取第5列,去掉开头结尾的引号,匹配以http://, https://, ftp://开头的行
* awk
awk -F"," 'str=gsub(/(^"*)|("*$)/,"",$5) {if($5~/(^http(s)?://)|(^ftp://)/) print $5}'
../data/t_video.csv > ../data/urls.csv
* php
<?php
// awk -F"," 'str=gsub(/(^"*)|("*$)/,"",$5) {if($5~/(^http(s)?://)|(^ftp://)/) print $5}'
// ../data/t_video.csv > ../data/urls.csv
$in = new SplFileObject('../data/t_video.csv', 'rb');
if (!$in) {
throw new Exception('open file for read failed!');
}
$out = new SplFileObject('../data/urls.csv', 'w');
if (!$out) {
throw new Exception('open file for write failed!');
}
$a = []; $videoURL = '';
foreach ($in as $lineNum => $line) {
$a = explode(',', $line);
if (!isset($a[4])) {
continue;
}
$videoURL = $a[4];
if (7<strlen($videoURL)) {
$videoURL = trim($videoURL, """);
if (preg_match('/^[http://|ftp://|https://]/', $videoURL)) {
$out->fwrite($videoURL.PHP_EOL);
}
}
}
input:
../data/t_video.csv
"9","其他","ULTIMATE PHOTO GUIDE",NULL,"http://118.190.209.209/media/mp4/1.mp4","http://118.190.209.209/media/png/1.png","ULTIMATE PHOTO GUIDE" "10","其他","THE VERGE",NULL,"http://118.190.209.209/media/mp4/2.mp4","http://118.190.209.209/media/png/2.the_verge.png","THE VERGE" "11","其他","Microsoft Power BI",NULL,"http://118.190.209.209/media/mp4/3.mp4","http://118.190.209.209/media/png/3.png","Microsoft Power BI"
output:
../data/url.csv
http://118.190.209.209/media/mp4/1.mp4 http://118.190.209.209/media/mp4/2.mp4 http://118.190.209.209/media/mp4/3.mp4
http://php.net/manual/en/class.splfileobject.php