f5f49c7b1d
We don't usually want an async detectWeb, since HTTP requests should only be used there in very exceptional cases. We do usually want an async scrape (and we were already - mistakenly - awaiting it).
72 lines
1.9 KiB
JavaScript
72 lines
1.9 KiB
JavaScript
/*
|
|
***** BEGIN LICENSE BLOCK *****
|
|
|
|
Copyright © 2022 YOUR_NAME <- TODO
|
|
|
|
This file is part of Zotero.
|
|
|
|
Zotero is free software: you can redistribute it and/or modify
|
|
it under the terms of the GNU Affero General Public License as published by
|
|
the Free Software Foundation, either version 3 of the License, or
|
|
(at your option) any later version.
|
|
|
|
Zotero is distributed in the hope that it will be useful,
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
GNU Affero General Public License for more details.
|
|
|
|
You should have received a copy of the GNU Affero General Public License
|
|
along with Zotero. If not, see <http://www.gnu.org/licenses/>.
|
|
|
|
***** END LICENSE BLOCK *****
|
|
*/
|
|
|
|
|
|
function detectWeb(doc, url) {
|
|
// TODO: adjust the logic here
|
|
if ($$CURSOR$$url.includes('/article/')) {
|
|
return 'newspaperArticle';
|
|
}
|
|
else if (getSearchResults(doc, true)) {
|
|
return 'multiple';
|
|
}
|
|
return false;
|
|
}
|
|
|
|
function getSearchResults(doc, checkOnly) {
|
|
var items = {};
|
|
var found = false;
|
|
// TODO: adjust the CSS selector
|
|
var rows = doc.querySelectorAll('h2 > a.title[href*="/article/"]');
|
|
for (let row of rows) {
|
|
// TODO: check and maybe adjust
|
|
let href = row.href;
|
|
// TODO: check and maybe adjust
|
|
let title = ZU.trimInternal(row.textContent);
|
|
if (!href || !title) continue;
|
|
if (checkOnly) return true;
|
|
found = true;
|
|
items[href] = title;
|
|
}
|
|
return found ? items : false;
|
|
}
|
|
|
|
async function doWeb(doc, url) {
|
|
if (detectWeb(doc, url) == 'multiple') {
|
|
let items = await Zotero.selectItems(getSearchResults(doc, false));
|
|
if (items) {
|
|
await Promise.all(
|
|
Object.keys(items)
|
|
.map(url => requestDocument(url).then(scrape))
|
|
);
|
|
}
|
|
}
|
|
else {
|
|
await scrape(doc, url);
|
|
}
|
|
}
|
|
|
|
async function scrape(doc, url = doc.location.href) {
|
|
// TODO: implement or add a scrape function template
|
|
}
|
|
|