PHP 抓取新浪读书频道的小说并生成txt电子书的代码_PHP教程
程序员文章站
2022-05-13 22:21:36
...
复制代码 代码如下:
/* Author: Yang Yu
//想看什么电子书，先去新浪读书搜索，然后填入对应的参数即可
//http://vip.book.sina.com.cn/
//电子书参数
$array_book[0] = 38884; //小说id
$array_book[1] = 22172; //章节起始id
$array_book[2] = 32533; //章节结束id
$array_book[3] = '中国特种部队生存实录：狼牙'; //小说名字
//匹配参数
$title_pre = "/
(.*?)/"; //标题部分
$contents_pre = "/(.*?)/"; //内容部分
//生成电子书
for( $i = $array_book[1]; $i $url = "http://vip.book.sina.com.cn/book/chapter_{$array_book[0]}_{$i}.html";
$html = file_get_contents($url);
preg_match_all($title_pre,$html,$title);
preg_match_all($contents_pre,$html,$contents);
$fh = fopen($array_book[3].'.txt','a+');
$write_contents = $title[1][0]."\r\n".str_replace('',"\r\n",str_replace('',' ',$contents[1][0]))."\r\n";
if( fwrite($fh,$write_contents) ){
echo '第'.$i.'节抓取完毕';
}
fclose($fh);
}
//生成电子书
for( $i = $array_book[1]; $i $url = "http://vip.book.sina.com.cn/book/chapter_{$array_book[0]}_{$i}.html";
$html = file_get_contents($url);
preg_match_all($title_pre,$html,$title);
preg_match_all($contents_pre,$html,$contents);
$fh = fopen($array_book[3].'.txt','a+');
$write_contents = $title[1][0]."\r\n".str_replace('',"\r\n",str_replace('
',' ',$contents[1][0]))."\r\n";
if( fwrite($fh,$write_contents) ){
echo '第'.$i.'节抓取完毕';
}
fclose($fh);
}