item.py 1.5 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869
  1. """
  2. @author: luojunhui
  3. """
  4. import time
  5. default_single_video_table_fields = {
  6. "platform": "gzh",
  7. "article_title": None,
  8. "content_trace_id": None,
  9. "read_cnt": 0,
  10. "article_index": None,
  11. "out_account_name": None,
  12. "article_url": None,
  13. "url_unique_md5": None,
  14. "category": None,
  15. "publish_timestamp": None,
  16. "out_account_id": None,
  17. "cover_url": None,
  18. "crawler_timestamp": int(time.time()),
  19. "source_account": 1,
  20. "article_publish_type": None,
  21. "like_cnt": 0,
  22. "bad_status": 0,
  23. "tags": None,
  24. "video_oss_path": None,
  25. }
  26. class Item(object):
  27. """
  28. format save to article meta table or single video source table
  29. """
  30. def __init__(self):
  31. self.item = {}
  32. def add(self, key, value):
  33. """
  34. add key value to item
  35. """
  36. self.item[key] = value
  37. def check_video_item(self):
  38. """
  39. check video item
  40. """
  41. fields = list(default_single_video_table_fields.keys())
  42. for field in fields:
  43. if self.item.get(field, None) is not None:
  44. continue
  45. else:
  46. self.item[field] = default_single_video_table_fields[field]
  47. def check_article_item(self):
  48. """
  49. check article item
  50. """
  51. return
  52. def check(self, source):
  53. """
  54. check item
  55. """
  56. match source:
  57. case "video":
  58. self.check_video_item()
  59. case "article":
  60. self.check_article_item()