1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19

url='https://scrapbox.io/api/pages/yuwd?limit=500'
# url='https://scrapbox.io/api/pages/yuwd?limit=10'
dates=(`curl $url | jq ".pages[].updated" | xargs`)
echo "COUNT=${#dates[@]}"
i=0
IFS=$'\n'
for title in $(curl $url | jq ".pages[].title" | sed -e "s/^\"//g" | sed -e "s/\"$//g")
do
    md_title=`echo $title | tr ' ' '_' | sed s/\?//g | sed s/!//g | sed s/://g`
    etitle=$(echo $title | python -c 'import sys;from urllib.parse import quote; [print(quote(l)[:-3],end="") for l in sys.stdin]')
    if [ ! -e $md_title.md ]; then
        echo $title
        url="https://scrapbox.io/api/pages/yuwd/${etitle}/text"
        echo $url
        curl $url | node sb2md.js > $md_title.md
        python scrapbox.py $md_title.md "${dates[$i]}"
    fi
    i=`expr $i + 1`
done

 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
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69

// https://gist.github.com/yuntan/bb82cdf336ec76a15c66b910754f5f33

if (!Object.prototype.then) {
  Object.prototype.then = function (f) { return f.call(null, this); }
}

process.stdin.resume();
process.stdin.setEncoding('utf8');
let input_string = '';

process.stdin.on('data', chunk => {
  input_string += chunk;
});

process.stdin.on('end', () => {
  const text = input_string;
  console.log(sb2md(text));
});

function sb2md(text) {
  // code block
  const escapeCodeBlocks = s => s.replace(
    /^code:(.+)$((\n^[ \t].*$)+)/mg,
    (_, p1, p2) =>
      '```' + p1 + p2.replace(/^[ \t]/mg, '').replace(/\r|\n|\r\n/g, '
') + '
```'
  );

  const unescapeCodeBlocks = s => s.replace(/\+{3}/g, '\n');

  const replaceLine = line =>
    /^`{3}/.test(line) ? line :
      // level 2 heading
      line.replace(/^\[\[([^\[\]]+)\]\]$/, '## $1')
      .replace(/^\[\*\s+(\S[^\[\]]*)\]$/, '## $1')

      // anchor link
      .replace(/\[(\S.*)\s+(https?:\/\/\S+)\](https://scrapbox.io/yuwd/%28%5CS.%2A%29%5Cs%2B%28https%3F%3A%5C/%5C/%5CS%2B%29%5C)/g, '[$1]($2)')
      .replace(/\[(https?:\/\/\S+)\s+(\S.*)\](https://scrapbox.io/yuwd/%28https%3F%3A%5C/%5C/%5CS%2B%29%5Cs%2B%28%5CS.%2A%29%5C)/g, '[$2]($1)')

      // image block
      .replace(/^\[(https?:\/\/\S+\.(png|gif|jpe?g))\](https://scrapbox.io/yuwd/%28https%3F%3A%5C/%5C/%5CS%2B%5C.%28png%7Cgif%7Cjpe%3Fg%29%29%5C)$/, '![]($1)')
      .replace(/^\[(https:\/\/gyazo.com\/\S+)\](https://scrapbox.io/yuwd/%28https%3A%5C/%5C/gyazo.com%5C/%5CS%2B%29%5C)$/, '![]($1.png)')

      // unordered list
      .replace(/^\s{6}(\S.*)$/, '          - $1')
      .replace(/^\s{5}(\S.*)$/, '        - $1')
      .replace(/^\s{4}(\S.*)$/, '      - $1')
      .replace(/^\s{3}(\S.*)$/, '    - $1')
      .replace(/^\s{2}(\S.*)$/, '  - $1')
      .replace(/^\s(\S.*)$/, '- $1')

      // bold text
      .replace(/\[\[([^\[\]]+)\]\]/g, '**$1**')
      .replace(/\[\*\s+([^\[\]]+)\]/g, '**$1**')

      // italic text
      .replace(/\[\/\s+([^\[\]]+)\]/g, '*$1*');

  return text
    .then(escapeCodeBlocks)
    .split(/\r|\n|\r\n/)
    // first line is level 1 heading
    .then(lines => [lines[0].replace(/^(.+)$/, '$1')].concat(lines.slice(1)))
    .map(replaceLine)
    .join('\n')
    .then(unescapeCodeBlocks);
}