main
QMZ 2 months ago
parent 42a10ae8a9
commit 5a030c6d89

@ -1,6 +1,8 @@
import requests import requests
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
import re import re
import time
import random
import jieba # 结巴分词 pip install jieba import jieba # 结巴分词 pip install jieba
import wordcloud # 词云图 pip install wordcloud import wordcloud # 词云图 pip install wordcloud
import imageio # 读取本地图片 修改词云图形 import imageio # 读取本地图片 修改词云图形
@ -58,6 +60,10 @@ def get_danmu(id):
txtsss=[txts.replace(' ','') for txts in txtss] #将字符串中的空格消除掉 txtsss=[txts.replace(' ','') for txts in txtss] #将字符串中的空格消除掉
return(txtsss) ###打印便可看见一条条弹幕的属性和内容了。 return(txtsss) ###打印便可看见一条条弹幕的属性和内容了。
def page(url,num):
num=num+1
url=f'https://search.bilibili.com/video?keyword=2024巴黎奥运会&page={num}'
return url
# 主函数 # 主函数
def main(search_url): def main(search_url):
@ -75,12 +81,17 @@ def main(search_url):
return(cids) return(cids)
# 示例搜索页 URL需要替换为实际的搜索页 URL # 示例搜索页 URL需要替换为实际的搜索页 URL
search_url = 'https://search.bilibili.com/all?keyword=2024巴黎奥运会' search_url = 'https://search.bilibili.com/video?keyword=2024巴黎奥运会'
aa = main(search_url)
alltxt=[] alltxt=[]
for id in aa:
txt = get_danmu(id) for i in range(10):
alltxt=alltxt + txt
aa = main(page(search_url,i))
for id in aa:
txt = get_danmu(id)
alltxt=alltxt + txt
time.sleep(random.randint(0,3)+random.random())
danmustr=''.join(i for i in alltxt) #将所有弹幕拼接在一起 danmustr=''.join(i for i in alltxt) #将所有弹幕拼接在一起
words=list(jieba.cut(danmustr)) ###利用jieba库将弹幕按词进行切分 words=list(jieba.cut(danmustr)) ###利用jieba库将弹幕按词进行切分
words=[i for i in words if len(i)>1] ###挑出长度大于1的词语为去除诸如啊等字符 words=[i for i in words if len(i)>1] ###挑出长度大于1的词语为去除诸如啊等字符

Loading…
Cancel
Save