From 4006830f05eebe67aa4fd07e48ca82ebd3a2f7fa Mon Sep 17 00:00:00 2001
From: posql3f6g <2974352416@qq.com>
Date: Tue, 25 Apr 2023 16:48:47 +0800
Subject: [PATCH] =?UTF-8?q?=E7=94=A8=E8=AF=8D=E4=BA=91=E7=9A=84=E6=96=B9?=
 =?UTF-8?q?=E6=B3=95=E5=81=9A=E5=8F=AF=E8=A7=86=E5=8C=96=E5=A4=84=E7=90=86?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 爬取弹幕并做词云可视化处理.py | 41 ++++++++++++++++++++++
 1 file changed, 41 insertions(+)
 create mode 100644 爬取弹幕并做词云可视化处理.py

diff --git a/爬取弹幕并做词云可视化处理.py b/爬取弹幕并做词云可视化处理.py
new file mode 100644
index 0000000..c096cdf
--- /dev/null
+++ b/爬取弹幕并做词云可视化处理.py
@@ -0,0 +1,41 @@
+import urllib.request
+from lxml import etree
+import requests
+import re
+
+url='https://www.ibilibili.com/video/BV1o24y1F7wV/?spm_id_from=333.999.0.0&vd_source=59fecc30e7f4791084968599ca1f8b82'
+
+headers={
+    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36'
+}
+
+request=urllib.request.Request(url=url,headers=headers)
+response=urllib.request.urlopen(request)
+content=response.read().decode('utf-8')
+tree=etree.HTML(content)
+danmuurl=tree.xpath('//div[@class="btn-group"]/a[3]/@href')
+
+response2 = requests.get(url=danmuurl[0], headers=headers)
+response2.encoding = 'utf-8'
+content_list = re.findall('<d p=".*?">(.*?)</d>', response2.text)
+
+for content in content_list:
+    with open('弹幕.txt',mode='a',encoding='utf-8')  as f:
+        f.write(content)
+        f.write('\n')
+
+import jieba
+from wordcloud import WordCloud
+fp=open('弹幕.txt',mode='r',encoding='UTF-8')
+txt=fp.read()
+words=jieba.lcut(txt)
+new_txt=" ".join(words)
+wordcloud=WordCloud(font_path='simkai.ttf',\
+                    background_color='white',\
+                    height=400,\
+                    width=600,\
+                    max_font_size=100,\
+                    max_words=200
+                    ).generate(new_txt)
+wordcloud.to_file('弹幕词云.jpg')
+