Created
March 19, 2017 02:30
-
-
Save zoeyfyi/b4d0172f45811cab572e36e9a5c0b2e5 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter | |
from pdfminer.converter import TextConverter | |
from pdfminer.layout import LAParams, LTRect, LTLine, LTTextBoxHorizontal | |
from pdfminer.pdfpage import PDFPage | |
from cStringIO import StringIO | |
from pdfminer.converter import PDFPageAggregator | |
from wand.image import Image | |
laparams = LAParams() | |
rsrcmgr = PDFResourceManager() | |
document = file('c3u.pdf', 'rb') | |
device = PDFPageAggregator(rsrcmgr, laparams=laparams) | |
interpreter = PDFPageInterpreter(rsrcmgr, device) | |
for i, page in enumerate(PDFPage.get_pages(document)): | |
# if i == 3: | |
# break | |
print "Page {}".format(i) | |
interpreter.process_page(page) | |
layout = device.get_result() | |
# print layout._objs | |
space = 0 | |
textboxes = [r for r in layout._objs if type(r) is LTTextBoxHorizontal ] | |
for t in textboxes: | |
if t.get_text().startswith("Answer space for question"): | |
space = t.y0 | |
path = os.path.join(os.getcwd(), "c3u.pdf[{}]".format(i)) | |
scale = 3 | |
with Image(filename=path, resolution=int(72*scale)) as img: | |
# Crop the margins | |
x = 46 * scale | |
y = 66 * scale | |
width = 489 * scale | |
height = 711 * scale | |
height -= max((space - 51) * scale, 1) | |
img.crop(int(x), int(y), width=int(width), height=int(height)) | |
img.save(filename="test/test{}.jpg".format(i)) |
Author
zoeyfyi
commented
Mar 19, 2017
- Remove front page
- Remove blank pages
- Handle drawing boxes
- Test more papers
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment