测试文件

test/cloud.py

@@ -0,0 +1,20 @@
+import requests
+from bs4 import BeautifulSoup
+import re
+import time
+import jieba  
+import wordcloud  
+import matplotlib.pyplot as plt
+import pandas as pd  
+from pandas import ExcelWriter
+from collections import Counter
+
+def chuli(etxt):
+    #danmustr=''.join(i for i in etxt) #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=[i for i in etxt if len(i)>1] ###挑出长度大于1的词语（为去除诸如？，哈，啊等字符）
+    wc=wordcloud.WordCloud(background_color='white',height=1000,width=1000,font_path='simsun.ttc')#利用wordcloud库定义词云图片的信息
+    wc.generate(' '.join(words))   ##生成图片
+    print(wc)
+    plt.imshow(wc)
+    plt.show()

test/getcidfrombv.py

@@ -0,0 +1,60 @@
+import requests
+from bs4 import BeautifulSoup
+import re
+
+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'   }
+# 获取搜索结果页面的内容
+def get_search_page(search_url):
+    response = requests.get(search_url, headers=headers)
+    response.raise_for_status()  # 确保请求成功
+    return response.text
+
+# 提取页面中所有视频的链接
+def extract_video_links(page_content):
+    soup = BeautifulSoup(page_content, 'html.parser')
+    video_links = []
+    for a_tag in soup.select(".video-list.row div.bili-video-card > div > a"):
+        link = a_tag.get('href')
+        video_links.append(link)
+        
+    return video_links
+# 提取视频的BV号
+def extract__BV(video_url):
+    video_id_match = re.search(r'/video/([^/]+)', video_url)
+    if video_id_match:
+        return video_id_match.group(1)
+    return None
+    
+def get_cid_from_bv(bv_ids):
+    cids=[]
+    for bv_id in bv_ids:
+        # 视频详情 API 地址
+        video_url = f'https://api.bilibili.com/x/web-interface/view?bvid={bv_id}'
+
+        # 发送请求
+        response = requests.get(video_url, headers=headers)
+        response.raise_for_status()
+        data = response.json()
+        # 提取 cid
+        if data.get('code') == 0:
+            cid = data.get('data', {}).get('cid')
+            cids.append(cid)
+    return cids
+
+# 主函数
+def main(search_url):
+    page_content = get_search_page(search_url)
+    video_links = extract_video_links(page_content)
+    bvs = []
+    for link in video_links:
+        bv = extract__BV(link)
+        if bv:
+            bvs.append(bv)
+    cids = []
+    cids = get_cid_from_bv(bvs)
+    return cids
+search_url = 'https://search.bilibili.com/all?keyword=2024巴黎奥运会'
+aa = main(search_url)
+print(aa)
+
+

test/handle.py

@@ -0,0 +1,32 @@
+import requests
+from bs4 import BeautifulSoup
+import re
+import time
+import jieba  
+import wordcloud  
+import matplotlib.pyplot as plt
+import pandas as pd  
+from pandas import ExcelWriter
+from collections import Counter
+headers = {
+    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36 Edg/127.0.0.0',
+   
+}
+keywords = [
+    'AI', '人工智能', '机器学习', '深度学习', '神经网络', '自动化', 
+    '算法', '数据科学' '自然语言处理', '计算机视觉',  '人工智能技术', 'AI技术', 'AI应用', 'AI模型', 
+    '大数据', '预测分析', '机器视觉', '自动驾驶',
+     '智能推荐', '计算机科学', '人工智能应用',
+    '数据分析','智能化', '情感计算','ai'
+]
+
+
+def sort(txt, keywords):
+    
+    comment_counter = Counter()
+    for line in txt:
+        line.strip()
+        if any(word in keywords for word in jieba.cut(line)):
+            comment_counter[line] += 1
+    
+    return comment_counter

test/test_getcid.py

@@ -0,0 +1,51 @@
+import requests
+from bs4 import BeautifulSoup
+import re
+import getcidfrombv as cid
+import unittest
+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'   }
+
+
+class TestFunctions(unittest.TestCase):
+
+    def setUp(self):
+        # 在每个测试之前运行
+        self.content_list = [
+        'www.bilibili.com/video/BV1mE4m1R71o',
+        'www.bilibili.com/video/BV1wH4y1F7KD',
+        'www.bilibili.com/video/BV1M142187NQ',
+        'www.bilibili.com/video/BV1im42137XE',
+        'www.bilibili.com/video/BV1wS421d7Mj',
+        'www.bilibili.com/video/BV1FE4m1d7tS',
+        'www.bilibili.com/video/BV1PU411S7HC',
+        'www.bilibili.com/video/BV1fx4y1x7eW',
+        'www.bilibili.com/video/BV1rw4m1r7nF',
+        'www.bilibili.com/video/BV19E4m1R7Kf'
+    ]
+
+    def test_getcid(self):
+        # 测试 sort 函数
+        expected_output = [
+        1646607366,
+        1663877514,
+        1648215637,
+        1627769596,
+        1628417603,
+        1640306641,
+        1627951394,
+        1650192254,
+        1649785565,
+        1629439509
+    ]
+        actual_output=[]
+        bvs = []
+        for link in self.content_list:
+            bv = cid.extract__BV(link)
+            bvs.append(bv)
+        actual_output = cid.get_cid_from_bv(bvs)
+        self.assertEqual(expected_output, actual_output)
+
+
+if __name__ == '__main__':
+    unittest.main()
+

test/test_sort.py

@@ -0,0 +1,50 @@
+import unittest
+from io import StringIO
+from unittest.mock import patch
+import jieba
+import wordcloud
+import matplotlib.pyplot as plt
+from collections import Counter
+import handle
+
+# 单元测试类
+class TestFunctions(unittest.TestCase):
+
+    def setUp(self):
+        # 在每个测试之前运行
+        self.keywords = [
+            'AI', '人工智能', '机器学习', '深度学习', '神经网络', '自动',
+            '算法', '数据科学', '自然语言', '计算机', '人工智能技术',
+            '大数据', '预测分析', '机器视觉', 
+            '智能', '计算机', '人工智能应用',
+            '数据分析', '情感计算', 'ai'
+        ]
+        self.sample_comments = [
+            '人工智能是未来的趋势。',
+            '机器学习算法在自动化中扮演了重要角色。',
+            '深度学习和神经网络的结合使得AI技术更加强大。',
+            '我喜欢学习计算机视觉和数据科学。',
+            '自动驾驶技术还需要进一步发展。',
+            '智能推荐系统可以大大提升用户体验。',
+            '情感计算是自然语言处理的一个重要方向。',
+            '这只是一些无关的评论。'
+            ''
+        ]
+
+    def test_sort(self):
+        # 测试 sort 函数
+        expected_output = Counter({
+            '人工智能是未来的趋势。': 1,
+            '机器学习算法在自动化中扮演了重要角色。': 1,
+            '深度学习和神经网络的结合使得AI技术更加强大。': 1,
+            '我喜欢学习计算机视觉和数据科学。': 1,
+            '自动驾驶技术还需要进一步发展。': 1,
+            '智能推荐系统可以大大提升用户体验。': 1,
+            '情感计算是自然语言处理的一个重要方向。': 1
+        })
+        actual_output = handle.sort(self.sample_comments, self.keywords)
+        self.assertEqual(expected_output, actual_output)
+
+
+if __name__ == '__main__':
+    unittest.main()

test/testwordcloud.py

@@ -0,0 +1,39 @@
+import unittest
+from unittest.mock import patch, MagicMock
+from cloud import chuli  # 替换为实际模块名
+
+class TestChuliFunction(unittest.TestCase):
+
+    @patch('wordcloud.WordCloud')
+    @patch('matplotlib.pyplot.imshow')
+    @patch('matplotlib.pyplot.show')
+    def test_chuli(self, mock_plt_show, mock_plt_imshow, MockWordCloud):
+        # 创建一个模拟的 WordCloud 对象
+        mock_wc = MockWordCloud.return_value
+        mock_wc.generate.return_value = None
+        
+        # 输入测试数据
+        test_input = ['测试', '词云', '功能', '正常']
+        
+        # 调用 chuli 函数
+        chuli(test_input)
+        
+        # 验证 WordCloud 的构造函数是否被正确调用
+        MockWordCloud.assert_called_once_with(
+            background_color='white',
+            height=1000,
+            width=1000,
+            font_path='simsun.ttc'
+        )
+        
+        # 验证 WordCloud 的 generate 方法是否被正确调用
+        mock_wc.generate.assert_called_once_with('测试 词云 功能 正常')
+        
+        # 验证 plt.imshow 是否被调用
+        mock_plt_imshow.assert_called_once_with(mock_wc)
+        
+        # 验证 plt.show 是否被调用
+        mock_plt_show.assert_called_once()
+
+if __name__ == '__main__':
+    unittest.main()