDFResourceManager() # # 设定参数进行分析 # laparams=LAParams() # # 创建一个PDF设备对象 # # device=PDFDevice(rsrcmgr) # device=PDFPageAggregator(rsrcmgr,laparams=laparams) # # 创建一个PDF解释器对象 # interpreter=PDFPageInterpreter(rsrcmgr,device) # # 处理每一页 # for page in PDFPage.create_pages(document): # interpreter.process_page(page) # # 接受该页面的LTPage对象 # layout=device.get_result() # for x in layout: # if(isinstance(x,LTTextBoxHorizontal)): # with open('h.txt','w') as f: # f.write(str(x.get_text().encode('utf-8'))+"\n") # print("process done") #_*_coding:utf-8_*_ from pdfminer.pdfparser import PDFParser from pdfminer.pdfdocument import PDFDocument from pdfminer.pdfpage import PDFPage from pdfminer.pdfdevice import PDFDevice from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter from pdfminer.converter import PDFPageAggregator from pdfminer.layout import LTTextBoxHorizontal,LAParams from pdfminer.pdfpage import PDFTextExtractionNotAllowed def parse(Path,Save_name): parser = PDFParser(Path) document = PDFDocument(parser) if not document.is_extractable: raise PDFTextExtractionNotAllowed else: rsrcmgr = PDFResourceManager() laparams = LAParams() device = PDFPageAggregator(rsrcmgr,laparams=laparams) interpreter = PDFPageInterpreter(rsrcmgr,device) for page in PDFPage.create_pages(document): interpreter.process_page(page) layout = device.get_result() for x in layout: if(isinstance(x,LTTextBoxHorizontal)): with open('%s'%(Save_name),'a') as f: # results = x.get_text().encode('gbk') results = x.get_text() f.write(results) if __name__ == '__main__': Path = open('s.pdf','rb') parse(Path,'1.txt')
标签:layout,laparams,python,rsrcmgr,pdfminer,device,pdf,import,txt 来源: https://www.cnblogs.com/shunguo/p/14533230.html
本站声明: 1. iCode9 技术分享网(下文简称本站)提供的所有内容,仅供技术学习、探讨和分享; 2. 关于本站的所有留言、评论、转载及引用,纯属内容发起人的个人观点,与本站观点和立场无关; 3. 关于本站的所有言论和文字,纯属内容发起人的个人观点,与本站观点和立场无关; 4. 本站文章均是网友提供,不完全保证技术分享内容的完整性、准确性、时效性、风险性和版权归属;如您发现该文章侵犯了您的权益,可联系我们第一时间进行删除; 5. 本站为非盈利性的个人网站,所有内容不会用来进行牟利,也不会利用任何形式的广告来间接获益,纯粹是为了广大技术爱好者提供技术内容和技术思想的分享性交流网站。