|
|
import requests
|
|
|
import re
|
|
|
#一、首先定义获取弹幕huqudanmu函数
|
|
|
def huoqudanmu(cid):
|
|
|
url=f'https://api.bilibili.com/x/v1/dm/list.so?oid={cid}'#通过cid值获取对应视频的弹幕
|
|
|
Hddf = {
|
|
|
"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"
|
|
|
}
|
|
|
resp= requests.get(url,headers=Hddf)#从网址获取弹幕
|
|
|
resp.encoding="utf-8"#弹幕中文编码
|
|
|
Data=resp.text#提取text文本
|
|
|
context=re.findall('<d p=.*?>(.*?)</d>',Data)#提取弹幕文本
|
|
|
print(context)
|
|
|
for index in context:
|
|
|
with open('总弹幕.txt',mode='a',encoding='utf-8')as f:
|
|
|
f.write(index)#写入text文件
|
|
|
f.write('\n')
|
|
|
|
|
|
#二、获取所需弹幕地址
|
|
|
headers0={
|
|
|
"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"
|
|
|
}#请求头
|
|
|
for page0 in range(1,11):#从搜索的十页获取网址，一页30个视频
|
|
|
if page0==1 :
|
|
|
url="https://search.bilibili.com/all?vt=93020172&keyword=2024%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=5"
|
|
|
else:
|
|
|
url=f"https://search.bilibili.com/all?vt=93020172&keyword=2024%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=5&page={page0}"
|
|
|
res0=requests.get(url,headers=headers0)#获取网页数据
|
|
|
Text0=res0.text
|
|
|
bvid=re.findall('bvid:"(.*?)",title:',Text0)#获取视频bvid号
|
|
|
for bvid1 in bvid:#
|
|
|
url=f"https://www.bilibili.com/video/{bvid1.strip()}/?spm_id_from=333.337.search-card.all.click&vd_source=516714ff716c382225c801afa2c87d8d"
|
|
|
res0=requests.get(url,headers=headers0)#获取视频数据
|
|
|
Text0=res0.text
|
|
|
oid=re.findall('"embedPlayer":{"p":.*?,"aid":.*?,"bvid":".*?","cid":(.*?),',Text0)#获取oid值(多余空格去除，不然匹配不到)
|
|
|
for oid1 in oid:#提取oid值
|
|
|
huoqudanmu(oid1)#调用获取弹幕的函数
|
|
|
|
|
|
#三、生成词云图
|
|
|
import jieba
|
|
|
import wordcloud
|
|
|
import imageio
|
|
|
#1.读取弹幕数据
|
|
|
f =open("总弹幕.txt",encoding='utf-8')
|
|
|
text =f.read()
|
|
|
#2.分词
|
|
|
text_list=jieba.lcut(text)
|
|
|
text_str=' '.join(text_list)
|
|
|
#3.词云图
|
|
|
f2=open("中文常见停用词.text",encoding='utf-8')
|
|
|
text2=f2.read().splitlines()#读取弹幕
|
|
|
img= imageio.v2.imread('地球.png')#导入词云形状的图片
|
|
|
wc=wordcloud.WordCloud(#设置词云格式
|
|
|
width=1160,#宽
|
|
|
height=800,#高
|
|
|
background_color='white',#背景颜色
|
|
|
mask=img,#云图样式
|
|
|
stopwords=text2,#禁用词
|
|
|
font_path='msyh.ttc'#字体
|
|
|
)
|
|
|
wc.generate(text_str)
|
|
|
wc.to_file('词云图.png')
|
