{"id":1337,"date":"2017-08-31T15:13:09","date_gmt":"2017-08-31T07:13:09","guid":{"rendered":"http:\/\/www.yueguangzu.net\/?p=1337"},"modified":"2017-08-31T15:13:22","modified_gmt":"2017-08-31T07:13:22","slug":"12306%e4%b8%93%e9%a2%98%e7%ac%ac%e4%b8%80%e7%af%8712306%e7%9a%84urlliburllib2","status":"publish","type":"post","link":"http:\/\/www.yueguangzu.net\/?p=1337","title":{"rendered":"[12306\u4e13\u9898]\u7b2c\u4e00\u7bc712306\u7684urllib,urllib2"},"content":{"rendered":"<h4 class=\"md-end-block md-heading md-focus\"><span class=\"md-expand\">1.\u8ba4\u8bc6urllib\u548curllib2\u6a21\u5757<\/span><\/h4>\n<h5 class=\"md-end-block md-heading\"><span class=\"\">Python\u8bf7\u6c42URL\u76f8\u5173\u7684\u64cd\u4f5c,\u9700\u8981\u4f7f\u7528\u5230\u76f8\u5173\u6a21\u5757,\u5728python2\u4e2d,\u5982\u679c\u4e0d\u4f9d\u8d56\u4e8e\u7b2c\u4e09\u65b9\u6846\u67b6\u6216\u8005\u6a21\u5757,\u90a3\u4e48urllib\u548curllib2\u662f\u6700\u5e38\u7528\u7684.<\/span><\/h5>\n<blockquote>\n<h5 class=\"md-end-block md-heading\">\u901a\u5e38,urllib\u548curllib2\u662f\u8054\u5408\u4f7f\u7528\u7684,\u533a\u522b\u4e8e\u8054\u7cfb:<\/h5>\n<ul class=\"ul-list\" data-mark=\"-\">\n<li>\n<h5 class=\"md-end-block md-heading\">urllib\u53ea\u63a5\u6536\u4e00\u4e2aURL\uff0c\u4e0d\u80fd\u8bbe\u7f6e\u7528\u6237\u4ee3\u7406\u5b57\u7b26\u4e32.\u4f46\u662furllib\u5185\u7f6e\u4e86urlencode\u7684\u65b9\u6cd5,\u53ef\u4ee5\u628a\u4e00\u4e2a\u5b57\u5178,\u8f6c\u6362\u6210\u4e3aurl\u4f20\u8f93\u6240\u4f7f\u7528\u7684\u5b57\u7b26\u4e32.\u8fd9\u65b9\u6cd5\u5728urllib2\u4e0d\u5b58\u5728.<\/h5>\n<\/li>\n<li>\n<h5 class=\"md-end-block md-heading\">urllib2\u53ef\u4ee5\u63a5\u53d7\u4e00\u4e2aRequest\u5bf9\u8c61,\u53ef\u4ee5\u6765\u8bbe\u7f6e\u4e00\u4e2aURL\u7684headers,\u4f2a\u9020\u6210\u6d4f\u89c8\u5668\u6b63\u5e38\u8bbf\u95ee.<\/h5>\n<\/li>\n<\/ul>\n<\/blockquote>\n<h5 class=\"md-end-block md-heading\">1.1\u5e38\u89c1\u7684\u7528\u6cd5urlopen\u76f4\u63a5\u63a5\u6536URL<\/h5>\n<h5 class=\"md-end-block md-heading\">urllib2.<span spellcheck=\"false\"><code>urlopen(url[, data][, timeout])<\/code><\/span><\/h5>\n<ul class=\"ul-list\" data-mark=\"-\">\n<li>\n<h5 class=\"md-end-block md-heading\"><span spellcheck=\"false\"><code>urlopen<\/code><\/span>\u65b9\u6cd5\u662furllib2\u6a21\u5757\u6700\u5e38\u7528\u4e5f\u6700\u7b80\u5355\u7684\u65b9\u6cd5\uff0c\u5b83\u6253\u5f00URL\u7f51\u5740\uff0curl\u53c2\u6570\u53ef\u4ee5\u662f\u4e00\u4e2a\u5b57\u7b26\u4e32url\u6216\u8005\u662f\u4e00\u4e2arequest\u5bf9\u8c61\u3002Request\u5bf9\u8c61\u548cdata\u5728request\u7c7b\u4e2d\u8bf4\u660e\uff0c\u5b9a\u4e49\u90fd\u662f\u4e00\u6837\u7684\u3002<\/h5>\n<\/li>\n<li>\n<h5 class=\"md-end-block md-heading\">\u5bf9\u4e8e\u53ef\u9009\u7684\u53c2\u6570timeout\uff0c\u963b\u585e\u64cd\u4f5c\u4ee5\u79d2\u4e3a\u5355\u4f4d<\/h5>\n<\/li>\n<\/ul>\n<blockquote>\n<h5 class=\"md-end-block md-heading\">\u7b80\u5355\u7684\u7528\u6cd5,\u8bbf\u95ee<span spellcheck=\"false\"><a href=\"http:\/\/www.yueguangzu.net\">http:\/\/www.yueguangzu.net<\/a><\/span>\u9875\u9762html\u5185\u5bb9,\u4fdd\u5b58\u5230\u53d8\u91cfh<\/h5>\n<\/blockquote>\n<pre class=\"md-fences md-end-block\" lang=\"python\" contenteditable=\"false\"><span class=\"cm-keyword\">import<\/span> <span class=\"cm-variable\">urllib2<\/span>\r\n<span class=\"cm-variable\">r<\/span>=<span class=\"cm-variable\">urllib2<\/span>.<span class=\"cm-property\">urlopen<\/span>(<span class=\"cm-string\">'http:\/\/www.yueguangzu.net'<\/span>)<span class=\"cm-comment\">#\u4f7f\u7528urllib2\u6a21\u5757\u91ccurlopen\u65b9\u6cd5\u6253\u5f00\u7f51\u9875<\/span>\r\n<span class=\"cm-variable\">h<\/span>=<span class=\"cm-variable\">r<\/span>.<span class=\"cm-property\">read<\/span>() <span class=\"cm-comment\">#\u5e76\u5c06\u8bf7\u6c42\u5230\u7684\u54cd\u5e94response\u7528read\u65b9\u6cd5\u8bfb\u51fa,\u4fdd\u5b58\u5230\u53d8\u91cfh<\/span><\/pre>\n<blockquote>\n<h5 class=\"md-end-block md-heading\">\u5982\u679c\u662fpython3,urllib2\u5e93\u4e0d\u662f\u6807\u51c6\u5e93,urllib2\u6a21\u5757\u9700\u8981\u66ff\u6362\u6210urllib.request<\/h5>\n<\/blockquote>\n<pre class=\"md-fences md-end-block\" lang=\"python\" contenteditable=\"false\">\r\n<span class=\"cm-comment\">#python3\u4ee3\u7801<\/span>\r\n<span class=\"cm-keyword\">import<\/span> <span class=\"cm-variable\">urllib<\/span>.<span class=\"cm-property\">request<\/span>\r\n<span class=\"cm-variable\">r<\/span>=<span class=\"cm-variable\">urllib<\/span>.<span class=\"cm-property\">request<\/span>.<span class=\"cm-property\">urlopen<\/span>(<span class=\"cm-string\">'http:\/\/www.yueguangzu.net'<\/span>)\r\n<span class=\"cm-variable\">h<\/span>=<span class=\"cm-variable\">r<\/span>.<span class=\"cm-property\">read<\/span>()<\/pre>\n<h5 class=\"md-end-block md-heading\">\u8bf7\u6c42\u5230\u7684html\u62a5\u6587\u6570\u636e<\/h5>\n<p><span class=\"md-line md-end-block\"><span class=\"md-image md-img-loaded\" contenteditable=\"false\" data-src=\"http:\/\/www.yueguangzu.net\/wp-content\/uploads\/2017\/08\/named1.png\"><img style=\"box-sizing: border-box; border-width: 0px 4px 0px 2px; border-image: initial; vertical-align: middle; max-width: 100%; cursor: default; border-color: initial transparent initial transparent; border-style: initial solid initial solid;\" src=\"http:\/\/www.yueguangzu.net\/wp-content\/uploads\/2017\/08\/named1.png\" \/><\/span><\/span><\/p>\n<h5 class=\"md-end-block md-heading\">\u6d4f\u89c8\u5668\u89e3\u6790\u540e\u7684\u6548\u679c<\/h5>\n<p><span class=\"md-line md-end-block\"><span class=\"md-image md-img-loaded\" contenteditable=\"false\" data-src=\"http:\/\/www.yueguangzu.net\/wp-content\/uploads\/2017\/08\/named2.png\"><img style=\"box-sizing: border-box; border-width: 0px 4px 0px 2px; border-image: initial; vertical-align: middle; max-width: 100%; cursor: default; border-color: initial transparent initial transparent; border-style: initial solid initial solid;\" src=\"http:\/\/www.yueguangzu.net\/wp-content\/uploads\/2017\/08\/named2.png\" \/><\/span><\/span><\/p>\n<h5 class=\"md-end-block md-heading\">1.2 <span spellcheck=\"false\"><code>urlopen<\/code><\/span>\u63a5\u6536\u5bf9\u8c61<\/h5>\n<h5 class=\"md-end-block md-heading\">\u5982\u679c\u9700\u8981\u8bf7\u6c42\u7684\u9875\u9762,\u4e0d\u652f\u6301\u76f4\u63a5\u8bbf\u95ee,\u9700\u8981\u6a21\u62df\u6d4f\u89c8\u5668\u8bbf\u95ee\u65f6,\u5219\u9700\u8981\u4f7f\u7528\u5230<\/h5>\n<h5 class=\"md-end-block md-heading\">urllib2.<span spellcheck=\"false\"><code>Request<\/code><\/span>(url<a data-ref=\", headers\">, data<\/a><a data-ref=\", unverifiable\">,headers, origin_req_host<\/a>)<\/h5>\n<blockquote>\n<h5 class=\"md-end-block md-heading\">Request\u7c7b\u662f\u4e00\u4e2a\u62bd\u8c61\u7684URL\u8bf7\u6c42\u3002<\/h5>\n<h5 class=\"md-end-block md-heading\">data\u662f\u4f5c\u4e3a\u53c2\u6570\u8bf7\u6c42\uff0c\u5982\u679cdata\u4e0d\u7b49\u4e8eNone\uff0c\u5219\u8be5\u8bf7\u6c42\u4e3aPOST\uff0c\u5426\u5219\u4e3aGET,headers\u662f\u8bf7\u6c42\u7684\u5934\u6587\u4ef6,\u662f\u4e00\u4e2a\u5b57\u5178<\/h5>\n<\/blockquote>\n<h5 class=\"md-end-block md-heading\">\u4ee5\u7cd7\u4e8b\u767e\u79d1`<span spellcheck=\"false\"><a href=\"https:\/\/www.qiushibaike.com\">https:\/\/www.qiushibaike.com<\/a><\/span>\u4e3a\u4f8b\u5b50,\u8be5\u7f51\u7ad9\u505a\u4e86\u9632\u6b62\u722c\u53d6\u6570\u636e\u7684\u673a\u5236,\u5bf9\u4e8e\u4e0d\u662f\u6d4f\u89c8\u5668\u8bbf\u95ee\u7684\u884c\u4e3a,\u4e0d\u4f1a\u54cd\u5e94.\u9700\u8981\u8bbe\u7f6eUser-Agent(\u7528\u6237\u4ee3\u7406).\u6240\u4ee5\u9700\u8981\u5c06UA\u5c01\u88c5\u5230\u4e00\u4e2a\u5bf9\u8c61,\u8ba9urlopen\u4f7f\u7528\u5e26\u6709\u8fd9\u4e2aUA\u5934\u7684\u5bf9\u8c61\u53bb\u8bbf\u95ee\u7f51\u7ad9.<\/h5>\n<pre class=\"md-fences md-end-block\" lang=\"python\" contenteditable=\"false\">\r\n<span class=\"cm-comment\">#\u8c37\u6b4c\u7684UA<\/span>\r\n<span class=\"cm-variable\">user<\/span><span class=\"cm-operator\">-<\/span><span class=\"cm-variable\">agent<\/span>:<span class=\"cm-variable\">Mozilla<\/span><span class=\"cm-operator\">\/<\/span><span class=\"cm-number\">5.0<\/span> (<span class=\"cm-variable\">Windows<\/span> <span class=\"cm-variable\">NT<\/span> <span class=\"cm-number\">6.1<\/span>) <span class=\"cm-variable\">AppleWebKit<\/span><span class=\"cm-operator\">\/<\/span><span class=\"cm-number\">537.36<\/span> (<span class=\"cm-variable\">KHTML<\/span>, <span class=\"cm-variable\">like<\/span> <span class=\"cm-variable\">Gecko<\/span>) <span class=\"cm-variable\">Chrome<\/span><span class=\"cm-operator\">\/<\/span><span class=\"cm-number\">58.0.3029.96<\/span> <span class=\"cm-variable\">Safari<\/span><span class=\"cm-operator\">\/<\/span><span class=\"cm-number\">537.36<\/span>\r\n<span class=\"cm-comment\">#ie8\u7684UA<\/span>\r\n<span class=\"cm-variable\">User<\/span><span class=\"cm-operator\">-<\/span><span class=\"cm-variable\">Agent<\/span>:<span class=\"cm-variable\">Mozilla<\/span><span class=\"cm-operator\">\/<\/span><span class=\"cm-number\">4.0<\/span> (<span class=\"cm-variable\">compatible<\/span>; <span class=\"cm-variable\">MSIE<\/span> <span class=\"cm-number\">8.0<\/span>; <span class=\"cm-variable\">Windows<\/span> <span class=\"cm-variable\">NT<\/span> <span class=\"cm-number\">6.1<\/span>; <span class=\"cm-variable\">Trident<\/span><span class=\"cm-operator\">\/<\/span><span class=\"cm-number\">4.0<\/span>; <span class=\"cm-variable\">SLCC2<\/span>; .<span class=\"cm-property\">NET<\/span> <span class=\"cm-variable\">CLR<\/span> <span class=\"cm-number\">2.0.50727<\/span>; .<span class=\"cm-property\">NET<\/span> <span class=\"cm-variable\">CLR<\/span> <span class=\"cm-number\">3.5.30729<\/span>; .<span class=\"cm-property\">NET<\/span> <span class=\"cm-variable\">CLR<\/span> <span class=\"cm-number\">3.0.30729<\/span>; <span class=\"cm-variable\">Media<\/span> <span class=\"cm-variable\">Center<\/span> <span class=\"cm-variable\">PC<\/span> <span class=\"cm-number\">6.0<\/span>; .<span class=\"cm-property\">NET4<\/span><span class=\"cm-number\">.0<\/span><span class=\"cm-variable\">C<\/span>; .<span class=\"cm-property\">NET4<\/span><span class=\"cm-number\">.0<\/span><span class=\"cm-variable\">E<\/span>; <span class=\"cm-variable\">Tablet<\/span> <span class=\"cm-variable\">PC<\/span> <span class=\"cm-number\">2.0<\/span>; <span class=\"cm-variable\">InfoPath<\/span><span class=\"cm-number\">.3<\/span>; .<span class=\"cm-property\">NET<\/span> <span class=\"cm-variable\">CLR<\/span> <span class=\"cm-number\">1.1.4322<\/span>)<\/pre>\n<blockquote>\n<h5 class=\"md-end-block md-heading\">\u9996\u5148\u9700\u8981\u6784\u9020\u4e00\u4e2aRequest\u5305\u542bheaders,url<\/h5>\n<\/blockquote>\n<pre class=\"md-fences md-end-block\" lang=\"python\" contenteditable=\"false\"><span class=\"cm-comment\">#-*- coding:utf-8 -*-<\/span>\r\n<span class=\"cm-keyword\">import<\/span> <span class=\"cm-variable\">urllib2<\/span>\r\n<span class=\"cm-variable\">url<\/span>=<span class=\"cm-string\">'http:\/\/www.qiushibaike.com'<\/span> <span class=\"cm-comment\">#\u7cd7\u4e8b\u767e\u79d1\u7684\u7f51\u5740<\/span>\r\n<span class=\"cm-variable\">headers<\/span>={\r\n \u00a0<span class=\"cm-string\">'user-agent'<\/span>:<span class=\"cm-string\">'Mozilla\/5.0 (Windows NT 6.1) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/58.0.3029.96 Safari\/537.36'<\/span>,\r\n} <span class=\"cm-comment\">#\u6784\u9020\u4e00\u4e2aheader\u7684\u5b57\u5178\u5bf9\u8c61,\u952e\u503c\u5bf9\u662fUser-agent\u4ee5\u53ca\u5bf9\u5e94\u7684\u503c.\u5982\u679c\u4e0d\u6307\u5b9aUser-Agent,python\u4f1a\u9ed8\u8ba4\u4f7f\u7528Python-urllib\/2.6<\/span>\r\n\u200b\r\n<span class=\"cm-variable\">req<\/span>=<span class=\"cm-variable\">urllib2<\/span>.<span class=\"cm-property\">Request<\/span>(<span class=\"cm-variable\">url<\/span>,<span class=\"cm-variable\">headers<\/span>=<span class=\"cm-variable\">headers<\/span>) <span class=\"cm-comment\">#\u5c06url\u548c\u6784\u9020\u7684\u5934\u6587\u4ef6\u5b9e\u4f8b\u5316Request\u7c7b\u5230req<\/span>\r\n<span class=\"cm-variable\">r<\/span>=<span class=\"cm-variable\">urllib2<\/span>.<span class=\"cm-property\">urlopen<\/span>(<span class=\"cm-variable\">req<\/span>) \u00a0<span class=\"cm-comment\">#\u7528urlopen\u6253\u5f00\u8fd9\u4e2a\u5bf9\u8c61\u53bb\u8bf7\u6c42\u7cd7\u4e8b\u767e\u79d1<\/span>\r\n<span class=\"cm-variable\">h<\/span>=<span class=\"cm-variable\">r<\/span>.<span class=\"cm-property\">read<\/span>() \r\n<span class=\"cm-builtin\">print<\/span> <span class=\"cm-variable\">h<\/span><\/pre>\n<blockquote>\n<h5 class=\"md-end-block md-heading\">python3\u4ee3\u7801<\/h5>\n<\/blockquote>\n<pre class=\"md-fences md-end-block\" lang=\"python\" contenteditable=\"false\">\r\n<span class=\"cm-comment\">#python3\u4ee3\u7801<\/span>\r\n<span class=\"cm-keyword\">import<\/span> <span class=\"cm-variable\">urllib<\/span>.<span class=\"cm-property\">request<\/span>\r\n<span class=\"cm-variable\">url<\/span>=<span class=\"cm-string\">'http:\/\/www.qiushibaike.com'<\/span> <span class=\"cm-comment\">#\u7cd7\u4e8b\u767e\u79d1\u7684\u7f51\u5740<\/span>\r\n<span class=\"cm-variable\">headers<\/span>={\r\n \u00a0<span class=\"cm-string\">'user-agent'<\/span>:<span class=\"cm-string\">'Mozilla\/5.0 (Windows NT 6.1) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/58.0.3029.96 Safari\/537.36'<\/span>,\r\n} <span class=\"cm-comment\">#\u6784\u9020\u4e00\u4e2aheader\u7684\u5b57\u5178\u5bf9\u8c61,\u952e\u503c\u5bf9\u662fUser-agent\u4ee5\u53ca\u5bf9\u5e94\u7684\u503c.\u5982\u679c\u4e0d\u6307\u5b9aUser-Agent,python\u4f1a\u9ed8\u8ba4\u4f7f\u7528Python-urllib\/2.6<\/span>\r\n\u200b\r\n<span class=\"cm-variable\">req<\/span>=<span class=\"cm-variable\">urllib<\/span>.<span class=\"cm-property\">request<\/span>.<span class=\"cm-property\">Request<\/span>(<span class=\"cm-variable\">url<\/span>,<span class=\"cm-variable\">headers<\/span>=<span class=\"cm-variable\">headers<\/span>) <span class=\"cm-comment\">#\u5c06url\u548c\u6784\u9020\u7684\u5934\u6587\u4ef6\u5b9e\u4f8b\u5316Request\u7c7b\u5230req<\/span>\r\n<span class=\"cm-variable\">r<\/span>=<span class=\"cm-variable\">urllib<\/span>.<span class=\"cm-property\">request<\/span>.<span class=\"cm-property\">urlopen<\/span>(<span class=\"cm-variable\">req<\/span>) \u00a0<span class=\"cm-comment\">#\u7528urlopen\u6253\u5f00\u8fd9\u4e2a\u5bf9\u8c61\u53bb\u8bf7\u6c42\u7cd7\u4e8b\u767e\u79d1<\/span>\r\n<span class=\"cm-variable\">h<\/span>=<span class=\"cm-variable\">r<\/span>.<span class=\"cm-property\">read<\/span>() \r\n<span class=\"cm-builtin\">print<\/span>(<span class=\"cm-variable\">h<\/span>)<\/pre>\n<pre class=\"md-fences md-end-block\" lang=\"python\" contenteditable=\"false\">\r\n<span class=\"cm-comment\">#\u4e5f\u53ef\u4ee5\u4f7f\u7528<\/span>\r\n<span class=\"cm-variable\">req<\/span>.<span class=\"cm-property\">add_header<\/span>(<span class=\"cm-string\">'User-Agent'<\/span>,<span class=\"cm-string\">'Mozilla\/5.0 (Windows NT 6.1) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/58.0.3029.96 Safari\/537.36'<\/span>)\r\n<span class=\"cm-variable\">\u6dfb\u52a0header\u5230\u5bf9\u8c61<\/span>.<\/pre>\n<blockquote>\n<h5 class=\"md-end-block md-heading\">\u6548\u679c\u9884\u89c8<\/h5>\n<\/blockquote>\n<p><span class=\"md-line md-end-block\"><span class=\"md-image md-img-loaded\" contenteditable=\"false\" data-src=\"http:\/\/www.yueguangzu.net\/wp-content\/uploads\/2017\/08\/named3.png\"><img style=\"box-sizing: border-box; border-width: 0px 4px 0px 2px; border-image: initial; vertical-align: middle; max-width: 100%; cursor: default; border-color: initial transparent initial transparent; border-style: initial solid initial solid;\" src=\"http:\/\/www.yueguangzu.net\/wp-content\/uploads\/2017\/08\/named3.png\" \/><\/span><\/span><\/p>\n<p><span class=\"md-line md-end-block\"><span class=\"md-image md-img-loaded\" contenteditable=\"false\" data-src=\"http:\/\/www.yueguangzu.net\/wp-content\/uploads\/2017\/08\/named4.png\"><img style=\"box-sizing: border-box; border-width: 0px 4px 0px 2px; border-image: initial; vertical-align: middle; max-width: 100%; cursor: default; border-color: initial transparent initial transparent; border-style: initial solid initial solid;\" src=\"http:\/\/www.yueguangzu.net\/wp-content\/uploads\/2017\/08\/named4.png\" \/><\/span><\/span><\/p>\n<h5 class=\"md-end-block md-heading\">1.3<span spellcheck=\"false\"><code>geturl()<\/code><\/span>\u7684\u7528\u6cd5<\/h5>\n<ul class=\"ul-list\" data-mark=\"-\">\n<li>\n<h5 class=\"md-end-block md-heading\">geturl() \u2014 \u8fd4\u56de\u68c0\u7d22\u7684URL\u8d44\u6e90\uff0c\u8fd9\u4e2a\u662f\u8fd4\u56de\u7684\u771f\u6b63url\uff0c\u901a\u5e38\u662f\u7528\u6765\u9274\u5b9a\u662f\u5426\u91cd\u5b9a\u5411\u7684\uff0c\u5e38\u7528\u6765\u786e\u5b9a\u8981\u83b7\u53d6\u90a3\u4e2a\u6700\u7ec8\u7684\u4e0b\u8f7d\u5730\u5740.<\/h5>\n<\/li>\n<\/ul>\n<ul class=\"ul-list\" data-mark=\"-\">\n<li>\n<h5 class=\"md-end-block md-heading\">getcode() \u2014 \u8fd4\u56de\u54cd\u5e94\u7684HTTP\u72b6\u6001\u4ee3\u7801\uff0c\u6b63\u5e38\u8fd4\u56de\u72b6\u6001\u4e3acode=200,\u5982\u679c\u8fd4\u56de\u503c\u4e3a302,\u8bf4\u660e\u53d1\u751f\u4e86\u91cd\u5b9a\u5411\u3002<\/h5>\n<\/li>\n<\/ul>\n<h5 class=\"md-end-block md-heading\">1.4 <span spellcheck=\"false\"><code>HTTPCookieProcessor<\/code><\/span><\/h5>\n<h5 class=\"md-end-block md-heading\">\u5f88\u591a\u7f51\u7ad9\u9700\u8981\u767b\u5f55,\u767b\u5f55\u540e\u7684\u4fe1\u606f\u9ed8\u8ba4\u4fdd\u5b58\u5728cookies\u91cc.<\/h5>\n<blockquote>\n<h5 class=\"md-end-block md-heading\">\u5f88\u591a\u7f51\u7ad9\u7684\u8d44\u6e90\u9700\u8981\u7528\u6237\u767b\u5f55\u4e4b\u540e\u624d\u80fd\u83b7\u53d6\u3002<\/h5>\n<ul class=\"ul-list\" data-mark=\"-\">\n<li>\n<h5 class=\"md-end-block md-heading\">\u4e00\u822c\u6765\u8bf4\uff0c\u7528\u6237\u5728\u767b\u5f55\u4e4b\u540e\uff0c\u670d\u52a1\u5668\u7aef\u4f1a\u4e3a\u8be5\u7528\u6237\u521b\u5efa\u4e00\u4e2aSession\u3002Session\u76f8\u5f53\u4e8e\u8be5\u7528\u6237\u7684\u6863\u6848\u3002\u8be5\u6863\u6848\u5c31\u4ee3\u8868\u7740\u8be5\u7528\u6237\u3002<\/h5>\n<\/li>\n<li>\n<h5 class=\"md-end-block md-heading\">\u90a3\u4e48\u67d0\u4e00\u6b21\u8bbf\u95ee\u8bf7\u6c42\u662f\u5c5e\u4e8e\u8be5\u7528\u6237\u5462\uff1f\u767b\u5f55\u7684\u65f6\u5019\u670d\u52a1\u5668\u8981\u6c42\u6d4f\u89c8\u5668\u50a8\u5b58\u4e86\u4e00\u4e2aSession ID\u7684Cookie\u503c\u3002\u6bcf\u4e00\u4e2a\u8bbf\u95ee\u90fd\u5e26\u4e0a\u4e86\u8be5Cookie\u3002\u670d\u52a1\u5668\u5c06Cookie\u4e2d\u7684Session ID\u4e0e\u670d\u52a1\u5668\u4e2d\u7684Session ID\u6bd4\u5bf9\u5c31\u77e5\u9053\u8be5\u8bf7\u6c42\u6765\u81ea\u54ea\u4e2a\u7528\u6237\u4e86\u3002<\/h5>\n<\/li>\n<\/ul>\n<\/blockquote>\n<h5 class=\"md-end-block md-heading\">1.5 opener<\/h5>\n<blockquote>\n<h5 class=\"md-end-block md-heading\">\u6211\u4eec\u5728\u8c03\u7528urllib2.urlopen(url)\u7684\u65f6\u5019\uff0c\u5176\u5b9eurllib2\u5728open\u51fd\u6570\u5185\u90e8\u521b\u5efa\u4e86\u4e00\u4e2a\u9ed8\u8ba4\u7684opener\u5bf9\u8c61\u3002\u7136\u540e\u8c03\u7528opener.open()\u51fd\u6570\u3002\u4f46\u662f\u9ed8\u8ba4\u7684opener\u5e76\u4e0d\u652f\u6301cookie\u3002\u6240\u4ee5\u6211\u4eec\u5148\u65b0\u5efa\u4e00\u4e2a\u652f\u6301cookie\u7684opener\u3002urllib2\u4e2d\u4f9b\u6211\u4eec\u4f7f\u7528\u7684\u662fHTTPCookieProcessor\u3002\u521b\u5efaHTTPCookieProcessor\u9700\u8981\u4e00\u4e2a\u5b58\u653ecookie\u7684\u5bb9\u5668\u3002<\/h5>\n<\/blockquote>\n<pre class=\"md-fences md-end-block\" lang=\"python\" contenteditable=\"false\">\r\n<span class=\"cm-variable\">Python\u63d0\u4f9b\u7684\u5b58\u653ecookie\u7684\u5bb9\u5668\u4f4d\u4e8ecookielib\u6709\u4ee5\u4e0b\u51e0\u4e2a<\/span>:\r\n<span class=\"cm-variable\">CookieJar<\/span>\r\n<span class=\"cm-variable\">FileCookieJar<\/span>\r\n<span class=\"cm-variable\">MozillaCookieJar<\/span>\r\n<span class=\"cm-variable\">LWPCookieJar<\/span><\/pre>\n<h5 class=\"md-end-block md-heading\">\u4f7f\u7528opener\u8bf7\u6c42\u9875\u9762\u7684\u4e00\u4e2a\u4f8b\u5b50<\/h5>\n<pre class=\"md-fences md-end-block\" lang=\"python\" contenteditable=\"false\">\r\n<span class=\"cm-operator\">&gt;&gt;&gt;<\/span> <span class=\"cm-keyword\">import<\/span> <span class=\"cm-variable\">cookielib<\/span>\r\n<span class=\"cm-operator\">&gt;&gt;&gt;<\/span> <span class=\"cm-keyword\">import<\/span> <span class=\"cm-variable\">urllib2<\/span>\r\n<span class=\"cm-operator\">&gt;&gt;&gt;<\/span> <span class=\"cm-variable\">cookies<\/span>=<span class=\"cm-variable\">cookielib<\/span>.<span class=\"cm-property\">CookieJar<\/span>()\r\n<span class=\"cm-operator\">&gt;&gt;&gt;<\/span> <span class=\"cm-variable\">cookieHandler<\/span>=<span class=\"cm-variable\">urllib2<\/span>.<span class=\"cm-property\">HTTPCookieProcessor<\/span>(<span class=\"cm-variable\">cookiejar<\/span>=<span class=\"cm-variable\">cookies<\/span>)\r\n<span class=\"cm-operator\">&gt;&gt;&gt;<\/span> <span class=\"cm-variable\">opener<\/span>=<span class=\"cm-variable\">urllib2<\/span>.<span class=\"cm-property\">build_opener<\/span>(<span class=\"cm-variable\">cookieHandler<\/span>)\r\n<span class=\"cm-operator\">&gt;&gt;&gt;<\/span> <span class=\"cm-variable\">req<\/span>=<span class=\"cm-variable\">urllib2<\/span>.<span class=\"cm-property\">Request<\/span>(<span class=\"cm-string\">'http:\/\/www.yueguangzu.net'<\/span>)\r\n<span class=\"cm-operator\">&gt;&gt;&gt;<\/span> <span class=\"cm-variable\">r<\/span>=<span class=\"cm-variable\">urllib2<\/span>.<span class=\"cm-property\">urlopen<\/span>(<span class=\"cm-variable\">req<\/span>).<span class=\"cm-property\">read<\/span>()<\/pre>\n<blockquote>\n<h5 class=\"md-end-block md-heading\">python3\u7248\u672c<\/h5>\n<\/blockquote>\n<pre class=\"md-fences md-end-block\" lang=\"python\" contenteditable=\"false\">\r\n<span class=\"cm-operator\">&gt;&gt;&gt;<\/span> <span class=\"cm-keyword\">import<\/span> <span class=\"cm-variable\">http<\/span>.<span class=\"cm-property\">cookiejar<\/span> <span class=\"cm-comment\">#python3\u5c06cookielib\u6539\u6210\u4e86http.cookiejar<\/span>\r\n<span class=\"cm-operator\">&gt;&gt;&gt;<\/span> <span class=\"cm-keyword\">import<\/span> <span class=\"cm-variable\">urllib<\/span>.<span class=\"cm-property\">request<\/span> \r\n<span class=\"cm-operator\">&gt;&gt;&gt;<\/span> <span class=\"cm-variable\">cookies<\/span>=<span class=\"cm-variable\">http<\/span>.<span class=\"cm-property\">cookiejar<\/span>.<span class=\"cm-property\">CookieJar<\/span>()\r\n<span class=\"cm-operator\">&gt;&gt;&gt;<\/span> <span class=\"cm-variable\">cookieHandler<\/span>=<span class=\"cm-variable\">urllib<\/span>.<span class=\"cm-property\">request<\/span>.<span class=\"cm-property\">HTTPCookieProcessor<\/span>(<span class=\"cm-variable\">cookies<\/span>)\r\n<span class=\"cm-operator\">&gt;&gt;&gt;<\/span> <span class=\"cm-variable\">opener<\/span>=<span class=\"cm-variable\">urllib<\/span>.<span class=\"cm-property\">request<\/span>.<span class=\"cm-property\">build_opener<\/span>(<span class=\"cm-variable\">cookieHandler<\/span>)\r\n<span class=\"cm-operator\">&gt;&gt;&gt;<\/span> <span class=\"cm-variable\">req<\/span>=<span class=\"cm-variable\">urllib<\/span>.<span class=\"cm-property\">request<\/span>.<span class=\"cm-property\">Request<\/span>(<span class=\"cm-string\">'http:\/\/www.yueguangzu.net'<\/span>)\r\n<span class=\"cm-operator\">&gt;&gt;&gt;<\/span> <span class=\"cm-variable\">r<\/span>=<span class=\"cm-variable\">urllib<\/span>.<span class=\"cm-property\">request<\/span>.<span class=\"cm-property\">urlopen<\/span>(<span class=\"cm-variable\">req<\/span>).<span class=\"cm-property\">read<\/span>()<\/pre>\n<h2 class=\"md-end-block md-heading\">\u603b\u7ed3<\/h2>\n<h5 class=\"md-end-block md-heading\">urllib,urllib2\u662fpython\u81ea\u5e26\u7684\u8bf7\u6c42\u9875\u9762\u6570\u636e\u7684\u6a21\u5757,\u4e24\u8005\u9700\u7ed3\u5408\u4f7f\u7528,\u53ef\u4ee5\u5b8c\u6210\u5927\u90e8\u5206\u7684\u7f51\u9875\u91c7\u96c6\u5de5\u4f5c.\u6d89\u53ca\u4f1a\u8bdd,\u5219\u9700\u8981\u91c7\u7528cookielib\u5e93\u521b\u5efa\u5e26\u6709cookie\u7684opener\u5b8c\u6210\u8bf7\u6c42.\u63a5\u4e0b\u6765\u768412306\u767b\u9646,\u67e5\u8be2\u5c06\u4f1a\u6d89\u53ca\u5230,\u6240\u4ee5\u9700\u8981\u719f\u6089\u638c\u63e1.<\/h5>\n","protected":false},"excerpt":{"rendered":"<p>1.\u8ba4\u8bc6urllib\u548curllib2\u6a21\u5757 Python\u8bf7\u6c42URL\u76f8\u5173\u7684\u64cd\u4f5c,\u9700\u8981\u4f7f\u7528\u5230\u76f8\u5173\u6a21\u5757,\u5728python2\u4e2d,\u5982\u679c\u4e0d\u4f9d\u8d56\u4e8e\u7b2c\u4e09\u65b9\u6846\u67b6\u6216\u8005\u6a21\u5757,\u90a3\u4e48urllib\u548curllib2\u662f\u6700\u5e38\u7528\u7684. \u901a\u5e38,urllib\u548curllib2\u662f\u8054\u5408\u4f7f\u7528\u7684 [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[54],"tags":[72,76,74,73,75],"_links":{"self":[{"href":"http:\/\/www.yueguangzu.net\/index.php?rest_route=\/wp\/v2\/posts\/1337"}],"collection":[{"href":"http:\/\/www.yueguangzu.net\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.yueguangzu.net\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.yueguangzu.net\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"http:\/\/www.yueguangzu.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1337"}],"version-history":[{"count":2,"href":"http:\/\/www.yueguangzu.net\/index.php?rest_route=\/wp\/v2\/posts\/1337\/revisions"}],"predecessor-version":[{"id":1343,"href":"http:\/\/www.yueguangzu.net\/index.php?rest_route=\/wp\/v2\/posts\/1337\/revisions\/1343"}],"wp:attachment":[{"href":"http:\/\/www.yueguangzu.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1337"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.yueguangzu.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1337"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.yueguangzu.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1337"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}