صفحهٔ اصلی گشت‌و‌گذار راهنما
ورود
huangzhifeng
/
jd-tb-yaofang-2
1
0
انشعاب 0
پرونده‌ها مشکلات 0 درخواست واکشی 0 ویکی
شاخه: main
شاخه‌ها تگ‌ها
jd-tb-yaofang-2
/
start_run_yaofangwang.py

start_run_yaofangwang.py 2.5 KB
لینک دائمی تاريخچه خام

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172 
  1. from spiders.yaofangwang.yaofangwang_crawl import YaofangwangCrawl
    2. 

  2. from commons.scheduler import CrawlerScheduler
    3. 

  3. from commons.Logger import logger
    4. 

  4. from commons.config import YAOFANGWANG_DEVICE_NAME, PLATFORM_ID_YAOFANGWANG
    5. 

  5. 

  6. PLATFORM_NAME = "药房网"
    7. 

  7. PLATFORM_ID = PLATFORM_ID_YAOFANGWANG
    8. 

  8. 

  9. class YFW():
    10. 

  10.         
    11. 

  11.     def __init__(self):
    12. 

  12.         self.crawl_count = ""
    13. 

  13.         self.task_id = ""
    14. 

  14.         self.task_dict=''
    15. 

  15. 

  16.     def run(self):
    17. 

  17. 

  18.         spider_schedule =  CrawlerScheduler(YAOFANGWANG_DEVICE_NAME, PLATFORM_ID_YAOFANGWANG)
    19. 

  19.         spider_schedule.start()
    20. 

  20.         time.sleep(3)
    21. 

  21. 

  22.         while 1 :
    23. 

  23.             print(f'not spider_schedule.end:{not spider_schedule.end}')
    24. 

  24.             if(not spider_schedule.end):
    25. 

  25.                 print('进入工作')
    26. 

  26. 

  27.                 self.task_dict = spider_schedule.get_task()
    28. 

  28.                 
    29. 

  29.                 #self.task_dict = {'id': 149, 'company_id': 0, 'product_name': '藿香正气合剂', 'product_specs': '', 'product_brand': '999', 'product_keyword': '', 'current_page': 0, 'start_offset': 0}
    30. 

  30. 

  31.                 print(self.task_dict)
    32. 

  32. 

  33. 

  34. 

  35.                 if not self.task_dict:
    36. 

  36.                     logger.info(f"{PLATFORM_NAME}暂无任务")
    37. 

  37.                     time.sleep(35)
    38. 

  38.                     continue
    39. 

  39. 

  40.                 
    41. 

  41.                 crawl_count, is_success = YaofangwangCrawl(self.task_dict,spider_schedule).run()
    42. 

  42.                 spider_schedule.stop()
    43. 

  43.             else:
    44. 

  44.                 spider_schedule.start()
    45. 

  45.                 print('休息')
    46. 

  46.                 time.sleep(35)
    47. 

  47. 

  48.             
    49. 

  49.             time.sleep(30)
    50. 

  50. 

  51. TASK_LIST = [
    52. 

  52.     {"brand": "天和", "product": "骨通贴膏", "spec": ""},
    53. 

  53.     {"brand": "天和", "product": "追风膏", "spec": ""},
    54. 

  54.     {"brand": "天和", "product": "麝香壮骨膏", "spec": ""},
    55. 

  55.     {"brand": "达因", "product": "维生素D滴剂", "spec": ""},
    56. 

  56.     {"brand": "999", "product": "益血生胶囊", "spec": ""},
    57. 

  57.     {"brand": "999", "product": "尪痹胶囊", "spec": ""},
    58. 

  58.     {"brand": "999", "product": "气滞胃痛颗粒", "spec": ""},
    59. 

  59.     {"brand": "好娃娃", "product": "小儿氨酚烷胺颗粒", "spec": ""},
    60. 

  60.     {"brand": "澳诺", "product": "澳诺葡萄糖酸钙锌口服溶液", "spec": ""},
    61. 

  61.     {"brand": "易善复", "product": "多烯磷脂酰胆碱胶囊", "spec": ""},
    62. 

  62.     {"brand": "达因", "product": "伊可新维生素AD滴剂", "spec": ""},
    63. 

  63.     {"brand": "999", "product": "消痔软膏", "spec": ""},
    64. 

  64. ]
    65. 

  65. 

  66. if __name__ == "__main__":
    67. 

  67. 

  68.     import time
    69. 

  69.     YFW().run()
    70. 

  70.     #
    71. 

  71.     # run_scheduled_loop(PLATFORM_NAME, PLATFORM_ID, YaofangwangCrawl)
    72. 

  72.