# -*- Mode: Python; -*-
# -*- coding: utf-8 -*-
# vi:si:et:sw=2:sts=2:ts=2

import re

from BeautifulSoup import BeautifulSoup

from google import google
from utils import read_url, read_url_utf8, stripTags
import tvcom
import imdb

def epguidesUrl(title):
  ''' 
    Search Epguide Url for Show via Show Title.
    Use Google to search the url, this is also done on Epguide.
  '''
  for (name, url, desc) in google('allintitle: site:epguides.com %s' % title, 1):
    if url.startswith('http://epguides.com'):
      if re.search(title, name):
        return url
  return None

def getShowImdb(title):
  imdbid = None
  url = epguidesUrl(title)
  if url:
    data = read_url(url)
    soup = BeautifulSoup(data)
    links = soup('a', {'href': re.compile('imdb.com/title/tt')})
    if links:
      link = links[0].get('href')
      imdbid = "%07d" % int(re.compile('title/tt(\d*)').findall(link)[0])
  if not imdbid:
    imdbid = imdb.guess(title)
  return imdbid
  
def getEpisodeData(title, episode, show_url = None):
  '''
    Collect information about an episode.
    
    Returns dict with title, show, description and episode
  '''
  episodeData = {
    'title': u'',
    'show': title,
    'description': u'',
    'episode': episode,
  }
  description = u''
  data = u''
  if not show_url:
    show_url = epguidesUrl(title)
  if show_url:
    data = read_url_utf8(show_url)
  else:
    return imdb.getEpisodeData(title, episode)
  estring =  u'' +episode.replace('S','').replace('E','-').replace('0',' ').strip()
  for line in data.split('\n'):
    a = line.split(estring)
    if len(a) == 2:
      soup = BeautifulSoup(line)
      episodeData['title'] = soup('a')[0].contents[0]
      tvcom_url = soup('a')[0].get('href')
      episodeData['description'] = tvcom.getEpisodeData(tvcom_url)['description']
      break
  return episodeData