scriptie_scraper.py 文件源码

def reader(title):
    """Leest de PDF en converteert het naar TEXT"""
    pdfFileObj = open(title,'rb')
    pdfReader = PyPDF2.PdfFileReader(pdfFileObj)
    text = ""
    maxpage = int(pdfReader.numPages) + 1
    for x in range(0, maxpage + 100):
        try:
            pageObj = pdfReader.getPage(x)
            text += str(pageObj.extractText())
        except:
            break
    return text