convert/convert.py

# -*- coding: utf-8 -*-
import sys
sys.getdefaultencoding()
reload(sys)
sys.setdefaultencoding('UTF-8')
from demeter.core import *
import os
import os.path
import requests
import shutil

# 测试命令行传参 python convert.py -f file.doc
param = {}
param['file'] = 'f'
Demeter.getopt(param)

def command(file):
	id = int(file)
	model = Demeter.model('convert')
	model.id = id
	info = convert.select(type='fetchone')

	status = True
	if info['status'] == 1 or info['status'] == 4:
		status = False

	if info and status == False:
		model.id = id
		update = {}
		update['status'] = 2
		#model.update(update)

		if not File.exists(info['local']):
			if 'http' in info['file']:
				r = requests.get(info['file'], stream=True)
				with open(info['local'], 'wb') as up:
					for chunk in r.iter_content(chunk_size=1024):
						if chunk:
							up.write(chunk)

			else:
				shutil.copyfile(info['file'], info['local'])

		if not File.exists(info['html']):
			convert = 'cd ' + info['path'] + ' && '
			convert = convert + 'libreoffice  --invisible --convert-to pdf ' + info['local']
			convert = convert + ' && '
			convert = convert + 'pdf2htmlEX --zoom 1.3 --no-drm 1 --split-pages 1 '
			convert = convert + '--embed-css 1  --embed-javascript 0 --embed-image 0 --embed-font 1 '
			convert = convert + '--embed-external-font 0 --dest-dir '+info['path']+' --page-filename %d.page ' + info['pdf']

			print convert
			return
			Shell.popen(convert)
			if File.exists(info['html']):
				# 获取有多少页
				page = total(info['path'])
				model.id = id
				update = {}
				update['page'] = page
				update['status'] = 3
				model.update(update)
				return

		model.id = id
		update = {}
		update['status'] = 4
		model.update(update)
		


def total(path):
	page = 0
	for parentdir,dirname,filenames in os.walk(path):  
		for filename in filenames:
			if os.path.splitext(filename)[1]=='.page':
				page = page + 1
	return page

file = Demeter.option['file']
command(file)