php与python实现的线程池多线程爬虫功能示例

本文实例讲述了php与python实现的线程池多线程爬虫功能。分享给大家供大家参考，具体如下：

多线程爬虫可以用于抓取内容了这个可以提升性能了，这里我们来看php与python 线程池多线程爬虫的例子，代码如下：

php例子

<?php
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; //定义抓取的连接
$check_urls = array( 'http://xxx.com' => "xx网",);
$pool = new pool(10, "connect", array()); //建立10个线程池
foreach ($check_urls as $url => $name)
{
$pool->submit(new query($url));
}
$pool->shutdown();
}
check_urls_multi_pthreads();
python 多线程
def handle(sid)://这个方法内执行爬虫数据处理
pass
class mythread(thread):
"""docstring for classname"""
def __init__(self, sid):
thread.__init__(self)
self.sid = sid
def 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 线程池爬虫：

from queue import queue
from threading import thread, lock
import urllib.parse
import socket
import re
import time
seen_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))

更多关于php相关内容感兴趣的读者可查看本站专题：《php curl用法总结》、《php数组(array)操作技巧大全》、《php排序算法总结》、《php常用遍历算法与技巧总结》、《php数据结构与算法教程》、《php程序设计算法总结》、《php数学运算技巧总结》、《php正则表达式用法总结》、《php运算与运算符用法总结》、《php字符串(string)用法总结》及《php常见数据库操作技巧汇总》

希望本文所述对大家php程序设计有所帮助。