import reimport urllib.requestimport urllibfrom collections import dequequeue = deque()visited = set()url = ‘http://www.nutjs.com/‘# 初始抓取网站queue.append(url)cnt = 0 #抓取网页计数器while queue:    #队列循环bfs抓取    url = queue.popleft()    visited |= {url}     #去重，防止重复抓取    print(‘正在抓取:‘+ url)    cnt+=1    urlop = urllib.request.urlopen(url)    if ‘html‘ not in urlop.getheader(‘Content-Type‘): continue     #过滤出合法所需的文本    try:        data = urlop.read().decode(‘utf-8‘)    except:        continue        linkre = re.compile(‘href=http://www.mamicode.com/"(.+?)\"‘)    for x in linkre.findall(data):        # print(x)        if ‘http‘ in x and x not in visited:            queue.append(x)