2014-05-03_23-28-59.txt

# 1. "get information from google"
# 2. "parse json/xml"
# 3. "loop by tier"
# 4. "loop by component"
# 5. "split by name and link"
# ---
# Get data from Google Docs, parse the data, split by tier, each tier by components,
#     get a component and its name and link.

from xml.dom import minidom
from urllib.request import urlopen

COMPONENTS = ['gpu', 'cpu', 'hsf', 'mobo',
              'ram', 'hdd', 'ssd', 'psu', 'case']

TIERS = ['Destitute', 'Poor', 'Minimum', 'Entry', 'Modest',
         'Fair', 'Good', 'Very good', 'Great', 'Suberb',
         'Excellent', 'Outstanding', 'Exceptional', 'Enthusiast',
         'Extremist', 'Monstrous']

def get_text(parent, tagname):
    elements = parent.getElementsByTagName(tagname)
    if len(elements) != 0:
        element = elements[0]
        if element.hasChildNodes():
            return element.childNodes[0].data
        else:
            return ""
    else:
        return ""

class Component(object):

    def __init__(self, _type, name, price, link, tier=""):
        self.type = _type
        self.name = name
        self.price = round(float(price) + 0.2)
        self.link = link
        self.tier = tier

    def __eq__(self, other):
        return (self.type == other.type and self.name == other.name and
            self.price == other.price and self.link == other.link)

    def __repr__(self):
        return 'Component(name={!r})'.format(self.name)

class Tier(object):
    
    def __init__(self, name):
        self.name = name
        self.component_list = []

    def __contains__(self, other):
        if other in self.component_list:
            return True
        else:
            return False

    def __eq__(self, other):
        return self.name == other.name

    def __repr__(self):
        return 'Tier(name={!r})'.format(self.name)

    def add(self, component):
        if component not in self.component_list or component.name != "":
            component.tier = self.name
            self.component_list.append(component)

    def get(self, _type):
        result = []
        for component in component_list:
            if component.type == _type:
                result.append(component)
            else:
                continue
        return result

    def get_all(self):
        return self.component_list

    def from_entry(self, entry):
        for component in COMPONENTS:
            name = get_text(entry, 'gsx:' + component)
            price = 0
            link = ""
            if name not in ["", "Stock", "None"]:
                price = get_text(entry, 'gsx:' + component + 'price')
                link = get_text(entry, 'gsx:' + component + 'link')
                self.add(Component(component, name, price, link, self.name))
            else:
                continue


class Table(object):

    def __init__(self, entries):
        self.tiers = {}
        prev = ""
        for entry in entries:
            name = get_text(entry, 'gsx:tier')
            if name == "":
                tier = self.tiers[prev]
            else:
                tier = Tier(name)
            tier.from_entry(entry)
            self.tiers[tier.name] = tier
            prev = tier.name

    def __getitem__(self, tier):
        return self.tiers[tier]

    def __repr__(self):
        return 'Tiers: {!r}'.format(TIERS)


def get_entries(sheet):
    # convert to text
    xmldoc = minidom.parse(sheet)
    entries = xmldoc.getElementsByTagName('entry')
    return entries

sheet_url = "https://spreadsheets.google.com/feeds/list/1eI_N4YWuQRR3fCasrU7w9lDMPo15ayVL-MV40sE794g/od6/public/values"
# sheet_text = urlopen(sheet_url)
sheet_text = "values.xht"
entries = get_entries(sheet_text)

sheet = Table(entries)