def select_image_layer(infiles, output_file, log, context):
"""Selects the image layer for the output page. If possible this is the
orientation-corrected input page, or an image of the whole page converted
to PDF."""
options = context.get_options()
page_pdf = next(ii for ii in infiles if ii.endswith('.ocr.oriented.pdf'))
image = next(ii for ii in infiles if ii.endswith('.image'))
if options.lossless_reconstruction:
log.debug(
f"{page_number(page_pdf):4d}: page eligible for lossless reconstruction"
)
re_symlink(page_pdf, output_file, log) # Still points to multipage
return
pageinfo = get_pageinfo(image, context)
# We rasterize a square DPI version of each page because most image
# processing tools don't support rectangular DPI. Use the square DPI as it
# accurately describes the image. It would be possible to resample the image
# at this stage back to non-square DPI to more closely resemble the input,
# except that the hocr renderer does not understand non-square DPI. The
# sandwich renderer would be fine.
dpi = get_page_square_dpi(pageinfo, options)
layout_fun = img2pdf.get_fixed_dpi_layout_fun((dpi, dpi))
# This create a single page PDF
with open(image, 'rb') as imfile, open(output_file, 'wb') as pdf:
log.debug(f'{page_number(page_pdf):4d}: convert')
img2pdf.convert(
imfile, with_pdfrw=False, layout_fun=layout_fun, outputstream=pdf
)
log.debug(f'{page_number(page_pdf):4d}: convert done')
def triage_image_file(input_file, output_file, log, options):
try:
log.info("Input file is not a PDF, checking if it is an image...")
im = Image.open(input_file)
except EnvironmentError as e:
msg = str(e)
# Recover the original filename
realpath = ''
if os.path.islink(input_file):
realpath = os.path.realpath(input_file)
elif os.path.isfile(input_file):
realpath = '<stdin>'
msg = msg.replace(input_file, realpath)
log.error(msg)
raise UnsupportedImageFormatError() from e
else:
log.info("Input file is an image")
if 'dpi' in im.info:
if im.info['dpi'] <= (96, 96) and not options.image_dpi:
log.info("Image size: (%d, %d)" % im.size)
log.info("Image resolution: (%d, %d)" % im.info['dpi'])
log.error(
"Input file is an image, but the resolution (DPI) is "
"not credible. Estimate the resolution at which the "
"image was scanned and specify it using --image-dpi.")
raise DpiError()
elif not options.image_dpi:
log.info("Image size: (%d, %d)" % im.size)
log.error(
"Input file is an image, but has no resolution (DPI) "
"in its metadata. Estimate the resolution at which "
"image was scanned and specify it using --image-dpi.")
raise DpiError()
if 'iccprofile' not in im.info:
if im.mode == 'RGB':
log.info('Input image has no ICC profile, assuming sRGB')
elif im.mode == 'CMYK':
log.info('Input CMYK image has no ICC profile, not usable')
raise UnsupportedImageFormatError()
im.close()
try:
log.info("Image seems valid. Try converting to PDF...")
layout_fun = img2pdf.default_layout_fun
if options.image_dpi:
layout_fun = img2pdf.get_fixed_dpi_layout_fun(
(options.image_dpi, options.image_dpi))
with open(output_file, 'wb') as outf:
img2pdf.convert(
input_file,
layout_fun=layout_fun,
with_pdfrw=False,
outputstream=outf)
log.info("Successfully converted to PDF, processing...")
except img2pdf.ImageOpenError as e:
log.error(e)
raise UnsupportedImageFormatError() from e
def select_image_layer(infiles, output_file, log, context):
"""Selects the image layer for the output page. If possible this is the
orientation-corrected input page, or an image of the whole page converted
to PDF."""
options = context.get_options()
page_pdf = next(ii for ii in infiles if ii.endswith('.ocr.oriented.pdf'))
image = next(ii for ii in infiles if ii.endswith('.image'))
if options.lossless_reconstruction:
log.debug("{:4d}: page eligible for lossless reconstruction".format(
page_number(page_pdf)))
re_symlink(page_pdf, output_file, log)
else:
pageinfo = get_pageinfo(image, context)
# We rasterize a square DPI version of each page because most image
# processing tools don't support rectangular DPI. Use the square DPI
# as it accurately describes the image. It would be possible to
# resample the image at this stage back to non-square DPI to more
# closely resemble the input, except that the hocr renderer does not
# understand non-square DPI. The tess4 renderer would be fine.
dpi = get_page_square_dpi(pageinfo, options)
layout_fun = img2pdf.get_fixed_dpi_layout_fun((dpi, dpi))
with open(image, 'rb') as imfile, \
open(output_file, 'wb') as pdf:
log.debug('{:4d}: convert'.format(page_number(page_pdf)))
img2pdf.convert(imfile,
with_pdfrw=False,
layout_fun=layout_fun,
outputstream=pdf)
log.debug('{:4d}: convert done'.format(page_number(page_pdf)))
def select_image_layer(
infiles,
output_file,
log,
pdfinfo,
pdfinfo_lock):
page_pdf = next(ii for ii in infiles if ii.endswith('.ocr.oriented.pdf'))
image = next(ii for ii in infiles if ii.endswith('.image'))
if lossless_reconstruction:
log.debug("{:4d}: page eligible for lossless reconstruction".format(
page_number(page_pdf)))
re_symlink(page_pdf, output_file)
else:
pageinfo = get_pageinfo(image, pdfinfo, pdfinfo_lock)
dpi = get_page_dpi(pageinfo)
dpi = float(dpi[0]), float(dpi[1])
layout_fun = img2pdf.get_fixed_dpi_layout_fun(dpi)
with open(image, 'rb') as imfile, \
open(output_file, 'wb') as pdf:
rawdata = imfile.read()
img2pdf.convert(
rawdata, with_pdfrw=False,
layout_fun=layout_fun, outputstream=pdf)
def triage_image_file(input_file, output_file, log):
try:
log.info("Input file is not a PDF, checking if it is an image...")
im = Image.open(input_file)
except EnvironmentError as e:
msg = str(e)
# Recover the original filename
realpath = ''
if os.path.islink(input_file):
realpath = os.path.realpath(input_file)
elif os.path.isfile(input_file):
realpath = '<stdin>'
msg = msg.replace(input_file, realpath)
log.error(msg)
sys.exit(ExitCode.input_file)
return
else:
log.info("Input file is an image")
if 'dpi' in im.info:
if im.info['dpi'] <= (96, 96) and not options.image_dpi:
log.info("Image size: (%d, %d)" % im.size)
log.info("Image resolution: (%d, %d)" % im.info['dpi'])
log.error(
"Input file is an image, but the resolution (DPI) is "
"not credible. Estimate the resolution at which the "
"image was scanned and specify it using --image-dpi.")
sys.exit(ExitCode.input_file)
elif not options.image_dpi:
log.info("Image size: (%d, %d)" % im.size)
log.error("Input file is an image, but has no resolution (DPI) "
"in its metadata. Estimate the resolution at which "
"image was scanned and specify it using --image-dpi.")
sys.exit(ExitCode.input_file)
if 'iccprofile' not in im.info:
if im.mode == 'RGB':
log.info('Input image has no ICC profile, assuming sRGB')
elif im.mode == 'CMYK':
log.info('Input CMYK image has no ICC profile, not usable')
sys.exit(ExitCode.input_file)
im.close()
try:
log.info("Image seems valid. Try converting to PDF...")
layout_fun = img2pdf.default_layout_fun
if options.image_dpi:
layout_fun = img2pdf.get_fixed_dpi_layout_fun(
(options.image_dpi, options.image_dpi))
with open(output_file, 'wb') as outf:
img2pdf.convert(input_file,
layout_fun=layout_fun,
with_pdfrw=False,
outputstream=outf)
log.info("Successfully converted to PDF, processing...")
except img2pdf.ImageOpenError as e:
log.error(e)
sys.exit(ExitCode.input_file)
def triage_image_file(input_file, output_file, options, log):
log.info("Input file is not a PDF, checking if it is an image...")
try:
im = Image.open(input_file)
except EnvironmentError as e:
# Recover the original filename
log.error(str(e).replace(input_file, options.input_file))
raise UnsupportedImageFormatError() from e
with im:
log.info("Input file is an image")
if 'dpi' in im.info:
if im.info['dpi'] <= (96, 96) and not options.image_dpi:
log.info("Image size: (%d, %d)" % im.size)
log.info("Image resolution: (%d, %d)" % im.info['dpi'])
log.error(
"Input file is an image, but the resolution (DPI) is "
"not credible. Estimate the resolution at which the "
"image was scanned and specify it using --image-dpi."
)
raise DpiError()
elif not options.image_dpi:
log.info("Image size: (%d, %d)" % im.size)
log.error(
"Input file is an image, but has no resolution (DPI) "
"in its metadata. Estimate the resolution at which "
"image was scanned and specify it using --image-dpi."
)
raise DpiError()
if im.mode in ('RGBA', 'LA'):
log.error(
"The input image has an alpha channel. Remove the alpha "
"channel first."
)
raise UnsupportedImageFormatError()
if 'iccprofile' not in im.info:
if im.mode == 'RGB':
log.info("Input image has no ICC profile, assuming sRGB")
elif im.mode == 'CMYK':
log.error("Input CMYK image has no ICC profile, not usable")
raise UnsupportedImageFormatError()
try:
log.info("Image seems valid. Try converting to PDF...")
layout_fun = img2pdf.default_layout_fun
if options.image_dpi:
layout_fun = img2pdf.get_fixed_dpi_layout_fun(
(options.image_dpi, options.image_dpi)
)
with open(output_file, 'wb') as outf:
img2pdf.convert(
input_file, layout_fun=layout_fun, with_pdfrw=False, outputstream=outf
)
log.info("Successfully converted to PDF, processing...")
except img2pdf.ImageOpenError as e:
log.error(e)
raise UnsupportedImageFormatError() from e
def triage_image_file(input_file, output_file, log):
try:
log.info("Input file is not a PDF, checking if it is an image...")
im = Image.open(input_file)
except EnvironmentError as e:
log.error(e)
sys.exit(ExitCode.input_file)
return
else:
log.info("Input file is an image")
if 'dpi' in im.info:
if im.info['dpi'] <= (96, 96) and not options.image_dpi:
log.info("Image size: (%d, %d)" % im.size)
log.info("Image resolution: (%d, %d)" % im.info['dpi'])
log.error(
"Input file is an image, but the resolution (DPI) is "
"not credible. Estimate the resolution at which the "
"image was scanned and specify it using --image-dpi.")
sys.exit(ExitCode.input_file)
elif not options.image_dpi:
log.info("Image size: (%d, %d)" % im.size)
log.error(
"Input file is an image, but has no resolution (DPI) "
"in its metadata. Estimate the resolution at which "
"image was scanned and specify it using --image-dpi.")
sys.exit(ExitCode.input_file)
if 'iccprofile' not in im.info:
if im.mode == 'RGB':
log.info('Input image has no ICC profile, assuming sRGB')
elif im.mode == 'CMYK':
log.info('Input CMYK image has no ICC profile, not usable')
sys.exit(ExitCode.input_file)
im.close()
try:
log.info("Image seems valid. Try converting to PDF...")
layout_fun = img2pdf.default_layout_fun
if options.image_dpi:
layout_fun = img2pdf.get_fixed_dpi_layout_fun(
(options.image_dpi, options.image_dpi))
with open(output_file, 'wb') as outf:
img2pdf.convert(
input_file,
layout_fun=layout_fun,
with_pdfrw=False,
outputstream=outf)
log.info("Successfully converted to PDF, processing...")
except img2pdf.ImageOpenError as e:
log.error(e)
sys.exit(ExitCode.input_file)
def create_pdf_page_from_image(image, page_context):
# We rasterize a square DPI version of each page because most image
# processing tools don't support rectangular DPI. Use the square DPI as it
# accurately describes the image. It would be possible to resample the image
# at this stage back to non-square DPI to more closely resemble the input,
# except that the hocr renderer does not understand non-square DPI. The
# sandwich renderer would be fine.
output_file = page_context.get_path('visible.pdf')
dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
layout_fun = img2pdf.get_fixed_dpi_layout_fun((dpi, dpi))
# This create a single page PDF
with open(image, 'rb') as imfile, open(output_file, 'wb') as pdf:
page_context.log.debug('convert')
img2pdf.convert(
imfile, with_pdfrw=False, layout_fun=layout_fun, outputstream=pdf
)
page_context.log.debug('convert done')
return output_file
def make_rotate_test(prefix, image_angle, page_angle):
im = Image.open(fspath(resources / 'typewriter.png'))
if image_angle != 0:
ccw_angle = -image_angle % 360
im = im.transpose(getattr(Image, 'ROTATE_{}'.format(ccw_angle)))
memimg = BytesIO()
im.save(memimg, format='PNG')
memimg.seek(0)
mempdf = BytesIO()
img2pdf.convert(memimg.read(),
layout_fun=img2pdf.get_fixed_dpi_layout_fun(
(200, 200)),
outputstream=mempdf)
mempdf.seek(0)
pike = pikepdf.open(mempdf)
pike.pages[0].Rotate = page_angle
target = outdir / '{}_{}_{}.pdf'.format(prefix, image_angle,
page_angle)
pike.save(target)
return target
def make_rotate_test(prefix, image_angle, page_angle):
im = Image.open(fspath(resources / 'typewriter.png'))
if image_angle != 0:
ccw_angle = -image_angle % 360
im = im.transpose(getattr(Image, f'ROTATE_{ccw_angle}'))
memimg = BytesIO()
im.save(memimg, format='PNG')
memimg.seek(0)
mempdf = BytesIO()
img2pdf.convert(
memimg.read(),
layout_fun=img2pdf.get_fixed_dpi_layout_fun((200, 200)),
outputstream=mempdf,
)
mempdf.seek(0)
pike = pikepdf.open(mempdf)
pike.pages[0].Rotate = page_angle
target = outdir / f'{prefix}_{image_angle}_{page_angle}.pdf'
pike.save(target)
return target
def select_image_layer(infiles, output_file, log, pdfinfo, pdfinfo_lock):
page_pdf = next(ii for ii in infiles if ii.endswith('.ocr.oriented.pdf'))
image = next(ii for ii in infiles if ii.endswith('.image'))
if lossless_reconstruction:
log.debug("{:4d}: page eligible for lossless reconstruction".format(
page_number(page_pdf)))
re_symlink(page_pdf, output_file)
else:
pageinfo = get_pageinfo(image, pdfinfo, pdfinfo_lock)
dpi = get_page_dpi(pageinfo)
dpi = float(dpi[0]), float(dpi[1])
layout_fun = img2pdf.get_fixed_dpi_layout_fun(dpi)
with open(image, 'rb') as imfile, \
open(output_file, 'wb') as pdf:
rawdata = imfile.read()
img2pdf.convert(rawdata,
with_pdfrw=False,
layout_fun=layout_fun,
outputstream=pdf)
elif len(
response.content
) < 1024: # 图书馆如果页码不存在，也会响应 HTTP 200，并返回一个 142 Bytes 的 content
print(pic_name + ' 超出页码范围')
pic_path_list.remove(pic_full_path)
PAGE_TYPE[type_i][2] = i - 1 # 设置页码数，合并 pdf 时用
break
else:
with open(pic_full_path, 'wb') as f:
f.write(response.content) # 写入图片
print(pic_name + ' 下载成功')
# 将图片合成为 pdf
print('开始生成 PDF……')
with open(PDF_PATH, "wb+") as f: # w+ 直接覆盖
layout_fun = img2pdf.get_fixed_dpi_layout_fun(
(300, 300)) # 固定 DPI，避免封面、正文 DPI 不同导致尺寸不同
f.write(img2pdf.convert(pic_path_list, layout_fun=layout_fun))
# 为 PDF 添加简单的书签
# from PyPDF2 import PdfFileReader, PdfFileWriter
# def _get_parent_bookmark(current_indent, history_indent, bookmarks):
# '''The parent of A is the nearest bookmark whose indent is smaller than A's
# '''
# assert len(history_indent) == len(bookmarks)
# if current_indent == 0:
# return None
# for i in range(len(history_indent) - 1, -1, -1):
# # len(history_indent) - 1 ===> 0
# if history_indent[i] < current_indent:
# return bookmarks[i]
# return None
