python pdf获取关键字坐标_如何从PDF文件中提取文本和文本坐标？

新行在最终输出中转换为下划线.这是我发现的最小工作解决方案.

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 LAParams

from pdfminer.converter import PDFPageAggregator

import pdfminer

# Open a PDF file.

fp = open('/Users/me/Downloads/test.pdf', 'rb')

# Create a PDF parser object associated with the file object.

parser = PDFParser(fp)

# Create a PDF document object that stores the document structure.

# Password for initialization as 2nd parameter

document = PDFDocument(parser)

# Check if the document