Pdf.py

#########################
# PDF
#########################
#extract text from the PDF
import PyPDF2
pdfFile = open(sFilePdf, 'rb')
reader = PyPDF2.PdfFileRead(pdfFile)
reader.numPages
page = reader.getPage(0)
pageText = page.extractText()

for pageNum in range(reader.numPages)
    print(reader.getPage(pageNum).extractText())

#it cannot write a PDF file but only read the text in it. No images.
#it can re-order or remove pages, or add new pages from a differernt document. It allow therefore editing a page level

#take all the pages of the PDF1 and PDF2 and build a new PDF out of it
import PyPDF2
pdfFile1 = open(sFilePdf1, 'rb')
pdfFile2 = open(sFilePdf2, 'rb')
reader1 = PyPDF2.PdfFileRead(pdfFile1)
reader2 = PyPDF2.PdfFileRead(pdfFile2)

writer = PyPDF2.PdfFileWriter()   #it exists at this point only in the cache
for pageNum in range(reader1.numPages)
    page = reader1.getPage(pageNum)
    writer.addPage(page)
for pageNum in range(reader2.numPages)
    page = reader2.getPage(pageNum)
    writer.addPage(page)

outputFile = open(sCombinedFile, 'wb')
writer.write(outputFile)
outputFile.close()
pdfFile1.close()
pdfFile2.close()