Python PDF挖掘获取文本在每一行上的位置

Posted 2021-04-28

我目前正在使用答案中提供的课程：

How to extract text and text coordinates from a pdf file?

提供的类非常有帮助，因为我可以获得PDF中每个文本框的位置。每当文本框内有新行时，给定的类也会插入一个“ _”。

我想知道是否还有某种方法可以获取文本框中每一行文本的位置？

答案

找到它：解决方案是即使有TextBox，也要递归，直到找到文本行。当调用parsepdf方法时，下面的类应提供pdf上每一行文本的x和y坐标。

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

class pdfPositionHandling:

    def parse_obj(self, lt_objs):

        # loop over the object list
        for obj in lt_objs:

            if isinstance(obj, pdfminer.layout.LTTextLine):
                print "%6d, %6d, %s" % (obj.bbox[0], obj.bbox[1], obj.get_text().replace('
', '_'))

            # if it's a textbox, also recurse
            if isinstance(obj, pdfminer.layout.LTTextBoxHorizontal):
                self.parse_obj(obj._objs)

            # if it's a container, recurse
            elif isinstance(obj, pdfminer.layout.LTFigure):
                self.parse_obj(obj._objs)

    def parsepdf(self, filename, startpage, endpage):

        # Open a PDF file.
        fp = open(filename, '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 allows text extraction. If not, abort.
        if not document.is_extractable:
            raise PDFTextExtractionNotAllowed

        # Create a PDF resource manager object that stores shared resources.
        rsrcmgr = PDFResourceManager()

        # Create a PDF device object.
        device = PDFDevice(rsrcmgr)

        # BEGIN LAYOUT ANALYSIS
        # Set parameters for analysis.
        laparams = LAParams()

        # Create a PDF page aggregator object.
        device = PDFPageAggregator(rsrcmgr, laparams=laparams)

            # Create a PDF interpreter object.
        interpreter = PDFPageInterpreter(rsrcmgr, device)


        i = 0
        # loop over all pages in the document
        for page in PDFPage.create_pages(document):
            if i >= startpage and i <= endpage:
                # read the page into a layout object
                interpreter.process_page(page)
                layout = device.get_result()

                # extract text from this object
                self.parse_obj(layout._objs)
            i += 1