Google Scholar Chrome Extension Development Guide

// content.js — runs on scholar.google.com pages

/**
 * Extract paper data from a Scholar result element
 */
function extractPaperData(resultElement) {
  const titleEl = resultElement.querySelector('.gs_rt a, .gs_rt span')
  const authorsEl = resultElement.querySelector('.gs_a')
  const snippetEl = resultElement.querySelector('.gs_rs')
  const citedByEl = resultElement.querySelector('a[href*="cites="]')
  const yearEl = resultElement.querySelector('.gs_a')

  // Parse authors and year from the combined author string
  const authorText = authorsEl?.textContent || ''
  const yearMatch = authorText.match(/\b(19|20)\d{2}\b/)

  // Extract PDF link if present
  const pdfLinkEl = resultElement.querySelector('.gs_or_ggsm a')
  const scholarLink = resultElement.querySelector('.gs_rt a')

  return {
    title: titleEl?.textContent?.trim() || '',
    authors: authorText.split('-')[0]?.trim() || '',
    year: yearMatch ? parseInt(yearMatch[0]) : null,
    citedBy: citedByEl ? parseInt(citedByEl.textContent.replace(/\D/g, '')) : 0,
    snippet: snippetEl?.textContent?.trim() || '',
    pdfUrl: pdfLinkEl?.href || null,
    scholarUrl: scholarLink?.href || null,
  }
}

/**
 * Scrape all results on the current Scholar page
 */
function scrapeCurrentPage() {
  const results = document.querySelectorAll('.gs_r.gs_or.gs_scl')
  return Array.from(results).map(extractPaperData).filter(p => p.title)
}

// Listen for messages from popup
chrome.runtime.onMessage.addListener((message, sender, sendResponse) => {
  if (message.action === 'scrapePage') {
    const papers = scrapeCurrentPage()
    sendResponse({ papers })
  }

  if (message.action === 'exportCsv') {
    const papers = scrapeCurrentPage()
    const csv = papersToCSV(papers)
    downloadCSV(csv, 'scholar-results.csv')
    sendResponse({ success: true })
  }

  return true // Keep message channel open for async response
})

/**
 * Convert paper array to CSV
 */
function papersToCSV(papers) {
  const headers = ['Title', 'Authors', 'Year', 'Cited By', 'Scholar URL', 'PDF URL']
  const rows = papers.map(p => [
    `"${p.title.replace(/"/g, '""')}"`,
    `"${p.authors.replace(/"/g, '""')}"`,
    p.year || '',
    p.citedBy,
    p.scholarUrl || '',
    p.pdfUrl || ''
  ])

  return [headers, ...rows].map(row => row.join(',')).join('\n')
}

/**
 * Trigger CSV download in the browser
 */
function downloadCSV(content, filename) {
  const blob = new Blob([content], { type: 'text/csv' })
  const url = URL.createObjectURL(blob)
  const a = document.createElement('a')
  a.href = url
  a.download = filename
  a.click()
  URL.revokeObjectURL(url)
}

// popup.js
document.getElementById('export-csv').addEventListener('click', async () => {
  const [tab] = await chrome.tabs.query({ active: true, currentWindow: true })

  const status = document.getElementById('status')
  status.textContent = 'Extracting results...'

  const response = await chrome.tabs.sendMessage(tab.id, { action: 'exportCsv' })

  if (response?.success) {
    status.textContent = 'CSV downloaded successfully'
  } else {
    status.textContent = 'Error: are you on a Scholar results page?'
  }
})

document.getElementById('copy-titles').addEventListener('click', async () => {
  const [tab] = await chrome.tabs.query({ active: true, currentWindow: true })
  const response = await chrome.tabs.sendMessage(tab.id, { action: 'scrapePage' })

  if (response?.papers) {
    const titles = response.papers.map(p => p.title).join('\n')
    await navigator.clipboard.writeText(titles)
    document.getElementById('status').textContent = `${response.papers.length} titles copied`
  }
})

// background.js
// Manifest V3 uses service workers instead of persistent background pages

chrome.runtime.onInstalled.addListener(() => {
  console.log('Scholar Research Assistant installed')
})

// Handle extension icon click — open Scholar if not on Scholar tab
chrome.action.onClicked.addListener(async (tab) => {
  if (!tab.url?.includes('scholar.google.com')) {
    await chrome.tabs.create({ url: 'https://scholar.google.com' })
  }
})

// content.js — wait for results to load
function waitForResults(callback) {
  const existing = document.querySelectorAll('.gs_r.gs_or.gs_scl')
  if (existing.length > 0) {
    callback()
    return
  }

  const observer = new MutationObserver((mutations, obs) => {
    const results = document.querySelectorAll('.gs_r.gs_or.gs_scl')
    if (results.length > 0) {
      obs.disconnect()
      callback()
    }
  })

  observer.observe(document.body, { childList: true, subtree: true })
}

waitForResults(() => {
  // Safe to scrape now
  const papers = scrapeCurrentPage()
  console.log(`Found ${papers.length} papers`)
})