let INFO =
teramako
MIT
特定ページの画像とかのURLを取ってきて一気にZIPにしてダウンロードするお
-
:zipd :zipdownload
:zipdownload -list -filter=filter downloadPath
downloadPathへZIPでアーカイブする。
downloadPathがディレクトリの場合、"ページタイトル.zip"となる。
省略された場合、以下の順に値を見て、そのディレクトリへダウンロードされる。
- g:zipDownloadDir (liberator.globalVariables.zipDownloadDir)
- browser.download.lastDir (Preference)
- ホームディレクトリ
-listオプションを指定すると、ダウンロードされるURLをリストする。
(ダウンロードはされない)
-filterオプションを指定すると、マッチするURLのアイテムのみダウンロードする。
-
g:zipDownloadDir
g:zipDownloadDir
liberator.globalVariables.zipDownloadDir
ダウンロード先ディレクトリ。downloadPathを省略した場合に、使用される。
例
:let g:zipDownloadDir="~/downloads"
-
g:zipDownloadFilter
g:zipDownloadFilter
liberator.globalVariables.zipDownloadFilter
デフォルトのフィルタfilterを省略した場合に、使用される。
例
:let g:zipDownloadFilter="\.(jpe?g|gif|png)$"
-
plugins.zipDeDownload.SITE_INFO
plugins.zipDeDownload.SITE_INFO
ページ毎の設定。詳細はコードを見よ。(見れば分かると思う)
;
// FIXME: 将来的には、storageに入れるべき
// FIXME: あと、それぞれダウンロード先を指定できた方が良い(?)
// XXX: WeData化してもOK
let SITE_INFO = [
{
label: "みんくちゃんねる",
site: "http://minkch\\.com/archives/.*\\.html",
xpath: '//a[img[@class="pict"]]|//div/img[@class="pict"]',
filter: "\\.(jpe?g|gif|png)$"
}, {
label: "カナ速",
site: "http://kanasoku\\.blog82\\.fc2\\.com/blog-entry-.*\\.html",
xpath: '//div[@class="entry_body"]//a[img]',
filter: "\\.(jpe?g|gif|png)$"
}, {
label: "がぞう~速報",
site: "http://stalker\\.livedoor\\.biz/archives/.*\\.html",
xpath: '//div[@class="main" or @class="mainmore"]//a/img[@class="pict"]/..',
filter: "\\.(jpe?g|gif|png)$"
}, {
label: "ギャルゲーブログ",
site: "http://suiseisekisuisui\\.blog107\\.fc2\\.com/blog-entry-.*.html",
xpath: '//div[@class="ently_text"]/a[img]',
filter: "\\.(jpe?g|gif|png)$"
}, {
label: "わくてか速報",
site: "http://blog\\.livedoor\\.jp/wakusoku/archives/.*\\.html",
xpath: '//div[@class="article-body-inner" or @class="article-body-more"]//a[//img[@class="pict"]]',
filter: "\\.(jpe?g|gif|png)$"
}, {
label: "らばQ",
site: "http://labaq\\.com/archives/.*\\.html",
xpath: '//img[@class="pict"]',
}, {
labe: "【2ch】ニュー速クオリティ",
site: "http://news4vip\\.livedoor\\.biz/archives/.*\\.html",
xpath: '//a[img[@class="pict"]] | //div/img[@class="pict"]',
filter: "\\.(jpe?g|gif|png)$"
}, {
label: "ねとねた",
site: "http://vitaminabcdefg\\.blog6\\.fc2\\.com/blog-entry-.*\\.html",
xpath: '//div[@class="mainEntryBody" or @class="mainEntryMore"]//a[img]',
filter: "\\.(jpe?g|gif|png)$"
}, {
label: "PINK速報",
site: "http://pinkimg\\.blog57\\.fc2\\.com/blog-entry-.*\\.html",
xpath: '//div[@class="entry_text"]/a[img]',
filter: "\\.(jpe?g|gif|png)$"
}
];
(function(){
// nsIZipWriter#open io-flags
const PR_RDONLY = 0x01;
const PR_WRONLY = 0x02;
const PR_RDWR = 0x04;
const PR_CREATE_FILE = 0x08;
const PR_APPEND = 0x10;
const PR_TRUNCATE = 0x20;
const PR_SYNC = 0x40;
const PR_EXCL = 0x80;
const mimeService = Cc["@mozilla.org/mime;1"].getService(Ci.nsIMIMEService);
const zipWriter = Components.Constructor("@mozilla.org/zipwriter;1", "nsIZipWriter");
function getFile(aFile){
return liberator.modules.io.File(aFile);
}
function createChannel(url){
return liberator.modules.services.get("io").newChannel(url, "UTF-8", null);
}
function getEntryName(uri, mimeType){
let mime;
try {
mime = mimeService.getTypeFromURI(uri);
} catch(e) {
liberator.reportError(e);
};
let ext = mimeService.getPrimaryExtension(mime ? mime : mimeType, null)
let name = uri.path.split("/").pop();
name = (name ? name : "index") + (mime ? "" : "." + ext);
return name;
}
function getDownloadDirectory(){
let path = liberator.globalVariables.zipDownloadDir ||
liberator.modules.options.getPref("browser.download.lastDir", null) ||
liberator.modules.services.get("directory").get("Home", Ci.nsIFile).path;
return getFile(path);
}
function fixFilename(filename){
const badChars = /[\\\/:;\*\?\"\<\>\|\#]/g;
return liberator.has('windows') ? filename.replace(badChars, '_') : filename;
}
function getXPathFromExtensions(exts){
function getXPath(elem){
if (!elem)
return '';
// 連番かもしれない id は無視する
let id = elem.getAttribute('id');
if (id && !/\d/(id))
return 'id("' + id + '")';
return getXPath(elem.parentNode) + '/' + elem.tagName.toLowerCase();
}
let extPattern = RegExp('(' + exts.join('|')+')(\\W|$)');
let links =
Array.slice( content.document.querySelectorAll('a')).filter(
function (link) (link.href && extPattern(link.href)));
let xs = {};
for each(let link in links){
let xpath = getXPath(link);
if (xs[xpath])
xs[xpath]++;
else
xs[xpath] = 1;
}
let result = null, max = 0;
for(let [xpath, count] in Iterator(xs)){
if (count > max)
[result, max] = [xpath, count];
}
return result;
}
function extensionValidator(vs)
vs && vs.every(function (v) /^[\da-zA-Z]+$/(v));
let self = {
downloadZip: function(path, urls, comment, isAppend){
let zipW = new zipWriter();
let urls = [url for each(url in urls)];
liberator.assert(urls.length > 0, "None of URLs");
if (!(/\.zip$/i).test(path)){
path += ".zip";
}
let zipFile = getFile(path);
if (isAppend && zipFile.exists()){
zipW.open(zipFile, PR_RDWR | PR_APPEND);
} else {
zipW.open(zipFile, PR_RDWR | PR_CREATE_FILE | PR_TRUNCATE);
}
if (comment)
zipW.comment = comment;
let i = 0;
for each(let url in urls){
let ch = createChannel(url);
try {
let stream = ch.open();
let entryName = ("000" + ++i).slice(-3) + "-" + getEntryName(ch.URI, ch.contentType);
liberator.echomsg("zip: " + url + " to " + entryName, 3);
zipW.addEntryStream(entryName, Date.now() * 1000, Ci.nsIZipWriter.COMPRESSION_DEFAULT, stream, false);
} catch (e) {
// XXX エラー分を通知すべき?
liberator.log('zip-de-download: error: ' + e);
}
}
zipW.close();
return zipFile;
},
getInfoFromBuffer: function(){
for each(data in SITE_INFO){
let reg = new RegExp(data.site);
if (reg.test(liberator.modules.buffer.URL)){
return data;
}
}
return null;
},
getURLs: function(info){
let filter = new RegExp(info.filter || liberator.globalVariables.zipDownloadFilter || ".");
let i = 0;
for (let elm in liberator.modules.util.evaluateXPath(info.xpath, content.document)){
let url;
if (elm instanceof Ci.nsIDOMHTMLAnchorElement)
url = elm.href;
else if (elm instanceof Ci.nsIDOMHTMLImageElement)
url = elm.src;
else
continue;
if (filter.test(url))
yield url;
}
},
download: function(zipPath, listOnly, option){
let info = this.getInfoFromBuffer() || {};
if (option){
let infoBuf = {};
for (let key in info){
infoBuf[key] = info[key];
}
for (let key in option){
infoBuf[key] = option[key];
}
info = infoBuf;
}
liberator.assert(info.xpath, "not registered in SITE_INFO");
let urls = this.getURLs(info);
let title = fixFilename(liberator.modules.buffer.title);
let comment = [title, liberator.modules.buffer.URL].join("\n");
let file;
if (!zipPath){
file = getDownloadDirectory();
file.append(title + ".zip");
} else {
file = getFile(zipPath);
if (file.exists() && file.isDirectory()){
file.append(title + ".zip");
}
}
if (listOnly){
return [file, urls, comment];
}
return this.downloadZip(file.path, urls, comment, info.append);
}
};
// ---------------------------------------------------
// Commands
// ---------------------------------------------------
liberator.modules.commands.addUserCommand(
["zipd[ownload]"], "download and archive to ZIP",
function (arg){
let option = {}
option.append = ("-append" in arg);
if ("-auto-detect" in arg){
option.xpath = getXPathFromExtensions(arg["-auto-detect"]);
}
if ("-xpath" in arg){
option.xpath = arg["-xpath"];
}
if ("-filter" in arg){
option.filter = arg["-filter"];
}
if ("-list" in arg){
let [file, urls, comment] = self.download(arg[0], true, option);
let xml = <>
Download :{file.path}
{comment}
{liberator.modules.template.map(urls, function(url) - {url}
)}
>;
liberator.echo(xml, true);
return;
}
liberator.echo("Started DownloadZip");
let zipFile = self.download(arg[0], false, option);
liberator.echo("Completed DownloadZip: " + zipFile.path);
}, {
argCount: "?",
literal: true,
options: [
[["-list", "-l"], liberator.modules.commands.OPTION_NOARG],
[["-append", "-a"], liberator.modules.commands.OPTION_NOARG],
[["-xpath", "-x"], liberator.modules.commands.OPTION_STRING],
[["-auto-detect", "-d"], liberator.modules.commands.OPTION_LIST, extensionValidator,
[["jpeg,jpg,png", "images"]]],
[["-filter", "-f"], liberator.modules.commands.OPTION_STRING]
],
completer: liberator.modules.completion.file
}, true);
util.extend(__context__, self);
})();
// vim: sw=2 ts=2 et:
='n263' href='#n263'>263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
|