جزئیات ویدیوی YouTube را به طور موثر با پایتون خراش دهید

pip install playwright
pip install lxml

playwright install

playwright install chromium

import asyncio
from playwright.async_api import Playwright, async_playwright
from lxml import html
import csv

browser = await playwright.chromium.launch(headless=True)
context = await browser.new_context()
page = await context.new_page()

# Navigate to the YouTube video
await page.goto("https://www.youtube.com/watch?v=Ct8Gxo8StBU", wait_until="networkidle")

# Scroll down to load more comments
for _ in range(20):
    await page.mouse.wheel(0, 200)
    await asyncio.sleep(0.2)

# Let some content load
await page.wait_for_timeout(1000)

page_content = await page.content()
parser = html.fromstring(page_content)

title = parser.xpath('//div[@id="title"]/h1/yt-formatted-string/text()')[0]
channel = parser.xpath('//yt-formatted-string[@id="text"]/a/text()')[0]
channel_link = 'https://www.youtube.com' + parser.xpath('//yt-formatted-string[@id="text"]/a/@href')[0]
posted = parser.xpath('//yt-formatted-string[@id="info"]/span/text()')[2]
total_views = parser.xpath('//yt-formatted-string[@id="info"]/span/text()')[0]
total_comments = parser.xpath('//h2[@id="count"]/yt-formatted-string/span/text()')[0]
comments_list = parser.xpath('//yt-attributed-string[@id="content-text"]/span/text()')

with open('youtube_video_data.csv', 'w', newline='', encoding='utf-8') as file:
    writer = csv.writer(file)
    writer.writerow(["Title", "Channel", "Channel Link", "Posted", "Total Views", "Total Comments", "Comments"])
    writer.writerow([title, channel, channel_link, posted, total_views, total_comments, ", ".join(comments_list)])

browser = await playwright.chromium.launch(
    headless=True,
    proxy={"server": "http://your_proxy_ip:port", "username": "your_username", "password": "your_password"}
)

import asyncio
from playwright.async_api import Playwright, async_playwright
from lxml import html
import csv

# Main function to scrape the YouTube video data
async def run(playwright: Playwright) -> None:
    # Launch the browser with proxy settings
    browser = await playwright.chromium.launch(
        headless=True,
        proxy={"server": "http://your_proxy_ip:port", "username": "your_username", "password": "your_password"}
    )
    context = await browser.new_context()
    page = await context.new_page()

    # Navigate to the YouTube video URL
    await page.goto("https://www.youtube.com/watch?v=Ct8Gxo8StBU", wait_until="networkidle")

    # Scroll to load more comments
    for _ in range(20):
        await page.mouse.wheel(0, 200)
        await asyncio.sleep(0.2)

    # Wait for additional content to load
    await page.wait_for_timeout(1000)

    # Get page content
    page_content = await page.content()

    # Close the browser
    await context.close()
    await browser.close()

    # Parse the HTML
    parser = html.fromstring(page_content)

    # Extract data
    title = parser.xpath('//div[@id="title"]/h1/yt-formatted-string/text()')[0]
    channel = parser.xpath('//yt-formatted-string[@id="text"]/a/text()')[0]
    channel_link = 'https://www.youtube.com' + parser.xpath('//yt-formatted-string[@id="text"]/a/@href')[0]
    posted = parser.xpath('//yt-formatted-string[@id="info"]/span/text()')[2]
    total_views = parser.xpath('//yt-formatted-string[@id="info"]/span/text()')[0]
    total_comments = parser.xpath('//h2[@id="count"]/yt-formatted-string/span/text()')[0]
    comments_list = parser.xpath('//yt-attributed-string[@id="content-text"]/span/text()')

    # Save the data to a CSV file
    with open('youtube_video_data.csv', 'w', newline='', encoding='utf-8') as file:
        writer = csv.writer(file)
        writer.writerow(["Title", "Channel", "Channel Link", "Posted", "Total Views", "Total Comments", "Comments"])
        writer.writerow([title, channel, channel_link, posted, total_views, total_comments, ", ".join(comments_list)])

# Running the async function
async def main():
    async with async_playwright() as playwright:
        await run(playwright)

asyncio.run(main())