[PHP代码] PHP远程获取网页内容

1. include 'StringBuilder.php';
2. class CutPage{

   http://www.kmnk01.com/hxpfk/2015/jzb_1203/193.html

3. function __construct(){
4. }

   http://www.kmnk01.com/hxpfk/2015/tf_1203/195.html

6. //方法一：连接 获取真个文件的文本内容
7. function getAllContent($url){

   http://www.kmnk01.com/hxpfk/2015/qb_1203/196.html

8. $resouce=fopen($url, "r") or die("文件打开失败！");
9. if(!$resouce){
10. echo "请求文件不存在！";
11. }
12. //$allcontent='';//长度太短了取不全用自购建的stringbuilder
13. $sb=new StringBuilder();

14. http://www.kmnk01.com/hxpfk/2015/tf_1203/197.html

15. while(!feof($resouce)){
16. //如果没有到文件的结尾则继续向下执行
17. $line=fgets($resouce,4096);
18. $sb->append($line);
19. }
20. fclose($resouce);
21. return $sb->toString();
22. }
23. //方法二：获取所有的文本进行文本title的匹配---------格式为：xxxx(xx)xxx的形式表达式
24. function matchContentTitle($content,$regex_title){
25. //echo "regex:".$regex_title;

    http://www.kmnk01.com/hxpfk/2015/xcy_1203/198.html

26. if(preg_match($regex_title, $content)){
27. $array=preg_split($regex_title, $content,-1,PREG_SPLIT_DELIM_CAPTURE);
28. return $array[1];

    http://www.kmnk01.com/hxpfk/2015/bdf_1203/199.html

29. }else{
30. echo "匹配失败！";
31. }

    http://www.kmnk01.com/hxpfk/2015/bdf_1203/200.html

32. }
33. //匹配章节 返回携带章节的array

    http://www.kmnk01.com/hxpfk/2015/bdf_1203/201.html

34. function matchContentChapter($content,$regex_chapter){
35. if(preg_match_all($regex_chapter, $content,$matcher)){
36. return $matcher[1];

    http://www.kmnk01.com/hxpfk/2015/npx_1203/202.html

37. }else{

    http://www.kmnk01.com/hxpfk/2015/py_1203/203.html

38. echo "匹配失败！";
39. return ;
40. }
41. }
43. }