crontab_back.txt 8.1 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151
  1. 0 3 * * * curl -X POST http://192.168.100.31:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "crawler_gzh_articles", "account_method": "1030-手动挑号", "crawl_mode": "account", "strategy": "V1"}'
  2. 0 4 * * * curl -X POST http://192.168.100.31:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "crawler_gzh_articles", "account_method": "cooperate_account", "crawl_mode": "account", "strategy": "V1"}'
  3. # 定时清理文件
  4. 0 1 * * * find /root/luojunhui/LongArticlesJob/static -type f -name "*.mp4" -mtime +5 -delete
  5. # 每天 9 点, 18 点执行 gzh 视频抓取
  6. 0 9,18 * * * bash /root/luojunhui/LongArticlesJob/sh/run_gzh_video_crawler.sh
  7. * * * * * bash /root/luojunhui/LongArticlesJob/sh/run_long_articles_job.sh
  8. # 外部服务号监测
  9. # 0 13 * * * curl -X POST http://127.0.0.1:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "outside_article_monitor"}'
  10. # 每天凌晨 4点,下午 4 点各执行一次头条视频抓取
  11. 0 4,16 * * * bash /root/luojunhui/LongArticlesJob/sh/run_toutiao_account_video_crawler.sh
  12. # 更新服务号数据
  13. 0 11,17 * * * bash /root/luojunhui/LongArticlesJob/sh/run_fwh_data_manager.sh
  14. # 每15分钟执行一次今日头条推荐流抓取
  15. */15 * * * * bash /root/luojunhui/LongArticlesJob/sh/run_toutiao_recommend.sh
  16. # 每10分钟执行一次从aigc系统获取发布文章
  17. */10 * * * * bash /root/luojunhui/LongArticlesJob/sh/run_update_article_info_from_aigc.sh
  18. # 每10分钟执行一次标题相似度计算任务
  19. */10 * * * * bash /root/luojunhui/LongArticlesJob/sh/run_title_similarity_task.sh
  20. # 每小时执行一次标题改写
  21. 0 * * * * bash /root/luojunhui/LongArticlesJob/sh/run_title_process_task.sh
  22. # 凌晨2点30执行更新小程序信息任务
  23. 30 2 * * * bash /root/luojunhui/LongArticlesJob/sh/run_update_minigram_info_daily.sh
  24. # 凌晨3:00,下午3:00执行视频号抓取任务
  25. 0 3,15 * * * bash /root/luojunhui/LongArticlesJob/sh/run_sph_video_crawler.sh
  26. # 每天上午10点30执行文章退场 && 晋升任务
  27. 30 10 * * * bash /root/luojunhui/LongArticlesJob/sh/run_article_title_exit_v1.sh
  28. # 每天上午4点执行账号冷启动任务
  29. # 0 1 * * * bash /root/luojunhui/LongArticlesJob/sh/run_account_cold_start_daily.sh
  30. # 晚上6点执行头条文章冷启动
  31. 0 18 * * * curl -X POST http://127.0.0.1:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "article_pool_cold_start", "platform": "toutiao", "crawler_methods": ["toutiao_account_association"]}'
  32. # 17:50执行公众号文章战冷启动
  33. 30 17 * * * curl -X POST http://127.0.0.1:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "article_pool_cold_start", "strategy": "strategy_v3"}'
  34. 0 4 * * * curl -X POST http://127.0.0.1:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "article_pool_cold_start", "strategy": "strategy_v1"}'
  35. # 早上执行sohu 抓取
  36. 0 6 * * * bash /root/luojunhui/LongArticlesJob/sh/run_schedule_app.sh
  37. 0 2 * * * curl -X POST http://127.0.0.1:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "crawler_toutiao"}'
  38. #
  39. 0 14 * * * bash /root/luojunhui/LongArticlesJob/sh/run_cold_start_publish.sh
  40. # 每日上午9点执行账号联想任务
  41. 0 9 * * * bash /root/luojunhui/LongArticlesJob/sh/run_account_association.sh
  42. # 每天 10 点执行前一天的阅读率均值代码
  43. # 0 10 * * * bash /root/luojunhui/LongArticlesJob/sh/run_update_account_read_rate_avg.sh
  44. # 每天10点40执行阅读均值任务
  45. # 40 10 * * * bash /root/luojunhui/LongArticlesJob/sh/run_update_account_avg_v3.sh
  46. # 执行阅读率均值
  47. 0 10 * * * curl -X POST http://192.168.142.66:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "update_account_read_rate_avg"}'
  48. # 执行阅读均值
  49. 40 10 * * * curl -X POST http://192.168.142.66:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "update_account_read_avg"}'
  50. # 执行打开率均值
  51. 50 10 * * * curl -X POST http://192.168.142.66:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "update_account_open_rate_avg"}'
  52. # 每天11点执行文章联想任务
  53. 0 11 * * * bash /root/luojunhui/LongArticlesJob/sh/run_article_association.sh
  54. # 每小时执行一次校验视频状态
  55. # 20 * * * * bash /root/luojunhui/LongArticlesJob/sh/run_check_video_status_hourly.sh
  56. 24 */4 * * * curl -X POST http://192.168.142.66:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "check_publish_video_audit_status"}'
  57. # 每天凌晨4:30 15:30执行视频发布和审核流程
  58. 0 1,8,19 * * * bash /root/luojunhui/LongArticlesJob/sh/run_video_publish_and_audit.sh
  59. # 每天 上午8:30, 下午1:00, 晚上8:50执行
  60. # 30 8 * * * bash /root/luojunhui/LongArticlesJob/sh/run_update_published_articles_daily.sh
  61. # 20 14 * * * bash /root/luojunhui/LongArticlesJob/sh/run_update_published_articles_daily.sh
  62. # 50 20 * * * bash /root/luojunhui/LongArticlesJob/sh/run_update_published_articles_daily.sh
  63. 30 8,15 * * * curl -X POST http://127.0.0.1:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "daily_publish_articles_recycle"}'
  64. 0 21 * * * curl -X POST http://127.0.0.1:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "daily_publish_articles_recycle"}'
  65. 10 22 * * * curl -X POST http://127.0.0.1:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "daily_publish_articles_recycle"}'
  66. 30 9,16,21 * * * curl -X POST http://127.0.0.1:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "update_root_source_id"}'
  67. 30 22 * * * curl -X POST http://127.0.0.1:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "update_root_source_id"}'
  68. # 每天上午9点,下午2点,晚上9点执行v2代码
  69. # 0 9,14,21 * * * bash /root/luojunhui/LongArticlesJob/sh/run_update_published_articles_daily_v2.sh
  70. # 每天上午 9:30 点,下午 2 点,晚上 7 点执行下架视频任务
  71. # 30 9 * * * bash /root/luojunhui/LongArticlesJob/sh/run_get_off_videos_three_times_per_day.sh
  72. # 0 15 * * * bash /root/luojunhui/LongArticlesJob/sh/run_get_off_videos_three_times_per_day.sh
  73. # 0 19 * * * bash /root/luojunhui/LongArticlesJob/sh/run_get_off_videos_three_times_per_day.sh
  74. 0 9,15,19 * * * curl -X POST http://127.0.0.1:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "get_off_videos"}'
  75. # 每天早上9点,下午2:30, 晚上7:30
  76. # 0 10,16,20 * * * bash /root/luojunhui/LongArticlesJob/sh/published_articles_monitor.sh
  77. 0 10,16,20 * * * curl -X POST http://192.168.142.66:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "inner_article_monitor"}'
  78. # 每开始执行百度视频
  79. 20 0,12 * * * bash /root/luojunhui/LongArticlesJob/sh/run_baidu_video_crawler.sh
  80. # check kimo balance hourly
  81. # 30 * * * * bash /root/luojunhui/LongArticlesJob/sh/run_kimi_balance_monitor.sh
  82. # 每4h校验一次kimi余额
  83. 25 */4 * * * curl -X POST http://127.0.0.1:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "check_kimi_balance"}'
  84. # 0 11,23 * * * bash /root/luojunhui/LongArticlesJob/sh/run_account_explore.sh
  85. # 0 5,10,15,20 * * * bash /root/luojunhui/LongArticlesJob/sh/run_account_quality_analysis.sh
  86. # 更新小程序信息
  87. 0 3,4,5,6,7,8 * * * curl -X POST http://192.168.142.66:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "mini_program_detail_process"}'
  88. # */8 * * * * curl -X POST http://192.168.142.66:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "extract_title_features", "batch_size": 50, "version": 2}'
  89. 0 9,16 * * * curl -X POST http://192.168.142.66:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "recycle_outside_account_articles"}'
  90. 35 16 * * * curl -X POST http://192.168.142.66:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "update_outside_account_article_root_source_id"}'
  91. # 执行限流文章分析
  92. 40 10 * * * curl -X POST http://192.168.142.66:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "update_limited_account_info"}'
  93. # 候选账号质量分析
  94. 0 5,10,15,20 * * * curl -X POST http://192.168.142.66:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "candidate_account_quality_analysis"}'