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

1. //获得当前的脚本网址
2. function get_php_url(){
3. if(!emptyempty($_SERVER["REQUEST_URI"])){
4. $scriptName = $_SERVER["REQUEST_URI"];
5. $nowurl = $scriptName;
6. }else{
7. $scriptName = $_SERVER["PHP_SELF"];
8. if(emptyempty($_SERVER["QUERY_STRING"])) $nowurl = $scriptName;
9. else $nowurl = $scriptName."?".$_SERVER["QUERY_STRING"];
10. }
11. return $nowurl;
12. }
13. //把全角数字转为半角数字
14. function GetAlabNum($fnum){
15. $nums = array("０","１","２","３","４","５","６","７","８","９");
16. $fnums = "0123456789";
17. for($i=0;$i<=9;$i++) $fnum = str_replace($nums[$i],$fnums[$i],$fnum);
18. $fnum = ereg_replace("[^0-9\.]|^0{1,}","",$fnum);
19. if($fnum=="") $fnum=0;
20. return $fnum;
21. }
22. //去除HTML标记
23. function Text2Html($txt){
24. $txt = str_replace(" ","　",$txt);
25. $txt = str_replace("<","<",$txt);
26. $txt = str_replace(">",">",$txt);
27. $txt = preg_replace("/[\r\n]{1,}/isU","
28. \r\n",$txt);
29. return $txt;
30. }
31. //清除HTML标记
32. function ClearHtml($str){
33. $str = str_replace('<','<',$str);
34. $str = str_replace('>','>',$str);
35. return $str;
36. }
37. //相对路径转化成绝对路径
38. function relative_to_absolute($content, $feed_url) {
39. preg_match('/(http|https|ftp):\/\//', $feed_url, $protocol);
40. $server_url = preg_replace("/(http|https|ftp|news):\/\//", "", $feed_url);
41. $server_url = preg_replace("/\/.*/", "", $server_url);
42. if ($server_url == '') {
43. return $content;
44. }
45. if (isset($protocol[0])) {
46. $new_content = preg_replace('/href="\//', 'href="'.$protocol[0].$server_url.'/', $content);
47. $new_content = preg_replace('/src="\//', 'src="'.$protocol[0].$server_url.'/', $new_content);
48. } else {
49. $new_content = $content;
50. }
51. return $new_content;
52. }
53. //取得所有链接
54. function get_all_url($code){
55. preg_match_all('/<a\s+href=["|\']?([^>"\' ]+)["|\']?\s*[^>]*>([^>]+)<\/a>/i',$code,$arr);
56. return array('name'=>$arr[2],'url'=>$arr[1]);
57. }
58. //获取指定标记中的内容
59. function get_tag_data($str, $start, $end){
60. if ( $start == '' || $end == '' ){
61. return;
62. }
63. $str = explode($start, $str);
64. $str = explode($end, $str[1]);
65. return $str[0];
66. }
67. //HTML表格的每行转为CSV格式数组
68. function get_tr_array($table) {
69. $table = preg_replace("'<td[^>]*?>'si",'"',$table);
70. $table = str_replace("",'",',$table);
71. $table = str_replace("","{tr}",$table);
72. //去掉 HTML 标记
73. $table = preg_replace("'<[\/\!]*?[^<>]*?>'si","",$table);
74. //去掉空白字符
75. $table = preg_replace("'([\r\n])[\s]+'","",$table);
76. $table = str_replace(" ","",$table);
77. $table = str_replace(" ","",$table);
78. $table = explode(",{tr}",$table);
79. array_pop($table);
80. return $table;
81. }
82. //将HTML表格的每行每列转为数组，采集表格数据
83. function get_td_array($table) {
84. $table = preg_replace("'<table[^>]*?>'si","",$table);
85. $table = preg_replace("'<tr[^>]*?>'si","",$table);
86. $table = preg_replace("'<td[^>]*?>'si","",$table);
87. $table = str_replace("","{tr}",$table);
88. $table = str_replace("","{td}",$table);
89. //去掉 HTML 标记
90. $table = preg_replace("'<[\/\!]*?[^<>]*?>'si","",$table);
91. //去掉空白字符
92. $table = preg_replace("'([\r\n])[\s]+'","",$table);
93. $table = str_replace(" ","",$table);
94. $table = str_replace(" ","",$table);
95. $table = explode('{tr}', $table);
96. array_pop($table);
97. foreach ($table as $key=>$tr) {
98. $td = explode('{td}', $tr);
99. array_pop($td);
100. $td_array[] = $td;
101. }
102. return $td_array;
103. }
104. //返回字符串中的所有单词 $distinct=true 去除重复
105. function split_en_str($str,$distinct=true) {
106. preg_match_all('/([a-zA-Z]+)/',$str,$match);
107. if ($distinct == true) {
108. $match[1] = array_unique($match[1]);
109. }
110. sort($match[1]);
111. return $match[1];
112. }
113. 函数描述及例子
114. PHP采集程序中常用的函数
115. 查询关键字
116. PHP采集程序中常用的函数
117. <!--?
118. //获得当前的脚本网址
119. function get_php_url(){
120. if(!emptyempty($_SERVER["REQUEST_URI"])){
121. $scriptName = $_SERVER["REQUEST_URI"];
122. $nowurl = $scriptName;
123. }else{
124. $scriptName = $_SERVER["PHP_SELF"];
125. if(emptyempty($_SERVER["QUERY_STRING"])) $nowurl = $scriptName;
126. else $nowurl = $scriptName."?".$_SERVER["QUERY_STRING"];
127. }
128. return $nowurl;
129. }
130. //把全角数字转为半角数字
131. function GetAlabNum($fnum){
132. $nums = array("０","１","２","３","４","５","６","７","８","９");
133. $fnums = "0123456789";
134. for($i=0;$i<=9;$i++) $fnum = str_replace($nums[$i],$fnums[$i],$fnum);
135. $fnum = ereg_replace("[^0-9\.]|^0{1,}","",$fnum);
136. if($fnum=="") $fnum=0;
137. return $fnum;
138. }
139. //去除HTML标记
140. function Text2Html($txt){
141. $txt = str_replace(" ","　",$txt);
142. $txt = str_replace("<","<",$txt);
143. $txt = str_replace("-->",">",$txt);
144. $txt = preg_replace("/[\r\n]{1,}/isU","
145. \r\n",$txt);
146. return $txt;
147. }
148. //清除HTML标记
149. function ClearHtml($str){
150. $str = str_replace('<','<',$str);
151. $str = str_replace('>','>',$str);
152. return $str;
153. }
154. //相对路径转化成绝对路径
155. function relative_to_absolute($content, $feed_url) {
156. preg_match('/(http|https|ftp):\/\//', $feed_url, $protocol);
157. $server_url = preg_replace("/(http|https|ftp|news):\/\//", "", $feed_url);
158. $server_url = preg_replace("/\/.*/", "", $server_url);
159. if ($server_url == '') {
160. return $content;
161. }
162. if (isset($protocol[0])) {
163. $new_content = preg_replace('/href="\//', 'href="'.$protocol[0].$server_url.'/', $content);
164. $new_content = preg_replace('/src="\//', 'src="'.$protocol[0].$server_url.'/', $new_content);
165. } else {
166. $new_content = $content;
167. }
168. return $new_content;
169. }
170. //取得所有链接
171. function get_all_url($code){
172. preg_match_all('/<a\s+href=["|\']?([^>"\' ]+)["|\']?\s*[^>]*>([^>]+)<\/a>/i',$code,$arr);
173. return array('name'=>$arr[2],'url'=>$arr[1]);
174. }
175. //获取指定标记中的内容
176. function get_tag_data($str, $start, $end){
177. if ( $start == '' || $end == '' ){
178. return;
179. }
180. $str = explode($start, $str);
181. $str = explode($end, $str[1]);
182. return $str[0];
183. }
184. //HTML表格的每行转为CSV格式数组
185. function get_tr_array($table) {
186. $table = preg_replace("'<td[^>]*?>'si",'"',$table);
187. $table = str_replace("",'",',$table);
188. $table = str_replace("","{tr}",$table);
189. //去掉 HTML 标记
190. $table = preg_replace("'<[\/\!]*?[^<>]*?>'si","",$table);
191. //去掉空白字符
192. $table = preg_replace("'([\r\n])[\s]+'","",$table);
193. $table = str_replace(" ","",$table);
194. $table = str_replace(" ","",$table);
195. $table = explode(",{tr}",$table);
196. array_pop($table);
197. return $table;
198. }
199. //将HTML表格的每行每列转为数组，采集表格数据
200. function get_td_array($table) {
201. $table = preg_replace("'<table[^>]*?>'si","",$table);
202. $table = preg_replace("'<tr[^>]*?>'si","",$table);
203. $table = preg_replace("'<td[^>]*?>'si","",$table);
204. $table = str_replace("","{tr}",$table);
205. $table = str_replace("","{td}",$table);
206. //去掉 HTML 标记
207. $table = preg_replace("'<[\/\!]*?[^<>]*?>'si","",$table);
208. //去掉空白字符
209. $table = preg_replace("'([\r\n])[\s]+'","",$table);
210. $table = str_replace(" ","",$table);
211. $table = str_replace(" ","",$table);
212. $table = explode('{tr}', $table);
213. array_pop($table);
214. foreach ($table as $key=>$tr) {
215. $td = explode('{td}', $tr);
216. array_pop($td);
217. $td_array[] = $td;
218. }
219. return $td_array;
220. }
221. //返回字符串中的所有单词 $distinct=true 去除重复
222. function split_en_str($str,$distinct=true) {
223. preg_match_all('/([a-zA-Z]+)/',$str,$match);
224. if ($distinct == true) {
225. $match[1] = array_unique($match[1]);
226. }
227. sort($match[1]);
228. return $match[1];
229. }
230. </td[^></tr[^></table[^></td[^></a\s+href=["|\']?([^></td[^></tr[^></table[^></td[^></a\s+href=["|\']?([^>