spider-python/pdf_converter.py at main · jdchart/spider-python · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
from pdf2image import convert_from_path
from PyPDF2 import PdfReader
import os


pdf_doc = "/Users/jacob/Downloads/scene_walden/Programme_colline.pdf"
dest_path = "/Users/jacob/Downloads/scene_walden/program"


def parseDocument(path):
    """Derrive information from a pdf file."""

    pdfFile = PdfReader(path)

    maxWid = pdfFile.pages[0].mediabox.width
    maxHeight = pdfFile.pages[0].mediabox.height

    for page in pdfFile.pages:
        if page.mediabox.width > maxWid:
            maxWid = page.mediabox.width
        if page.mediabox.height > maxHeight:
            maxHeight = page.mediabox.height

    return {
        "dimensions" : [int(maxWid), int(maxHeight)],
        "pages" : len(pdfFile.pages)
    }


def convertPDF(pathIn, pathOut, numPages, createFile):
    if createFile:
        images = convert_from_path(pathIn)
    filename = os.path.splitext(os.path.basename(pathIn))[0]
    fileList = []
    for i in range(numPages):
        if createFile:
            images[i].save(os.path.join(pathOut, filename + "_page_" + str(i + 1) +'.jpg'), 'JPEG')
        fileList.append(filename + "_page_" + str(i + 1) +'.jpg')
    return fileList


doc_info = parseDocument(pdf_doc)
print(doc_info)
convertPDF(pdf_doc, dest_path, doc_info["pages"], True)
#convertPDF(pdf_doc, dest_path, pages, True)
print("done.")