Python解析Pdf文件的简单方法

做Java web系统的时候，经常需要处理一些PDF文件，用Java来去读解析感觉麻烦，所以就想用Python来处理。Python果然是比Java少了很多代码。

还是直接上代码吧：

# !/usr/bin/python3
# -*- coding: utf-8 -*-
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfpage import PDFPage, PDFTextExtractionNotAllowed
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import LAParams
import io
def pdf2txt(path: str):
    output = io.StringIO()
    with open(path, 'rb') as f:
        praser = PDFParser(f)
        doc = PDFDocument(praser)
        if not doc.is_extractable:
            raise PDFTextExtractionNotAllowed

        pdfrm = PDFResourceManager()
        laparams = LAParams()
        device = PDFPageAggregator(pdfrm, laparams=laparams)
        interpreter = PDFPageInterpreter(pdfrm, device)
        for page in PDFPage.create_pages(doc):
            interpreter.process_page(page)
            layout = device.get_result()
            for x in layout:
                if hasattr(x, "get_text"):
                    content = x.get_text()
                    output.write(content)

    content = output.getvalue()
    output.close()
    return content

print(pdf2txt('C:\\Users\\Administrator\\Desktop\\test.pdf'))