diff --git a/test3.py b/test3.py new file mode 100644 index 0000000..ed8215f --- /dev/null +++ b/test3.py @@ -0,0 +1,139 @@ +import requests +import time +from bs4 import BeautifulSoup + +# 固定的 User-Agent +custom_user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36' + +# 固定的 Cookie +custom_cookie = 'SESSDATA=f088e027%2C1742009093%2C2981a%2A91CjAZOWy34Bnk2yutAp0iAkrT9_GnVSnWjaJxjZh5xNycojooqqb3GBAqWEkeXTkUQLQSVk5rcWNaekt5VjNUVkJYV2VtaWo4NHlvc2NPQUFabTRhY2RBUkg5U1B4d3RoMmQ4eXQzN1R3Y1BXc0dBelJEenk4WTgyQjFJRlhmcFZZel94aThkQXVRIIEC; bili_jct=b51d3572b16a74e3ffc7a59f8a252e91; DedeUserID=3494376802093902;' + +# 1. 搜索视频,按照综合排序 +def get_search_results(keyword, page): + search_url = "https://api.bilibili.com/x/web-interface/search/type" + params = { + "keyword": keyword, + "page": page, + "search_type": "video", + "order": "totalrank" # 添加综合排序参数 + } + + headers = { + 'User-Agent': custom_user_agent, + 'Accept': 'application/json, text/javascript, */*; q=0.01', + 'Referer': 'https://www.bilibili.com/', + 'Cookie': custom_cookie + } + + try: + response = requests.get(search_url, headers=headers, params=params) + response.raise_for_status() # 检查 HTTP 状态码 + + result = response.json() + if 'data' in result and 'result' in result['data']: + return result['data']['result'] + else: + print(f"第 {page} 页的搜索结果未找到") + return [] + except requests.exceptions.HTTPError as http_err: + print(f"HTTP 错误: {http_err}") + return [] + except requests.exceptions.RequestException as e: + print(f"请求失败: {e}") + return [] + +# 2. 获取视频的 CID (使用 bvid) +def get_cid(bvid): + url = f"https://api.bilibili.com/x/player/pagelist?bvid={bvid}" + headers = { + 'User-Agent': custom_user_agent, + 'Referer': f"https://www.bilibili.com/video/{bvid}", + 'Cookie': custom_cookie + } + + try: + response = requests.get(url, headers=headers) + response.raise_for_status() + data = response.json() + if 'data' in data and len(data['data']) > 0: + return data['data'][0]['cid'] # 获取第一个页面的CID + else: + print(f"视频 {bvid} 的 CID 获取失败") + return None + except Exception as e: + print(f"获取 CID 失败: {e}") + return None + +# 3. 获取弹幕 +def get_danmaku(cid, bvid): + danmaku_url = f"https://comment.bilibili.com/{cid}.xml" + headers = { + 'User-Agent': custom_user_agent, + 'Referer': f"https://www.bilibili.com/video/{bvid}", + 'Cookie': custom_cookie + } + + try: + response = requests.get(danmaku_url, headers=headers) + response.raise_for_status() + soup = BeautifulSoup(response.content, 'lxml') + danmakus = [d.text for d in soup.find_all('d')] # 提取每条弹幕的内容 + return danmakus + except Exception as e: + print(f"获取弹幕失败: {e}") + return [] + +# 4. 主逻辑 +def main(): + keyword = "2024巴黎奥运会" + videos = [] + + # 获取前300个视频 + for page in range(1, 16): # 每页有20个视频,15页大概可以获取到300个 + results = get_search_results(keyword, page) + + if results: + videos.extend(results) + print(f"第 {page} 页获取到 {len(results)} 个视频") + else: + print(f"第 {page} 页的搜索结果未找到或请求失败") + + if len(videos) >= 300: + break + + time.sleep(1) # 每页请求间隔1秒,防止爬取过快 + + print(f"共找到 {len(videos)} 个视频") + + if not videos: + print("未找到任何视频,停止爬取") + return + + # 获取每个视频的弹幕 + all_danmakus = [] + for i, video in enumerate(videos[:300]): # 只处理前300个视频 + bvid = video['bvid'] # 使用 bvid 而不是 aid + title = video['title'] + try: + cid = get_cid(bvid) + if cid: + danmakus = get_danmaku(cid, bvid) + print(f"获取视频 {i+1}/{len(videos)} 的弹幕: {title}, 弹幕数: {len(danmakus)}") + all_danmakus.extend(danmakus) + else: + print(f"视频 {title} 的 CID 获取失败") + except Exception as e: + print(f"视频 {title} 的弹幕获取失败: {e}") + + time.sleep(2) # 每次请求间隔2秒,避免请求过快 + + # 保存弹幕数据到本地文件 + with open("danmakus_2024_olympics.txt", "w", encoding='utf-8') as f: + for danmaku in all_danmakus: + f.write(danmaku + "\n") + + print(f"所有弹幕已保存至 danmakus_2024_olympics.txt") + +# 运行主程序 +if __name__ == "__main__": + main()