{"id":895,"date":"2013-08-13T13:28:42","date_gmt":"2013-08-13T05:28:42","guid":{"rendered":"http:\/\/www.hawkwithwind.net\/blog\/?p=895"},"modified":"2013-08-13T13:34:44","modified_gmt":"2013-08-13T05:34:44","slug":"python-urllib2-%e9%87%8d%e5%ae%9a%e5%90%91%e6%97%b6%e8%8e%b7%e5%8f%96cookie","status":"publish","type":"post","link":"https:\/\/www.hawkwithwind.net\/blog\/2013\/08\/13\/python-urllib2-%e9%87%8d%e5%ae%9a%e5%90%91%e6%97%b6%e8%8e%b7%e5%8f%96cookie\/","title":{"rendered":"python urllib2 \u91cd\u5b9a\u5411\u65f6\u83b7\u53d6cookie"},"content":{"rendered":"<p>\u6700\u8fd1\u7528python\u5199\u4e00\u4e2a\u7b80\u5355\u7684\u722c\u866b\uff0c\u5728\u6a21\u62df\u7f51\u7ad9\u767b\u5f55\u65f6\u9047\u5230\u95ee\u9898\uff0c\u5c31\u662f\u767b\u5f55\u540e\u7d27\u8ddf\u7740302\u91cd\u5b9a\u5411\uff0c\u8fd9\u65f6\u5019cookie\u83b7\u53d6\u6ca1\u505a\u597d\uff0c\u5c31\u4f1a\u767b\u5f55\u5931\u8d25\u3002<\/p>\n<p>\u7f51\u4e0a\u627e\u4e86\u5f88\u591a\u6587\u7ae0\uff0c\u53ef\u80fd\u662f\u56e0\u4e3apython\u7248\u672c\u4e0d\u540c\u4e4b\u7c7b\u7684\u539f\u56e0\u5427\uff0c\u5f88\u591a\u65b9\u6cd5\u8bd5\u4e86\u90fd\u6ca1\u7528\u3002\u8fd9\u91cc\u8e0f\u7834\u94c1\u978b\u627e\u5230\u4e86\u53ef\u7528\u7684\u65b9\u6848\uff0c\u8bb0\u5f55\u4e00\u4e0b\uff0c\u5e0c\u671b\u80fd\u5e2e\u5230\u540e\u6765\u7684\u670b\u53cb\u3002<br \/>\n\u9274\u4e8epython\u7684\u7248\u672c\u6d46\u7cca\u95ee\u9898\uff0c\u8fd9\u91cc\u58f0\u660e\u4e0b\uff0c\u6211\u4f7f\u7528\u7684python\u7248\u672c2.7.3\uff0c\u5e76\u4e14\u4f7f\u7528\u7684\u662furllib2\u5e93\u3002<\/p>\n<p>\u89e3\u51b3\u8fd9\u4e2a\u95ee\u9898\uff0c\u5176\u5b9e\u8bf4\u8d77\u6765\u5f88\u7b80\u5355\uff0c\u5c31\u662f\u8981\u81ea\u5df1\u5b9a\u4e49\u4e00\u4e2aRedirectHandler,\u5728\u521b\u5efaopener\u7684\u65f6\u5019\u4f5c\u4e3a\u53c2\u6570\u653e\u8fdb\u53bb\u3002<br \/>\n<code class=\"python\"><\/p>\n<pre>\r\n    cj = cookielib.LWPCookieJar()\r\n    opener = urllib2.build_opener(MyRedirectHandler,\r\n                                  urllib2.HTTPCookieProcessor(cj))\r\n<\/pre>\n<p><\/code><\/p>\n<p>\u8fd9\u91cc\u6211\u8fd8\u8981\u8bb0\u5f55cookie\u4fe1\u606f\u56e0\u6b64\u8fd8\u4f7f\u7528\u4e86cookiejar\u3002<br \/>\n\u73b0\u5728\u96be\u70b9\u5c31\u5728\u4e8e\u8fd9\u4e2aRedirectHandler\u5982\u4f55\u91cd\u5199\u4e86\u3002<br \/>\n<code class=\"python\"><\/p>\n<pre>\r\n    urllib2.HTTPRedirectHandler.http_error_302(self, req, fp, \r\n                                               code, msg, headers)\r\n<\/pre>\n<p><\/code><br \/>\n\u901a\u8fc7\u8fd9\u6837\u4e00\u53e5\u8c03\u7528\uff0c\u9ed8\u8ba4\u7684redirectHandler\u5df2\u7ecf\u652f\u6301\u5728\u53d1\u73b0302\u5934\u90e8\u7684\u65f6\u5019\u81ea\u52a8\u8df3\u8f6c\u5230\u65b0\u7684location\u53bb\u3002\u4f46\u95ee\u9898\u662f\u8fd4\u56de\u7684response\u4e2d\u7f3a\u5c11\u4e86\u524d\u4e00\u4e2a\u8bf7\u6c42\u8fd4\u56de\u7684cookie\u4fe1\u606f\u3002\u56e0\u6b64\u91cd\u70b9\u662f\u5982\u4f55\u5728redirect handle\u4e2d\u628a\u524d\u4e00\u4e2a\u8bf7\u6c42\u7684cookie\u8bbe\u7f6e\u5230\u65b0\u7684\u8bf7\u6c42\u4e2d\u53bb\u3002<\/p>\n<p><code class=\"python\"><\/p>\n<pre>\r\nclass MyRedirectHandler(urllib2.HTTPRedirectHandler):\r\n    def http_error_302(self, req, fp, code, msg, headers):\r\n        setcookie = str(headers[\"Set-Cookie\"])\r\n        cookieTokens = [\"Domain\",\"Expires\", \"Path\", \"Max-Age\"]\r\n        tokens = setcookie.split(\";\")\r\n        for cookie in tokens:\r\n            cookie = cookie.strip()\r\n            if cookie.startswith(\"Expires=\"):\r\n                cookies = cookie.split(\",\", 2)\r\n                if len(cookies) > 2:\r\n                    cookie = cookies[2]\r\n                    cookie = cookie.strip()\r\n            else :\r\n                cookies = cookie.split(\",\", 1)\r\n                if len(cookies) > 1:\r\n                    cookie = cookies[1]\r\n                    cookie = cookie.strip()\r\n            namevalue = cookie.split(\"=\", 1)\r\n            if len(namevalue) > 1:\r\n                name = namevalue[0]\r\n                value = namevalue[1]\r\n                if name not in cookieTokens:\r\n                    cookiemap[name] = value\r\n\r\n        newcookie = cookiestring(cookiemap)\r\n        req.add_header(\"Cookie\", newcookie)\r\n        return urllib2.HTTPRedirectHandler.http_error_302(\r\n                         self, req, fp, code, msg, headers)\r\n<\/pre>\n<p><\/code><\/p>\n<p>\u8fd9\u91cc\u6211\u5904\u7406cookie\u4f7f\u7528\u4e86\u6bd4\u8f83\u571f\u7684\u65b9\u6cd5\u624b\u52a8\u89e3\u6790\u7684\uff0c\u5404\u4f4d\u5982\u679c\u6709\u66f4\u597d\u7684\u65b9\u6cd5\u4e5f\u8bf7\u4e0d\u541d\u8d50\u6559\u3002<br \/>\n\u91cd\u70b9\u5176\u5b9e\u5c31\u662f\u90a3\u4e00\u53e5req.add_header(&#8220;Cookie&#8221;, newcookie)\uff0c\u8fd9\u91cc\u662f\u4eceset-cookie\u4e2d\u89e3\u6790\u51facookie\u4e32\u540e\u62fc\u63a5\u6210\u8bf7\u6c42\u5934\u586b\u5165req\u4e2d\uff0c\u5728\u63a5\u4e0b\u6765\u7684\u4e00\u53e5\u8c03\u7528\u9ed8\u8ba4handle\u7684\u51fd\u6570\u65f6\u8bf7\u6c42\u5934\u5c31\u4f1a\u9644\u6709\u65b0\u7684cookie\u4fe1\u606f\u4e86\u3002<\/p>\n<p>\u5982\u6b64\u5904\u7406\u540e\u7684\u8bf7\u6c42\uff0c\u8fd4\u56de\u540e\u5373\u53ef\u4eceresponse\u4e2d\u8bfb\u53d6\u51facookie\u4fe1\u606f<br \/>\n<code class=\"python\"><\/p>\n<pre>\r\n    response = opener.open(request)\r\n    cookies = cj.make_cookies(response, request)\r\n<\/pre>\n<p><\/code><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u6700\u8fd1\u7528python\u5199\u4e00\u4e2a\u7b80\u5355\u7684\u722c\u866b\uff0c\u5728\u6a21\u62df\u7f51\u7ad9\u767b\u5f55\u65f6\u9047\u5230\u95ee\u9898\uff0c\u5c31\u662f\u767b\u5f55\u540e\u7d27\u8ddf\u7740302\u91cd\u5b9a\u5411\uff0c\u8fd9\u65f6\u5019cookie\u83b7\u53d6\u6ca1\u505a\u597d\uff0c\u5c31\u4f1a\u767b\u5f55\u5931\u8d25\u3002 \u7f51\u4e0a\u627e\u4e86\u5f88\u591a\u6587\u7ae0\uff0c\u53ef\u80fd\u662f\u56e0\u4e3apython\u7248\u672c\u4e0d\u540c\u4e4b\u7c7b\u7684\u539f\u56e0\u5427\uff0c\u5f88\u591a\u65b9\u6cd5\u8bd5\u4e86\u90fd\u6ca1\u7528\u3002\u8fd9\u91cc\u8e0f\u7834\u94c1\u978b\u627e\u5230\u4e86\u53ef\u7528\u7684\u65b9\u6848\uff0c\u8bb0\u5f55\u4e00\u4e0b\uff0c\u5e0c\u671b\u80fd\u5e2e\u5230\u540e\u6765\u7684\u670b\u53cb\u3002 \u9274\u4e8epython\u7684\u7248\u672c\u6d46\u7cca\u95ee\u9898\uff0c\u8fd9\u91cc\u58f0\u660e\u4e0b\uff0c\u6211\u4f7f\u7528\u7684python\u7248\u672c2.7.3\uff0c\u5e76\u4e14\u4f7f\u7528\u7684\u662furllib2\u5e93\u3002 \u89e3\u51b3\u8fd9\u4e2a\u95ee\u9898\uff0c\u5176\u5b9e\u8bf4\u8d77\u6765\u5f88\u7b80\u5355\uff0c\u5c31\u662f\u8981\u81ea\u5df1\u5b9a\u4e49\u4e00\u4e2aRedirectHandler,\u5728\u521b\u5efaopener\u7684\u65f6\u5019\u4f5c\u4e3a\u53c2\u6570\u653e\u8fdb\u53bb\u3002 cj = cookielib.LWPCookieJar() opener = urllib2.build_opener(MyRedirectHandler, urllib2.HTTPCookieProcessor(cj)) \u8fd9\u91cc\u6211\u8fd8\u8981\u8bb0\u5f55cookie\u4fe1\u606f\u56e0\u6b64\u8fd8\u4f7f\u7528\u4e86cookiejar\u3002 \u73b0\u5728\u96be\u70b9\u5c31\u5728\u4e8e\u8fd9\u4e2aRedirectHandler\u5982\u4f55\u91cd\u5199\u4e86\u3002 urllib2.HTTPRedirectHandler.http_error_302(self, req, fp, code, msg, headers) \u901a\u8fc7\u8fd9\u6837\u4e00\u53e5\u8c03\u7528\uff0c\u9ed8\u8ba4\u7684redirectHandler\u5df2\u7ecf\u652f\u6301\u5728\u53d1\u73b0302\u5934\u90e8\u7684\u65f6\u5019\u81ea\u52a8\u8df3\u8f6c\u5230\u65b0\u7684location\u53bb\u3002\u4f46\u95ee\u9898\u662f\u8fd4\u56de\u7684response\u4e2d\u7f3a\u5c11\u4e86\u524d\u4e00\u4e2a\u8bf7\u6c42\u8fd4\u56de\u7684cookie\u4fe1\u606f\u3002\u56e0\u6b64\u91cd\u70b9\u662f\u5982\u4f55\u5728redirect handle\u4e2d\u628a\u524d\u4e00\u4e2a\u8bf7\u6c42\u7684cookie\u8bbe\u7f6e\u5230\u65b0\u7684\u8bf7\u6c42\u4e2d\u53bb\u3002 class MyRedirectHandler(urllib2.HTTPRedirectHandler): def http_error_302(self, req, fp, code, msg, headers): setcookie = str(headers[&#8220;Set-Cookie&#8221;]) cookieTokens = [&#8220;Domain&#8221;,&#8221;Expires&#8221;, &#8220;Path&#8221;, &#8220;Max-Age&#8221;] tokens = setcookie.split(&#8220;;&#8221;) for cookie in tokens: cookie = cookie.strip() if cookie.startswith(&#8220;Expires=&#8221;): cookies = cookie.split(&#8220;,&#8221;, 2) if &hellip;<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3],"tags":[71,73,69,72,70,51],"class_list":["post-895","post","type-post","status-publish","format-standard","hentry","category-post","tag-cookie","tag-http","tag-python","tag-redirect","tag-70","tag-51"],"_links":{"self":[{"href":"https:\/\/www.hawkwithwind.net\/blog\/wp-json\/wp\/v2\/posts\/895","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.hawkwithwind.net\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.hawkwithwind.net\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.hawkwithwind.net\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.hawkwithwind.net\/blog\/wp-json\/wp\/v2\/comments?post=895"}],"version-history":[{"count":4,"href":"https:\/\/www.hawkwithwind.net\/blog\/wp-json\/wp\/v2\/posts\/895\/revisions"}],"predecessor-version":[{"id":899,"href":"https:\/\/www.hawkwithwind.net\/blog\/wp-json\/wp\/v2\/posts\/895\/revisions\/899"}],"wp:attachment":[{"href":"https:\/\/www.hawkwithwind.net\/blog\/wp-json\/wp\/v2\/media?parent=895"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.hawkwithwind.net\/blog\/wp-json\/wp\/v2\/categories?post=895"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.hawkwithwind.net\/blog\/wp-json\/wp\/v2\/tags?post=895"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}