Sheyiyuan/SAM-bilibili
2
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add:comments

Browse Source
This commit is contained in:
Sheyiyuan 2025-03-24 07:35:33 +08:00
parent a040da8242
commit af9887a0a6
1 changed files with 28 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

51
main.py
View File

@ -206,24 +206,24 @@ class BiliWebCrawler:
print(f"解析UP主数据失败: {str(e)}") print(f"解析UP主数据失败: {str(e)}")
send_notification(f"解析UP主数据失败: {str(e)}") send_notification(f"解析UP主数据失败: {str(e)}")
return None return None
try: # try:
# 获取投稿列表 # # 获取投稿列表
archive_url = f'https://api.bilibili.com/x/space/arc/search?mid={mid}&ps=30' # archive_url = f'https://api.bilibili.com/x/space/arc/search?mid={mid}&ps=30'
sleep(5) # sleep(1)
archive_resp = self._safe_request(archive_url) # archive_resp = self._safe_request(archive_url)
if archive_resp and archive_resp.status_code == 200: # if archive_resp and archive_resp.status_code == 200:
archive_data = archive_resp.json() # archive_data = archive_resp.json()
# print(archive_data) # # print(archive_data)
videos = archive_data.get('data', {}).get('list', {}).get('vlist', []) # videos = archive_data.get('data', {}).get('list', {}).get('vlist', [])
#
# 计算30天前的时间戳 # # 计算30天前的时间戳
month_ago = time.time() - 30 * 86400 # month_ago = time.time() - 30 * 86400
# 统计符合时间条件的视频 # # 统计符合时间条件的视频
recent_count = sum(1 for v in videos if v.get('created') > month_ago) # recent_count = sum(1 for v in videos if v.get('created') > month_ago)
up_info['近一个月投稿数'] = recent_count # up_info['近一个月投稿数'] = recent_count
except Exception as e: # except Exception as e:
print(f"获取投稿数据失败: {str(e)}") # print(f"获取投稿数据失败: {str(e)}")
send_notification(f"获取投稿数据失败: {str(e)}") # send_notification(f"获取投稿数据失败: {str(e)}")
return up_info return up_info
@ -300,7 +300,7 @@ class BiliWebCrawler:
print(f"请求出错: {e}") print(f"请求出错: {e}")
break break
# 适当调整请求间隔 # 适当调整请求间隔
sleep(5) sleep(1)
return comments return comments
# 移除 fetch_comment_replies 方法（原方法不再需要） # 移除 fetch_comment_replies 方法（原方法不再需要）
@ -343,7 +343,7 @@ class BiliWebCrawler:
video_info_filename = os.path.join(video_dir, f'{self.bvid}_{play_count}_info.csv') video_info_filename = os.path.join(video_dir, f'{self.bvid}_{play_count}_info.csv')
self.save_to_csv([video_info], video_info_filename) self.save_to_csv([video_info], video_info_filename)
sleep(5) sleep(1)
# 新增弹幕抓取 # 新增弹幕抓取
print("正在抓取弹幕数据...") print("正在抓取弹幕数据...")
@ -351,7 +351,7 @@ class BiliWebCrawler:
danmaku_filename = os.path.join(video_dir, f'{self.bvid}_{len(danmaku)}_danmaku.csv') danmaku_filename = os.path.join(video_dir, f'{self.bvid}_{len(danmaku)}_danmaku.csv')
self.save_to_csv(danmaku, danmaku_filename) self.save_to_csv(danmaku, danmaku_filename)
sleep(5) sleep(1)
# 新增评论抓取 # 新增评论抓取
print("正在抓取评论数据...") print("正在抓取评论数据...")
@ -359,7 +359,7 @@ class BiliWebCrawler:
comments_filename = os.path.join(video_dir, f'{self.bvid}_{len(comments)}_comments.csv') comments_filename = os.path.join(video_dir, f'{self.bvid}_{len(comments)}_comments.csv')
self.save_to_csv(comments, comments_filename) self.save_to_csv(comments, comments_filename)
sleep(5) sleep(1)
# 新增UP主信息记录 # 新增UP主信息记录
print("正在获取UP主信息...") print("正在获取UP主信息...")
@ -382,8 +382,13 @@ if __name__ == "__main__":
send_notification("未找到有效的BV号，程序退出") send_notification("未找到有效的BV号，程序退出")
exit() exit()
send_info_log(f"开始批量处理 {len(targets)} 个视频") send_info_log(f"开始批量处理 {len(targets)} 个视频")
i=0
for bvid in targets: for bvid in targets:
print(f"\n{'=' * 30} 开始处理 {bvid} {'=' * 30}") print(f"\n{'=' * 30} 开始处理 {bvid} {'=' * 30}")
crawler = BiliWebCrawler(f"https://www.bilibili.com/video/{bvid}",cookie) crawler = BiliWebCrawler(f"https://www.bilibili.com/video/{bvid}",cookie)
crawler.run() crawler.run()
sleep(5) i=i+1
if i%20==0:
send_info_log(f"已完成 {i} 个视频,进度:{i/len(targets)*100:.2f}%")
sleep(1)
send_info_log(f"批量处理完成！")