get stats of kickstarter' project

kickstat.py

#-*- coding:utf-8 -*-
__author__ = 'bluele'

from BeautifulSoup import BeautifulSoup as bs
import urllib
import requests
import re


class Project(object):

    def __init__(self, soup):
        self.soup = soup
        self.__name_pattern = re.compile(ur'^by\n(?P<name>.*)')

    def _parse_author(self, author_text):
        regx = self.__name_pattern.search(author_text)
        if not regx:
            raise ValueError(author_text)
        return regx.groupdict()['name']

    @property
    def name(self):
        """ プロジェクト名
        """
        if not hasattr(self, '__name'):
            self.__name = self.soup.find('h2', {
                'class': 'bbcard_name'
            }).find('strong').text
        return self.__name

    @property
    def author(self):
        """ 投稿者
        by\nを取り除く
        """
        if not hasattr(self, '__author'):
            self.__author = self._parse_author(
                self.soup.find('h2', {
                    'class': 'bbcard_name'
                }).find('span').text
            )
        return self.__author

    @property
    def funded(self):
        """ 目標金額に対する収集金額 """
        if not hasattr(self, '__funded'):
            self.__funded = self.soup.find('li', {
                'class': 'first funded'
            }).find('strong').text
        return self.__funded

    @property
    def pledged(self):
        """ 収集金額
        """
        if not hasattr(self, '__pledged'):
            self.__pledged =  self.soup.find('li', {
                'class': 'pledged'
            }).find('strong').text
        return self.__pledged

    @property
    def deadline(self):
        """ 締め切り日時
        """
        if not hasattr(self, '__deadline'):
            self.__deadline =  self.soup.find('div', {
                'class': 'deadline'
            }).text
        return self.__deadline
    
    @property
    def url(self):
        """ プロジェクトのURL
        """
        raise NotImplementedError
        return None


def get_base_url(category, separate):
    url = 'http://www.kickstarter.com/discover/categories/%s/%s' % (urllib.quote(category), separate)
    print 'Analyze URL: %s' % url
    return url


def get_projects(soup):
    return soup.findAll('div', {
        'class': 'project-card'
    })

def process_content(soup):
    projects = list()
    for project_soup in get_projects(soup):
        projects.append(Project(project_soup))

    assert projects[0].name == 'IG Guitars. Designer Guitars You Personalise'
    assert projects[0].author == "Rob O'Reilly"
    assert projects[0].funded == '106%'
    assert projects[0].pledged == '$26,505'
    assert projects[0].deadline.upper() == 'APR 01, 2013'

    #for project in projects:
    #    pass

def get_page_number(soup):
    """ ページ数を返します
    """
    soup = soup.find('div', {
        'class': 'pagination'
    })
    links = soup.findAll('a')
    return int(links[-2].text)


def process(base_url):
    resp = requests.get(
        base_url,
        params={
            'page': 1
        }
    )
    soup = bs(resp.content)
    process_content(soup)
    return # DEBUG
    limit = get_page_number(soup)
    for page in xrange(2, limit+1):
        resp = requests.get(
            base_url,
            params={
                'page': page
            }
        )
        process_content(bs(resp.content))


def main():
    categories = [
        'product design',
    ]
    separates = [
        'successful',
        #'most-funded'
    ]
    for category in categories:
        for separate in separates:
            return process(get_base_url(category, separate))


if __name__ == '__main__':
    main()