本文实例讲述了PHP实现的抓取小说网站内容功能。分享给大家供大家参考,具体如下:
爬取免费内容,弄到手机,听书,妥妥的。
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
|
ini_set ( 'user_agent' , 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30; GreenBrowser)' ); ini_set ( 'max_execution_time' , '0' ); $base = 'https://www.qu.la/book/19434/' ; $start = '7504808.html' ; $content_grep = '/ (.*)<br\/>/' ; //$content_grep = '/<div id="content">(.*)<br\/>/sS'; $next_grep = '/<a id="pager_next" href=\"(\d+\.html)\" target="_top" class="next">下一章<\/a>/' ; $next = $start ; $file_name = '听书了.txt' ; while ( $next ) { echo 'getting ' . $next . PHP_EOL; $result = file_get_contents ( $base . $next ); preg_match_all( $content_grep , $result , $match ); $isTitle = true; $content = "" ; foreach ( $match [1] as $line ) { $line = str_replace ( "<br/>" , '' , $line ); $line = str_replace ( " " , '' , $line ); if ( $isTitle ) { $content = $line . PHP_EOL . PHP_EOL; $isTitle = false; } else { $content .= ' ' . $line . PHP_EOL . PHP_EOL; } } $file = fopen ( $file_name , 'a' ); echo 'write length: ' . strlen ( $content ) . PHP_EOL; fwrite( $file , $content ); fclose( $file ); echo '.' ; preg_match( $next_grep , $result , $match ); $next = $match [1]; } |
希望本文所述对大家PHP程序设计有所帮助。
原文链接:https://blog.csdn.net/Alen_xiaoxin/article/details/79567579