php与python实现的线程池多线程爬虫功能实例详解-php教程-PHP中文网

首页

后端开发

php教程

php与python实现的线程池多线程爬虫功能实例详解

墨辰丷

Jun 01, 2018 am 09:57 AM

php python 爬虫

这篇文章主要介绍了php与python实现的线程池多线程爬虫功能,结合实例形式分析了php与python实现线程池多线程爬虫的完整实现方法,需要的朋友可以参考下

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[&#39;http_code&#39;] != 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( &#39;http://xxx.com&#39; => "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()

登录后复制

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([&#39;/&#39;])
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((&#39;localhost&#39;, 3000))
      get = &#39;GET {} HTTP/1.0\r\nHost: localhost\r\n\r\n&#39;.format(url)
      sock.send(get.encode(&#39;ascii&#39;))
      response = b&#39;&#39;
      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(&#39;error: {}&#39;.format(fetched_url))
      return set()
    if not self._is_html(response):
      return set()
    urls = set(re.findall(r&#39;&#39;&#39;(?i)href=["&#39;]?([^\s"&#39;<>]+)&#39;&#39;&#39;,
               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 (&#39;&#39;, &#39;http&#39;, &#39;https&#39;):
        continue
      host, port = urllib.parse.splitport(parts.netloc)
      if host and host.lower() not in (&#39;localhost&#39;):
        continue
      defragmented, frag = urllib.parse.urldefrag(parts.path)
      links.add(defragmented)
    return links
  def body(self, response):
    body = response.split(b&#39;\r\n\r\n&#39;, 1)[1]
    return body.decode(&#39;utf-8&#39;)
  def _is_html(self, response):
    head, body = response.split(b&#39;\r\n\r\n&#39;, 1)
    headers = dict(h.split(&#39;: &#39;) for h in head.decode().split(&#39;\r\n&#39;)[1:])
    return headers.get(&#39;Content-Type&#39;, &#39;&#39;).startswith(&#39;text/html&#39;)
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__ == &#39;__main__&#39;:
  start = time.time()
  pool = ThreadPool(4)
  pool.add_task("/")
  pool.wait_completion()
  print(&#39;{} URLs fetched in {:.1f} seconds&#39;.format(len(seen_urls),time.time() - start))

登录后复制

总结：以上就是本篇文的全部内容，希望能对大家的学习有所帮助。