main.py

import threading
import Queue
from hngspider import HngSpider
from domain import *
from general import *

PROJECT_NAME = raw_input("Enter Project Name:")
HOMEPAGE = raw_input("Enter the url to the homepage: ")
DOMAIN_NAME = get_domain_name(HOMEPAGE)
QUEUE_FILE = PROJECT_NAME + '/queue.txt'
CRAWLED_FILE = PROJECT_NAME + '/crawled.txt'
NUMBER_OF_THREADS = int(input("Enter the number of threads \n(this is OS specific as well as hardware specific"
                              "so ensure you know what your doing):"))

queue = Queue.Queue()
HngSpider(PROJECT_NAME, HOMEPAGE, DOMAIN_NAME)


# Create the worker threads (will die when main exits)
def create_workers():
    for _ in range(NUMBER_OF_THREADS):
        t = threading.Thread(target=work)
        t.daemon = True
        t.start()


# Do the next job in the queue
def work():
    while True:
        url = queue.get()
        HngSpider.crawl_page(threading.current_thread().name, url)
        queue.task_done()


# Each queued link is a new job
def create_jobs():
    for link in file_to_set(QUEUE_FILE):
        queue.put(link)
    queue.join()
    crawl()


# Check if there are items in the queue, if so, crawl them
def crawl():
    queued_links = file_to_set(QUEUE_FILE)
    if len(queued_links) > 0:
        print(str(len(queued_links)) + ' links in the queue')
        create_jobs()

create_workers()
crawl()