import re
import urllib.request
import urllib.parse
from bs4 import BeautifulSoup


class UrlManager(object):
  def __init__(self):
    self.new_urls = set()
    self.old_urls = set()

  def add_new_url(self, url):
    if url is None:
      return
    if url not in self.new_urls and url not in self.old_urls:
      self.new_urls.add(url)

  def add_new_urls(self, urls):
    if urls is None or len(urls) == 0:
      return
    for url in urls:
      self.add_new_url(url)

  def has_new_url(self):
    return len(self.new_urls) != 0

  def get_new_url(self):
    new_url = self.new_urls.pop()
    self.old_urls.add(new_url)
    return new_url

class HtmlDownloader(object):
  def download(self, url):
    if url is None:
      return None
    try:
      request = urllib.request.Request(url)
      response = urllib.request.urlopen(request)
      content = response.read().decode('utf-8').encode('utf-8')
      if content is None:
        return None
      if response.getcode() != 200:
        return None
    except urllib.request.URLError as e:
      print(e)
      return None

    return content

links = soup.find_all('a', href=re.compile(r'^(%s).*(/|html)$' % self.domain))`

class HtmlParser(object):
  def __init__(self, domain_url):
    self.domain = domain_url
    self.res = HtmlDownloader()

  def _get_new_urls(self, page_url, soup):
    new_urls = set()
    links = soup.find_all('a', href=re.compile(r'^(%s).*(/|html)$' % self.domain))

    try:
      for link in links:
        new_url = link['href']
        new_full_url = urllib.parse.urljoin(self.domain, new_url)
        new_urls.add(new_full_url)

      new_urls = list(new_urls)
      return new_urls
    except AttributeError as e:
      print(e)
      return None

  def _get_new_content(self, page_url, soup):
    try:
      title_name = soup.title.string
      return title_name
    except AttributeError as e:
      print(e)
      return None

  def get_url_title(self):
    content = self.res.download(self.domain)

    try:
      soup = BeautifulSoup(content, 'html.parser', from_encoding='utf-8')
      title_name = soup.title.string
      return title_name
    except:
      title_name = 'None Title'
      return title_name

  def parse(self, page_url, html_cont):
    if page_url is None or html_cont is None:
      return None

    soup = BeautifulSoup(html_cont, 'html.parser', from_encoding='utf-8')
    new_data = self._get_new_content(page_url, soup)
    new_urls = self._get_new_urls(page_url, soup)

    return new_urls, new_data

class BuildIndex(object):
  def add_page_index(self, index, url, content):
    words = content.split()
    for word in words:
      index = self.add_key_index(index, url, word)
    return index

  def add_key_index(self, index, url, keyword):
    if keyword in index:
      if url not in index[keyword]:
        index[keyword].append(url)
    else:
      temp = []
      index[keyword] = temp
      index[keyword].append(url)
    return index

class SpiderMain(object):
  def __init__(self, root_url):
    self.root_url = root_url
    self.urls = UrlManager()
    self.downloader = HtmlDownloader()
    self.parser = HtmlParser(self.root_url)
    self.build = BuildIndex()

  def craw(self):
    index = graph = {}
    self.urls.add_new_url(self.root_url)
    while self.urls.has_new_url():
      try:
        new_url = self.urls.get_new_url()
        html_cont = self.downloader.download(new_url)
        new_urls, new_title = self.parser.parse(new_url, html_cont)
        index = self.build.add_page_index(index, new_url, new_title)
        graph[new_url] = list(new_urls)
        self.urls.add_new_urls(new_urls)
      except Exception as e:
        print(e)
        return None

    return index, graph

if __name__ == '__main__':
  spider = SpiderMain('http://www.xael.org/')
  index, graph = spider.craw()
  print(index)
  print(graph)