0.py

#-*- coding:utf-8 -*-

import requests
import re
import os
import webbrowser
import time

RE_URL = "http://www.dm5.com/m([0-9]*)/"
RE_PAGE = 'm[0-9]*?-p([0-9]*?)/'

info_base = 'http://www.dm5.com/m%s/chapterfun.ashx?cid=%s&page=%s'

def get_url(url):
	if os.popen('node') == '':
		print 'Error - node required'
		return 'E',[]
	urls = re.findall(RE_URL,url)
	if urls == []:
		print 'Error - illegal url'
		return 'E',[]
	else:
		id = urls[0]
	webbrowser.open_new(url)
	time.sleep(3)
	session = requests.session()
	page = session.get(url).content
	page_no = re.findall(RE_PAGE,page)
	return_list = []
	max = 0
	for no in page_no:
		if int(no)>max:
			max = int(no)
	for i in range(1,max+1):
		page_url = info_base%(id,id,i,)
		Script = session.get(page_url).content#.replace('return p','console.log(p)')
		print Script
		FileHandle=open('Script.js','w')
		Script='console.log('+Script.strip()+')'
		FileHandle.write(Script)
		FileHandle.close()
		RunScript='node Script.js'
		Result=os.popen(RunScript).read()
		os.remove('Script.js')
		try:
			temp_list = eval(Result)
		except:
			print Result
		return_list = return_list + temp_list
	return return_list

get_url('http://www.dm5.com/m178597/')