PHP采集程序中常用的函数_PHP教程-tutorial php-php.cn

Rumah

pembangunan bahagian belakang

tutorial php

PHP采集程序中常用的函数_PHP教程

Jul 15, 2016 pm 01:22 PM

php contoh Kata kunci fungsi Pertanyaan praktikal daripada program dapatkan koleksi

函数描述及例子 PHP采集程序中常用的函数查询关键字 PHP采集程序中常用的函数

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

//获得当前的脚本网址 
function get_php_url(){ 
        if(!empty($_SERVER["REQUEST_URI"])){ 
                $scriptName = $_SERVER["REQUEST_URI"]; 
                $nowurl = $scriptName; 
        }else{ 
                $scriptName = $_SERVER["PHP_SELF"]; 
                if(empty($_SERVER["QUERY_STRING"])) $nowurl = $scriptName; 
                else $nowurl = $scriptName."?".$_SERVER["QUERY_STRING"]; 
        } 
        return $nowurl; 
} 
//把全角数字转为半角数字 
function GetAlabNum($fnum){ 
        $nums = array("０","１","２","３","４","５","６","７","８","９"); 
        $fnums = "0123456789"; 
        for($i=0;$i<=9;$i++) $fnum = str_replace($nums[$i],$fnums[$i],$fnum); 
        $fnum = ereg_replace("[^0-9\.]|^0{1,}","",$fnum); 
        if($fnum=="") $fnum=0; 
        return $fnum; 
} 
//去除HTML标记 
function Text2Html($txt){ 
        $txt = str_replace("  ","　",$txt); 
        $txt = str_replace("<","<",$txt); 
        $txt = str_replace(">",">",$txt); 
        $txt = preg_replace("/[\r\n]{1,}/isU","
\r\n",$txt); 
        return $txt; 
}
//清除HTML标记 
function ClearHtml($str){ 
        $str = str_replace(&#39;<&#39;,&#39;<&#39;,$str); 
        $str = str_replace(&#39;>&#39;,&#39;>&#39;,$str); 
        return $str; 
} 
//相对路径转化成绝对路径 
function relative_to_absolute($content, $feed_url) { 
    preg_match(&#39;/(http|https|ftp):\/\//&#39;, $feed_url, $protocol); 
    $server_url = preg_replace("/(http|https|ftp|news):\/\//", "", $feed_url); 
    $server_url = preg_replace("/\/.*/", "", $server_url);
    if ($server_url == &#39;&#39;) { 
        return $content; 
    }
    if (isset($protocol[0])) { 
        $new_content = preg_replace(&#39;/href="\//&#39;, &#39;href="&#39;.$protocol[0].$server_url.&#39;/&#39;, $content); 
        $new_content = preg_replace(&#39;/src="\//&#39;, &#39;src="&#39;.$protocol[0].$server_url.&#39;/&#39;, $new_content); 
    } else { 
        $new_content = $content; 
    } 
    return $new_content; 
} 
//取得所有链接 
function get_all_url($code){ 
        preg_match_all(&#39;/"\&#39; ]+)["|\&#39;]?\s*[^>]*>([^>]+)<\/a>/i&#39;,$code,$arr); 
        return array(&#39;name&#39;=>$arr[2],&#39;url&#39;=>$arr[1]); 
}
//获取指定标记中的内容 
function get_tag_data($str, $start, $end){ 
        if ( $start == &#39;&#39; || $end == &#39;&#39; ){ 
               return; 
        } 
        $str = explode($start, $str); 
        $str = explode($end, $str[1]); 
        return $str[0]; 
} 
//HTML表格的每行转为CSV格式数组 
function get_tr_array($table) { 
        $table = preg_replace("&#39;<td[^>]*?>&#39;si",&#39;"&#39;,$table); 
        $table = str_replace("",&#39;",&#39;,$table); 
        $table = str_replace("","{tr}",$table); 
        //去掉 HTML 标记 
        $table = preg_replace("&#39;<[\/\!]*?[^<>]*?>&#39;si","",$table); 
        //去掉空白字符 
        $table = preg_replace("&#39;([\r\n])[\s]+&#39;","",$table); 
        $table = str_replace(" ","",$table); 
        $table = str_replace(" ","",$table);
        $table = explode(",{tr}",$table); 
        array_pop($table); 
        return $table; 
}
//将HTML表格的每行每列转为数组，采集表格数据 
function get_td_array($table) { 
        $table = preg_replace("&#39;<table[^>]*?>&#39;si","",$table); 
        $table = preg_replace("&#39;<tr[^>]*?>&#39;si","",$table); 
        $table = preg_replace("&#39;<td[^>]*?>&#39;si","",$table); 
        $table = str_replace("","{tr}",$table); 
        $table = str_replace("","{td}",$table); 
        //去掉 HTML 标记 
        $table = preg_replace("&#39;<[\/\!]*?[^<>]*?>&#39;si","",$table); 
        //去掉空白字符 
        $table = preg_replace("&#39;([\r\n])[\s]+&#39;","",$table); 
        $table = str_replace(" ","",$table); 
        $table = str_replace(" ","",$table); 
         
        $table = explode(&#39;{tr}&#39;, $table); 
        array_pop($table); 
        foreach ($table as $key=>$tr) { 
                $td = explode(&#39;{td}&#39;, $tr); 
                array_pop($td); 
            $td_array[] = $td; 
        } 
        return $td_array; 
}
//返回字符串中的所有单词 $distinct=true 去除重复 
function split_en_str($str,$distinct=true) { 
        preg_match_all(&#39;/([a-zA-Z]+)/&#39;,$str,$match); 
        if ($distinct == true) { 
                $match[1] = array_unique($match[1]); 
        } 
        sort($match[1]); 
        return $match[1]; 
}
  
函数描述及例子
  
PHP采集程序中常用的函数
 
查询关键字
  
PHP采集程序中常用的函数
<!--?
//获得当前的脚本网址 
function get_php_url(){ 
        if(!empty($_SERVER["REQUEST_URI"])){ 
                $scriptName = $_SERVER["REQUEST_URI"]; 
                $nowurl = $scriptName; 
        }else{ 
                $scriptName = $_SERVER["PHP_SELF"]; 
                if(empty($_SERVER["QUERY_STRING"])) $nowurl = $scriptName; 
                else $nowurl = $scriptName."?".$_SERVER["QUERY_STRING"]; 
        } 
        return $nowurl; 
} 
//把全角数字转为半角数字 
function GetAlabNum($fnum){ 
        $nums = array("０","１","２","３","４","５","６","７","８","９"); 
        $fnums = "0123456789"; 
        for($i=0;$i<=9;$i++) $fnum = str_replace($nums[$i],$fnums[$i],$fnum); 
        $fnum = ereg_replace("[^0-9\.]|^0{1,}","",$fnum); 
        if($fnum=="") $fnum=0; 
        return $fnum; 
} 
//去除HTML标记 
function Text2Html($txt){ 
        $txt = str_replace("  ","　",$txt); 
        $txt = str_replace("<","<",$txt); 
        $txt = str_replace("-->",">",$txt); 
        $txt = preg_replace("/[\r\n]{1,}/isU","
\r\n",$txt); 
        return $txt; 
}
//清除HTML标记 
function ClearHtml($str){ 
        $str = str_replace(&#39;<&#39;,&#39;<&#39;,$str); 
        $str = str_replace(&#39;>&#39;,&#39;>&#39;,$str); 
        return $str; 
} 
//相对路径转化成绝对路径 
function relative_to_absolute($content, $feed_url) { 
    preg_match(&#39;/(http|https|ftp):\/\//&#39;, $feed_url, $protocol); 
    $server_url = preg_replace("/(http|https|ftp|news):\/\//", "", $feed_url); 
    $server_url = preg_replace("/\/.*/", "", $server_url);
    if ($server_url == &#39;&#39;) { 
        return $content; 
    }
    if (isset($protocol[0])) { 
        $new_content = preg_replace(&#39;/href="\//&#39;, &#39;href="&#39;.$protocol[0].$server_url.&#39;/&#39;, $content); 
        $new_content = preg_replace(&#39;/src="\//&#39;, &#39;src="&#39;.$protocol[0].$server_url.&#39;/&#39;, $new_content); 
    } else { 
        $new_content = $content; 
    } 
    return $new_content; 
} 
//取得所有链接 
function get_all_url($code){ 
        preg_match_all(&#39;/"\&#39; ]+)["|\&#39;]?\s*[^>]*>([^>]+)<\/a>/i&#39;,$code,$arr); 
        return array(&#39;name&#39;=>$arr[2],&#39;url&#39;=>$arr[1]); 
}
//获取指定标记中的内容 
function get_tag_data($str, $start, $end){ 
        if ( $start == &#39;&#39; || $end == &#39;&#39; ){ 
               return; 
        } 
        $str = explode($start, $str); 
        $str = explode($end, $str[1]); 
        return $str[0]; 
} 
//HTML表格的每行转为CSV格式数组 
function get_tr_array($table) { 
        $table = preg_replace("&#39;<td[^>]*?>&#39;si",&#39;"&#39;,$table); 
        $table = str_replace("",&#39;",&#39;,$table); 
        $table = str_replace("","{tr}",$table); 
        //去掉 HTML 标记 
        $table = preg_replace("&#39;<[\/\!]*?[^<>]*?>&#39;si","",$table); 
        //去掉空白字符 
        $table = preg_replace("&#39;([\r\n])[\s]+&#39;","",$table); 
        $table = str_replace(" ","",$table); 
        $table = str_replace(" ","",$table);
        $table = explode(",{tr}",$table); 
        array_pop($table); 
        return $table; 
}
//将HTML表格的每行每列转为数组，采集表格数据 
function get_td_array($table) { 
        $table = preg_replace("&#39;<table[^>]*?>&#39;si","",$table); 
        $table = preg_replace("&#39;<tr[^>]*?>&#39;si","",$table); 
        $table = preg_replace("&#39;<td[^>]*?>&#39;si","",$table); 
        $table = str_replace("","{tr}",$table); 
        $table = str_replace("","{td}",$table); 
        //去掉 HTML 标记 
        $table = preg_replace("&#39;<[\/\!]*?[^<>]*?>&#39;si","",$table); 
        //去掉空白字符 
        $table = preg_replace("&#39;([\r\n])[\s]+&#39;","",$table); 
        $table = str_replace(" ","",$table); 
        $table = str_replace(" ","",$table); 
         
        $table = explode(&#39;{tr}&#39;, $table); 
        array_pop($table); 
        foreach ($table as $key=>$tr) { 
                $td = explode(&#39;{td}&#39;, $tr); 
                array_pop($td); 
            $td_array[] = $td; 
        } 
        return $td_array; 
}
//返回字符串中的所有单词 $distinct=true 去除重复 
function split_en_str($str,$distinct=true) { 
        preg_match_all(&#39;/([a-zA-Z]+)/&#39;,$str,$match); 
        if ($distinct == true) { 
                $match[1] = array_unique($match[1]); 
        } 
        sort($match[1]); 
        return $match[1]; 
}
  
</td[^></tr[^></table[^></td[^></a\s+href=["|\&#39;]?([^></td[^></tr[^></table[^></td[^></a\s+href=["|\&#39;]?([^>

Salin selepas log masuk

Kenyataan Laman Web ini

Kandungan artikel ini disumbangkan secara sukarela oleh netizen, dan hak cipta adalah milik pengarang asal. Laman web ini tidak memikul tanggungjawab undang-undang yang sepadan. Jika anda menemui sebarang kandungan yang disyaki plagiarisme atau pelanggaran, sila hubungi admin@php.cn