正则表达式实例
2016-02-18 00:00
381 查看
采集http://www.gelbeseiten.de网站客户信息
/* * 输入一个网页的源码内容 * 返回数组(所有诊所的所有内容) */ function getClinicArray($pageContent){ $pattern = "/START i\_print\_tn\_container(.| )*?ENDE i\_print\_tn\_container/i"; preg\_match\_all($pattern,$pageContent,$out, PREG\_SET\_ORDER); $clinicArray = array(); $clinicNum = count($out); for($i = 0 ;$i < $clinicNum ;$i ++){ $clinicArray[$i] = $out[$i][0]; } return $clinicArray; } /* * 输入一个诊所的所有内容 * 输出诊所详细内容数组 */ function getClinicDetailArray($oneClinic){ //return array(name,address,bread,phone,fax,web,email) $clinicDetailArray = array(); $patternName = "/(.|)*?/i"; preg\_match\_all($patternName,$oneClinic,$outName,PREG\_SET\_ORDER); $clinicDetailArray['name'] = mb\_convert\_encoding(trim(strip\_tags($outName[0][0])),'utf-8','Latin1'); $patternAddress = "/(.*)/i"; preg\_match\_all($patternAddress,$oneClinic,$outAddress,PREG\_SET\_ORDER); $clinicDetailArray['address'] = mb\_convert\_encoding(trim($outAddress[0][1]),'utf-8','Latin1'); $patternBread = "/(.|)*?/i"; preg\_match\_all($patternBread,$oneClinic,$outBread,PREG\_SET\_ORDER); $clinicDetailArray['bread'] = mb\_convert\_encoding(preg\_replace("/[s]{2,}/","",str\_replace(" ",'',trim(strip\_tags($outBread[0][0])))),'utf-8','Latin1'); $patternPhone = "/Tel:(.*)