Created
December 4, 2020 19:29
-
-
Save ryanmuller/2f8b9754b72bbf98bd70f0c974243ecd to your computer and use it in GitHub Desktop.
scrape google scholar for roam as chrome extension
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| chrome.runtime.onMessage.addListener(function(msg, sender, callback) { | |
| let title, year, journal, url; | |
| let authors = []; | |
| const citationRows = document.getElementById('gs_citt').getElementsByTagName('tr'); | |
| for (let i = 0; i < citationRows.length; i++) { | |
| if (citationRows[i].getElementsByTagName('th')[0].textContent === 'Chicago') { | |
| const chicagoCitation = citationRows[i].getElementsByTagName('td')[1].textContent; | |
| // TODO: improve year match | |
| const matches = chicagoCitation.match(/^(.*)\.\ "(.*)\."\ (?:In\ )?([^,]*).*\b(\d\d\d\d)\b/); | |
| const authorParts = matches[1].split(', '); | |
| authorParts[authorParts.length - 1] = authorParts[authorParts.length - 1].replace('and ', ''); | |
| authors.push(authorParts[1] + ' ' + authorParts[0]); | |
| authors = authors.concat(authorParts.slice(2)); | |
| title = matches[2]; | |
| journal = matches[3]; | |
| year = matches[4]; | |
| } | |
| } | |
| // alternative option for title: document.getElementsByTagName('h3')[0].textContent; | |
| const links = document.getElementsByClassName('gs_or_ggsm'); | |
| if (links.length) { | |
| url = links[0].getElementsByTagName('a')[0].href; | |
| } | |
| callback({ title, authors, year, journal, url }); | |
| }); |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| <!DOCTYPE html> | |
| <html> | |
| <body> | |
| <label>title</label> | |
| <textarea id="title" cols="80"></textarea> | |
| <label>meta</label> | |
| <textarea id="meta" cols="80" rows="3"></textarea> | |
| <script src="popup.js"></script> | |
| </body> | |
| </html> |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| const titleOut = document.getElementById('title'); | |
| const metaOut = document.getElementById('meta'); | |
| chrome.tabs.query({active: true, currentWindow: true}, function(tabs) { | |
| chrome.tabs.sendMessage(tabs[0].id, {}, function(data) { | |
| const authorStr = data.authors.map(a => `[[${a}]]`).join(', '); | |
| titleOut.value = `[[${data.title}]]`; | |
| metaOut.value = | |
| `* **Authors:** ${authorStr} | |
| * **Year:** ${data.year} | |
| * **Publication:** ${data.journal} | |
| * **URL:** ${data.url}`; | |
| }); | |
| }); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment