カテゴリー: スクリプト

wget --mirror \
    --page-requisites \
    --quiet --show-progress \
    --no-parent \
    --convert-links \
    --adjust-extension \
    --execute robots=off \
    https://retoge-mag.hatenablog.com/

cp -r retoge-mag.hatenablog.com viewpage

for file in `find ./viewpage -name \*.html -print`
do
 sed -i -e "s/retoge-mag.hatenablog.com/retoge-mag.websa.jp\/old\/viewpage/g" $file
done

<IfModule mod_rewrite.c>
RewriteEngine On

RewriteCond     %{REQUEST_FILENAME} !-f
RewriteRule     ^(.*)$ $1.html [L]

</IfModule>

for file in `find ./viewpage -name \*.html -print`
do
 grep -oE 'http(s?)://[0-9a-zA-Z?=#+_&:;/.%\-]+' $file >> urllists.txt
done
sort urllists.txt | uniq > urllists2.txt
grep st-hatena.com urllists2.txt > urllists3.txt
wget --mirror     --page-requisites     --quiet --show-progress     --no-parent     --convert-links     --adjust-extension -i urllists3.txt

for file in `find ./viewpage -name \*.html -print`
do
 sed -i -e "s/b.st-hatena.com/retoge-mag.websa.jp\/old\/b.st-hatena.com/g" $file
 sed -i -e "s/cdn-ak.f.st-hatena.com/retoge-mag.websa.jp\/old\/cdn-ak.f.st-hatena.com/g" $file
 sed -i -e "s/cdn.blog.st-hatena.com/retoge-mag.websa.jp\/old\/cdn.blog.st-hatena.com/g" $file
 sed -i -e "s/cdn.pool.st-hatena.com/retoge-mag.websa.jp\/old\/cdn.pool.st-hatena.com/g" $file
 sed -i -e "s/cdn.profile-image.st-hatena.com/retoge-mag.websa.jp\/old\/cdn.profile-image.st-hatena.com/g" $file
 sed -i -e "s/cdn.user.blog.st-hatena.com/retoge-mag.websa.jp\/old\/cdn.user.blog.st-hatena.com/g" $file
 sed -i -e "s/usercss.blog.st-hatena.com/retoge-mag.websa.jp\/old\/usercss.blog.st-hatena.com/g" $file
done

<?xml version="1.0" encoding="UTF-8" ?>

<rss version="2.0"
	xmlns:excerpt="http://wordpress.org/export/1.2/excerpt/"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:wp="http://wordpress.org/export/1.2/"
>

<channel>
	<wp:wxr_version>1.2</wp:wxr_version>
	<wp:author></wp:author>

	<item>
		<title>Test 1</title>
		<description></description>
		<content:encoded><![CDATA[Test Post 1]]></content:encoded>
		<excerpt:encoded><![CDATA[]]></excerpt:encoded>
		<wp:status>publish</wp:status>
		<wp:post_type>post</wp:post_type>
		<category domain="post_tag" nicename="redy"><![CDATA[redy]]></category>
		<category domain="category" nicename="teory"><![CDATA[Teory]]></category>
		<category domain="category" nicename="tree"><![CDATA[Tree]]></category>
	</item>
	<item>
		<title>Test 2</title>
		<description></description>
		<content:encoded><![CDATA[Test Post 2]]></content:encoded>
		<excerpt:encoded><![CDATA[]]></excerpt:encoded>
		<wp:status>publish</wp:status>
		<wp:post_type>post</wp:post_type>
		<category domain="category" nicename="test-category"><![CDATA[Test Category]]></category>
	</item>
</channel>
</rss>

#!/bin/perl
#

use strict;
use warnings;

my $sourcefile=$ARGV[0];

if(!-f $sourcefile){
        print "file not found\n";
        exit 1;
}

my $i=0;
my @bodys;

open(FILE,$sourcefile);
while(<FILE>){
        $bodys[$i]=$_;
        $i++;
}
close(FILE);

my $maxline=$i;
my $line;

my ($st,$ed,$tmp);

my $createdate="";
my $modifydate="";
my $title="";
my $categorys="";
my $categoryssub="";
my $categorysterm="";
my $author="";
my $contents="";
my $description="";

$i=0;
while($i<$maxline){
        $line=$bodys[$i];
        if(($line =~ /<time datetime=/)&&($createdate eq "")){
                # 作成日取得
                # 下の方に他のページのdatetimeもあるので1個目だけ採用
                $st=index($line,"datetime=");
                $st=index($line,"\"",$st)+length("\"");
                $ed=index($line,"\"",$st);
                $createdate=substr($line,$st,$ed-$st);
        #}elsif(($line =~ /entry-footer-time/)&&($line =~ /class=\"updated\"/)){
        }elsif($line =~ /dateModified/){
                # 更新日取得
                $st=index($line,"dateModified");
                $st=index($line,":",$st);
                $st=index($line,"\"",$st)+length("\"");
                $ed=index($line,"\"",$st);
                $modifydate=substr($line,$st,$ed-$st);
        }elsif($line =~ /entry-title-link/){
                # タイトル取得
                $st=index($line,">")+length(">");
                $ed=index($line,"</",$st);
                $title=substr($line,$st,$ed-$st);
        }elsif($line =~ /entry-categories/){
                # カテゴリ取得
                my $flag=0;
                while($flag==0){
                        $i++;
                        $line=$bodys[$i];
                        if($line =~/<\/div>/){
                                # カテゴリ終了
                                $flag=1;
                        }elsif($line =~ /entry-category-link/){
                                $st=index($line,">")+length(">");
                                $ed=index($line,"</",$st);
                                $tmp=substr($line,$st,$ed-$st);
                                $categorys.="<category domain=\"category\" nicename=\"".$tmp."\" ><![CDATA[".$tmp."]]></category>";
                        }
                }
        }elsif($line =~ /author vcard/){
                # 作者取得
                $ed=index($line,"</");
                $st=rindex($line,">",$ed)+length(">");
                $author=substr($line,$st,$ed-$st);
        }elsif($line =~ /entry-content/){
                # 本文取得
                my $flag=0;
                while($flag==0){
                        $i++;
                        $line=$bodys[$i];
                        if($line =~/entry-footer/){
                                # 本文終了
                                $flag=1;
                        }else{
                                $contents.=$line;
                        }
                }
        }elsif($line =~ /og:description/){
                # description取得
                $st=index($line,"content=\"")+length("content=\"");
                $ed=index($line,"\"",$st);
                $description=substr($line,$st,$ed-$st);
        }


        $i++;
}
# URL変換処理
$contents =~ s/b.st-hatena.com/retoge-mag.websa.jp\/old\/b.st-hatena.com/g;
$contents =~ s/cdn-ak.f.st-hatena.com/retoge-mag.websa.jp\/old\/cdn-ak.f.st-hatena.com/g;
$contents =~ s/cdn.blog.st-hatena.com/retoge-mag.websa.jp\/old\/cdn.blog.st-hatena.com/g;
$contents =~ s/cdn.pool.st-hatena.com/retoge-mag.websa.jp\/old\/cdn.pool.st-hatena.com/g;
$contents =~ s/cdn.profile-image.st-hatena.com/retoge-mag.websa.jp\/old\/cdn.profile-image.st-hatena.com/g;
$contents =~ s/cdn.user.blog.st-hatena.com/retoge-mag.websa.jp\/old\/cdn.user.blog.st-hatena.com/g;
$contents =~ s/usercss.blog.st-hatena.com/retoge-mag.websa.jp\/old\/usercss.blog.st-hatena.com/g;

#


print "<item>\n";
print "<description>".$description."</description>\n";
print "<excerpt:encoded><![CDATA[]]></excerpt:encoded>\n";
print "<wp:status>publish</wp:status>\n";
print "<wp:post_type>post</wp:post_type>\n";
print "<wp:post_date_gmt>".$createdate."</wp:post_date_gmt>\n";
#print "<wp:post_modified_gmt>".$modifydate."</wp:post_modified_gmt>\n";
print "<wp:post_modified>".$modifydate."</wp:post_modified>\n";
print "<title><![CDATA[".$title."]]></title>\n";
print $categorys."\n";
#print "<dc:creator><![CDATA[".$author."]]></dc:creator>\n";
print "<dc:creator><![CDATA[pc88multi2]]></dc:creator>\n";
#print "<content:encoded><![CDATA[<!-- wp:paragraph -->\n".$contents."<!-- /wp:paragraph -->]]></content:encoded>\n";
print "<content:encoded><![CDATA[".$contents."]]></content:encoded>\n";
print "</item>\n";

echo '<?xml version="1.0" encoding="UTF-8" ?>' > wordpress.xml
echo '<rss version="2.0" xmlns:excerpt="http://wordpress.org/export/1.2/excerpt/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:wfw="http://wellformedweb.org/CommentAPI/"  xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:wp="http://wordpress.org/export/1.2/" >' >> wordpress.xml

echo '<channel><wp:wxr_version>1.2</wp:wxr_version>' >> wordpress.xml
echo '<wp:author></wp:author>' >> wordpress.xml

for file in `find retoge-mag.hatenablog.com/entry/* -name \*.html`
do echo --- $file ---
        ./test.pl $file >> wordpress.xml
done

echo '</channel>' >> wordpress.xml
echo '</rss>' >> wordpress.xml