|
@@ -1,23 +1,20 @@
|
|
|
+import json
|
|
|
import datetime
|
|
|
+import traceback
|
|
|
+
|
|
|
from pymysql.cursors import DictCursor
|
|
|
+from tqdm import tqdm
|
|
|
|
|
|
from applications import bot, aiditApi
|
|
|
+from applications.const import SingleVideoPoolPublishTaskConst
|
|
|
from applications.db import DatabaseConnector
|
|
|
-from config import long_articles_config
|
|
|
+from config import long_articles_config, apolloConfig
|
|
|
+
|
|
|
+config = apolloConfig()
|
|
|
+const = SingleVideoPoolPublishTaskConst()
|
|
|
|
|
|
-generate_plan_map = {
|
|
|
- "gzh": "20250321060236316993274",
|
|
|
- "sph": "20250321055917369191992",
|
|
|
- "toutiao": "20250321060107537529410",
|
|
|
- "hksp": "20250321060438155415100",
|
|
|
-}
|
|
|
+video_pool_config = json.loads(config.getConfigValue(key="video_pool_config"))
|
|
|
|
|
|
-platform_name_map = {
|
|
|
- "gzh": "公众号",
|
|
|
- "sph": "视频号",
|
|
|
- "toutiao": "头条号",
|
|
|
- "hksp": "好看视频",
|
|
|
-}
|
|
|
|
|
|
class PublishSingleVideoPoolVideos:
|
|
|
def __init__(self):
|
|
@@ -25,24 +22,13 @@ class PublishSingleVideoPoolVideos:
|
|
|
self.db_client.connect()
|
|
|
|
|
|
def get_task_list(self, platform:str) -> list[dict]:
|
|
|
- match platform:
|
|
|
- case "sph":
|
|
|
- task_count = 218
|
|
|
- case "gzh":
|
|
|
- task_count = 201
|
|
|
- case "toutiao":
|
|
|
- task_count = 411
|
|
|
- case "hksp":
|
|
|
- task_count = 165
|
|
|
- case _:
|
|
|
- return []
|
|
|
-
|
|
|
+ daily_limit = video_pool_config[platform]['process_num_each_day']
|
|
|
fetch_query = f"""
|
|
|
select id, content_trace_id, pq_vid
|
|
|
from single_video_transform_queue
|
|
|
- where status = 0 and platform = '{platform}'
|
|
|
+ where status = {const.TRANSFORM_INIT_STATUS} and platform = '{platform}'
|
|
|
order by score desc
|
|
|
- limit 2000
|
|
|
+ limit {daily_limit};
|
|
|
"""
|
|
|
fetch_response = self.db_client.fetch(query=fetch_query, cursor_type=DictCursor)
|
|
|
return fetch_response
|
|
@@ -67,41 +53,65 @@ class PublishSingleVideoPoolVideos:
|
|
|
entrance of this class
|
|
|
"""
|
|
|
platform_list = ["sph", "gzh", "toutiao", "hksp"]
|
|
|
- for platform in platform_list:
|
|
|
+ for platform in tqdm(platform_list, desc='process each platform'):
|
|
|
task_list = self.get_task_list(platform)
|
|
|
task_id_tuple = tuple([task['id'] for task in task_list])
|
|
|
vid_list = [task['pq_vid'] for task in task_list]
|
|
|
if vid_list:
|
|
|
- # create video crawler plan
|
|
|
- plan_name = f"{platform_name_map[platform]}-{datetime.datetime.today().strftime('%Y-%m-%d')}-视频数量: {len(vid_list)}"
|
|
|
- crawler_plan_response = aiditApi.auto_create_single_video_crawler_task(
|
|
|
- plan_name=plan_name,
|
|
|
- plan_tag="单视频供给冷启动",
|
|
|
- video_id_list=vid_list,
|
|
|
- )
|
|
|
- crawler_plan_id = crawler_plan_response["data"]["id"]
|
|
|
- crawler_plan_name = crawler_plan_response["data"]["name"]
|
|
|
- # update status
|
|
|
- self.update_tasks_status(
|
|
|
- task_id_tuple=task_id_tuple,
|
|
|
- ori_status=0,
|
|
|
- new_status=1,
|
|
|
- )
|
|
|
- # bind crawler plan to generate plan
|
|
|
- crawler_task_list = [
|
|
|
- {
|
|
|
- "contentType": 1,
|
|
|
- "inputSourceModal": 4,
|
|
|
- "inputSourceChannel": 10,
|
|
|
- "inputSourceType": 2,
|
|
|
- "inputSourceValue": crawler_plan_id,
|
|
|
- "inputSourceSubType": None,
|
|
|
- "fieldName": None,
|
|
|
- "inputSourceLabel": "原始帖子-视频-票圈小程序-内容添加计划-{}".format(crawler_plan_name),
|
|
|
- }
|
|
|
- ]
|
|
|
- generate_plan_id = generate_plan_map[platform]
|
|
|
- aiditApi.bind_crawler_task_to_generate_task(
|
|
|
- crawler_task_list=crawler_task_list,
|
|
|
- generate_task_id=generate_plan_id,
|
|
|
+ try:
|
|
|
+ # create video crawler plan
|
|
|
+ plan_name = f"{video_pool_config[platform]['nick_name']}-{datetime.datetime.today().strftime('%Y-%m-%d')}-视频数量: {len(vid_list)}"
|
|
|
+ crawler_plan_response = aiditApi.auto_create_single_video_crawler_task(
|
|
|
+ plan_name=plan_name,
|
|
|
+ plan_tag="单视频供给冷启动",
|
|
|
+ video_id_list=vid_list,
|
|
|
+ )
|
|
|
+ crawler_plan_id = crawler_plan_response["data"]["id"]
|
|
|
+ crawler_plan_name = crawler_plan_response["data"]["name"]
|
|
|
+
|
|
|
+ # bind crawler plan to generate plan
|
|
|
+ crawler_task_list = [
|
|
|
+ {
|
|
|
+ "contentType": 1,
|
|
|
+ "inputSourceModal": 4,
|
|
|
+ "inputSourceChannel": 10,
|
|
|
+ "inputSourceType": 2,
|
|
|
+ "inputSourceValue": crawler_plan_id,
|
|
|
+ "inputSourceSubType": None,
|
|
|
+ "fieldName": None,
|
|
|
+ "inputSourceLabel": "原始帖子-视频-票圈小程序-内容添加计划-{}".format(crawler_plan_name),
|
|
|
+ }
|
|
|
+ ]
|
|
|
+ generate_plan_id = video_pool_config[platform]['generate_plan_id']
|
|
|
+ aiditApi.bind_crawler_task_to_generate_task(
|
|
|
+ crawler_task_list=crawler_task_list,
|
|
|
+ generate_task_id=generate_plan_id,
|
|
|
+ )
|
|
|
+
|
|
|
+ # update status
|
|
|
+ self.update_tasks_status(
|
|
|
+ task_id_tuple=task_id_tuple,
|
|
|
+ ori_status=const.TRANSFORM_INIT_STATUS,
|
|
|
+ new_status=const.TRANSFORM_SUCCESS_STATUS
|
|
|
+ )
|
|
|
+ except Exception as e:
|
|
|
+ bot(
|
|
|
+ title='视频内容池发布任务',
|
|
|
+ detail={
|
|
|
+ 'platform': platform,
|
|
|
+ 'date': datetime.datetime.today().strftime('%Y-%m-%d'),
|
|
|
+ 'msg': '发布视频内容池失败,原因:{}'.format(str(e)),
|
|
|
+ 'detail': traceback.format_exc(),
|
|
|
+ },
|
|
|
+ mention=False
|
|
|
+ )
|
|
|
+ else:
|
|
|
+ bot(
|
|
|
+ title='视频内容池发布任务',
|
|
|
+ detail={
|
|
|
+ 'platform': platform,
|
|
|
+ 'date': datetime.datetime.today().strftime('%Y-%m-%d'),
|
|
|
+ 'msg': '该平台无待发布视频,请关注供给的抓取'
|
|
|
+ },
|
|
|
+ mention=False
|
|
|
)
|