Recipe 511465 revision 2

import pyPdf

def getPDFContent(path):
    content = ""
    # Load PDF into pyPDF
    pdf = pyPdf.PdfFileReader(file(path, "rb"))
    # Iterate pages
    for i in range(0, pdf.getNumPages()):
        # Extract text from page and add to content
        content += pdf.getPage(i).extractText() + "\n"
    # Collapse whitespace
    content = " ".join(content.replace("\xa0", " ").strip().split())
    return content

print getPDFContent("test.pdf")

• « Back to Recipe 511465

History

• revision 2 (17 years ago)
• previous revisions are not available