#!/usr/bin/python
# coding:utf8
# @IgnorePep8

import os
import sys
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)) + '/..')

from crawler.utils import server_list, get_http_url_list, get_hash_list, read_hid_list, write_hash_url_dic, read_hash_url_dic, wait_start_signal

def get_hid_server_url_list(hid, server):
    url_list = []
    url = '%s/ShowMovie.aspx?name=v&hid=%s&tn=v' % (server, hid)
    url_list = get_http_url_list(url)
    return url_list

def get_hid_url_list(hid):
    hid_url_list = []
    for server in server_list:
        hid_server_url_list = get_hid_server_url_list(hid, server)
        hid_url_list += hid_server_url_list
    hid_url_list = list(set(hid_url_list))
    return hid_url_list

def get_url_list(hid_list):
    url_list = []
    for hid in hid_list:
        hid_url_list = get_hid_url_list(hid)
        url_list += hid_url_list
        print 'HID: %s URL NUM: %s' % (hid, len(hid_url_list))
    url_list = list(set(url_list))
    print 'URL NUM: %s' % len(url_list)
    return url_list

def get_hash_url_dic(url_list):
    hash_url = {}
    for url in url_list:
        hash_list = get_hash_list(url)
        for hash_s in hash_list:
            l = hash_url.get(hash_s, [])
            l.append(url)
            hash_url[hash_s] = l
    for hash_s in hash_url.keys():
        hash_url[hash_s] = list(set(hash_url.get(hash_s, [])))
    return hash_url

def search_url(hash_s):
    hash_url = read_hash_url_dic()
    url_list = hash_url.get(hash_s, [])
    print 'HASH: %s\n%s' % (hash_s, '\t'+'\n\t'.join(url_list))
    open('result','a').write('HASH: %s\n%s' % (hash_s, '\t'+'\n\t'.join(url_list)))
    return url_list
    
def run():
    hid_list = read_hid_list()
    url_list = get_url_list(hid_list)
    hash_url = get_hash_url_dic(url_list)
    write_hash_url_dic(hash_url)

if __name__ == '__main__':
    #print 'WAITING FOR HID LIST......'
    #wait_start_signal()
    run()