麻豆小视频在线观看_中文黄色一级片_久久久成人精品_成片免费观看视频大全_午夜精品久久久久久久99热浪潮_成人一区二区三区四区

首頁 > 編程 > Python > 正文

php與python實現的線程池多線程爬蟲功能實例詳解

2020-03-22 19:01:15
字體:
來源:轉載
供稿:網友
這篇文章主要介紹了php與python實現的線程池多線程爬蟲功能,結合實例形式分析了php與python實現線程池多線程爬蟲的完整實現方法,需要的朋友可以參考下

多線程爬蟲可以用于抓取內容了這個可以提升性能了,這里我們來看php與python 線程池多線程爬蟲的例子,代碼如下:

php例子

<?phphtml' target='_blank'>class Connect extends Worker //worker模式{public function __construct(){}public function getConnection(){if (!self::$ch){self::$ch = curl_init();curl_setopt(self::$ch, CURLOPT_TIMEOUT, 2);curl_setopt(self::$ch, CURLOPT_RETURNTRANSFER, 1);curl_setopt(self::$ch, CURLOPT_HEADER, 0);curl_setopt(self::$ch, CURLOPT_NOSIGNAL, true);curl_setopt(self::$ch, CURLOPT_USERAGENT, "Firefox");curl_setopt(self::$ch, CURLOPT_FOLLOWLOCATION, 1);}/* do some exception/error stuff here maybe */return self::$ch;}public function closeConnection(){curl_close(self::$ch);}/*** Note that the link is stored statically, which for pthreads, means thread local* */protected static $ch;}class Query extends Threaded{public function __construct($url){$this->url = $url;}public function run(){$ch = $this->worker->getConnection();curl_setopt($ch, CURLOPT_URL, $this->url);$page = curl_exec($ch);$info = curl_getinfo($ch);$error = curl_error($ch);$this->deal_data($this->url, $page, $info, $error);$this->result = $page;}function deal_data($url, $page, $info, $error){$parts = explode(".", $url);$id = $parts[1];if ($info['http_code'] != 200){$this->show_msg($id, $error);} else{$this->show_msg($id, "OK");}}function show_msg($id, $msg){echo $id."/t$msg/n";}public function getResult(){return $this->result;}protected $url;protected $result;}function check_urls_multi_pthreads(){global $check_urls; //定義抓取的連接$check_urls = array( 'http://xxx.com' => "xx網",);$pool = new Pool(10, "Connect", array()); //建立10個線程池foreach ($check_urls as $url => $name){$pool->submit(new Query($url));}$pool->shutdown();}check_urls_multi_pthreads();python 多線程def handle(sid)://這個方法內執行爬蟲數據處理passclass MyThread(Thread):"""docstring for ClassName"""def __init__(self, sid):Thread.__init__(self)self.sid = siddef run():handle(self.sid)threads = []for i in xrange(1,11):t = MyThread(i)threads.append(t)t.start()for t in threads:t.join()

python 線程池爬蟲:

from queue import Queuefrom threading import Thread, Lockimport urllib.parseimport socketimport reimport timeseen_urls = set(['/'])lock = Lock()class Fetcher(Thread):  def __init__(self, tasks):    Thread.__init__(self)    self.tasks = tasks    self.daemon = True    self.start()  def run(self):    while True:      url = self.tasks.get()      print(url)      sock = socket.socket()      sock.connect(('localhost', 3000))      get = 'GET {} HTTP/1.0/r/nHost: localhost/r/n/r/n'.format(url)      sock.send(get.encode('ascii'))      response = b''      chunk = sock.recv(4096)      while chunk:        response += chunk        chunk = sock.recv(4096)      links = self.parse_links(url, response)      lock.acquire()      for link in links.difference(seen_urls):        self.tasks.put(link)      seen_urls.update(links)      lock.release()      self.tasks.task_done()  def parse_links(self, fetched_url, response):    if not response:      print('error: {}'.format(fetched_url))      return set()    if not self._is_html(response):      return set()    urls = set(re.findall(r'''(?i)href=["']?([^/s"'<>]+)''',               self.body(response)))    links = set()    for url in urls:      normalized = urllib.parse.urljoin(fetched_url, url)      parts = urllib.parse.urlparse(normalized)      if parts.scheme not in ('', 'http', 'https'):        continue      host, port = urllib.parse.splitport(parts.netloc)      if host and host.lower() not in ('localhost'):        continue      defragmented, frag = urllib.parse.urldefrag(parts.path)      links.add(defragmented)    return links  def body(self, response):    body = response.split(b'/r/n/r/n', 1)[1]    return body.decode('utf-8')  def _is_html(self, response):    head, body = response.split(b'/r/n/r/n', 1)    headers = dict(h.split(': ') for h in head.decode().split('/r/n')[1:])    return headers.get('Content-Type', '').startswith('text/html')class ThreadPool:  def __init__(self, num_threads):    self.tasks = Queue()    for _ in range(num_threads):      Fetcher(self.tasks)  def add_task(self, url):    self.tasks.put(url)  def wait_completion(self):    self.tasks.join()if __name__ == '__main__':  start = time.time()  pool = ThreadPool(4)  pool.add_task("/")  pool.wait_completion()  print('{} URLs fetched in {:.1f} seconds'.format(len(seen_urls),time.time() - start))        

鄭重聲明:本文版權歸原作者所有,轉載文章僅為傳播更多信息之目的,如作者信息標記有誤,請第一時間聯系我們修改或刪除,多謝。

發表評論 共有條評論
用戶名: 密碼:
驗證碼: 匿名發表
主站蜘蛛池模板: 在线成人影视 | 久久久久久久久久亚洲 | 99精品国产在热久久婷婷 | 亚洲视频在线免费看 | 国产一区二区免费看 | 欧美精品v国产精品v日韩精品 | 7777网站| 久久艹精品 | 久久精品久久精品国产大片 | 久久精品艹| av日韩一区二区 | 日韩黄色片免费看 | 欧美成人性生活片 | 国产精品99久久久久久宅女 | 国产午夜精品视频免费不卡69堂 | 亚洲视频观看 | 国产精品观看在线亚洲人成网 | 毛片在线免费视频 | 黄色免费大片 | 91 在线免费观看 | 亚洲第五色综合网 | 毛片118极品美女写真 | 久久人体| 欧美精品一区二区久久 | 欧洲精品久久久 | 亚洲国产高清自拍 | 在线观看免费视频麻豆 | 国产一区二区视频观看 | 国产91丝袜在线熟 | 一区二区视 | 一级黄片毛片免费看 | 91精品久久久久久久 | 成年人黄色免费网站 | 日本免费一区二区三区四区 | 久久免费观看一级毛片 | 久久九九热re6这里有精品 | 亚洲网站在线播放 | 在线日韩亚洲 | 看黄在线观看 | 久久国产精品一区 | 毛片大全|