{"id":932,"date":"2021-03-10T18:06:21","date_gmt":"2021-03-10T10:06:21","guid":{"rendered":"http:\/\/www.tra56.com\/?p=932"},"modified":"2021-03-10T18:06:21","modified_gmt":"2021-03-10T10:06:21","slug":"932","status":"publish","type":"post","link":"https:\/\/www.tra56.com\/932.html","title":{"rendered":"PHP \u641c\u7d22\u5f15\u64ce\u8718\u86db\u8bbf\u95ee\u68c0\u6d4b\u548c\u7edf\u8ba1"},"content":{"rendered":"<p><span style=\"color: rgb(77, 77, 77); font-family: -apple-system, &quot;SF UI Text&quot;, Arial, &quot;PingFang SC&quot;, &quot;Hiragino Sans GB&quot;, &quot;Microsoft YaHei&quot;, &quot;WenQuanYi Micro Hei&quot;, sans-serif, SimHei, SimSun; background-color: rgb(255, 255, 255);\">1.\u5efa\u7acb\u4e00\u4e2a\u6570\u636e\u5e93<\/span><\/p>\n<pre class=\"brush:sql;toolbar:false\">create&nbsp;table&nbsp;crawler&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;\r\n(&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;\r\n&nbsp;&nbsp;&nbsp;&nbsp;crawler_ID&nbsp;bigint(20)&nbsp;unsigned&nbsp;not&nbsp;null&nbsp;auto_increment&nbsp;primary&nbsp;key,&nbsp;\r\n&nbsp;&nbsp;&nbsp;&nbsp;crawler_category&nbsp;varchar(20)&nbsp;not&nbsp;null,&nbsp;\r\n&nbsp;&nbsp;&nbsp;&nbsp;crawler_date&nbsp;datetime&nbsp;not&nbsp;null&nbsp;default&nbsp;&#39;0000-00-00&nbsp;00:00:00&#39;,\r\n&nbsp;&nbsp;&nbsp;&nbsp;crawler_url&nbsp;varchar(50)&nbsp;not&nbsp;null,&nbsp;\r\n&nbsp;&nbsp;&nbsp;&nbsp;crawler_IP&nbsp;varchar(50)&nbsp;not&nbsp;null\r\n)default&nbsp;charset=utf8;<\/pre>\n<p><span style=\"color: rgb(77, 77, 77); font-family: -apple-system, &quot;SF UI Text&quot;, Arial, &quot;PingFang SC&quot;, &quot;Hiragino Sans GB&quot;, &quot;Microsoft YaHei&quot;, &quot;WenQuanYi Micro Hei&quot;, sans-serif, SimHei, SimSun; background-color: rgb(255, 255, 255);\">2.\u901a\u8fc7PHP\u811a\u672c\u68c0\u6d4b\u7edf\u8ba1\u6570\u636e<\/span><\/p>\n<pre class=\"brush:php;toolbar:false\">&lt;?php\r\n&nbsp;&nbsp;&nbsp;&nbsp;$ServerName&nbsp;=&nbsp;$_SERVER[&quot;SERVER_NAME&quot;]&nbsp;;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;\r\n\t$ServerPort&nbsp;=&nbsp;$_SERVER[&quot;SERVER_PORT&quot;]&nbsp;;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;\r\n\t$ScriptName&nbsp;=&nbsp;$_SERVER[&quot;SCRIPT_NAME&quot;]&nbsp;;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;\r\n\t$QueryString&nbsp;=&nbsp;$_SERVER[&quot;QUERY_STRING&quot;];&nbsp;&nbsp;&nbsp;&nbsp;\r\n\t$serverip&nbsp;=&nbsp;$_SERVER[&quot;REMOTE_ADDR&quot;]&nbsp;;&nbsp;&nbsp;&nbsp;\r\n\t$Url=&quot;http:\/\/&quot;.$ServerName;\r\n\tif&nbsp;($ServerPort&nbsp;!=&nbsp;&quot;80&quot;)&nbsp;\r\n\t{\r\n\t\t$Url&nbsp;=&nbsp;$Url.&quot;:&quot;.$ServerPort&nbsp;;&nbsp;\r\n\t}&nbsp;&nbsp;&nbsp;&nbsp;\r\n\t$Url=$Url.$ScriptName;\r\n\tif&nbsp;($QueryString&nbsp;!=&quot;&quot;)\r\n\t{\r\n\t\t$Url=$Url.&quot;?&quot;.$QueryString;&nbsp;\r\n\t}&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;\r\n\t$GetLocationURL=$Url&nbsp;;\r\n&nbsp;&nbsp;&nbsp;&nbsp;$agent1&nbsp;=&nbsp;$_SERVER[&quot;HTTP_USER_AGENT&quot;];&nbsp;&nbsp;\r\n\t$agent=strtolower($agent1);\r\n\t$Bot&nbsp;=&quot;&quot;;\r\n&nbsp;&nbsp;&nbsp;&nbsp;if&nbsp;(strpos($agent,&quot;bot&quot;)&gt;-1)\r\n\t{\r\n\t\t$Bot&nbsp;=&nbsp;&quot;Other&nbsp;Crawler&quot;;\r\n\t}\r\n\tif&nbsp;(strpos($agent,&quot;googlebot&quot;)&gt;-1)\r\n\t{\r\n\t\t$Bot&nbsp;=&nbsp;&quot;Google&quot;;\r\n\t}&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;\r\n&nbsp;&nbsp;&nbsp;&nbsp;if&nbsp;(strpos($agent,&quot;mediapartners-google&quot;)&gt;-1)\r\n\t{\r\n\t\t$Bot&nbsp;=&nbsp;&quot;Google&nbsp;Adsense&quot;;\r\n\t}\r\n\tif&nbsp;(strpos($agent,&quot;baiduspider&quot;)&gt;-1)\r\n\t{\r\n\t\t$Bot&nbsp;=&nbsp;&quot;Baidu&quot;;\r\n\t}\r\n\tif&nbsp;(strpos($agent,&quot;sogou&nbsp;spider&quot;)&gt;-1)\r\n\t{\r\n\t\t$Bot&nbsp;=&nbsp;&quot;Sogou&quot;;\r\n\t}\r\n\tif&nbsp;(strpos($agent,&quot;yahoo&quot;)&gt;-1)\r\n\t{\r\n\t\t$Bot&nbsp;=&nbsp;&quot;Yahoo!&quot;;\r\n\t}\r\n\tif&nbsp;(strpos($agent,&quot;msn&quot;)&gt;-1)\r\n\t{\r\n\t\t$Bot&nbsp;=&nbsp;&quot;MSN&quot;;\r\n\t}\r\n\tif&nbsp;(strpos($agent,&quot;ia_archiver&quot;)&gt;-1)\r\n\t{\r\n\t\t$Bot&nbsp;=&nbsp;&quot;Alexa&quot;;\r\n\t}\r\n\tif&nbsp;(strpos($agent,&quot;iaarchiver&quot;)&gt;-1)\r\n\t{\r\n\t\t$Bot&nbsp;=&nbsp;&quot;Alexa&quot;;\r\n\t}\r\n\tif&nbsp;(strpos($agent,&quot;sohu&quot;)&gt;-1)\r\n\t{\r\n\t\t$Bot&nbsp;=&nbsp;&quot;Sohu&quot;;\r\n\t}\r\n\tif&nbsp;(strpos($agent,&quot;sqworm&quot;)&gt;-1)&nbsp;\r\n\t{\r\n\t\t$Bot&nbsp;=&nbsp;&quot;AOL&quot;;\r\n\t}\r\n\tif&nbsp;(strpos($agent,&quot;yodaoBot&quot;)&gt;-1)\r\n\t{\r\n\t\t$Bot&nbsp;=&nbsp;&quot;Yodao&quot;;\r\n\t}\r\n\tif&nbsp;(strpos($agent,&quot;iaskspider&quot;)&gt;-1)\r\n\t{\r\n\t\t$Bot&nbsp;=&nbsp;&quot;Iask&quot;;\r\n\t}\r\n\t&nbsp;&nbsp;&nbsp;\r\n\trequire(&quot;.\/dbinfo.php&quot;);\r\n\t\r\n&nbsp;&nbsp;&nbsp;&nbsp;date_default_timezone_set(&#39;PRC&#39;);&nbsp;&nbsp;\r\n\t$shijian=date(&quot;Y-m-d&nbsp;h:i:s&quot;,&nbsp;time());\r\n\t\r\n\t\/\/&nbsp;\u8fde\u63a5\u5230&nbsp;MySQL&nbsp;\u670d\u52a1\u5668\r\n\t$connection&nbsp;=&nbsp;mysql_connect&nbsp;($host,&nbsp;$username,&nbsp;$password);\r\n\tif&nbsp;(!$connection)&nbsp;\r\n\t{\r\n&nbsp;&nbsp;\t\tdie(&#39;Not&nbsp;connected&nbsp;:&nbsp;&#39;&nbsp;.&nbsp;mysql_error());\r\n\t}\r\n\t\r\n\t\/\/&nbsp;\u8bbe\u7f6e\u6d3b\u52a8\u7684&nbsp;MySQL&nbsp;\u6570\u636e\u5e93\r\n\t$db_selected&nbsp;=&nbsp;mysql_select_db($database,&nbsp;$connection);\r\n\tif&nbsp;(!$db_selected)&nbsp;\r\n\t{\r\n&nbsp;&nbsp;\t\tdie&nbsp;(&#39;Can\\&#39;t&nbsp;use&nbsp;db&nbsp;:&nbsp;&#39;&nbsp;.&nbsp;mysql_error());\r\n\t}\r\n\t\r\n\t\/\/&nbsp;\u5411\u6570\u636e\u5e93\u63d2\u5165\u6570\u636e\r\n\t$query&nbsp;=&nbsp;&quot;insert&nbsp;into&nbsp;crawler&nbsp;(crawler_category,&nbsp;crawler_date,&nbsp;crawler_url,&nbsp;crawler_IP)&nbsp;values&nbsp;(&#39;$Bot&#39;,&#39;$shijian&#39;,&#39;$GetLocationURL&#39;,&#39;$serverip&#39;)&quot;;&nbsp;\r\n\t\r\n\t$result&nbsp;=&nbsp;mysql_query($query);\r\n\tif&nbsp;(!$result)&nbsp;\r\n\t{\r\n&nbsp;&nbsp;\t\tdie(&#39;Invalid&nbsp;query:&nbsp;&#39;&nbsp;.&nbsp;mysql_error());\r\n\t}\r\n\t&nbsp;\r\n?&gt;<\/pre>\n<p><span style=\"color: rgb(77, 77, 77); font-family: -apple-system, &quot;SF UI Text&quot;, Arial, &quot;PingFang SC&quot;, &quot;Hiragino Sans GB&quot;, &quot;Microsoft YaHei&quot;, &quot;WenQuanYi Micro Hei&quot;, sans-serif, SimHei, SimSun; background-color: rgb(255, 255, 255);\">3.\u663e\u793a\u7edf\u8ba1\u6570\u636e<\/span><\/p>\n<pre class=\"brush:php;toolbar:false\">&lt;?php\r\ninclude&nbsp;&#39;.\/robot.php&#39;;\r\ninclude&nbsp;&#39;..\/library\/page.Class.php&#39;;\r\n$page&nbsp;=&nbsp;$_GET[&#39;page&#39;];\r\n&nbsp;\r\n&nbsp;\r\ninclude&nbsp;&#39;..\/library\/conn_new.php&#39;;\r\n\t\t\r\n$count&nbsp;=&nbsp;$mysql&nbsp;-&gt;&nbsp;num_rows($mysql&nbsp;-&gt;&nbsp;query(&quot;select&nbsp;*&nbsp;&nbsp;from&nbsp;crawler&quot;));\r\n$pages&nbsp;=&nbsp;new&nbsp;PageClass($count,25,$_GET[&#39;page&#39;],$_SERVER[&#39;PHP_SELF&#39;].&#39;?page={page}&#39;);\r\n$sql&nbsp;&nbsp;=&nbsp;&quot;select&nbsp;*&nbsp;from&nbsp;crawler&nbsp;order&nbsp;by&nbsp;&quot;;\r\n$sql&nbsp;.=&nbsp;&quot;crawler_date&nbsp;desc&nbsp;limit&nbsp;&quot;.$pages&nbsp;-&gt;&nbsp;page_limit.&quot;,&quot;.$pages&nbsp;-&gt;&nbsp;myde_size;\r\n$result&nbsp;=&nbsp;$mysql&nbsp;-&gt;&nbsp;query($sql);\r\n?&gt;\r\n&nbsp;\r\n&lt;table&nbsp;width=&quot;700&quot;&gt;\r\n\t&lt;thead&gt;\r\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&lt;tr&gt;&nbsp;&nbsp;\r\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;\t&lt;td&nbsp;bgcolor=&quot;#CCFFFF&quot;&gt;&lt;\/td&gt;&nbsp;&nbsp;\r\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;\t&lt;td&nbsp;bgcolor=&quot;#CCFFFF&quot;&nbsp;align=&quot;center&quot;&nbsp;style=&quot;color:#555&quot;&gt;\u722c\u866b\u8bbf\u95ee\u65f6\u95f4&lt;\/td&gt;&nbsp;&nbsp;\r\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;\t&lt;td&nbsp;bgcolor=&quot;#CCFFFF&quot;&nbsp;align=&quot;center&quot;&nbsp;style=&quot;color:#555&quot;&gt;\u722c\u866b\u5206\u7c7b&lt;\/td&gt;&nbsp;\r\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;\t&lt;td&nbsp;bgcolor=&quot;#CCFFFF&quot;&nbsp;align=&quot;center&quot;&nbsp;style=&quot;color:#555&quot;&gt;\u722c\u866bIP&lt;\/td&gt;&nbsp;\r\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&lt;td&nbsp;bgcolor=&quot;#CCFFFF&quot;&nbsp;align=&quot;center&quot;&nbsp;style=&quot;color:#555&quot;&gt;\u722c\u866b\u8bbf\u95ee\u7684URL&lt;\/td&gt;&nbsp;\r\n&nbsp;\t\t&lt;\/tr&gt;&nbsp;\r\n\t&lt;\/thead&gt;\r\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;\r\n&lt;?php\r\nwhile($myrow&nbsp;=&nbsp;$mysql&nbsp;-&gt;&nbsp;fetch_array($result)){\r\n?&gt;\r\n&lt;tr&gt;\r\n&nbsp;&nbsp;&nbsp;&nbsp;&lt;td&nbsp;width=&quot;30&quot;&gt;&lt;img&nbsp;src=&quot;..\/images\/topicnew.gif&quot;&nbsp;\/&gt;&lt;\/td&gt;\r\n&nbsp;&nbsp;&nbsp;&nbsp;&lt;td&nbsp;width=&quot;150&quot;&nbsp;style=&quot;font-family:Georgia&quot;&gt;&lt;?&nbsp;echo&nbsp;$myrow[&quot;crawler_date&quot;]&nbsp;?&gt;&lt;\/td&gt;\r\n&nbsp;&nbsp;&nbsp;&nbsp;&lt;td&nbsp;width=&quot;100&quot;&nbsp;style=&quot;color:#5F7A77&quot;&gt;&lt;?&nbsp;echo&nbsp;$myrow[&quot;crawler_category&quot;]&nbsp;?&gt;&lt;\/td&gt;\r\n&nbsp;&nbsp;&nbsp;&nbsp;&lt;td&nbsp;width=&quot;100&quot;&gt;&lt;?&nbsp;echo&nbsp;$myrow[&quot;crawler_IP&quot;]&nbsp;?&gt;&lt;\/td&gt;\r\n&nbsp;&nbsp;&nbsp;&nbsp;&lt;td&nbsp;width=&quot;320&quot;&gt;&lt;?&nbsp;echo&nbsp;$myrow[&quot;crawler_url&quot;]&nbsp;?&gt;&lt;\/td&gt;\r\n&lt;\/tr&gt;\r\n&lt;?php\r\n\t}\r\n?&gt;\r\n&nbsp;&nbsp;&nbsp;&nbsp;&lt;\/table&gt;\r\n&lt;?php\r\n&nbsp;&nbsp;\techo&nbsp;$pages&nbsp;-&gt;&nbsp;myde_write();\r\n?&gt;<\/pre>\n<p><span style=\"color: rgb(77, 77, 77); font-family: -apple-system, &quot;SF UI Text&quot;, Arial, &quot;PingFang SC&quot;, &quot;Hiragino Sans GB&quot;, &quot;Microsoft YaHei&quot;, &quot;WenQuanYi Micro Hei&quot;, sans-serif, SimHei, SimSun; background-color: rgb(255, 255, 255);\">4.\u68c0\u6d4b\u662f\u5426\u662f\u722c\u866b<\/span><\/p>\n<pre class=\"brush:php;toolbar:false\">function&nbsp;isRobot()&nbsp;{\r\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;static&nbsp;$_robot&nbsp;=&nbsp;null;\r\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;if(is_null($_robot))&nbsp;{\r\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;$spiders&nbsp;=&nbsp;&#39;Bot|Crawl|Spider|slurp|sohu-search|lycos|robozilla&#39;;\r\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;$browsers&nbsp;=&nbsp;&#39;MSIE|Netscape|Opera|Konqueror|Mozilla&#39;;\r\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;if(preg_match(&quot;\/($browsers)\/&quot;,&nbsp;$_SERVER[&#39;HTTP_USER_AGENT&#39;]))&nbsp;{\r\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;$_robot\t&nbsp;=\t&nbsp;&nbsp;false&nbsp;;\r\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;}&nbsp;elseif(preg_match(&quot;\/($spiders)\/&quot;,&nbsp;$_SERVER[&#39;HTTP_USER_AGENT&#39;]))&nbsp;{\r\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;$_robot\t&nbsp;=\t&nbsp;&nbsp;true;\r\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;}&nbsp;else&nbsp;{\r\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;$_robot\t&nbsp;=\t&nbsp;&nbsp;false;\r\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;}\r\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;}\r\n&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;return&nbsp;$_robot;\r\n}<\/pre>\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>1.\u5efa\u7acb\u4e00\u4e2a\u6570\u636e\u5e93 create&nbsp;table&nbsp;crawler&nbsp;&nbsp;&#038;nb [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[10],"tags":[26,72,70],"class_list":["post-932","post","type-post","status-publish","format-standard","hentry","category-php","tag-php"],"_links":{"self":[{"href":"https:\/\/www.tra56.com\/wp-json\/wp\/v2\/posts\/932"}],"collection":[{"href":"https:\/\/www.tra56.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.tra56.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.tra56.com\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.tra56.com\/wp-json\/wp\/v2\/comments?post=932"}],"version-history":[{"count":1,"href":"https:\/\/www.tra56.com\/wp-json\/wp\/v2\/posts\/932\/revisions"}],"predecessor-version":[{"id":933,"href":"https:\/\/www.tra56.com\/wp-json\/wp\/v2\/posts\/932\/revisions\/933"}],"wp:attachment":[{"href":"https:\/\/www.tra56.com\/wp-json\/wp\/v2\/media?parent=932"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.tra56.com\/wp-json\/wp\/v2\/categories?post=932"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.tra56.com\/wp-json\/wp\/v2\/tags?post=932"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}