环境搭建
使用语言 python3
安装imagemagick(pdf转jpg是内部需要调用到此工具)
apt-get install imagemagick
安装libreoffice(此工具用于将word文档转化成pdf文件)
apt-get install libreoffice
安装python wand,PIL库
pip install wand
pip install PIL
PDF转JPG
先转png,再转jpg是为了避免出现黑色,透明等背景,造成转换出来的图片与pdf文件显示不一样
from PIL import Image as Image2
from wand.image import Image
from wand.color import Color
def convert_pdf_to_jpg(filename):
end_length = len(filename.split('.')[-1]) + 1
title = filename[0:-end_length]
title = title.split('/')[-1]
#resolution为分辨率,background为背景颜色
with Image(filename=filename, resolution=150, background=Color('White')) as img :
#页数
length = len(img.sequence)
#如果页数超过1页,生成的文件名会依次加上页码数
with img.convert('png') as converted:
path = 'static/local_images/%s.png' % title
converted.save(filename=path)
image_list = []
if length == 1:
path = 'static/local_images/%s.png' % title
image_list.append(path)
else:
for i in range(0, length):
path = 'static/local_images/%s-%d.png' % (title, i)
image_list.append(path)
jpg_list = []
for img in image_list:
image = Image2.open(img)
x,y = image.size
background = Image2.new('RGBA', image.size, (255,255,255))
try:
background.paste(image, (0, 0, x, y), image)
image = background.convert('RGB')
except:
image = image.convert('RGBA')
background.paste(image, (0, 0, x, y), image)
image = background.convert('RGB')
title = img.split('.')[0]
name = title + '.jpg'
image.save(name)
os.remove(img)
name = "%s/%s" %(static_host, name)
jpg_list.append(name)
return jpg_list
word文档转PDF
python没有直接把word转换成pdf文档的库,只能先安装libreoffice工具,然后利用os库系统调用libreoffice工具
import os
def convert_doc_to_pdf(filename):
end_length = len(filename.split('.')[-1]) + 1
name = filename[0:-end_length]
cmd = 'libreoffice --convert-to pdf %s' % filename
os.system(cmd)
name = name.split('/')[-1] + '.pdf'
return name