自动生成文章摘要的php代码

3. // PHP 4.3 or above needed

4. define("BRIEF_LENGTH", 800); //Word amount of the Briefing of an Article
5. function Generate_Brief($text){
6. global $Briefing_Length;
7. if(strlen($text) <= BRIEF_LENGTH ) return $text;
8. $Foremost = substr($text, 0, BRIEF_LENGTH);
9. $re = "/<(\/?)(P|DIV|H1|H2|H3|H4|H5|H6|ADDRESS|PRE|TABLE|TR|TD|TH|INPUT|SELECT|TEXTAREA|OBJECT|A|UL|OL|LI|BASE|META|LINK|HR|BR|PARAM|IMG|AREA|INPUT|SPAN)[^>]*(>?)/i";
10. $Single = "/BASE|META|LINK|HR|BR|PARAM|IMG|AREA|INPUT/i";
11. $Stack = array(); $posStack = array();
12. preg_match_all($re,$Foremost,$matches, PREG_SET_ORDER | PREG_OFFSET_CAPTURE);
13. /* [Child-matching Specification]:
14. $matches[$i][1] : A "/" charactor indicating whether current "<...>" Friction is Closing Part
15. $matches[$i][2] : Element Name.
16. $matches[$i][3] : Right > of a "<...>" Friction */
17. for($i = 0 ; $i < count($matches); $i++){
18. if($matches[$i][1][0] == ""){
19. $Elem = $matches[$i][2][0];
20. if(preg_match($Single,$Elem) && $matches[$i][3][0] !=""){
21. continue;
22. }
23. array_push($Stack, strtoupper($matches[$i][2][0]));
24. array_push($posStack, $matches[$i][2][1]);
25. if($matches[$i][3][0] =="") break;
26. }else{
27. $StackTop = $Stack[count($Stack)-1];
28. $End = strtoupper($matches[$i][2][0]);
29. if(strcasecmp($StackTop,$End)==0){
30. array_pop($Stack);
31. array_pop($posStack);
32. if($matches[$i][3][0] ==""){
33. $Foremost = $Foremost.">";
34. }
35. }
36. }
37. }
38. $cutpos = array_shift($posStack) - 1;
39. $Foremost = substr($Foremost,0,$cutpos);
40. return $Foremost;
41. };
42. 若遇到函数对多字节字符集支持得不好的情况，大家可以参考下下面这个代码。

43. 代码2：

44. function Generate_Brief($text){
45. global $Briefing_Length;
46. mb_regex_encoding("UTF-8");
47. if(mb_strlen($text) <= BRIEF_LENGTH ) return $text;
48. $Foremost = mb_substr($text, 0, BRIEF_LENGTH);
49. $re = "<(\/?)(P|DIV|H1|H2|H3|H4|H5|H6|ADDRESS|PRE|TABLE|TR|TD|TH|INPUT|SELECT|TEXTAREA|OBJECT|A|UL|OL|LI|BASE|META|LINK|HR|BR|PARAM|IMG|AREA|INPUT|SPAN)[^>]*(>?)";
50. $Single = "/BASE|META|LINK|HR|BR|PARAM|IMG|AREA|INPUT|BR/i";
51. $Stack = array(); $posStack = array();
52. mb_ereg_search_init($Foremost, $re, 'i');
53. while($pos = mb_ereg_search_pos()){
54. $match = mb_ereg_search_getregs();
55. /* [Child-matching Formulation]:
56. $matche[1] : A "/" charactor indicating whether current "<...>" Friction is Closing Part
57. $matche[2] : Element Name.
58. $matche[3] : Right > of a "<...>" Friction
59. */
60. if($match[1]==""){
61. $Elem = $match[2];
62. if(mb_eregi($Single, $Elem) && $match[3] !=""){
63. continue;
64. }
65. array_push($Stack, mb_strtoupper($Elem));
66. array_push($posStack, $pos[0]);
67. }else{
68. $StackTop = $Stack[count($Stack)-1];
69. $End = mb_strtoupper($match[2]);
70. if(strcasecmp($StackTop,$End)==0){
71. array_pop($Stack);
72. array_pop($posStack);
73. if($match[3] ==""){
74. $Foremost = $Foremost.">";
75. }
76. }
77. }
78. }
79. $cutpos = array_shift($posStack) - 1;
80. $Foremost = mb_substr($Foremost,0,$cutpos,"UTF-8");
81. return $Foremost;
82. };
83. ?>

至此，自动生成文章摘要的php代码的两种方法都介绍完了，希望对您有所帮助。 编辑推荐： php 摘要生成函数(自定义,无乱码)