README.md

@@ -1,3 +0,0 @@
-# ai2
-
-代码在master分支里

code_test.py

@@ -0,0 +1,119 @@
+import time
+import requests
+import xml.etree.ElementTree as ET
+import re
+import wordcloud
+import pandas as pd
+from collections import Counter
+from concurrent.futures import ThreadPoolExecutor, as_completed
+
+#获取视频bv号
+def get_bvid(headers):
+    bv_list = []          #目的bv列表
+    url = 'https://search.bilibili.com/video?vt=83711075&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=3'
+    for page in range(1, 11):
+        page = str(page)
+        param ={
+            'spm_id_from': '333.1007',
+            'search_source': '3',
+            'page': page,
+            'o': ''
+        }
+
+        bi_text = requests.get(url=url,headers=headers,params=param).text
+        # 正则选出bv号
+        r = re.findall('<div.*?<a href="//www.bilibili.com/video/(.*?)/".*?</div></a>',bi_text)
+        r_list = list(set(r))
+        for index in r_list:
+            bv_list.append(index)
+        time.sleep(1)
+    bv_list = list(set(bv_list))
+    return bv_list
+
+# 获取视频的 cid
+def get_cid(bv_id, headers):
+    url = f"https://api.bilibili.com/x/web-interface/view?bvid={bv_id}"
+    response = requests.get(url,headers=headers)
+    data = response.json()
+    return data['data']['cid']
+
+# 获取弹幕 XML
+def get_danmu(cid, headers):
+    url = f"https://comment.bilibili.com/{cid}.xml"
+    response = requests.get(url, headers=headers)
+    if response.status_code == 200:
+        return response.content
+    else:
+        print(f"弹幕请求失败，状态码: {response.status_code}")
+        return None
+
+# 解析 XML 并返回弹幕内容
+def parse_danmu(xml_content):
+    root = ET.fromstring(xml_content)
+    danmu_list = [d.text for d in root.findall('d')]
+    pattern = re.compile(r'([^a-z?]AI[^a-z?])',re.I)
+    danmu_ai_list = [ai for ai in danmu_list if pattern.search(ai)]
+    return danmu_ai_list
+# 多线程处理弹幕爬取
+def fetch_danmu(bv_id, headers):
+    cid = get_cid(bv_id, headers)
+    if cid:
+        xml_content = get_danmu(cid,headers)
+        if xml_content:
+            return parse_danmu(xml_content)
+    return []
+
+
+# 多线程爬取多个视频的弹幕
+def fetch_all_danmus(bv_list, headers):
+    all_danmu = []
+
+    # 使用多线程池
+    with ThreadPoolExecutor(max_workers=5) as executor:
+        future_to_bv_id = {executor.submit(fetch_danmu, bv_id,headers): bv_id for bv_id in bv_list}
+
+        for future in as_completed(future_to_bv_id):
+            bv_id = future_to_bv_id[future]
+            try:
+                danmus = future.result()
+                if danmus:
+                    all_danmu.extend(danmus)
+            except Exception as exc:
+                print(f"{bv_id} 弹幕爬取时发生异常: {exc}")
+
+    return all_danmu
+
+#统计弹幕数量 导出为excel表格 并输出数量前8名的弹幕
+def top_danmu(danmu_list):
+    counter = Counter(danmu_list)
+    #导出Excel
+    df = pd.DataFrame(list(counter.items()), columns=['Danmu', 'Count'])
+    df.to_excel('danmu_ai_count.xlsx',index=False)
+    #输出前8名
+    top_danmus = counter.most_common(8)
+    for danmu, count in top_danmus:
+        print(f"{danmu}: {count}")
+
+#根据弹幕输出词云图
+def wordcloud_danmu(danmu_list):
+    danmu_string = ''.join(danmu_list)
+    wc = wordcloud.WordCloud(
+        height=300,
+        width=500,
+        background_color='white',
+        font_path='msyh.ttc',
+        scale=15
+    )
+    wc.generate(danmu_string)
+    wc.to_file('1.png')
+
+#主函数
+headers = {
+        'Cookie': 'buvid_fp=bf8beba45de9821b7ea7e50612d09908; LIVE_BUVID=AUTO4116559027162689; CURRENT_FNVAL=4048; buvid3=973F36A7-32C2-B0E4-8ACE-5E0B758E2FF782902infoc; b_nut=1701966882; _uuid=CC9ED47C-31078-19D2-10595-CD6B1057A2631005192infoc; buvid4=CE632AC2-E7EE-2F09-30E0-9BF3F5C2D40878774-024042908-KwURbcfX8EBz810RKJAgEw%3D%3D; rpdid=|(u))kkYu|)m0J\'u~uRJ~)J~m; header_theme_version=CLOSE; enable_web_push=DISABLE; bili_ticket=eyJhbGciOiJIUzI1NiIsImtpZCI6InMwMyIsInR5cCI6IkpXVCJ9.eyJleHAiOjE3MjY3NjQ0NTksImlhdCI6MTcyNjUwNTE5OSwicGx0IjotMX0.hMTE7drIcEEwzsI8zYxYXI1o7zzeK2ggwuLaW7EbN2M; bili_ticket_expires=1726764399; bp_t_offset_593983186=978039902421647360; SESSDATA=1a5c072c%2C1742137341%2C9ab0d%2A92CjC2gzBMHSu21uOWgbHRFRswIo1CHBMpBvihPj-9d6qWyU-A5dWmJF_QPAEJPwyIBJ0SVm13Uzk1bENFZGR2bk9nR3ZtaDNmQXJTeE8xVDR5RFZoRkIxS3NmYU9kc01Sb0VKZ0hnMTRjbEhLVHQ3REdqdDVYNm5LLWhYOGp1RE42QjhPS1Ntb3B3IIEC; bili_jct=369030ec2cf370e475f8d79829b8f725; DedeUserID=593983186; DedeUserID__ckMd5=48e87375187f5f74; sid=8vio5fpf; b_lsid=7102AB72D_1920545EF21; bsource=search_bing; bmg_af_switch=1; bmg_src_def_domain=i1.hdslb.com; home_feed_column=4; browser_resolution=659-994',
+        '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'
+    }
+bv_list = get_bvid(headers)
+all_danmu = fetch_all_danmus(bv_list,headers)
+if all_danmu:
+    top_danmu(all_danmu)
+    wordcloud_danmu(all_danmu)

requirements.txt

@@ -0,0 +1,3 @@
+pandas==2.2.2
+Requests==2.32.3
+wordcloud==1.9.3