用词云的方法做可视化处理

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')
+