pdfminer PDF转word txt

最新推荐文章于 2025-06-14 12:39:53 发布

原创

最新推荐文章于 2025-06-14 12:39:53 发布 · 1.2k 阅读

6 ·

CC 4.0 BY-SA版权

本文介绍如何利用pdfminer库进行PDF到Word和TXT的转换，详细阐述了转换过程和技术要点，帮助读者掌握PDF文档处理技巧。

from pdfminer.pdfparser import PDFParser, PDFDocument
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.layout import LAParams
from pdfminer.converter import PDFPageAggregator
from pdfminer.pdfinterp import PDFTextExtractionNotAllowed

def parse():

    fn = open('D:\\search\\1804.03567.pdf','rb') #转成word好点   TXT中RELATED WORK键字找不到  word中可以

    parser = PDFParser(fn)
    doc = PDFDocument()
    parser.set_document(doc)
    doc.set_parser(parser)
    doc.initialize("")
    if not doc.is_extractable:
        raise PDFTextExtractionNotAllowed
    else:
        resource = PDFResourceManager()
        laparams = LAParams()
        device = PDFPageAggregator(resource,laparams=laparams)
        interpreter = PDFPageInterpreter(resource,device)
        for page in doc.get_pages():
            interpreter.process_page(page)
            layout = device.get_result()
            for out in layout:
                if h