from selenium import webdriver
url = 'https://www.bilibili.com/video/BV1Wi4y1a7h5'
options = webdriver.ChromeOptions()
options.add_experimental_option('detach', True)
driver = webdriver.Chrome(options=options)
driver.get(url)
import time
time.sleep(5)
html = driver.page_source
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
title = soup.find('h1', class_="video-title")
count = soup.find('span', class_="view item")
dm = soup.find('span', class_="dm item")
datetime = soup.find('span', class_="pubdate-text")
comments = soup.find_all('div', class_="content-warp")
comments_text = []
for comment in comments:
name = comment.find('div', class_="user-info").text
text = comment.find('span', class_="reply-content").text
comments_text.append({
'name': name,
'text': text
})
# 输出结果
print(f"标题:{title.text},播放量:{count.text.strip()},弹幕数:{dm.text.strip()}")
for comment in comments_text:
print(f"评论:\nID:{comment['name']},评论内容:{comment['text']}")
driver.close()
考试自用爬虫
最新推荐文章于 2024-10-08 17:02:35 发布