Created
December 25, 2023 02:58
-
-
Save ejfox/492436ba80f9762e87bf51041f58221c to your computer and use it in GitHub Desktop.
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 puppeteer = require('puppeteer'); | |
const fs = require('fs'); | |
(async () => { | |
try { | |
// Read the CSV file | |
const inputCsv = fs.readFileSync('output.csv', 'utf-8'); | |
const records = inputCsv.split('\n').map((row, index) => { | |
if (index === 0) return null; // Skip the header row | |
const [Index, Title, URL] = row.split(','); | |
const longerURL = URL?.match(/"(.*?)"/)[1]; // Extract the longer URL | |
return { Index, Title, URL: longerURL }; | |
}).filter(record => record !== null); | |
// Check if the video has already been scraped | |
const scrapedCsvPath = 'updated_youtube_videos.csv'; | |
let scrapedCsv = ''; | |
if (fs.existsSync(scrapedCsvPath)) { | |
scrapedCsv = fs.readFileSync(scrapedCsvPath, 'utf-8'); | |
} | |
const scrapedRecords = scrapedCsv.split('\n').map((row, index) => { | |
if (index === 0) return null; // Skip the header row | |
const [Index, Title, URL] = row.split(','); | |
return { Index, Title, URL }; | |
}).filter(record => record !== null); | |
const unscrapedRecords = records.filter(record => { | |
const isScraped = scrapedRecords.some(scrapedRecord => scrapedRecord.URL === record.URL); | |
return !isScraped; | |
}); | |
// Launch Puppeteer | |
const browser = await puppeteer.launch({ | |
headless: false | |
}); | |
const page = await browser.newPage(); | |
// Process each URL to get the video title | |
for (const record of unscrapedRecords) { | |
try { | |
await page.goto(record.URL, { waitUntil: 'networkidle2', timeout: 30000 }); | |
const title = await page.title(); | |
// Update the title in your record | |
record.Title = title.replace(' - YouTube', ''); // Removing additional YouTube text | |
console.log(`Updated record ${record.Index} with title ${record.Title}`); | |
} catch (error) { | |
console.error(`Error processing record ${record.Index}: ${error.message}`); | |
// Continue to the next record | |
continue; | |
} | |
} | |
// Close the browser | |
await browser.close(); | |
// Convert the updated records back to CSV | |
const outputCsv = unscrapedRecords.map(record => `${record.Index},"${record.Title}",${record.URL}`).join('\n'); | |
// Write the new CSV to file | |
fs.writeFileSync('updated_youtube_videos.csv', outputCsv); | |
} catch (error) { | |
console.error(`An error occurred: ${error.message}`); | |
} | |
})(); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment