#!/usr/bin/python
#
ver=0.041
# This version not ready for prime time
# scrapes craigslist for work
# pflint Sat 19 Apr 2014 09:42:23 AM EDT 
#
# PYTHONIOENCODING=utf-8 # die unicode die
#
import os
import re
import sys
import stat
import optparse
import subprocess
import unicodedata
import doctest
import signal
import time
import io
import csv
import string
from subprocess import call
# from BeautifulSoup import BeautifulSoup
from bs4 import BeautifulSoup
import urllib2
# base="https://montreal.fr.craigslist.ca/search/"
cityw = {
	'Burlington VT':'https://burlington.craigslist.org/search/',
	'Washington DC':'https://washingtondc.craigslist.org/search/',
	'New York NY':'https://newyork.craigslist.org/search/',
	'Montreal CA':'https://montreal.fr.craigslist.ca/search/',
	'Albany NY':'https://albany.craigslist.org/search/',
	'Eastern CT':'https://newlondon.craigslist.org/search/',
	'Hartford CT':'https://hartford.craigslist.org/search/',
	'New Haven CT':'https://newhaven.craigslist.org/search/',
	'Northwest CT':'https://nwct.craigslist.org/search/',
	}
#	'':'',
# divider
#    	  }
# norun=  {
#
# 2014-10-06 08:02:24 spec changes...
# specs =['eng','sad','sof','tsh']
specs =['eng','sad','sof','tch']
for key, value in dict.items(cityw):
	# print key,value
	city=key
	base=value
	# print city+"\t"+base 
	for spec in specs:
		url=base+spec+"?is_telecommuting=1"
		# +"?addOne=telecommuting"
		# print url
		# Create the soup
		# Guidance on soup https://www.crummy.com/software/BeautifulSoup/bs4/doc/
		# Local guidance: http://docbox.flint.com:8081/boj#BeautifulsoupInstall
		# Additional Guidance:  http://docbox.flint.com:8081/boj#PythonBased
		# Past Programs: http://docbox.flint.com:8081/boj#programs
		# 2014-10-06 08:03:39 need error checking on open!!!
		page=urllib2.urlopen(url)
		soup = BeautifulSoup(page.read())
		# print(soup.prettify())
		# print(soup.title)
		#Search the soup
		# 2014-10-06 08:06:57 need a filter list.
		# print(soup.find_all('a'))
		# sline = soup.find_all('a',{'class':'row'})
		sline = soup.find_all('a')
		# sline = soup.findAll('p',{'class':'row'})
		# print sline
		# print('<p> '+city+' '+spec+' </p>')	
		# print('<base href="'+base+'">')
		burl='href="'+base[0:(len(base)-7)]
		# print burl
		# dline is a unicode bs4.element.Tag
		for dinstance in sline:
			udl=dinstance.encode("utf-8")
			mline=str([udl])
			dline=mline[2:(len(mline)-2)]
			print string.replace(dline,'href="/',burl);