You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
44 lines
1.7 KiB
44 lines
1.7 KiB
import requests
|
|
import json
|
|
import csv
|
|
import os
|
|
# 创建文件夹
|
|
if not os.path.exists('comment_files'):
|
|
os.makedirs('comment_files')
|
|
|
|
# 读取视频链接CSV文件
|
|
with open('video_links.csv', newline='', encoding='utf-8') as csvfile:
|
|
reader = csv.reader(csvfile)
|
|
# 跳过表头
|
|
next(reader)
|
|
# 遍历每个视频链接
|
|
for row in reader:
|
|
title, video_url, cover_url = row
|
|
# 获取BV号
|
|
bv = video_url.split('/')[-1]
|
|
# 请求头
|
|
headers = {
|
|
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) '
|
|
'AppleWebKit/537.36 (KHTML, like Gecko) '
|
|
'Chrome/58.0.3029.110 Safari/537.3'
|
|
}
|
|
# 请求URL
|
|
url = 'https://api.bilibili.com/x/v2/reply?type=1&oid=' + bv + '&pn='
|
|
# 评论总数
|
|
total_count = 0 # 默认值为0
|
|
# 遍历所有评论页
|
|
for page in range(1, total_count // 20 + 2):
|
|
# 发送HTTP请求并解析返回的JSON格式数据
|
|
response = requests.get(url + str(page), headers=headers)
|
|
data = json.loads(response.text)
|
|
# 判断评论总数是否已获取
|
|
if total_count == 0:
|
|
total_count = data['data']['page']['count']
|
|
# 判断是否存在评论
|
|
if 'data' in data:
|
|
reply_list = data['data']['replies']
|
|
# 如果存在评论，则将评论写入文件
|
|
with open(f'comment_files/{title}.csv', 'a', encoding='utf-8') as f:
|
|
for reply in reply_list:
|
|
f.write(reply['content']['message'] + '\n')
|