def crawl_add(seed, depth, index):
urls = web_crawler.crawl_web(seed, depth)
add_all_to_index(urls, index)
def crawl_build(seed, depth):
urls = web_crawler.crawl_web(seed, depth)
return build_index(urls)
# -*- coding: utf-8 -*-
import argparse
from web_crawler import crawl_web
if __name__ == '__main__':
arg_parser = argparse.ArgumentParser()
arg_parser.add_argument('seed_url')
args = arg_parser.parse_args()
crawl_web(args.seed_url, 2)
# -*- coding: utf-8 -*-
__author__ = 'masashi'
from web_crawler import crawl_web
if __name__ == '__main__':
crawl_web('http://docs.sphinx-users.jp/contents.html', 2)
# -*- coding: utf-8 -*-
from web_crawler import crawl_web
if __name__ == '__main__':
crawl_web('https://wikidocs.net/book/1', 2)
