feat: 增加搜索词来源渠道

media_platform/bilibili/core.py

@@ -17,7 +17,7 @@ from base.base_crawler import AbstractCrawler
 from proxy.proxy_ip_pool import IpInfoModel, create_ip_pool
 from store import bilibili as bilibili_store
 from tools import utils
-from var import crawler_type_var
+from var import crawler_type_var, source_keyword_var
 
 from .client import BilibiliClient
 from .exception import DataFetchError
@@ -96,6 +96,7 @@ class BilibiliCrawler(AbstractCrawler):
             config.CRAWLER_MAX_NOTES_COUNT = bili_limit_count
         start_page = config.START_PAGE  # start page number
         for keyword in config.KEYWORDS.split(","):
+            source_keyword_var.set(keyword)
             utils.logger.info(
                 f"[BilibiliCrawler.search] Current search keyword: {keyword}")
             page = 1

media_platform/douyin/core.py

@@ -12,7 +12,7 @@ from base.base_crawler import AbstractCrawler
 from proxy.proxy_ip_pool import IpInfoModel, create_ip_pool
 from store import douyin as douyin_store
 from tools import utils
-from var import crawler_type_var
+from var import crawler_type_var, source_keyword_var
 
 from .client import DOUYINClient
 from .exception import DataFetchError
@@ -80,6 +80,7 @@ class DouYinCrawler(AbstractCrawler):
             config.CRAWLER_MAX_NOTES_COUNT = dy_limit_count
         start_page = config.START_PAGE  # start page number
         for keyword in config.KEYWORDS.split(","):
+            source_keyword_var.set(keyword)
             utils.logger.info(f"[DouYinCrawler.search] Current keyword: {keyword}")
             aweme_list: List[str] = []
             page = 0

media_platform/kuaishou/core.py

@@ -13,7 +13,7 @@ from base.base_crawler import AbstractCrawler
 from proxy.proxy_ip_pool import IpInfoModel, create_ip_pool
 from store import kuaishou as kuaishou_store
 from tools import utils
-from var import comment_tasks_var, crawler_type_var
+from var import comment_tasks_var, crawler_type_var, source_keyword_var
 
 from .client import KuaiShouClient
 from .exception import DataFetchError
@@ -85,6 +85,7 @@ class KuaishouCrawler(AbstractCrawler):
             config.CRAWLER_MAX_NOTES_COUNT = ks_limit_count
         start_page = config.START_PAGE
         for keyword in config.KEYWORDS.split(","):
+            source_keyword_var.set(keyword)
             utils.logger.info(f"[KuaishouCrawler.search] Current search keyword: {keyword}")
             page = 1
             while (page - start_page + 1) * ks_limit_count <= config.CRAWLER_MAX_NOTES_COUNT:

media_platform/tieba/core.py

@@ -14,7 +14,7 @@ from proxy.proxy_ip_pool import IpInfoModel, create_ip_pool
 from store import tieba as tieba_store
 from tools import utils
 from tools.crawler_util import format_proxy_info
-from var import crawler_type_var
+from var import crawler_type_var, source_keyword_var
 
 from .client import BaiduTieBaClient
 from .field import SearchNoteType, SearchSortType
@@ -74,6 +74,7 @@ class TieBaCrawler(AbstractCrawler):
             config.CRAWLER_MAX_NOTES_COUNT = tieba_limit_count
         start_page = config.START_PAGE
         for keyword in config.KEYWORDS.split(","):
+            source_keyword_var.set(keyword)
             utils.logger.info(f"[BaiduTieBaCrawler.search] Current search keyword: {keyword}")
             page = 1
             while (page - start_page + 1) * tieba_limit_count <= config.CRAWLER_MAX_NOTES_COUNT:

media_platform/weibo/core.py

@@ -18,7 +18,7 @@ from base.base_crawler import AbstractCrawler
 from proxy.proxy_ip_pool import IpInfoModel, create_ip_pool
 from store import weibo as weibo_store
 from tools import utils
-from var import crawler_type_var
+from var import crawler_type_var, source_keyword_var
 
 from .client import WeiboClient
 from .exception import DataFetchError
@@ -99,6 +99,7 @@ class WeiboCrawler(AbstractCrawler):
             config.CRAWLER_MAX_NOTES_COUNT = weibo_limit_count
         start_page = config.START_PAGE
         for keyword in config.KEYWORDS.split(","):
+            source_keyword_var.set(keyword)
             utils.logger.info(f"[WeiboCrawler.search] Current search keyword: {keyword}")
             page = 1
             while (page - start_page + 1) * weibo_limit_count <= config.CRAWLER_MAX_NOTES_COUNT:

media_platform/xhs/core.py

@@ -12,7 +12,7 @@ from base.base_crawler import AbstractCrawler
 from proxy.proxy_ip_pool import IpInfoModel, create_ip_pool
 from store import xhs as xhs_store
 from tools import utils
-from var import crawler_type_var
+from var import crawler_type_var, source_keyword_var
 
 from .client import XiaoHongShuClient
 from .exception import DataFetchError
@@ -94,6 +94,7 @@ class XiaoHongShuCrawler(AbstractCrawler):
             config.CRAWLER_MAX_NOTES_COUNT = xhs_limit_count
         start_page = config.START_PAGE
         for keyword in config.KEYWORDS.split(","):
+            source_keyword_var.set(keyword)
             utils.logger.info(f"[XiaoHongShuCrawler.search] Current search keyword: {keyword}")
             page = 1
             while (page - start_page + 1) * xhs_limit_count <= config.CRAWLER_MAX_NOTES_COUNT:

model/m_baidu_tieba.py

@@ -21,6 +21,7 @@ class TiebaNote(BaseModel):
     total_replay_num: int = Field(default=0, description="回复总数")
     total_replay_page: int = Field(default=0, description="回复总页数")
     ip_location: Optional[str] = Field(default="", description="IP地理位置")
+    source_keyword: str = Field(default="", description="来源关键词")
 
 
 class TiebaComment(BaseModel):

schema/tables.sql

@@ -397,4 +397,12 @@ CREATE TABLE tieba_comment
     KEY               `idx_tieba_comment_comment_id` (`note_id`),
     KEY               `idx_tieba_comment_note_id` (`note_id`),
     KEY               `idx_tieba_comment_publish_time` (`publish_time`)
-) ENGINE=InnoDB AUTO_INCREMENT=1 DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_0900_ai_ci COMMENT='贴吧评论表';
+) ENGINE=InnoDB AUTO_INCREMENT=1 DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_0900_ai_ci COMMENT='贴吧评论表';
+
+-- 增加搜索来源关键字字段
+alter table bilibili_video add column `source_keyword` varchar(255) default '' comment '搜索来源关键字';
+alter table douyin_aweme add column `source_keyword` varchar(255) default '' comment '搜索来源关键字';
+alter table kuaishou_video add column `source_keyword` varchar(255) default '' comment '搜索来源关键字';
+alter table weibo_note add column `source_keyword` varchar(255) default '' comment '搜索来源关键字';
+alter table xhs_note add column `source_keyword` varchar(255) default '' comment '搜索来源关键字';
+alter table tieba_note add column `source_keyword` varchar(255) default '' comment '搜索来源关键字';

store/bilibili/__init__.py

@@ -6,6 +6,7 @@
 from typing import List
 
 import config
+from var import source_keyword_var
 
 from .bilibili_store_impl import *
 from .bilibilli_store_video import *
@@ -48,6 +49,7 @@ async def update_bilibili_video(video_item: Dict):
         "last_modify_ts": utils.get_current_timestamp(),
         "video_url": f"https://www.bilibili.com/video/av{video_id}",
         "video_cover_url": video_item_view.get("pic", ""),
+        "source_keyword": source_keyword_var.get(),
     }
     utils.logger.info(
         f"[store.bilibili.update_bilibili_video] bilibili video id:{video_id}, title:{save_content_item.get('title')}")

store/douyin/__init__.py

@@ -5,6 +5,7 @@
 from typing import List
 
 import config
+from var import source_keyword_var
 
 from .douyin_store_impl import *
 
@@ -48,7 +49,8 @@ async def update_douyin_aweme(aweme_item: Dict):
         "share_count": str(interact_info.get("share_count")),
         "ip_location": aweme_item.get("ip_label", ""),
         "last_modify_ts": utils.get_current_timestamp(),
-        "aweme_url": f"https://www.douyin.com/video/{aweme_id}"
+        "aweme_url": f"https://www.douyin.com/video/{aweme_id}",
+        "source_keyword": source_keyword_var.get(),
     }
     utils.logger.info(
         f"[store.douyin.update_douyin_aweme] douyin aweme id:{aweme_id}, title:{save_content_item.get('title')}")

store/kuaishou/__init__.py

@@ -5,6 +5,7 @@
 from typing import List
 
 import config
+from var import source_keyword_var
 
 from .kuaishou_store_impl import *
 
@@ -46,6 +47,7 @@ async def update_kuaishou_video(video_item: Dict):
         "video_url": f"https://www.kuaishou.com/short-video/{video_id}",
         "video_cover_url": photo_info.get("coverUrl", ""),
         "video_play_url": photo_info.get("photoUrl", ""),
+        "source_keyword": source_keyword_var.get(),
     }
     utils.logger.info(
         f"[store.kuaishou.update_kuaishou_video] Kuaishou video id:{video_id}, title:{save_content_item.get('title')}")

store/tieba/__init__.py

@@ -2,6 +2,7 @@
 from typing import List
 
 from model.m_baidu_tieba import TiebaComment, TiebaNote
+from var import source_keyword_var
 
 from . import tieba_store_impl
 from .tieba_store_impl import *
@@ -32,6 +33,7 @@ async def update_tieba_note(note_item: TiebaNote):
     Returns:
 
     """
+    note_item.source_keyword = source_keyword_var.get()
     save_note_item = note_item.model_dump()
     save_note_item.update({"last_modify_ts": utils.get_current_timestamp()})
     utils.logger.info(f"[store.tieba.update_tieba_note] tieba note: {save_note_item}")

store/weibo/__init__.py

@@ -6,6 +6,7 @@
 import re
 from typing import List
 
+from var import source_keyword_var
 from .weibo_store_image import *
 from .weibo_store_impl import *
 
@@ -51,6 +52,8 @@ async def update_weibo_note(note_item: Dict):
         "gender": user_info.get("gender", ""),
         "profile_url": user_info.get("profile_url", ""),
         "avatar": user_info.get("profile_image_url", ""),
+
+        "source_keyword": source_keyword_var.get(),
     }
     utils.logger.info(
         f"[store.weibo.update_weibo_note] weibo note id:{note_id}, title:{save_content_item.get('content')[:24]} ...")

store/xhs/__init__.py

@@ -5,6 +5,7 @@
 from typing import List
 
 import config
+from var import source_keyword_var
 
 from . import xhs_store_impl
 from .xhs_store_image import *
@@ -78,6 +79,7 @@ async def update_xhs_note(note_item: Dict):
         "tag_list": ','.join([tag.get('name', '') for tag in tag_list if tag.get('type') == 'topic']),
         "last_modify_ts": utils.get_current_timestamp(),
         "note_url": f"https://www.xiaohongshu.com/explore/{note_id}?xsec_token={note_item.get('xsec_token')}&xsec_source=pc_search",
+        "source_keyword": source_keyword_var.get(),
     }
     utils.logger.info(f"[store.xhs.update_xhs_note] xhs note: {local_db_item}")
     await XhsStoreFactory.create_store().store_content(local_db_item)

var.py

@@ -11,3 +11,4 @@ crawler_type_var: ContextVar[str] = ContextVar("crawler_type", default="")
 comment_tasks_var: ContextVar[List[Task]] = ContextVar("comment_tasks", default=[])
 media_crawler_db_var: ContextVar[AsyncMysqlDB] = ContextVar("media_crawler_db_var")
 db_conn_pool_var: ContextVar[aiomysql.Pool] = ContextVar("db_conn_pool_var")
+source_keyword_var: ContextVar[str] = ContextVar("source_keyword", default="")