# -*- coding: utf-8 -*-
from datetime import datetime
import sys
from os import environ
import urllib2
from re import findall

environ['DJANGO_SETTINGS_MODULE'] = 'settings'

import feedparser

from settings import *
from django.contrib.sessions.models import *
# proof-of-concept app
from diamandas.jobmaster.models import *

############
## Jobexpress
############
source = JobSource.objects.get(title='Jobexpress')
## IT

data = feedparser.parse('http://www.jobexpress.pl/recent,it,84.html')
if data and 'entries' in data:
	for elem in data['entries']:
		sum = elem['summary_detail']
		published = sum['value'].split(',')[0].strip().split('-')
		published = datetime(int(published[2]), int(published[1]), int(published[0]))
		company = sum['value'].split(',')[1].strip()
		
		opener = urllib2.build_opener()
		opener.addheaders = [('user-agent', 'Opera/9.64 (X11; Linux x86_64; U; en) Presto/2.1.1'), ('referer', 'http://www.jobexpress.pl/recent,it,84.html')]
		o = opener.open(elem['link'])
		of = o.read()
		text = findall(r'(?xs)<ul\s*class="oferta_pracy">(.*?)<!--\s*eof:\s*oferta''', str(of))
		if text and len(text) > 0:
			text = text[0]
			# cleaning
			text = '<ul>' + text
			text = text.replace('href="', 'href="http://www.jobexpress.pl/')
			text = text.replace('src="', 'src="http://www.jobexpress.pl/')
			
			city = findall(r'(?xs)<span\s*class="cv_label">Miejsce\s*pracy:\s*</span>(.*?)</li>''', text)
			try:
				city = city[0].strip()
			except:
				city = '???'
			
			# TODO
			region = 'Na bazie miasta'
			
			branch = 'Informatyka/Programowanie'
			try:
				j = JobOffer.objects.get(position=elem['title'], company=company, city=city)
			except:
				j = JobOffer(position=elem['title'], company=company, source=source, url=elem['link'], indexed_at=datetime.now(), updated_at=datetime.now(),
						published_on_source=published, city=city, region=region, branch=branch, offer=text)
				j.save()
			
				print u'ZAPISANO: %s' % elem['title']
			else:
				j.updated_at = datetime.now()
				j.offer=text
				j.save()
				print u'ZAKTUALIZOWANO: %s' % elem['title']
			

class JobSource(models.Model):
	"""
	Keeps a "list" of sites with job offers that are parsed by the application.
	Just for ease of data manipulation
	"""
	title = models.CharField(verbose_name='Tytuł', max_length=255)
	url = models.CharField(verbose_name='URL Strony głównej', max_length=255)
	css = models.TextField(verbose_name='Style CSS', blank=True)
	class Meta:
		verbose_name = 'Serwis z ofertami'
		verbose_name_plural = 'Serwisy z ofertami'
	def __str__(self):
		return self.title
	def __unicode__(self):
		return self.title

class JobOffer(models.Model):
	"""
	Indexed job offers from various sites
	"""
	position = models.CharField(verbose_name='Stanowisko', max_length=255)
	company = models.CharField(verbose_name='Firma', max_length=255)
	source = models.ForeignKey(JobSource, verbose_name='Źródło')
	url = models.CharField(verbose_name='URL oferty', max_length=255)
	indexed_at = models.DateTimeField(verbose_name='Data zaindeksowania oferty')
	updated_at = models.DateTimeField(blank=True, null=True, verbose_name='Data ostatniej aktualizacji')
	published_on_source = models.DateTimeField(blank=True, null=True, verbose_name='Data publikacji na stronie-źródle')
	is_inactive = models.BooleanField(blank=True, default=False, verbose_name='Oferta nieaktywna')
	city = models.CharField(verbose_name='Miasto', max_length=255)
	region = models.CharField(verbose_name='Województwo', max_length=255)
	branch = models.CharField(verbose_name='Branża', max_length=255)
	offer = models.TextField(verbose_name='Treść oferty')
	class Meta:
		verbose_name = 'Oferta'
		verbose_name_plural = 'Oferty'
	def __str__(self):
		return self.position
	def __unicode__(self):
		return self.position