def bmp_or_jpg_to_pdf(list_of_file_paths, destination_directory, delete_source=False):
operation_result = {}
invalid_file_paths = []
for files in list_of_file_paths:
if os.path.exists(files):
continue
else:
invalid_file_paths.append(files)
list_of_file_paths.remove(files)
for files in list_of_file_paths:
image = PyImage()
image.density("600")
image.read(files)
file_name = os.path.basename(files)
name, ext = os.path.splitext(file_name)
file_name_at_destination = os.path.join(destination_directory, name + ".pdf")
image.write(file_name_at_destination)
if delete_source is True:
for files in list_of_file_paths:
os.remove(files)
if not invalid_file_paths:
operation_result.update({"code": 0, "invalid_file_paths": "None"})
else:
invalid_files = ",".join(list_of_file_paths)
operation_result.update({"code": 1, "invalid_file_paths": invalid_files})
return operation_result
def main():
# os.environ["MAGICK_HOME"] = r"path_to_ImageMagick"
if len(sys.argv) == 1:
dirpath = '.'
else:
dirpath = sys.argv[1]
temp_dir = os.path.join(dirpath, '.temp')
if not os.path.exists(temp_dir):
os.mkdir(temp_dir)
for file_name in os.listdir(dirpath):
if not os.path.isfile(file_name) or not file_name.endswith('.pdf'):
continue
print('Converting file {} ...'.format(file_name))
in_path = os.path.join(dirpath, file_name)
with open(in_path, 'rb') as handle:
inputpdf = PdfFileReader(handle)
for i in xrange(inputpdf.numPages):
outputpdf = PdfFileWriter()
outputpdf.addPage(inputpdf.getPage(i))
new_file_name = file_name.replace('.pdf', '') + '_{}.pdf'.format(i)
new_in_path = os.path.join(temp_dir, new_file_name)
with open(new_in_path, 'wb') as handle:
outputpdf.write(handle)
output_file_name = new_file_name.replace('.pdf', '.jpeg')
output_path = os.path.join(dirpath, output_file_name)
p = Image()
p.density('1080')
p.read(os.path.abspath(new_in_path))
p.write(os.path.abspath(output_path))
os.remove(new_in_path)
os.rmdir(temp_dir)
def pdf2images(name):
np = getPdfNumPages(name)
for p in range(np):
i = Image()
i.density('200')
i.quality(100)
i.depth(24)
#i.backgroundColor(
#i.channel(
i.read(name + '[' + str(p) + ']')
i.write(name + str(p) + defaultImageExtension)
def main():
if len(sys.argv) < 2:
print('invalid usage!')
return
pdf_filename = sys.argv[1]
pdf = PdfFileReader(file(pdf_filename, "rb"))
npage = pdf.getNumPages()
fname = pdf_filename.split('/')[-1]
tmppath = '/dev/shm/'
for p in range(npage):
im = Image()
im.density('300')
im.read(pdf_filename + '[' + str(p) + ']')
im.write(tmppath + fname + '_' + str(p) + out_format)
def pdf2img(input_pdf, postfix='.png'):
img = Image(input_pdf)
img.density('300')
size = "%sx%s" % (img.columns(), img.rows())
output_img = Image(size, bgcolor)
output_img.type = img.type
output_img.composite(img, 0, 0,
PythonMagick.CompositeOperator.SrcOverCompositeOp)
output_img.resize(str(img.rows()))
output_img.magick('JPG')
output_img.quality(75)
output_jpg = input_pdf.replace(".pdf", postfix)
if os.path.exists(output_jpg):
os.remove(output_jpg)
output_img.write(output_jpg)
class Answers:
def __init__(self, filename, i):
self.image = Image()
self.image.density('%d' % DENSITY)
self.image.read('%s[%d]' % (filename, i))
temp = tempfile.NamedTemporaryFile(suffix='.png')
self.image.write(temp.name)
self.pimage = pygame.image.load(temp.name)
temp.close()
def draw(self, screen, C):
pygame.draw.rect(screen, (255, 255, 255), (0, 0, W, H), 0)
scaled = self.pimage
screen.blit(scaled, (0, 0), (C[0], C[1], C[2] - C[0], C[3] - C[1]))
pygame.display.flip()
class Answers:
def __init__(self, filename, i):
self.image = Image()
self.image.density('%d' % DENSITY)
self.image.read('%s[%d]' % (filename, i))
temp = tempfile.NamedTemporaryFile(suffix='.png')
self.image.write(temp.name)
self.pimage = pygame.image.load(temp.name)
temp.close()
def draw(self, screen, C):
pygame.draw.rect(screen, (255, 255, 255), (0, 0, W, H), 0)
scaled = self.pimage
screen.blit(scaled, (0, 0), (C[0], C[1], C[2] - C[0], C[3] - C[1]))
pygame.display.flip()
def pdf2img(input_pdf, postfix='.png', **kwargs):
# print os.path.exists(input_pdf)
img = Image(input_pdf)
img.density('300')
size = "%sx%s" % (img.columns(), img.rows())
output_img = Image(size, bgcolor)
output_img.type = img.type
output_img.composite(img, 0, 0,
PythonMagick.CompositeOperator.SrcOverCompositeOp)
output_img.resize(str(img.rows()))
output_img.magick('JPG')
output_img.quality(75)
if 'out_path' in kwargs:
output_jpg = kwargs['out_path']
else:
output_jpg = input_pdf + postfix
if os.path.exists(output_jpg):
os.remove(output_jpg)
output_img.write(output_jpg)
def pdf2jpg(pdf,temp):
#Generate the path for the jpg file. Need to use a temp directory in case
#pdf location is read only.
pdf = str(pdf)
base = os.path.basename(pdf)
basefile = os.path.splitext(base)
jpg = temp + basefile[0] + ".jpg"
#jpg = str(jpg.replace("\\","\\\\"))
jpg = str(jpg)
pdf = str(pdf)
img = PMImage()
img.density('300')
img.depth(24)
img.read(pdf)
img.write(jpg)
img = Image.open(jpg)
rgbimg = Image.new("RGBA", img.size)
rgbimg.paste(img)
rgbimg.save(jpg)
return jpg
def pdf_to_image():
for pdf in [
pdf_file for pdf_file in os.listdir(pdf_dir)
if pdf_file.endswith(".pdf")
]:
input_pdf = pdf_dir + "\\" + pdf + "[1]"
img = Image()
img.density('300')
print input_pdf
img.read(input_pdf)
size = "%sx%s" % (img.columns(), img.rows())
output_img = Image(size, bg_colour)
output_img.type = img.type
output_img.composite(img, 0, 0,
PythonMagick.CompositeOperator.SrcOverCompositeOp)
output_img.resize(str(img.rows()))
output_img.magick('JPG')
output_img.quality(75)
output_jpg = input_pdf.replace(".pdf", ".jpg")
output_img.write(output_jpg)
def pdftojpg(fname):
reader = PdfFileReader(open(fname, "rb"))
directory = os.path.basename(fname)
if not os.path.exists(directory):
os.makedirs(directory)
else:
shutil.rmtree(directory)
time.sleep(2)
os.makedirs(directory)
for page_num in range(reader.getNumPages()):
writer = PdfFileWriter()
writer.addPage(reader.getPage(page_num))
temp = NamedTemporaryFile(prefix=str(page_num), suffix=".pdf", delete=False)
writer.write(temp)
temp.close()
im = Magick_Image()
im.density("300") # DPI, for better quality
im.read(temp.name)
im.write(directory+"/some%d.jpg" % (int(page_num)+1))
os.remove(temp.name)
return(directory)
def convert(args):
dirname = getcwd()
ifilename = path.join(
dirname, args.ifile) if not path.isabs(args.ifile) else args.ifile
ofilename = path.join(
dirname, args.ofile) if not path.isabs(args.ofile) else args.ofile
ofilename_n_ext = path.splitext(ofilename)[0]
reader = PdfFileReader(open(ifilename, "rb"))
for page_num in xrange(reader.getNumPages()):
writer = PdfFileWriter()
writer.addPage(reader.getPage(page_num))
with open(path.join(dirname, 'temp.pdf'), 'wb') as temp:
writer.write(temp)
im = Image()
im.density("300") # DPI, for better quality
im.backgroundColor('white')
im.fillColor('white')
im.read(path.join(dirname, 'temp.pdf'))
im.write("%s_%d.jpg" % (ofilename_n_ext, page_num))
remove(path.join(dirname, 'temp.pdf'))
DPI='85'
APP_ID='??'
API_KEY='??'
SECRET_KEY='??'
path_wk=r'pdfkit安装位置设置'
pdfkit_config=pdfkit.configuration(wkhtmltopdf=path_wk)
pdfkit_options={'encoding':'UTF-8',}
os.chdir(path)
pdf_input=PdfFileReader(open(pdfname, 'rb'))
page_count=pdf_input.getNumPages()
page_range=range(page_count)
for page_num in page_range:
im=Image()
im.density(DPI)
im.read(pdfname + '[' + str(page_num) +']')
im.write(str(page_num)+ '.jpg')
client=AipOcr(APP_ID, API_KEY, SECRET_KEY)
def get_file_content(filePath):
with open(filePath, 'rb') as fp:
return fp.read()
options={}
options["language_type"]="CHN_ENG"
options["detect_direction"]="false"
options["detect_language"]="false"
options["probability"]="false"
allteststr=[]
for page_num in page_range:
dir, fname = os.path.split(_pdf_path)
base, ext = os.path.splitext(fname)
out_base, _ = os.path.splitext(_pdf_path)
# convert the pdf file to the jpg images
command = 'pdftoppm %s %s -jpeg' % (_pdf_path.replace(
' ', '\ '), out_base.replace(' ', '\ '))
os.system(command)
paths = []
# convert the jpg files to the list of cv image
for f in os.listdir(dir):
path = os.path.join(dir, f)
if os.path.exists(path) and f.find(
base) != -1 and os.path.splitext(f)[1].find('jpg') != -1:
paths.append(path)
return paths
if __name__ == '__main__':
import os, PythonMagick
from PythonMagick import Image
from datetime import datetime
bg_colour = "#ffffff"
input_pdf = pdf_dir + "\\" + pdf
img = Image()
img.density('300')
img.read(input_pdf)
def tiff_to_pdf(list_of_file_paths, destination_directory):
"""
This method converts individual TIFF image files to PDF.
:param list_of_file_paths: This argument is the list of absolute file paths for example
['C:/User/Documents/Images/Image1.tiff', 'C:/User/Documents/Images/Image2.tiff' ]
:param destination_directory: Pass in the absolute path to the directory you want the
converted files to be saved to.
:return: This method returns a dictionary giving information about the success or failure
of the operation and also gives the list of files that failed the conversion..
"""
operation_result = {}
invalid_file_paths = []
for files in list_of_file_paths:
if os.path.exists(files):
continue
else:
invalid_file_paths.append(files)
list_of_file_paths.remove(files)
if not os.path.exists(os.path.join(os.getcwd(), "temp_dir")):
os.mkdir(os.path.join(os.getcwd(), "temp_dir"))
path_to_temp = os.path.join(os.getcwd(), "temp_dir")
for image in list_of_file_paths:
temp_file_list = []
img = Image.open(image)
tif_file_full_name = os.path.basename(image)
tif_file_name, tif_file_ext = os.path.splitext(tif_file_full_name)
for i in range(100):
try:
img.seek(i)
temp_file_list.append(os.path.join(path_to_temp, 'page' + str(i + 1) + ".tif"))
img.save(os.path.join(path_to_temp, 'page' + str(i + 1) + ".tif"))
except EOFError:
break
png_temp_array = []
for tif_img in temp_file_list:
img_png = Image.open(tif_img)
file_name = os.path.basename(tif_img)
name, ext = os.path.splitext(file_name)
file_name_at_destination = os.path.join(path_to_temp, name + ".png")
png_temp_array.append(file_name_at_destination)
img_png.save(file_name_at_destination)
os.remove(tif_img)
pdf_temp_array = []
for png_img in png_temp_array:
image = PyImage()
image.density("600")
image.read(png_img)
png_file_name = os.path.basename(png_img)
png_name, png_ext = os.path.splitext(png_file_name)
file_name_at_destination = os.path.join(path_to_temp, png_name + ".pdf")
pdf_temp_array.append(file_name_at_destination)
image.write(file_name_at_destination)
os.remove(png_img)
if pdf_temp_array.__len__() > 1:
ImageOpr.merge_pdf(pdf_temp_array, destination_directory, tif_file_name, delete_source=False)
for pdfs in pdf_temp_array:
os.remove(pdfs)
else:
os.rename(pdf_temp_array[0], os.path.join(path_to_temp, tif_file_name + ".pdf"))
destination_directory_file_name = os.path.join(destination_directory, tif_file_name + ".pdf")
shutil.move(os.path.join(path_to_temp, tif_file_name + ".pdf"), destination_directory_file_name)
shutil.rmtree(path_to_temp, ignore_errors=True)
if not invalid_file_paths:
operation_result.update({"code": 0, "invalid_file_paths": "None"})
else:
invalid_files = ",".join(list_of_file_paths)
operation_result.update({"code": 1, "invalid_file_paths": invalid_files})
return operation_result
class Map:
def __init__(self, map_path):
self._map_path = map_path
self._map_image = None
self._ocr = OCR()
self._x = 0.0
self._y = 0.0
self._width = 0.0
self._height = 0.0
# The OCR gets a bit buggy for scale factors
# smaller than 3 and bigger than 5.
self._scale_factor = 5
self._RefreshCoordinates()
def IsValid(self):
if self._x is 0 or self._y is 0:
return False
if self._width is 0 or self._height is 0:
return False
if self._width < 0.001 or self._width > 0.04:
return False
if self._height > -0.001 or self._height < -0.04:
return False
map_geometry = self._GetMapGeometry()
height_pixel_ratio = self.GetHeight() / map_geometry.height()
width_pixel_ratio = self.GetWidth() / map_geometry.width()
# The ratio should not be very different from each other, otherwise
# we OCR'ed one of the coordinates wrong.
if (abs(height_pixel_ratio) - abs(width_pixel_ratio)) > 0.0001:
return False
return True
def SetScaleFactor(self, factor):
if factor is self._scale_factor:
return
self._scale_factor = factor
if self._map_image:
self._GenerateImage()
self._RefreshCoordinates()
def GetMapImage(self):
return self._CropGeometry(self._GetMapGeometry())
def GetX(self):
if self._x:
return self._x
map_geometry = self._GetMapGeometry()
offset = _MAGIC_COORDINATE_OFFSET_ * self._scale_factor
width = _MAGIC_COORDINATE_BBOX_WIDTH_ * self._scale_factor
height = _MAGIC_COORDINATE_BBOX_HEIGHT_ * self._scale_factor
coordinate_geometry = Geometry(width, height, map_geometry.xOff(), map_geometry.yOff() - offset - height)
image = self._CropGeometry(coordinate_geometry)
self._x = self._ocr.GetDecimalDegrees(image)
return self._x
def GetY(self):
if self._y:
return self._y
map_geometry = self._GetMapGeometry()
offset = _MAGIC_COORDINATE_OFFSET_ * self._scale_factor
width = _MAGIC_COORDINATE_BBOX_HEIGHT_ * self._scale_factor
height = _MAGIC_COORDINATE_BBOX_WIDTH_ * self._scale_factor
coordinate_geometry = Geometry(width, height, map_geometry.xOff() - offset - width, map_geometry.yOff())
image = self._CropGeometry(coordinate_geometry)
image.rotate(90)
self._y = self._ocr.GetDecimalDegrees(image)
return self._y
def GetWidth(self):
if self._width:
return self._width
map_geometry = self._GetMapGeometry()
offset = _MAGIC_COORDINATE_OFFSET_ * self._scale_factor
width = _MAGIC_COORDINATE_BBOX_WIDTH_ * self._scale_factor
height = _MAGIC_COORDINATE_BBOX_HEIGHT_ * self._scale_factor
x_offset = map_geometry.xOff() + map_geometry.width()
y_offset = map_geometry.yOff() + map_geometry.height()
coordinate_geometry = Geometry(width, height, x_offset - width, y_offset + offset)
image = self._CropGeometry(coordinate_geometry)
self._width = self._ocr.GetDecimalDegrees(image) - self.GetX()
return self._width
def GetHeight(self):
if self._height:
return self._height
map_geometry = self._GetMapGeometry()
offset = _MAGIC_COORDINATE_OFFSET_ * self._scale_factor
width = _MAGIC_COORDINATE_BBOX_HEIGHT_ * self._scale_factor
height = _MAGIC_COORDINATE_BBOX_WIDTH_ * self._scale_factor
x_offset = map_geometry.xOff() + map_geometry.width()
y_offset = map_geometry.yOff() + map_geometry.height()
coordinate_geometry = Geometry(width, height, x_offset + offset, y_offset - height)
image = self._CropGeometry(coordinate_geometry)
image.rotate(90)
self._height = self._ocr.GetDecimalDegrees(image) - self.GetY()
return self._height
def _RefreshCoordinates(self):
if self.IsValid():
return
self._x = 0.0
self._y = 0.0
self._width = 0.0
self._height = 0.0
self.GetWidth()
self.GetHeight()
def _CropGeometry(self, geometry):
if not self._map_image:
self._GenerateImage()
image = Image(self._map_image)
image.crop(geometry)
return image
def _GetMapGeometry(self):
width = self.WIDTH - self.MARGIN_LEFT - self.MARGIN_RIGHT
height = self.HEIGHT - self.MARGIN_TOP - self.MARGIN_BOTTOM
width *= self._scale_factor
height *= self._scale_factor
margin_left = self.MARGIN_LEFT * self._scale_factor
margin_top = self.MARGIN_TOP * self._scale_factor
return Geometry(width, height, margin_left, margin_top)
def _GenerateImage(self):
scaled_density = 72 * self._scale_factor
self._map_image = Image()
self._map_image.density("%dx%d" % (scaled_density, scaled_density))
self._map_image.read(self._map_path)
import os
import ghostscript
from PyPDF2 import PdfFileReader, PdfFileWriter
from tempfile import NamedTemporaryFile
from PythonMagick import Image
reader = PdfFileReader(open('C:\\Users\\user\\Desktop\\fp\\1.pdf', "rb"))
for page_num in xrange(reader.getNumPages()):
writer = PdfFileWriter()
writer.addPage(reader.getPage(page_num))
temp = NamedTemporaryFile(prefix=str(page_num),
suffix=".pdf",
delete=False)
writer.write(temp)
print temp.name
tempname = temp.name
temp.close()
im = Image(tempname)
im.density("3000")
#im.read(tempname)
im.write("some_%d.jpg" % (page_num))
os.remove(tempname)
reader.close()
def upload():
if request.method == 'POST':
file = request.files['file']
name = os.path.splitext(file.filename)[0]
extension = os.path.splitext(file.filename)[1]
f_name = name + extension
if extension == ".pdf":
file.save(os.path.join(basedir,UPLOAD_FOLDER , f_name))
filepath = os.path.join('./upload', f_name)
os.makedirs(os.path.join("./images", name))
filepath1 = os.path.join('./images', name)
reader = PdfFileReader(open(filepath, "rb"))
for page_num in xrange(reader.getNumPages()):
writer = PdfFileWriter()
writer.addPage(reader.getPage(page_num))
temp = NamedTemporaryFile(prefix=str(page_num), suffix=".pdf", delete=False)
writer.write(temp)
temp.close()
im = Image()
im.density("300") # DPI, for better quality
im.read(temp.name)
im.write("images/%s/ %d.jpg" % (str(name), page_num))
os.remove(temp.name)
os.remove(filepath)
dirs = os.listdir(filepath1)
dict = {}
i = 0
dict["file_name"] = f_name
for file in dirs:
filepath2 = os.path.join(filepath1, file)
with io.open(filepath2, 'rb') as image_file:
content= base64.b64encode(image_file.read())
payload = {
"requests": [
{
"image": {
"content": content
},
"features": [
{
"type": "TEXT_DETECTION"
}
]
}
]
}
r = requests.post(url, data=json.dumps(payload))
r = json.loads(r.text)
r=r['responses'][0]['textAnnotations'][0]['description']
key = "page_no-" + str(file)
dict[key] = r
shutil.rmtree(filepath1)
return json.dumps(dict)
elif extension == '.png' or extension == '.jpg' or extension == '.jpeg':
dict = {}
dict["file_name"] = f_name
file.save(os.path.join(basedir, UPLOAD_FOLDER, f_name))
filepath = os.path.join('./upload', f_name)
with io.open(filepath, 'rb') as image_file:
content = base64.b64encode(image_file.read())
payload = {
"requests": [
{
"image": {
"content": content
},
"features": [
{
"type": "TEXT_DETECTION"
}
]
}
]
}
r = requests.post(url, data=json.dumps(payload))
r=json.loads(r.text)
r=r['responses'][0]['textAnnotations'][0]['description']
dict["text"] = r
os.remove(filepath)
return json.dumps(dict)
else:
return json.dumps({'file format is wrong': f_name})
return json.dumps({'file proess completed': f_name})
import os
from pyPdf import PdfFileReader, PdfFileWriter
from tempfile import NamedTemporaryFile
from PythonMagick import Image
import sys
pdfname=sys.argv[1]
#os.system("rm /tmp/test2/*")
#os.system("mkdir /tmp/test2")
cmd="cp /opt/%s /tmp/test2/ocr.pdf"%(pdfname)
#os.system("cp /opt/corrected.html /tmp/test2/some_0.hocr")
os.system(cmd)
reader = PdfFileReader(open("/tmp/test2/ocr.pdf", "rb"))
for page_num in xrange(reader.getNumPages()):
writer = PdfFileWriter()
writer.addPage(reader.getPage(page_num))
temp = NamedTemporaryFile(prefix=str(page_num), suffix=".pdf", delete=False)
writer.write(temp)
temp.close()
im = Image()
im.density("300") # DPI, for better quality
im.read(temp.name)
im.write("/tmp/test2/some_%d.jpg" % (page_num))
os.remove(temp.name)
