proxypool.html 25 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398
  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 package &#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="prev" title="Welcome to proxypool’s documentation!" 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. <div class="section" id="proxypool-package">
  34. <h1>proxypool package<a class="headerlink" href="#proxypool-package" title="Permalink to this headline">¶</a></h1>
  35. <div class="section" id="submodules">
  36. <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this headline">¶</a></h2>
  37. </div>
  38. <div class="section" id="module-proxypool.api">
  39. <span id="proxypool-api-module"></span><h2>proxypool.api module<a class="headerlink" href="#module-proxypool.api" title="Permalink to this headline">¶</a></h2>
  40. <blockquote>
  41. <div><blockquote>
  42. <div><a class="reference external" href="http://127.0.0.1:5000">http://127.0.0.1:5000</a>/进入主页。
  43. 访问 <a class="reference external" href="http://127.0.0.1:5000/get">http://127.0.0.1:5000/get</a>
  44. 从代理池中获取一个代理。
  45. 访问 <a class="reference external" href="http://127.0.0.1:5000/count">http://127.0.0.1:5000/count</a>
  46. 获取代理池中可用代理的总数。</div></blockquote>
  47. <p>Author: Liu
  48. Date: 2016/12/9</p>
  49. </div></blockquote>
  50. </div>
  51. <hr class="docutils" />
  52. <div class="section" id="module-proxypool.db">
  53. <span id="proxypool-db-module"></span><h2>proxypool.db module<a class="headerlink" href="#module-proxypool.db" title="Permalink to this headline">¶</a></h2>
  54. <blockquote>
  55. <div><blockquote>
  56. <div>的交互。</div></blockquote>
  57. <p>Author: Liu
  58. Date: 2016/12/9</p>
  59. </div></blockquote>
  60. <hr class="docutils" />
  61. <dl class="class">
  62. <dt id="proxypool.db.RedisClient">
  63. <em class="property">class </em><code class="descclassname">proxypool.db.</code><code class="descname">RedisClient</code><span class="sig-paren">(</span><em>host='localhost'</em>, <em>port=6379</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/db.html#RedisClient"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.db.RedisClient" title="Permalink to this definition">¶</a></dt>
  64. <dd><p>Bases: <code class="xref py py-class docutils literal"><span class="pre">object</span></code></p>
  65. <p>Redis数据库操作类。</p>
  66. <dl class="method">
  67. <dt id="proxypool.db.RedisClient.flush">
  68. <code class="descname">flush</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/db.html#RedisClient.flush"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.db.RedisClient.flush" title="Permalink to this definition">¶</a></dt>
  69. <dd><p>刷新Redis中的全部内容,测试用。</p>
  70. </dd></dl>
  71. <dl class="method">
  72. <dt id="proxypool.db.RedisClient.get">
  73. <code class="descname">get</code><span class="sig-paren">(</span><em>count=1</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/db.html#RedisClient.get"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.db.RedisClient.get" title="Permalink to this definition">¶</a></dt>
  74. <dd><p>从Pool中获取一定量数据。</p>
  75. </dd></dl>
  76. <dl class="method">
  77. <dt id="proxypool.db.RedisClient.pop">
  78. <code class="descname">pop</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/db.html#RedisClient.pop"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.db.RedisClient.pop" title="Permalink to this definition">¶</a></dt>
  79. <dd><p>弹出一个可用代理。</p>
  80. </dd></dl>
  81. <dl class="method">
  82. <dt id="proxypool.db.RedisClient.put">
  83. <code class="descname">put</code><span class="sig-paren">(</span><em>proxy</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/db.html#RedisClient.put"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.db.RedisClient.put" title="Permalink to this definition">¶</a></dt>
  84. <dd><p>将代理压入Pool中。
  85. 用Redis的set容器来负责去重,如果proxy能被压入proxy_set,
  86. 就将其放入proxy pool中,否则不压入。</p>
  87. </dd></dl>
  88. <dl class="method">
  89. <dt id="proxypool.db.RedisClient.put_many">
  90. <code class="descname">put_many</code><span class="sig-paren">(</span><em>proxies</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/db.html#RedisClient.put_many"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.db.RedisClient.put_many" title="Permalink to this definition">¶</a></dt>
  91. <dd><p>将一定量的代理压入Pool。</p>
  92. </dd></dl>
  93. <dl class="attribute">
  94. <dt id="proxypool.db.RedisClient.queue_len">
  95. <code class="descname">queue_len</code><a class="headerlink" href="#proxypool.db.RedisClient.queue_len" title="Permalink to this definition">¶</a></dt>
  96. <dd><p>获取proxy pool的大小。</p>
  97. </dd></dl>
  98. </dd></dl>
  99. </div>
  100. <div class="section" id="module-proxypool.error">
  101. <span id="proxypool-error-module"></span><h2>proxypool.error module<a class="headerlink" href="#module-proxypool.error" title="Permalink to this headline">¶</a></h2>
  102. <blockquote>
  103. <div>Author: Liu
  104. Date: 2016/12/9</div></blockquote>
  105. <hr class="docutils" />
  106. <dl class="exception">
  107. <dt id="proxypool.error.PoolEmptyError">
  108. <em class="property">exception </em><code class="descclassname">proxypool.error.</code><code class="descname">PoolEmptyError</code><a class="reference internal" href="_modules/proxypool/error.html#PoolEmptyError"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.error.PoolEmptyError" title="Permalink to this definition">¶</a></dt>
  109. <dd><p>Bases: <code class="xref py py-class docutils literal"><span class="pre">Exception</span></code></p>
  110. <p>代理池空异常,如果代理池长时间为空,则抛出此异常。</p>
  111. </dd></dl>
  112. <dl class="exception">
  113. <dt id="proxypool.error.ResourceDepletionError">
  114. <em class="property">exception </em><code class="descclassname">proxypool.error.</code><code class="descname">ResourceDepletionError</code><a class="reference internal" href="_modules/proxypool/error.html#ResourceDepletionError"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.error.ResourceDepletionError" title="Permalink to this definition">¶</a></dt>
  115. <dd><p>Bases: <code class="xref py py-class docutils literal"><span class="pre">Exception</span></code></p>
  116. <p>资源枯竭异常,如果从所有抓取网站都抓不到可用的代理资源,
  117. 则抛出此异常。</p>
  118. </dd></dl>
  119. </div>
  120. <div class="section" id="module-proxypool.proxyGetter">
  121. <span id="proxypool-proxygetter-module"></span><h2>proxypool.proxyGetter module<a class="headerlink" href="#module-proxypool.proxyGetter" title="Permalink to this headline">¶</a></h2>
  122. <blockquote>
  123. <div>Author: Liu
  124. Date: 2016/12/9</div></blockquote>
  125. <hr class="docutils" />
  126. <dl class="class">
  127. <dt id="proxypool.proxyGetter.FreeProxyGetter">
  128. <em class="property">class </em><code class="descclassname">proxypool.proxyGetter.</code><code class="descname">FreeProxyGetter</code><a class="reference internal" href="_modules/proxypool/proxyGetter.html#FreeProxyGetter"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.proxyGetter.FreeProxyGetter" title="Permalink to this definition">¶</a></dt>
  129. <dd><p>Bases: <code class="xref py py-class docutils literal"><span class="pre">object</span></code></p>
  130. <p>代理爬虫,负责扫描各大代理网站,抓取代理。
  131. 该类有可扩展性,可根据需要自己添加新站点的代理抓取函数,
  132. 但是函数名必须以crawl_开头,返回值必须以&#8221;host:port&#8221;的形式返回,
  133. 添加器会自动识别并调用此类函数。</p>
  134. <dl class="method">
  135. <dt id="proxypool.proxyGetter.FreeProxyGetter.crawl_daili66">
  136. <code class="descname">crawl_daili66</code><span class="sig-paren">(</span><em>page_count=4</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/proxyGetter.html#FreeProxyGetter.crawl_daili66"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.proxyGetter.FreeProxyGetter.crawl_daili66" title="Permalink to this definition">¶</a></dt>
  137. <dd><p>抓取代理66网的数据。</p>
  138. </dd></dl>
  139. <dl class="method">
  140. <dt id="proxypool.proxyGetter.FreeProxyGetter.crawl_kuaidaili">
  141. <code class="descname">crawl_kuaidaili</code><span class="sig-paren">(</span><em>page_count=8</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/proxyGetter.html#FreeProxyGetter.crawl_kuaidaili"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.proxyGetter.FreeProxyGetter.crawl_kuaidaili" title="Permalink to this definition">¶</a></dt>
  142. <dd><p>抓取快代理网的数据</p>
  143. </dd></dl>
  144. <dl class="method">
  145. <dt id="proxypool.proxyGetter.FreeProxyGetter.crawl_proxy360">
  146. <code class="descname">crawl_proxy360</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/proxyGetter.html#FreeProxyGetter.crawl_proxy360"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.proxyGetter.FreeProxyGetter.crawl_proxy360" title="Permalink to this definition">¶</a></dt>
  147. <dd><p>抓取proxy360网的数据。</p>
  148. </dd></dl>
  149. <dl class="method">
  150. <dt id="proxypool.proxyGetter.FreeProxyGetter.crawl_xici">
  151. <code class="descname">crawl_xici</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/proxyGetter.html#FreeProxyGetter.crawl_xici"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.proxyGetter.FreeProxyGetter.crawl_xici" title="Permalink to this definition">¶</a></dt>
  152. <dd><p>抓取xici代理网的数据。</p>
  153. </dd></dl>
  154. <dl class="method">
  155. <dt id="proxypool.proxyGetter.FreeProxyGetter.get_raw_proxies">
  156. <code class="descname">get_raw_proxies</code><span class="sig-paren">(</span><em>callback</em>, <em>count=40</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/proxyGetter.html#FreeProxyGetter.get_raw_proxies"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.proxyGetter.FreeProxyGetter.get_raw_proxies" title="Permalink to this definition">¶</a></dt>
  157. <dd></dd></dl>
  158. </dd></dl>
  159. <dl class="class">
  160. <dt id="proxypool.proxyGetter.ProxyMetaclass">
  161. <em class="property">class </em><code class="descclassname">proxypool.proxyGetter.</code><code class="descname">ProxyMetaclass</code><a class="reference internal" href="_modules/proxypool/proxyGetter.html#ProxyMetaclass"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.proxyGetter.ProxyMetaclass" title="Permalink to this definition">¶</a></dt>
  162. <dd><p>Bases: <code class="xref py py-class docutils literal"><span class="pre">type</span></code></p>
  163. <p>爬虫的元类,在FreeProxyGetter类中加入
  164. __CrawlFunc__和__CrawlFuncCount__
  165. 两个参数,分别表示爬虫函数,和爬虫函数的数量。</p>
  166. </dd></dl>
  167. </div>
  168. <div class="section" id="module-proxypool.schedule">
  169. <span id="proxypool-schedule-module"></span><h2>proxypool.schedule module<a class="headerlink" href="#module-proxypool.schedule" title="Permalink to this headline">¶</a></h2>
  170. <blockquote>
  171. <div><blockquote>
  172. <div>包含ValidityTester,PoolAdder,
  173. Schedule三个类,负责维护代理池。</div></blockquote>
  174. <p>Author: Liu
  175. Date: 2016/12/9</p>
  176. </div></blockquote>
  177. <hr class="docutils" />
  178. <dl class="class">
  179. <dt id="proxypool.schedule.PoolAdder">
  180. <em class="property">class </em><code class="descclassname">proxypool.schedule.</code><code class="descname">PoolAdder</code><span class="sig-paren">(</span><em>threshold</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/schedule.html#PoolAdder"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.schedule.PoolAdder" title="Permalink to this definition">¶</a></dt>
  181. <dd><p>Bases: <code class="xref py py-class docutils literal"><span class="pre">object</span></code></p>
  182. <p>添加器,负责向池中补充代理</p>
  183. <dl class="method">
  184. <dt id="proxypool.schedule.PoolAdder.add_to_queue">
  185. <code class="descname">add_to_queue</code><span class="sig-paren">(</span><em>flag=40</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/schedule.html#PoolAdder.add_to_queue"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.schedule.PoolAdder.add_to_queue" title="Permalink to this definition">¶</a></dt>
  186. <dd><p>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
  187. 加入到代理池中。</p>
  188. </dd></dl>
  189. <dl class="method">
  190. <dt id="proxypool.schedule.PoolAdder.is_over_threshold">
  191. <code class="descname">is_over_threshold</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/schedule.html#PoolAdder.is_over_threshold"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.schedule.PoolAdder.is_over_threshold" title="Permalink to this definition">¶</a></dt>
  192. <dd><p>判断代理池中的数据量是否达到阈值。</p>
  193. </dd></dl>
  194. </dd></dl>
  195. <dl class="class">
  196. <dt id="proxypool.schedule.Schedule">
  197. <em class="property">class </em><code class="descclassname">proxypool.schedule.</code><code class="descname">Schedule</code><a class="reference internal" href="_modules/proxypool/schedule.html#Schedule"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.schedule.Schedule" title="Permalink to this definition">¶</a></dt>
  198. <dd><p>Bases: <code class="xref py py-class docutils literal"><span class="pre">object</span></code></p>
  199. <p>总调度器,用于协调各调度器模块</p>
  200. <dl class="staticmethod">
  201. <dt id="proxypool.schedule.Schedule.check_pool">
  202. <em class="property">static </em><code class="descname">check_pool</code><span class="sig-paren">(</span><em>lower_threshold=10</em>, <em>upper_threshold=40</em>, <em>cycle=20</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/schedule.html#Schedule.check_pool"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.schedule.Schedule.check_pool" title="Permalink to this definition">¶</a></dt>
  203. <dd><p>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
  204. 补充代理,当代理达到上阈值时,添加器停止工作。</p>
  205. </dd></dl>
  206. <dl class="method">
  207. <dt id="proxypool.schedule.Schedule.run">
  208. <code class="descname">run</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/schedule.html#Schedule.run"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.schedule.Schedule.run" title="Permalink to this definition">¶</a></dt>
  209. <dd><p>运行调度器,创建两个进程,对代理池进行维护。</p>
  210. </dd></dl>
  211. <dl class="staticmethod">
  212. <dt id="proxypool.schedule.Schedule.valid_proxy">
  213. <em class="property">static </em><code class="descname">valid_proxy</code><span class="sig-paren">(</span><em>cycle=600</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/schedule.html#Schedule.valid_proxy"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.schedule.Schedule.valid_proxy" title="Permalink to this definition">¶</a></dt>
  214. <dd><p>对已经如池的代理进行检测,防止池中的代理因长期
  215. 不使用而过期。
  216. 抽出代理池队列中前1/4的代理,检测,合格者压入队列尾。</p>
  217. </dd></dl>
  218. </dd></dl>
  219. <dl class="class">
  220. <dt id="proxypool.schedule.ValidityTester">
  221. <em class="property">class </em><code class="descclassname">proxypool.schedule.</code><code class="descname">ValidityTester</code><a class="reference internal" href="_modules/proxypool/schedule.html#ValidityTester"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.schedule.ValidityTester" title="Permalink to this definition">¶</a></dt>
  222. <dd><p>Bases: <code class="xref py py-class docutils literal"><span class="pre">object</span></code></p>
  223. <p>检验器,负责对未知的代理进行异步检测。</p>
  224. <dl class="method">
  225. <dt id="proxypool.schedule.ValidityTester.get_usable_proxies">
  226. <code class="descname">get_usable_proxies</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/schedule.html#ValidityTester.get_usable_proxies"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.schedule.ValidityTester.get_usable_proxies" title="Permalink to this definition">¶</a></dt>
  227. <dd></dd></dl>
  228. <dl class="method">
  229. <dt id="proxypool.schedule.ValidityTester.set_raw_proxies">
  230. <code class="descname">set_raw_proxies</code><span class="sig-paren">(</span><em>proxies</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/schedule.html#ValidityTester.set_raw_proxies"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.schedule.ValidityTester.set_raw_proxies" title="Permalink to this definition">¶</a></dt>
  231. <dd><p>设置待检测的代理。</p>
  232. </dd></dl>
  233. <dl class="method">
  234. <dt id="proxypool.schedule.ValidityTester.test">
  235. <code class="descname">test</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/schedule.html#ValidityTester.test"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.schedule.ValidityTester.test" title="Permalink to this definition">¶</a></dt>
  236. <dd><p>异步检测_raw_proxies中的全部代理。</p>
  237. </dd></dl>
  238. <dl class="attribute">
  239. <dt id="proxypool.schedule.ValidityTester.test_api">
  240. <code class="descname">test_api</code><em class="property"> = 'https://www.baidu.com'</em><a class="headerlink" href="#proxypool.schedule.ValidityTester.test_api" title="Permalink to this definition">¶</a></dt>
  241. <dd></dd></dl>
  242. <dl class="method">
  243. <dt id="proxypool.schedule.ValidityTester.test_single_proxy">
  244. <code class="descname">test_single_proxy</code><span class="sig-paren">(</span><em>proxy</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/schedule.html#ValidityTester.test_single_proxy"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.schedule.ValidityTester.test_single_proxy" title="Permalink to this definition">¶</a></dt>
  245. <dd><p>检测单个代理,如果可用,则将其加入_usable_proxies</p>
  246. </dd></dl>
  247. </dd></dl>
  248. </div>
  249. <div class="section" id="module-proxypool.setting">
  250. <span id="proxypool-setting-module"></span><h2>proxypool.setting module<a class="headerlink" href="#module-proxypool.setting" title="Permalink to this headline">¶</a></h2>
  251. <blockquote>
  252. <div>Author: Liu
  253. Date: 2016/12/9</div></blockquote>
  254. </div>
  255. <hr class="docutils" />
  256. <div class="section" id="module-proxypool.utils">
  257. <span id="proxypool-utils-module"></span><h2>proxypool.utils module<a class="headerlink" href="#module-proxypool.utils" title="Permalink to this headline">¶</a></h2>
  258. <dl class="class">
  259. <dt id="proxypool.utils.Downloader">
  260. <em class="property">class </em><code class="descclassname">proxypool.utils.</code><code class="descname">Downloader</code><span class="sig-paren">(</span><em>urls</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/utils.html#Downloader"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.utils.Downloader" title="Permalink to this definition">¶</a></dt>
  261. <dd><p>Bases: <code class="xref py py-class docutils literal"><span class="pre">object</span></code></p>
  262. <p>一个异步下载器,可以对代理源异步抓取,但是容易被BAN。</p>
  263. <dl class="method">
  264. <dt id="proxypool.utils.Downloader.download">
  265. <code class="descname">download</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/utils.html#Downloader.download"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.utils.Downloader.download" title="Permalink to this definition">¶</a></dt>
  266. <dd></dd></dl>
  267. <dl class="method">
  268. <dt id="proxypool.utils.Downloader.download_single_page">
  269. <code class="descname">download_single_page</code><span class="sig-paren">(</span><em>url</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/utils.html#Downloader.download_single_page"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.utils.Downloader.download_single_page" title="Permalink to this definition">¶</a></dt>
  270. <dd></dd></dl>
  271. <dl class="attribute">
  272. <dt id="proxypool.utils.Downloader.htmls">
  273. <code class="descname">htmls</code><a class="headerlink" href="#proxypool.utils.Downloader.htmls" title="Permalink to this definition">¶</a></dt>
  274. <dd></dd></dl>
  275. </dd></dl>
  276. <dl class="function">
  277. <dt id="proxypool.utils.get_page">
  278. <code class="descclassname">proxypool.utils.</code><code class="descname">get_page</code><span class="sig-paren">(</span><em>url</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/proxypool/utils.html#get_page"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#proxypool.utils.get_page" title="Permalink to this definition">¶</a></dt>
  279. <dd></dd></dl>
  280. </div>
  281. <div class="section" id="module-proxypool">
  282. <span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-proxypool" title="Permalink to this headline">¶</a></h2>
  283. </div>
  284. </div>
  285. </div>
  286. </div>
  287. </div>
  288. <div class="sphinxsidebar" role="navigation" aria-label="main navigation">
  289. <div class="sphinxsidebarwrapper">
  290. <h3><a href="index.html">Table Of Contents</a></h3>
  291. <ul>
  292. <li><a class="reference internal" href="#">proxypool package</a><ul>
  293. <li><a class="reference internal" href="#submodules">Submodules</a></li>
  294. <li><a class="reference internal" href="#module-proxypool.api">proxypool.api module</a></li>
  295. <li><a class="reference internal" href="#module-proxypool.db">proxypool.db module</a></li>
  296. <li><a class="reference internal" href="#module-proxypool.error">proxypool.error module</a></li>
  297. <li><a class="reference internal" href="#module-proxypool.proxyGetter">proxypool.proxyGetter module</a></li>
  298. <li><a class="reference internal" href="#module-proxypool.schedule">proxypool.schedule module</a></li>
  299. <li><a class="reference internal" href="#module-proxypool.setting">proxypool.setting module</a></li>
  300. <li><a class="reference internal" href="#module-proxypool.utils">proxypool.utils module</a></li>
  301. <li><a class="reference internal" href="#module-proxypool">Module contents</a></li>
  302. </ul>
  303. </li>
  304. </ul>
  305. <div class="relations">
  306. <h3>Related Topics</h3>
  307. <ul>
  308. <li><a href="index.html">Documentation overview</a><ul>
  309. <li>Previous: <a href="index.html" title="previous chapter">Welcome to proxypool&#8217;s documentation!</a></li>
  310. </ul></li>
  311. </ul>
  312. </div>
  313. <div role="note" aria-label="source link">
  314. <h3>This Page</h3>
  315. <ul class="this-page-menu">
  316. <li><a href="_sources/proxypool.txt"
  317. rel="nofollow">Show Source</a></li>
  318. </ul>
  319. </div>
  320. <div id="searchbox" style="display: none" role="search">
  321. <h3>Quick search</h3>
  322. <form class="search" action="search.html" method="get">
  323. <div><input type="text" name="q" /></div>
  324. <div><input type="submit" value="Go" /></div>
  325. <input type="hidden" name="check_keywords" value="yes" />
  326. <input type="hidden" name="area" value="default" />
  327. </form>
  328. </div>
  329. <script type="text/javascript">$('#searchbox').show(0);</script>
  330. </div>
  331. </div>
  332. <div class="clearer"></div>
  333. </div>
  334. <div class="footer">
  335. &copy;2016, Author.
  336. |
  337. Powered by <a href="http://sphinx-doc.org/">Sphinx 1.4.8</a>
  338. &amp; <a href="https://github.com/bitprophet/alabaster">Alabaster 0.7.9</a>
  339. |
  340. <a href="_sources/proxypool.txt"
  341. rel="nofollow">Page source</a>
  342. </div>
  343. </body>
  344. </html>