cloudyu / 60B_MoE_Coder_v3

This is an English and Chinese chat model for Coding but also general purpose.

example output

写一个python程序抓取youtube最流行的内容：从网页获取数据，

以下是一个python脚本，可以从Youtube上抓取最受欢迎的视频并将其保存到本地文件中。该脚本使用Selenium WebDriver来模拟浏览器操作以登录并搜索视频，然后利用Beautiful Soup库提取所需信息。如果您需要任何帮助或修改建议，请随时告诉我！

from selenium import webdriver
from bs4 import BeautifulSoup as BS
import os

# 设置ChromeDriver路径
CHROMEDRIVER_PATH = './chromedriver.exe' # 更换为实际路径

def main():
    # 启动Chrome浏览器并登录Youtube
    browser = webdriver.Chrome(executable_path=CHROMEDRIVER_PATH)
    browser.get('https://www.youtube.com/')
    login_url = 'https://accounts.google.com/signin'
    browser.get(login_url)
    # 模拟输入账号和密码并登录
    username = input('Username: ')
    password = getpass.getpass() # 防止密码显示在终端上
    submit_button = browser.find_element_by_class_name('whsLW', timeout=5)
    submit_button.click()

    # 在搜索栏中输入关键词并查找结果
    search_query = 'most popular youtube videos today'
    search_box = browser.find_element_by_id('search_query')
    search_box.send_keys(search_query)
    enter_key = browser.find_element_by_class_name('ytp-suggest-renderer__input-icon')
    enter_key.click()
    results = BS(browser.page_source, 'html.parser')

    # 从搜索结果中提取出最受欢迎的视频链接并保存到本地文件
    videos = results.find('ol', {'class': 'r'})
    video_urls = [a['href'] for a in videos.find_all('a')]
    saved_path = 'popular_videos/' + os.getcwd().split('/')[-2] + '_' + str(int(time.time())) + '/'
    if not os.path.exists(saved_path):
        os.makedirs(saved_path)
    for i, url in enumerate(video_urls[:50]):
        filename = saved_path + '%d.mp4' % (i+1)
        urllib.request.urlretrieve(url, filename)
    print('Downloaded top 50 videos to:', saved_path)

except Exception as e:
    print(e)