from grab import Grab #from grab.tools import rex #import re

""" STRUCT of CATALOG
category ( 'Люстры и бра. Классика ')
subcategory  (catalog/144_ODEON_Italiya/)  named by vendor
  series   {catalog/144_ODEON_Italiya/ ,  ['/catalog/1648_seriya_Alicante', 'серия Alicante'], ['/catalog/1732_seriya_Palacio1', 'серия Palacio1']
               items   [attrib1 : value1, \
                        attrib2 : value2  ]
"""
BASE_URL = "http://www.svetlux.ru"
document_charset='Windows-1251'

items = {}
categories_urls = []
categories_raw = []
categories_text = []
subcategories = {}
subcategories_urls = []
subcategories_raw = []
subcategories_text = []
series = {} # key = subcategoryurl : [[url, title],[url, title]] items = {}


def check_url(url):
        """ Check url for BASE_URL, append it if BASE_URL is missing
        Adds / between BASE_URL and url
         Adds end /
        """
        result_url = url
        if not url.startswith('/') and not BASE_URL.endswith('/'):
                url = '/' + url
        if BASE_URL not in url:
                result_url = BASE_URL + url
        if not url.endswith('/') and not url.endswith('.jpg'):
                result_url += '/'
        return result_url

def get_categories_raw(url):
        url = check_url(url)
        g = Grab()
        g.go(url = url,document_charset=document_charset)
        found = g.doc.select('//*[@class="category"]/a')
        if found.exists:
                for elem in found:
                        categories_raw.append(elem.html()) # parse category list in HTML
                        categories_text.append(elem.text()) # parse clean text return None

def get_subcategories_raw(url):
        url = check_url(url)
        g = Grab()
        g.go(url = url, document_charset=document_charset)
        found = g.doc.select('//*[@class="subcat"]/a')
        if found.exists:
                for elem in found: # TODO replace dict with # if url
             #           subcategories[url] = [[value,key],]
                        subcategories_raw.append(elem.html())   # parse category list in HTML
                        subcategories_text.append(elem.text())  # parse clean text


def get_series(url): #get all series of category
    url = check_url(url)
    g = Grab()
    g.go(url = url, document_charset=document_charset)
    found = g.doc.select('//*[@class="saleitem"]') # [@class="saleitem"]/div[1]
    if found.exists:
        for ser in found:
            k = ser.select('./div[*]/div[@class="zagolovok"]')
            img = ser.select('//*[@class="img lazy"]')
            for elem in k:
                try:
                    value = elem.html()[32: (elem.html().index('/">') ) ]
                    key = elem.text()
                    if url in series.keys() and value not in series[url]:
                        series[url].append([value,key])
                    else:
                        series[url] = [[value,key],]
                        #print(elem.text())  # parse clean text
                except:
                        ValueError

def get_urls(raw, dest): #
        for elem in raw:
                print(elem)
                dest.append( str(elem [9:elem.index('style') - 3 ]))
        print(dest)

def get_items(url, verbose=None):
    url = check_url(url)
    g = Grab()
    g.go(url = url, document_charset=document_charset)
    found = g.doc.select('//*[@class="fleft name2p"]')
    item_buffer = {}
    if found.exists:
        for ser in found:
            item_url = ser.html()
            item_title = ser.text()
            item_url = item_url[item_url.index('><a href="')+10:item_url.index('"><div') ]
            img_url = ser.html()
            img_url = img_url[img_url.index(": url('/")+8:img_url.index("') no-") ]
            item_buffer['item_title'] = item_title
            item_buffer['item_url'] = item_url
            item_buffer['img_url'] = img_url
            item_buffer['price'] = get_price(item_url)
    if item_url in items.keys():
        for k,v in item_buffer.items():
            if k not in items[item_url]:
                items[item_url].append({})
                items[item_url][k] = v
    else:
        items[item_url] = {}
        for k,v in item_buffer.items():
            items[item_url][k] = v
    if verbose:
        print(item_buffer)
    return item_buffer

def get_all_items():   # Grab first page of attributes of Series
    for url in series:
        get_items(url[1] + '/')
    print(items)


def get_item_table(item_url, verbose = None):
    item_url = check_url(item_url)
    g = Grab()
    g.go(url = item_url, document_charset=document_charset)
    found = g.doc.select('//*[@id="main"]/div[1]/div[2]/div[1]/table')
    item_buffer = {}
    if found.exists:
        result = []
        text = found.html()
        new_text = []
        for x in ['</table>','<table>','<b>','</b>','\n','<tr>']:
            text = text.replace(x,'')
            text = text.replace('</tr>','   ')

        text = text.split('   ')
        for a in text:
            new_text.append(a.replace('</td><td>','    '))
        for a in new_text:
            a = a.replace('<td>','')
            a = a.replace('</td>','')
            result.append(a)
        if verbose:
            print(result)   #  Вывод данных таблицы если входной verbose != None
        item_params={}
        for i in result:
            item_params[i.partition('    ')[0]] = i.partition('    ')[2]

        items[item_url] = item_params
        print(items)

def get_price(url):
    check_url(url)
    url = check_url(url)
    g = Grab()
    g.go(url = url, document_charset=document_charset)
    found = g.doc.select('/html/body/div[6]/div/div[6]/div[3]/div[1]/div[2]/div[2]/div[2]/div/div[1]/span[1] ')
    for k in found:
        price = k.text()
    return price

def view(source_list):      #  print a list (can handle)
    print(source_list)  #  subcategories_urls, subcategories_raw,subcategories_text

def list_series(url_list):
    for elem in url_list:
        get_series(elem)



if __name__ == '__main__':
    get_categories_raw(BASE_URL) # tested OK get_urls(categories_raw, categories_urls)
    get_urls(categories_raw, categories_urls)   #  tested OK
    get_subcategories_raw(BASE_URL) #  tested OK
    get_urls(subcategories_raw, subcategories_urls)   #  tested OK

    #get_series(BASE_URL + '/catalog/144_ODEON_Italiya/')  #  tested OK
    #get_items(BASE_URL + '/catalog/1980_seriya_Valle/',1)  #  tested OK
    #print(items)
   #get_item_table('http://www.svetlux.ru/catalog/1980_seriya_Valle/8460_Nastolnaya_lampa_Valle/')
    get_series(subcategories_urls)
    #list_series(subcategories_urls)
   # view(categories_urls)
    view(series)
   # get_all_items()
    for i in items:
        get_item_table(i[0])