Python - Processing PDF files

Python packages for manipulating PDF

• PyPDF2

• pdfminer.six - Python library that focuses on getting and analyzing text data, including a PDF converter to tranform PDF files into text or html.

• pdfrw - pure Python library that reads and writes PDFs

Split into pages

The PyPDF2 package works well for spliting the file into pages.

import sys
from subprocess import call
import PyPDF2

def split_into_pages(filename,outfile_prefix):
    with open(filename, "rb") as file:
        f = PyPDF2.PdfFileReader(file)
        for i in range(0, f.getNumPages()):
            page = f.getPage(i)
            base = outfile_prefix + "_page_" +str(i)
            pageFilename = base + ".pdf"

            output = PyPDF2.PdfFileWriter()
            output.addPage(page)
            with open(pageFilename, "wb") as outputStream:
                output.write(outputStream)

Create jpg for each page

• Split into pages and then convert to jpg

def split_into_jpg_pages(filename,outfile_prefix):
    generated_files = []
    with open(filename, "rb") as file:
        f = PyPDF2.PdfFileReader(file)
        for i in range(0, f.getNumPages()):
            page = f.getPage(i)
            base = f"{outfile_prefix}_page_{i}"
            pageFilename = base + ".pdf"

            # write pdf file
            output = PyPDF2.PdfFileWriter()
            output.addPage(page)
            with open(pageFilename, "wb") as outputStream:
                output.write(outputStream)

            # call external program 'convert' to convert to jpg
            jpgPageFilename = base + ".jpg"
            call(["convert", pageFilename, jpgPageFilename])
            # could remove the pdf file now

            generated_files.append(jpgPageFilename)

    return(generated_files)

Extract all text via PyPDF2

def extract_all_text(filename):
    page_text = []
    with open(filename, "rb") as file:
        f = PyPDF2.PdfFileReader(file)
        for i in range(0, f.getNumPages()):
            page = f.getPage(i)
            pcontent = page.extractText() + "\n"
            pcontent = " ".join(pcontent.replace(u"\xa0", u" ").strip().split())
            page_text.append(pcontent)
    return(page_text)

Extract all text via pdfminer

• Use tools/pdf2txt.py

This produces a cleaner text output.

Extracting JPGs from PDF, Quick and Dirty

From https://nedbatchelder.com/blog/200712/extracting_jpgs_from_pdfs.html (Converted to Python3)

Process a PDF file and create a jpg file o Create jpg files files each image, names jpg0.jpg, jpg1.jpg, and so on.

import sys

with open("source.pdf", "rb") as file:
    pdf = file.read()

startmark = b"\xff\xd8"
startfix = 0
endmark = b"\xff\xd9"
endfix = 2
i = 0

njpg = 0
while True:
    istream = pdf.find(b"stream", i)
    print("istream " + str(istream))
    if istream < 0:
        break
    istart = pdf.find(startmark, istream, istream+20)
    print("     istart " + str(istart))
    if istart < 0:
        i = istream+20
        continue
    iend = pdf.find(b"endstream", istart)
    if iend < 0:
        raise Exception("Didn't find end of stream!")
    iend = pdf.find(endmark, iend-20)
    if iend < 0:
        raise Exception("Didn't find end of JPG!")

    istart += startfix
    iend += endfix
    print( "JPG %d from %d to %d" % (njpg, istart, iend))
    jpg = pdf[istart:iend]
    with open("jpg%s.jpg" % njpg, "wb") as  jpgfile:
        jpgfile.write(jpg)

    njpg += 1
    i = iend

Extracting text

Example from https://stackoverflow.com/questions/20327681/extract-images-from-pdf-using-python-pypdf2

import sys
import PyPDF2

from PIL import Image

if __name__ == '__main__':
    input1 = PyPDF2.PdfFileReader(open("source.pdf", "rb"))

    page0 = input1.getPage(0)


    content = ""
        
    pages = []
    for i in range(0, input1.getNumPages()):
        pcontent = input1.getPage(i).extractText() + "\n"
        pcontent = " ".join(pcontent.replace(u"\xa0", u" ").strip().split())

        content += pcontent
        pages.append(pcontent)

    content = content.replace("IRB Number:","\n\nIRB Number:")
    print(content)
    #sys.exit()

    xObject = page0['/Resources']['/XObject'].getObject()

    for obj in xObject:
        if xObject[obj]['/Subtype'] == '/Image':
            size = (xObject[obj]['/Width'], xObject[obj]['/Height'])
            data = xObject[obj].getData()
            if xObject[obj]['/ColorSpace'] == '/DeviceRGB':
                mode = "RGB"
            else:
                mode = "P"

            if xObject[obj]['/Filter'] == '/FlateDecode':
                img = Image.frombytes(mode, size, data)
                img.save(obj[1:] + ".png")
            elif xObject[obj]['/Filter'] == '/DCTDecode':
                img = open(obj[1:] + ".jpg", "wb")
                img.write(data)
                img.close()
            elif xObject[obj]['/Filter'] == '/JPXDecode':
                img = open(obj[1:] + ".jp2", "wb")
                img.write(data)