python爬取bili弹幕

from selenium import webdriver
from selenium.webdriver.common.by import By
from bs4 import BeautifulSoup
import time

# 设置请求头信息
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36',
    'referer': 'https://www.bilibili.com',
}
# 定义原始视频链接
video_url = 'https://www.bilibili.com/video/BV1y94y1P7V5?p=5&vd_source=c2059fd378b370efe9d97ee1903c9680'

# 初始化浏览器驱动
options = webdriver.ChromeOptions()
options.add_argument('--headless')  # 无头模式，不显示浏览器界面
driver = webdriver.Chrome()
# 发送请求获取视频页面内容
driver.get(video_url)
time.sleep(5)  # 等待页面加载，可根据实际情况调整时间

# 获取页面源代码并解析
page_source = driver.page_source
soup = BeautifulSoup(page_source, 'html.parser')

# 获取所有data-cid值并去重
data_cids = set()
for tag in soup.find_all(attrs={'data-cid': True}):
    data_cids.add(tag['data-cid'])

# 将data-cid值写入文本文件
with open('data_cids1.txt', 'w', encoding='utf-8') as f:
    for cid in data_cids:
        f.write(cid + '\n')

import requests
from bs4 import BeautifulSoup as Bs
import time
import json

# 定义视频地址和请求头信息
cid_list = ['1361106922', '1361094183', '1361106754', '1361106735', '1361106809', '1361106932', '1361106663']
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36',
}

# 初始化列表和计数器
data_list = []
id_counter = 1

# 遍历每个视频的cid
for cid in cid_list:
    # 根据cid号，拼接xml接口地址，并发送请求
    danmu_url = 'http://comment.bilibili.com/{}.xml'.format(cid)  # 弹幕地址
    print('弹幕地址是:', danmu_url)
    r = requests.get(danmu_url)

    # 解析xml页面
    soup = Bs(r.text, 'xml')
    danmu_list = soup.find_all('d')
    print('共爬取到{}条弹幕'.format(len(danmu_list)))

    # 初始化视频信息字典
    video_info = {
        'id': id_counter,  # 视频ID自增
        'video_name': '【2023和平精英全球总决赛】12月9日 总决赛DAY2',  # 视频名称
        'url': 'https://www.bilibili.com/video/BV1y94y1P7V5?p=5&vd_source=c2059fd378b370efe9d97ee1903c9680',  # 视频链接
        'danmu_url': danmu_url,  # 弹幕链接
        'danmu': []  # 存储弹幕时间和弹幕内容的列表
    }

    # 提取弹幕信息并存入列表
    for d in danmu_list:
        data_split = d['p'].split(',')
        danmu_time = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(int(data_split[4])))
        danmu_content = d.text.encode('raw_unicode_escape').decode('utf-8')  # 处理编码问题
        video_info['danmu'].append({
            'time': danmu_time,
            'content': danmu_content
        })

        print('{}: {}'.format(danmu_time, danmu_content))

    # 将视频信息字典添加到列表中
    data_list.append(video_info)

    # 自增ID计数器
    id_counter += 1

# 写入JSON文件
output_file = 'bili.json'
with open(output_file, 'w', encoding='utf-8') as f:
    json.dump(data_list, f, ensure_ascii=False, indent=4)

print(f'弹幕数据已写入{output_file}文件中')

import json

# 读取 JSON 文件
input_file = 'bili.json'
with open(input_file, 'r', encoding='utf-8') as f:
    data_list = json.load(f)

# 遍历每个视频信息，对弹幕按照时间排序
for video_info in data_list:
    danmu_list = video_info['danmu']
    sorted_danmu_list = sorted(danmu_list, key=lambda x: x['time'])
    video_info['danmu'] = sorted_danmu_list


# print(json.dumps(data_list[0], ensure_ascii=False, indent=4))

# 可以将排序后的数据写入新的 JSON 文件
output_file_sorted = 'bili_326.json'
with open(output_file_sorted, 'w', encoding='utf-8') as f:
    json.dump(data_list, f, ensure_ascii=False, indent=4)

print(f'排序后的弹幕数据已写入 {output_file_sorted} 文件中')