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.
84 lines
4.0 KiB
84 lines
4.0 KiB
2 months ago
|
import requests
|
||
|
|
import re
|
||
|
|
from bs4 import BeautifulSoup
|
||
|
|
from collections import Counter
|
||
|
|
from openpyxl import Workbook
|
||
|
|
import pandas as pd
|
||
|
|
import jieba
|
||
|
|
from wordcloud import WordCloud
|
||
|
|
import imageio
|
||
|
|
|
||
|
|
# 自定义请求头
|
||
|
|
headers = {
|
||
|
|
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36 Edg/128.0.0.0",
|
||
|
|
"cookie": "buvid3=EC7F71FB-704D-BC2F-878E-060C9BB612D457758infoc; b_nut=1723797357; buvid_fp=c08f0cc51dccc720ed3a6ae23c5993ce; buvid4=BA329B3A-045C-D770-A220-0ABF4AB3A65459138-024081608-vt1IkSnsVWpP9n3wj7cBFA%3D%3D; _uuid=938B8637-6C16-573D-B41C-C2C777FB13B1097589infoc; header_theme_version=CLOSE; enable_web_push=DISABLE; is-2022-channel=1; CURRENT_FNVAL=4048; bili_ticket=eyJhbGciOiJIUzI1NiIsImtpZCI6InMwMyIsInR5cCI6IkpXVCJ9.eyJleHAiOjE3MjY4Mzk5MTUsImlhdCI6MTcyNjU4MDY1NSwicGx0IjotMX0.pZvh0NsfTw53cQQz2zS7FURglT5oimgQSKIewfAyX0U; bili_ticket_expires=1726839855; SESSDATA=f2257e8a%2C1742138056%2C7342c%2A91CjBj2a9mnoec-WGYJHyOS54IzHo75eIEzOFcQpBxBRhIJ1QkCht2IjeodCewKBabaXkSVkhUdDZiQWlhTjZTUGtIbnJnNGN6S3JwQnExakMzSV8zWkJLTVNvMW5wMmhPSEg2VDkyZm90R0tGakhhSW9UNzloTHJ6QzdEV2kzVnd3bjg4VjZhX1NBIIEC; bili_jct=68e737446e9c9510ab766b465af1c75f; DedeUserID=104367431; DedeUserID__ckMd5=50fce7fb6de2fe29; rpdid=|(JlRYJ)|R~|0J'u~kYl)YJR|; bp_t_offset_104367431=978170954758750208; b_lsid=95B101073A_19202E92625; sid=849wwfno; bsource=search_bing; browser_resolution=1272-560; home_feed_column=4"
|
||
|
|
}
|
||
|
|
|
||
|
|
# 检查文本是否包含“AI”或“人工智能”
|
||
|
|
def check_ai_content(text):
|
||
|
|
pattern = re.compile(r'(\bai\b|人工智能|([\u4e00-\u9fff]|\s|^)ai([\u4e00-\u9fff]|\s|$))', re.IGNORECASE)
|
||
|
|
return pattern.search(text)
|
||
|
|
|
||
|
|
# 获取网页内容
|
||
|
|
def fetch_html(url):
|
||
|
|
response = requests.get(url, headers=headers)
|
||
|
|
response.encoding = 'utf-8'
|
||
|
|
return response.text
|
||
|
|
|
||
|
|
# 提取视频链接
|
||
|
|
def extract_video_links(html_data):
|
||
|
|
soup = BeautifulSoup(html_data, 'html.parser')
|
||
|
|
video_links = set()
|
||
|
|
for link in soup.find_all('a', href=True):
|
||
|
|
video_links.add(link['href'])
|
||
|
|
return video_links
|
||
|
|
|
||
|
|
# 获取视频弹幕API链接
|
||
|
|
def get_danmaku_api_links(video_url):
|
||
|
|
response = requests.get(video_url, headers=headers)
|
||
|
|
if response.status_code == 200:
|
||
|
|
html_data = response.text
|
||
|
|
return extract_danmaku_api_links(html_data)
|
||
|
|
return []
|
||
|
|
|
||
|
|
# 提取弹幕API链接
|
||
|
|
def extract_danmaku_api_links(html_data):
|
||
|
|
pattern = re.compile(r'https://api\.bilibili\.com/x/v1/dm/list\.so\?')
|
||
|
|
return [url for url in html_data.split('\n') if pattern.match(url)]
|
||
|
|
|
||
|
|
# 主程序
|
||
|
|
def main():
|
||
|
|
ai_comments = [] # 存储AI相关的弹幕
|
||
|
|
danmaku_api_links = [] # 存储弹幕API链接
|
||
|
|
|
||
|
|
# 循环获取视频链接
|
||
|
|
for page in range(1, 8):
|
||
|
|
video_links = extract_video_links(fetch_html(f"https://search.bilibili.com/video?keyword=%E5%B7%B4%E9%BB%8E%E5%A5%A5%E8%BF%90%E4%BC%9A&from_source=webtop_search&spm_id_from=333.1007&search_source=2&page={page}"))
|
||
|
|
for video_link in video_links:
|
||
|
|
danmaku_api_links.extend(get_danmaku_api_links(video_link))
|
||
|
|
|
||
|
|
# 获取弹幕数据并筛选AI相关的弹幕
|
||
|
|
for danmaku_api in danmaku_api_links:
|
||
|
|
html_data = fetch_html(danmaku_api)
|
||
|
|
soup = BeautifulSoup(html_data, 'html.parser')
|
||
|
|
content_list = [danmaku['content'] for danmaku in soup.find_all('d')]
|
||
|
|
for content in content_list:
|
||
|
|
if check_ai_content(content):
|
||
|
|
ai_comments.append(content)
|
||
|
|
|
||
|
|
# 输出AI相关的弹幕数量
|
||
|
|
print(f"AI相关的弹幕数量: {len(ai_comments)}")
|
||
|
|
|
||
|
|
# 将数据转换为DataFrame
|
||
|
|
df = pd.DataFrame(ai_comments, columns=['弹幕'])
|
||
|
|
# 写入Excel文件
|
||
|
|
df.to_excel('ai_comments.xlsx', index=False)
|
||
|
|
|
||
|
|
# 绘制词云图
|
||
|
|
ai_str = ' '.join(ai_comments)
|
||
|
|
wc = WordCloud(width=500, height=500, background_color='white', font_path='msyh.ttc')
|
||
|
|
wc.generate(ai_str)
|
||
|
|
wc.to_file('ai_wordcloud.png')
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
main()
|