前几天一个网友我一个金山词霸的每日一句api,叫我写一下采集源码,其实难度不大,直接拿《采集毒鸡汤》的源码稍微改改就能用。
Api官方接口
每日:http://open.iciba.com/dsapi/
查指定时间:http://sentence.iciba.com/index.php?c=dailysentence&m=getdetail&title=2018-11-06&_=1541655200812
搭建采集接口
<?php header("Content-type: text/html; charset=utf-8"); //设置编码 utf-8 $t1 = microtime(true); $utime = date("Y-m-d");//api的尾缀时间 $translation = '0';//翻译语句,0不采集,1采集 $content = '1';//英语版,0不采集,1采集 //使用curl提高运行速度 不用动 function httpGet($url) { $curl = curl_init(); $httpheader[] = "Accept:*/*"; $httpheader[] = "Accept-Language:zh-CN,zh;q=0.8"; $httpheader[] = "Connection:close"; curl_setopt($curl, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows; U; Windows NT 5.1; rv:1.7.3) Gecko/20041001 Firefox/0.10.1" ); curl_setopt($curl, CURLOPT_HTTPHEADER, $httpheader); curl_setopt($curl, CURLOPT_RETURNTRANSFER, true); curl_setopt($curl, CURLOPT_TIMEOUT, 3); curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, false); curl_setopt($curl, CURLOPT_SSL_VERIFYHOST, false); curl_setopt($curl, CURLOPT_URL, $url); $res = curl_exec($curl); curl_close($curl); return $res; } $myfile = fopen("iciba.txt", "a+");//创建文件保存抓取的句子 //循环次数 2018-7-31 至现在日期相差的天数 for ($i=1; $i<100; $i++) { $json_string =httpGet('http://sentence.iciba.com/index.php?c=dailysentence&m=getdetail&title='.$utime.'&_='.time());//curl 自定义函数访问api $data= json_decode($json_string,true);//解析json 转为php if (isset($data['note'])) { $text1= $data['note']."\n"; fwrite($myfile, $text1); } if (isset($data['translation'])&&$translation==1) { $text2= str_replace('小编的话:', '', $data['translation'])."\n"; fwrite($myfile, $text2); } if (isset($data['content'])&&$content==1) { $text3= $data['content']."\n"; fwrite($myfile, $text3); } $utime= date("Y-m-d",strtotime("-".strval($i)." day")); //每循环一次 当前日期减去循环变量 } fclose($myfile); $t2 = microtime(true); echo 'ok,耗时'.round($t2-$t1,3).'秒'; ?>运行这个接口能采集到之前100天的。
一言接口
<?php //获取句子文件的绝对路径 //如果你介意别人可能会拖走这个文本,可以把文件名自定义一下,或者通过Nginx禁止拉取也行。 $path = dirname(__FILE__); $file = file($path."/iciba.txt"); //随机读取一行 $arr = mt_rand( 0, count( $file ) - 1 ); $content = trim($file[$arr]); //编码判断,用于输出相应的响应头部编码 if (isset($_GET['charset']) && !empty($_GET['charset'])) { $charset = $_GET['charset']; if (strcasecmp($charset,"gbk") == 0 ) { $content = mb_convert_encoding($content,'gbk', 'utf-8'); } } else { $charset = 'utf-8'; } //格式化判断,输出js或纯文本 if (isset($_GET['encode'])&&$_GET['encode'] === 'js') { header('Content-type: text/javascript;charset=utf-8'); echo "function iciba(){document.write('" . $content ."');}"; } else { echo $content; }
每日采集接口
<?php header("Content-type: text/html; charset=utf-8"); //设置编码 utf-8 $utime = date("Y-m-d"); $file_data = 'data.txt'; if(!file_exists($file_data)){ fopen($file_data, "w"); } $str = file_get_contents('data.txt'); $d=date('Y/m/d H:i',strtotime($str)); $translation = '0';//翻译语句,0不采集,1采集 $content = '1';//英语版,0不采集,1采集 //请更改监控key 默认iciba if($_GET['p']==='iciba'){ //判断今天是否已爬 if(strtotime($utime)>strtotime($d)){ //爬虫开始 //使用curl提高运行速度 不用动 function httpGet($url) { $curl = curl_init(); $httpheader[] = "Accept:*/*"; $httpheader[] = "Accept-Language:zh-CN,zh;q=0.8"; $httpheader[] = "Connection:close"; curl_setopt($curl, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows; U; Windows NT 5.1; rv:1.7.3) Gecko/20041001 Firefox/0.10.1" ); curl_setopt($curl, CURLOPT_HTTPHEADER, $httpheader); curl_setopt($curl, CURLOPT_RETURNTRANSFER, true); curl_setopt($curl, CURLOPT_TIMEOUT, 3); curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, false); curl_setopt($curl, CURLOPT_SSL_VERIFYHOST, false); curl_setopt($curl, CURLOPT_URL, $url); $res = curl_exec($curl); curl_close($curl); return $res; } //定义写入函数 function myfile($txt){ $myfile = fopen("iciba.txt", "a+"); fwrite($myfile,$txt); fclose($myfile); } $json_string =httpGet('http://open.iciba.com/dsapi/');//curl 自定义函数访问api $data= json_decode($json_string,true);//解析json 转为php //2018-4-11之前只有一条数据 so 加判断 if (isset($data['note'])) { $text1= $data['note']."\n"; myfile($text1); } if (isset($data['translation'])&&$translation==1) { $text2= str_replace('小编的话:', '', $data['translation'])."\n"; myfile($text2); } if (isset($data['content'])&&$content==1) { $text3= $data['content']."\n"; myfile($text3); } $myfile = fopen("data.txt", "w"); fwrite($myfile,$utime); fclose($myfile); echo "ok"; //爬虫结束 }else{ echo "已爬"; } }else echo "老铁 搞事情吗"; ?>之后可以把这个每日采集接口使用宝塔计划监控为每日采集即可。
ps:多的图文介绍也就不多说了,查看采集毒鸡汤的文章即可。
发表评论: