0

我有这个pdf 文件。基于图像的低分辨率 pdf 文件。我正在尝试提取其中的数据，而我尝试过的所有选项似乎都不起作用。

选项 1 - 使用 pdfminer

from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from io import StringIO

def convert_pdf_to_txt(path):
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, laparams=laparams)
    fp = open(path, 'rb')
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    password = ""
    maxpages = 0
    caching = True
    pagenos=set()

    for page in PDFPage.get_pages(fp, pagenos, maxpages=maxpages, password=password,caching=caching, check_extractable=True):
        interpreter.process_page(page)

    text = retstr.getvalue()

    fp.close()
    device.close()
    retstr.close()
    return text

选项 2 - 使用 tika

from tika import parser # pip install tika
raw = parser.from_file(path)
text=raw['content']
# I don't like to use it very much because it often corrupts the file

选项 3 - 使用 pypdf

    import PyPDF2
    pdf_file = open(path, 'rb')
    read_pdf = PyPDF2.PdfFileReader(pdf_file)
    number_of_pages = read_pdf.getNumPages()
    page = read_pdf.getPage(0)
    page_content = page.extractText()
    text=page_content.encode('utf-8')

所有选项都返回空结果。我想这可能与文件的质量有关。我知道我们可以处理图像并增加图像特征以简化数据提取（增加图像大小、处理阈值等，你可以用 PIL 做很多事情）。有没有一种有效的方法来处理 pdf 文件？

4

2 回答 2

1

我只尝试过提取非扫描 pdf 的文本，我记得 pdfminer 给出了最好的结果。然而，这！可能会对您有所帮助，还有一些其他的 OCR python 库可以用于此目的

于 2021-02-19T20:20:20.727 回答
0

最后，我想出了一个不理想但使用 pdfminer 和 pytesseract 为我工作的解决方案：

from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from io import StringIO

def convert_pdf_image_to_text(file_path):
    from pdf2image import convert_from_path
    import pytesseract

    dpi = 350 # dots per inch
    pages = convert_from_path(file_path ,dpi)
    text=""

    for i in range(len(pages)):
        page = pages[i]
        a=pytesseract.image_to_string(page)
        text=text+a

    return text

def convert_pdf_to_txt(path):
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, laparams=laparams)
    fp = open(path, 'rb')
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    password = ""
    maxpages = 0
    caching = True
    pagenos=set()

    for page in PDFPage.get_pages(fp, pagenos, maxpages=maxpages, password=password,caching=caching, check_extractable=True):
        interpreter.process_page(page)

    text = retstr.getvalue()

    fp.close()
    device.close()
    retstr.close()

# extracting data from image pdfs

if "a" not in text or "A" not in text and extract_image_pdfs==True:
    # my pdfs will always have an "a" that's why I use this if sentence above
    try:
        print('starting to convert to image')
        text=convert_pdf_image_to_text(path)
        print('finished converting to image')
    except:
        text="no text"
        print("not pdf nor image")

return text
于 2021-02-23T12:36:46.647 回答