#!/usr/bin/env python
from BeautifulSoup import BeautifulSoup, Tag, NavigableString
from PyRSS2Gen import RSSItem, Guid
import ScrapeNFeed
import string
import urllib
import datetime

class EatTheSeasonsFeed(ScrapeNFeed.ScrapedFeed):    

    def HTML2RSS(self, headers, body):
	link = "http://eattheseasons.co.uk"
        soup = BeautifulSoup(body)
	veggieContainer = soup.find('font', text="VEGETABLES").parent
	# Process the contents of veggieContainer -- scrub whitespace, replace '|' with readable tag elements
	#
	stripList = []
	veggieStrings = str(veggieContainer)
	veggieList = veggieStrings.split('|')
	for item in veggieList:
	        processed = item.strip() + r'</li><li>'
	        stripList.append(processed)
	# Read the processed contents of veggieContainer back into BeautifulSoup
	#
	soup = BeautifulSoup(''.join(stripList))
	breaks = soup.findAll('br')
	for item in breaks:
	        item.extract()
	text = soup.findAll(text=True)
	for item in text:
	        if item=='\n':
	                item.extract()
	soup.find(text='VEGETABLES').extract()
	# print soup.findAll(text=True) # (for debug)
	# Turn soup into an unordered list
	#
	newSoup = BeautifulSoup()
	tag1 = Tag(newSoup, "ul")
	tag2 = Tag(newSoup, "li")
	index = 0
	newSoup.insert(0, tag1)
	for item in soup.findAll(text=True):
		food = NavigableString("<li>"+item+r"</li>")
		tag1.insert(index, food)
		index = index + 1
	# print newSoup # (for debug)
	# Begin feed 
	items=[]
        items.append(RSSItem(title="Veggies for "+str(datetime.date.today()),
			     description=newSoup,
		      	     link=link))
        self.addRSSItems(items)

EatTheSeasonsFeed.load("Food In Season This Week",
                 'http://www.eattheseasons.co.uk',
                 "Keep track of the fruits and vegetables available at market this week!",
                 'seasonal.xml', 
		 'seasonal.pickle',
                 managingEditor='lev@mollusc.org (Lev Rickards)')