schedule.html 22 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238
  1. <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
  2. "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
  3. <html xmlns="http://www.w3.org/1999/xhtml" lang="en">
  4. <head>
  5. <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  6. <title>proxypool.schedule &#8212; proxypool documentation</title>
  7. <link rel="stylesheet" href="../../_static/alabaster.css" type="text/css" />
  8. <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
  9. <script type="text/javascript">
  10. var DOCUMENTATION_OPTIONS = {
  11. URL_ROOT: '../../',
  12. VERSION: '',
  13. COLLAPSE_INDEX: false,
  14. FILE_SUFFIX: '.html',
  15. HAS_SOURCE: true
  16. };
  17. </script>
  18. <script type="text/javascript" src="../../_static/jquery.js"></script>
  19. <script type="text/javascript" src="../../_static/underscore.js"></script>
  20. <script type="text/javascript" src="../../_static/doctools.js"></script>
  21. <link rel="index" title="Index" href="../../genindex.html" />
  22. <link rel="search" title="Search" href="../../search.html" />
  23. <link rel="top" title="proxypool documentation" href="../../index.html" />
  24. <link rel="up" title="Module code" href="../index.html" />
  25. <link rel="stylesheet" href="../../_static/custom.css" type="text/css" />
  26. <meta name="viewport" content="width=device-width, initial-scale=0.9, maximum-scale=0.9" />
  27. </head>
  28. <body role="document">
  29. <div class="document">
  30. <div class="documentwrapper">
  31. <div class="bodywrapper">
  32. <div class="body" role="main">
  33. <h1>Source code for proxypool.schedule</h1><div class="highlight"><pre>
  34. <span></span><span class="sd">&quot;&quot;&quot;</span>
  35. <span class="sd">-------------------------------------------------</span>
  36. <span class="sd"> File Name: schedule.py</span>
  37. <span class="sd"> Description: 调度器模块,</span>
  38. <span class="sd"> 包含ValidityTester,PoolAdder,</span>
  39. <span class="sd"> Schedule三个类,负责维护代理池。</span>
  40. <span class="sd"> Author: Liu</span>
  41. <span class="sd"> Date: 2016/12/9</span>
  42. <span class="sd">-------------------------------------------------</span>
  43. <span class="sd">&quot;&quot;&quot;</span>
  44. <span class="kn">import</span> <span class="nn">time</span>
  45. <span class="kn">from</span> <span class="nn">multiprocessing</span> <span class="k">import</span> <span class="n">Process</span>
  46. <span class="kn">import</span> <span class="nn">asyncio</span>
  47. <span class="kn">import</span> <span class="nn">aiohttp</span>
  48. <span class="kn">from</span> <span class="nn">.db</span> <span class="k">import</span> <span class="n">RedisClient</span>
  49. <span class="kn">from</span> <span class="nn">.error</span> <span class="k">import</span> <span class="n">ResourceDepletionError</span>
  50. <span class="kn">from</span> <span class="nn">.proxyGetter</span> <span class="k">import</span> <span class="n">FreeProxyGetter</span>
  51. <span class="kn">from</span> <span class="nn">.setting</span> <span class="k">import</span> <span class="o">*</span>
  52. <div class="viewcode-block" id="ValidityTester"><a class="viewcode-back" href="../../proxypool.html#proxypool.schedule.ValidityTester">[docs]</a><span class="k">class</span> <span class="nc">ValidityTester</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
  53. <span class="sd">&quot;&quot;&quot;</span>
  54. <span class="sd"> 检验器,负责对未知的代理进行异步检测。</span>
  55. <span class="sd"> &quot;&quot;&quot;</span>
  56. <span class="c1"># 用百度的首页来检验</span>
  57. <span class="n">test_api</span> <span class="o">=</span> <span class="s1">&#39;https://www.baidu.com&#39;</span>
  58. <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
  59. <span class="bp">self</span><span class="o">.</span><span class="n">_raw_proxies</span> <span class="o">=</span> <span class="kc">None</span>
  60. <span class="bp">self</span><span class="o">.</span><span class="n">_usable_proxies</span> <span class="o">=</span> <span class="p">[]</span>
  61. <div class="viewcode-block" id="ValidityTester.set_raw_proxies"><a class="viewcode-back" href="../../proxypool.html#proxypool.schedule.ValidityTester.set_raw_proxies">[docs]</a> <span class="k">def</span> <span class="nf">set_raw_proxies</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">proxies</span><span class="p">):</span>
  62. <span class="sd">&quot;&quot;&quot;设置待检测的代理。</span>
  63. <span class="sd"> &quot;&quot;&quot;</span>
  64. <span class="bp">self</span><span class="o">.</span><span class="n">_raw_proxies</span> <span class="o">=</span> <span class="n">proxies</span>
  65. <span class="bp">self</span><span class="o">.</span><span class="n">_usable_proxies</span> <span class="o">=</span> <span class="p">[]</span></div>
  66. <div class="viewcode-block" id="ValidityTester.test_single_proxy"><a class="viewcode-back" href="../../proxypool.html#proxypool.schedule.ValidityTester.test_single_proxy">[docs]</a> <span class="k">async</span> <span class="k">def</span> <span class="nf">test_single_proxy</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">proxy</span><span class="p">):</span>
  67. <span class="sd">&quot;&quot;&quot;检测单个代理,如果可用,则将其加入_usable_proxies</span>
  68. <span class="sd"> &quot;&quot;&quot;</span>
  69. <span class="k">async</span> <span class="k">with</span> <span class="n">aiohttp</span><span class="o">.</span><span class="n">ClientSession</span><span class="p">()</span> <span class="k">as</span> <span class="n">session</span><span class="p">:</span>
  70. <span class="k">try</span><span class="p">:</span>
  71. <span class="n">real_proxy</span> <span class="o">=</span> <span class="s1">&#39;http://&#39;</span> <span class="o">+</span> <span class="n">proxy</span>
  72. <span class="k">async</span> <span class="k">with</span> <span class="n">session</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">test_api</span><span class="p">,</span> <span class="n">proxy</span><span class="o">=</span><span class="n">real_proxy</span><span class="p">,</span> <span class="n">timeout</span><span class="o">=</span><span class="mi">15</span><span class="p">)</span> <span class="k">as</span> <span class="n">resp</span><span class="p">:</span>
  73. <span class="bp">self</span><span class="o">.</span><span class="n">_usable_proxies</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">proxy</span><span class="p">)</span>
  74. <span class="k">except</span> <span class="ne">Exception</span><span class="p">:</span>
  75. <span class="k">pass</span></div>
  76. <div class="viewcode-block" id="ValidityTester.test"><a class="viewcode-back" href="../../proxypool.html#proxypool.schedule.ValidityTester.test">[docs]</a> <span class="k">def</span> <span class="nf">test</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
  77. <span class="sd">&quot;&quot;&quot;异步检测_raw_proxies中的全部代理。</span>
  78. <span class="sd"> &quot;&quot;&quot;</span>
  79. <span class="nb">print</span><span class="p">(</span><span class="s1">&#39;ValidityTester is working&#39;</span><span class="p">)</span>
  80. <span class="n">loop</span> <span class="o">=</span> <span class="n">asyncio</span><span class="o">.</span><span class="n">get_event_loop</span><span class="p">()</span>
  81. <span class="n">tasks</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">test_single_proxy</span><span class="p">(</span><span class="n">proxy</span><span class="p">)</span> <span class="k">for</span> <span class="n">proxy</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_raw_proxies</span><span class="p">]</span>
  82. <span class="n">loop</span><span class="o">.</span><span class="n">run_until_complete</span><span class="p">(</span><span class="n">asyncio</span><span class="o">.</span><span class="n">wait</span><span class="p">(</span><span class="n">tasks</span><span class="p">))</span></div>
  83. <div class="viewcode-block" id="ValidityTester.get_usable_proxies"><a class="viewcode-back" href="../../proxypool.html#proxypool.schedule.ValidityTester.get_usable_proxies">[docs]</a> <span class="k">def</span> <span class="nf">get_usable_proxies</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
  84. <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_usable_proxies</span></div></div>
  85. <div class="viewcode-block" id="PoolAdder"><a class="viewcode-back" href="../../proxypool.html#proxypool.schedule.PoolAdder">[docs]</a><span class="k">class</span> <span class="nc">PoolAdder</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
  86. <span class="sd">&quot;&quot;&quot;</span>
  87. <span class="sd"> 添加器,负责向池中补充代理</span>
  88. <span class="sd"> &quot;&quot;&quot;</span>
  89. <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">threshold</span><span class="p">):</span>
  90. <span class="bp">self</span><span class="o">.</span><span class="n">_threshold</span> <span class="o">=</span> <span class="n">threshold</span>
  91. <span class="bp">self</span><span class="o">.</span><span class="n">_conn</span> <span class="o">=</span> <span class="n">RedisClient</span><span class="p">()</span>
  92. <span class="bp">self</span><span class="o">.</span><span class="n">_tester</span> <span class="o">=</span> <span class="n">ValidityTester</span><span class="p">()</span>
  93. <span class="bp">self</span><span class="o">.</span><span class="n">_crawler</span> <span class="o">=</span> <span class="n">FreeProxyGetter</span><span class="p">()</span>
  94. <div class="viewcode-block" id="PoolAdder.is_over_threshold"><a class="viewcode-back" href="../../proxypool.html#proxypool.schedule.PoolAdder.is_over_threshold">[docs]</a> <span class="k">def</span> <span class="nf">is_over_threshold</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
  95. <span class="sd">&quot;&quot;&quot;</span>
  96. <span class="sd"> 判断代理池中的数据量是否达到阈值。</span>
  97. <span class="sd"> &quot;&quot;&quot;</span>
  98. <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_conn</span><span class="o">.</span><span class="n">queue_len</span> <span class="o">&gt;=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_threshold</span><span class="p">:</span>
  99. <span class="k">return</span> <span class="kc">True</span>
  100. <span class="k">else</span><span class="p">:</span>
  101. <span class="k">return</span> <span class="kc">False</span></div>
  102. <div class="viewcode-block" id="PoolAdder.add_to_queue"><a class="viewcode-back" href="../../proxypool.html#proxypool.schedule.PoolAdder.add_to_queue">[docs]</a> <span class="k">def</span> <span class="nf">add_to_queue</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">flag</span><span class="o">=</span><span class="mi">40</span><span class="p">):</span>
  103. <span class="sd">&quot;&quot;&quot;</span>
  104. <span class="sd"> 命令爬虫抓取一定量未检测的代理,然后检测,将通过检测的代理</span>
  105. <span class="sd"> 加入到代理池中。</span>
  106. <span class="sd"> &quot;&quot;&quot;</span>
  107. <span class="nb">print</span><span class="p">(</span><span class="s1">&#39;PoolAdder is working&#39;</span><span class="p">)</span>
  108. <span class="k">while</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_over_threshold</span><span class="p">():</span>
  109. <span class="k">for</span> <span class="n">callback_label</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_crawler</span><span class="o">.</span><span class="n">__CrawlFuncCount__</span><span class="p">):</span>
  110. <span class="n">callback</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_crawler</span><span class="o">.</span><span class="n">__CrawlFunc__</span><span class="p">[</span><span class="n">callback_label</span><span class="p">]</span>
  111. <span class="n">raw_proxies</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_crawler</span><span class="o">.</span><span class="n">get_raw_proxies</span><span class="p">(</span><span class="n">callback</span><span class="p">,</span> <span class="n">flag</span><span class="p">)</span>
  112. <span class="bp">self</span><span class="o">.</span><span class="n">_tester</span><span class="o">.</span><span class="n">set_raw_proxies</span><span class="p">(</span><span class="n">raw_proxies</span><span class="p">)</span>
  113. <span class="bp">self</span><span class="o">.</span><span class="n">_tester</span><span class="o">.</span><span class="n">test</span><span class="p">()</span>
  114. <span class="bp">self</span><span class="o">.</span><span class="n">_conn</span><span class="o">.</span><span class="n">put_many</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_tester</span><span class="o">.</span><span class="n">get_usable_proxies</span><span class="p">())</span>
  115. <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_over_threshold</span><span class="p">():</span>
  116. <span class="k">break</span>
  117. <span class="n">flag</span> <span class="o">+=</span> <span class="n">flag</span>
  118. <span class="k">if</span> <span class="n">flag</span> <span class="o">&gt;=</span> <span class="mi">10</span> <span class="o">*</span> <span class="n">flag</span><span class="p">:</span>
  119. <span class="k">raise</span> <span class="n">ResourceDepletionError</span></div></div>
  120. <div class="viewcode-block" id="Schedule"><a class="viewcode-back" href="../../proxypool.html#proxypool.schedule.Schedule">[docs]</a><span class="k">class</span> <span class="nc">Schedule</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
  121. <span class="sd">&quot;&quot;&quot;</span>
  122. <span class="sd"> 总调度器,用于协调各调度器模块</span>
  123. <span class="sd"> &quot;&quot;&quot;</span>
  124. <span class="nd">@staticmethod</span>
  125. <div class="viewcode-block" id="Schedule.valid_proxy"><a class="viewcode-back" href="../../proxypool.html#proxypool.schedule.Schedule.valid_proxy">[docs]</a> <span class="k">def</span> <span class="nf">valid_proxy</span><span class="p">(</span><span class="n">cycle</span><span class="o">=</span><span class="n">VALID_CHECK_CYCLE</span><span class="p">):</span>
  126. <span class="sd">&quot;&quot;&quot;</span>
  127. <span class="sd"> 对已经如池的代理进行检测,防止池中的代理因长期</span>
  128. <span class="sd"> 不使用而过期。</span>
  129. <span class="sd"> 抽出代理池队列中前1/4的代理,检测,合格者压入队列尾。</span>
  130. <span class="sd"> &quot;&quot;&quot;</span>
  131. <span class="n">conn</span> <span class="o">=</span> <span class="n">RedisClient</span><span class="p">()</span>
  132. <span class="n">tester</span> <span class="o">=</span> <span class="n">ValidityTester</span><span class="p">()</span>
  133. <span class="k">while</span> <span class="kc">True</span><span class="p">:</span>
  134. <span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="n">cycle</span><span class="p">)</span>
  135. <span class="n">count</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="mf">0.25</span> <span class="o">*</span> <span class="n">conn</span><span class="o">.</span><span class="n">queue_len</span><span class="p">)</span>
  136. <span class="k">if</span> <span class="n">count</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
  137. <span class="k">continue</span>
  138. <span class="n">raw_proxies</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">count</span><span class="p">)</span>
  139. <span class="n">tester</span><span class="o">.</span><span class="n">set_raw_proxies</span><span class="p">(</span><span class="n">raw_proxies</span><span class="p">)</span>
  140. <span class="n">tester</span><span class="o">.</span><span class="n">test</span><span class="p">()</span>
  141. <span class="n">proxies</span> <span class="o">=</span> <span class="n">tester</span><span class="o">.</span><span class="n">get_usable_proxies</span><span class="p">()</span>
  142. <span class="n">conn</span><span class="o">.</span><span class="n">put_many</span><span class="p">(</span><span class="n">proxies</span><span class="p">)</span></div>
  143. <span class="nd">@staticmethod</span>
  144. <div class="viewcode-block" id="Schedule.check_pool"><a class="viewcode-back" href="../../proxypool.html#proxypool.schedule.Schedule.check_pool">[docs]</a> <span class="k">def</span> <span class="nf">check_pool</span><span class="p">(</span><span class="n">lower_threshold</span><span class="o">=</span><span class="n">POOL_LOWER_THRESHOLD</span><span class="p">,</span>
  145. <span class="n">upper_threshold</span><span class="o">=</span><span class="n">POOL_UPPER_THRESHOLD</span><span class="p">,</span>
  146. <span class="n">cycle</span><span class="o">=</span><span class="n">POOL_LEN_CHECK_CYCLE</span><span class="p">):</span>
  147. <span class="sd">&quot;&quot;&quot;</span>
  148. <span class="sd"> 协调添加器,当代理池中可用代理的数量低于下阈值时,触发添加器,启动爬虫</span>
  149. <span class="sd"> 补充代理,当代理达到上阈值时,添加器停止工作。</span>
  150. <span class="sd"> &quot;&quot;&quot;</span>
  151. <span class="n">conn</span> <span class="o">=</span> <span class="n">RedisClient</span><span class="p">()</span>
  152. <span class="n">adder</span> <span class="o">=</span> <span class="n">PoolAdder</span><span class="p">(</span><span class="n">upper_threshold</span><span class="p">)</span>
  153. <span class="k">while</span> <span class="kc">True</span><span class="p">:</span>
  154. <span class="k">if</span> <span class="n">conn</span><span class="o">.</span><span class="n">queue_len</span> <span class="o">&lt;</span> <span class="n">lower_threshold</span><span class="p">:</span>
  155. <span class="n">adder</span><span class="o">.</span><span class="n">add_to_queue</span><span class="p">()</span>
  156. <span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="n">cycle</span><span class="p">)</span></div>
  157. <div class="viewcode-block" id="Schedule.run"><a class="viewcode-back" href="../../proxypool.html#proxypool.schedule.Schedule.run">[docs]</a> <span class="k">def</span> <span class="nf">run</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
  158. <span class="sd">&quot;&quot;&quot;</span>
  159. <span class="sd"> 运行调度器,创建两个进程,对代理池进行维护。</span>
  160. <span class="sd"> &quot;&quot;&quot;</span>
  161. <span class="n">valid_process</span> <span class="o">=</span> <span class="n">Process</span><span class="p">(</span><span class="n">target</span><span class="o">=</span><span class="n">Schedule</span><span class="o">.</span><span class="n">valid_proxy</span><span class="p">)</span>
  162. <span class="n">check_process</span> <span class="o">=</span> <span class="n">Process</span><span class="p">(</span><span class="n">target</span><span class="o">=</span><span class="n">Schedule</span><span class="o">.</span><span class="n">check_pool</span><span class="p">)</span>
  163. <span class="n">valid_process</span><span class="o">.</span><span class="n">start</span><span class="p">()</span>
  164. <span class="n">check_process</span><span class="o">.</span><span class="n">start</span><span class="p">()</span></div></div>
  165. </pre></div>
  166. </div>
  167. </div>
  168. </div>
  169. <div class="sphinxsidebar" role="navigation" aria-label="main navigation">
  170. <div class="sphinxsidebarwrapper"><div class="relations">
  171. <h3>Related Topics</h3>
  172. <ul>
  173. <li><a href="../../index.html">Documentation overview</a><ul>
  174. <li><a href="../index.html">Module code</a><ul>
  175. </ul></li>
  176. </ul></li>
  177. </ul>
  178. </div>
  179. <div id="searchbox" style="display: none" role="search">
  180. <h3>Quick search</h3>
  181. <form class="search" action="../../search.html" method="get">
  182. <div><input type="text" name="q" /></div>
  183. <div><input type="submit" value="Go" /></div>
  184. <input type="hidden" name="check_keywords" value="yes" />
  185. <input type="hidden" name="area" value="default" />
  186. </form>
  187. </div>
  188. <script type="text/javascript">$('#searchbox').show(0);</script>
  189. </div>
  190. </div>
  191. <div class="clearer"></div>
  192. </div>
  193. <div class="footer">
  194. &copy;2016, Author.
  195. |
  196. Powered by <a href="http://sphinx-doc.org/">Sphinx 1.4.8</a>
  197. &amp; <a href="https://github.com/bitprophet/alabaster">Alabaster 0.7.9</a>
  198. </div>
  199. </body>
  200. </html>