PHP 抓取网页内容的几个函数

稍微有点意义的函数是：get_content_by_socket(), get_url(), get_content_url(), get_content_object 几个函数，也许能够给你点什么想法。

1. <?php
   
2. 
   
3. //获取所有内容url保存到文件
   
4. function get_index($save_file, $prefix="index_"){
   
5. $count = 68;
   
6. $i = 1;
   
7. if (file_exists($save_file)) @unlink($save_file);
   
8. $fp = fopen($save_file, "a+") or die("Open ". $save_file ." failed");
   
9. while($i<$count){
   
10. $url = $prefix . $i .".htm";
    
11. echo "Get ". $url ."...";
    
12. $url_str = get_content_url(get_url($url));
    
13. echo " OKn";
    
14. fwrite($fp, $url_str);
    
15. ++$i;
    
16. }
    
17. fclose($fp);
    
18. }
    
19. 
    
20. //获取目标多媒体对象
    
21. function get_object($url_file, $save_file, $split="|--:**:--|"){
    
22. if (!file_exists($url_file)) die($url_file ." not exist");
    
23. $file_arr = file($url_file);
    
24. if (!is_array($file_arr) || empty($file_arr)) die($url_file ." not content");
    
25. $url_arr = array_unique($file_arr);
    
26. if (file_exists($save_file)) @unlink($save_file);
    
27. $fp = fopen($save_file, "a+") or die("Open save file ". $save_file ." failed");
    
28. foreach($url_arr as $url){
    
29. if (empty($url)) continue;
    
30. echo "Get ". $url ."...";
    
31. $html_str = get_url($url);
    
32. echo $html_str;
    
33. echo $url;
    
34. exit;
    
35. $obj_str = get_content_object($html_str);
    
36. echo " OKn";
    
37. fwrite($fp, $obj_str);
    
38. }
    
39. fclose($fp);
    
40. }
    
41. 
    
42. //遍历目录获取文件内容
    
43. function get_dir($save_file, $dir){
    
44. $dp = opendir($dir);
    
45. if (file_exists($save_file)) @unlink($save_file);
    
46. $fp = fopen($save_file, "a+") or die("Open save file ". $save_file ." failed");
    
47. while(($file = readdir($dp)) != false){
    
48. if ($file!="." && $file!=".."){
    
49. echo "Read file ". $file ."...";
    
50. $file_content = file_get_contents($dir . $file);
    
51. $obj_str = get_content_object($file_content);
    
52. echo " OKn";
    
53. fwrite($fp, $obj_str);
    
54. }
    
55. }
    
56. fclose($fp);
    
57. }
    
58. 
    
59. //获取指定url内容
    
60. function get_url($url){
    
61. $reg = '/^http:\/\/[^\/].+$/';
    
62. if (!preg_match($reg, $url)) die($url ." invalid");
    
63. $fp = fopen($url, "r") or die("Open url: ". $url ." failed.");
    
64. while($fc = fread($fp, 8192)){
    
65. $content .= $fc;
    
66. }
    
67. fclose($fp);
    
68. if (empty($content)){
    
69. die("Get url: ". $url ." content failed.");
    
70. }
    
71. return $content;
    
72. }
    
73. 
    
74. //使用socket获取指定网页
    
75. function get_content_by_socket($url, $host){
    
76. $fp = fsockopen($host, 80) or die("Open ". $url ." failed");
    
77. $header = "GET /".$url ." HTTP/1.1rn";
    
78. $header .= "Accept: */*rn";
    
79. $header .= "Accept-Language: zh-cnrn";
    
80. $header .= "Accept-Encoding: gzip, deflatern";
    
81. $header .= "User-Agent: Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; Maxthon; InfoPath.1; .NET CLR 2.0.50727)rn";
    
82. $header .= "Host: ". $host ."rn";
    
83. $header .= "Connection: Keep-Alivern";
    
84. //$header .= "Cookie: cnzz02=2; rtime=1; ltime=1148456424859; cnzz_eid=56601755-rnrn";
    
85. $header .= "Connection: Closernrn";
    
86. 
    
87. fwrite($fp, $header);
    
88. while (!feof($fp)) {
    
89. $contents .= fgets($fp, 8192);
    
90. }
    
91. fclose($fp);
    
92. return $contents;
    
93. }
    
94. 
    
95. //获取指定内容里的url
    
96. function get_content_url($host_url, $file_contents){
    
97. 
    
98. //$reg = '/^(#|javascript.*?|ftp://.+|http://.+|.*?href.*?|play.*?|index.*?|.*?asp)+$/i';
    
99. //$reg = '/^(down.*?.html|d+_d+.htm.*?)$/i';
    
100. $rex = "/([hH][rR][eE][Ff])s*=s*['"]*([^>'"s]+)["'>]*s*/i";
     
101. $reg = '/^(down.*?.html)$/i';
     
102. preg_match_all ($rex, $file_contents, $r);
     
103. $result = ""; //array();
     
104. foreach($r as $c){
     
105. if (is_array($c)){
     
106. foreach($c as $d){
     
107. if (preg_match($reg, $d)){ $result .= $host_url . $d."n"; }
     
108. }
     
109. }
     
110. }
     
111. return $result;
     
112. }
     
113. 
     
114. //获取指定内容中的多媒体文件
     
115. function get_content_object($str, $split="|--:**:--|"){
     
116. $regx = "/hrefs*=s*['"]*([^>'"s]+)["'>]*s*(<b>.*?</b>)/i";
     
117. preg_match_all($regx, $str, $result);
     
118. 
     
119. if (count($result) == 3){
     
120. $result[2] = str_replace("<b>多媒体： ", "", $result[2]);
     
121. $result[2] = str_replace("</b>", "", $result[2]);
     
122. $result = $result[1][0] . $split .$result[2][0] . "n";
     
123. }
     
124. return $result;
     
125. }
     
126. 
     
127. ?>

复制代码