環境搭建
使用語言 python3
安裝imagemagick(pdf轉jpg是内部需要調用到此工具)
apt-get install imagemagick
安裝libreoffice(此工具用于将word文檔轉化成pdf檔案)
apt-get install libreoffice
安裝python wand，PIL庫
pip install wand
pip install PIL
PDF轉JPG
先轉png，再轉jpg是為了避免出現黑色，透明等背景，造成轉換出來的圖檔與pdf檔案顯示不一樣
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為分辨率，background為背景顔色
with Image(filename=filename, resolution=150, background=Color('White')) as img :
#頁數
length = len(img.sequence)
#如果頁數超過1頁，生成的檔案名會依次加上頁碼數
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文檔轉PDF
python沒有直接把word轉換成pdf文檔的庫，隻能先安裝libreoffice工具，然後利用os庫系統調用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