From 04cbe549af3874d3caa04fd2416f42aeccba63ec Mon Sep 17 00:00:00 2001
From: Relakkes <relakkes@gmail.com>
Date: Tue, 20 Aug 2024 03:09:42 +0800
Subject: [PATCH] =?UTF-8?q?fix:=20=E4=BF=AE=E5=A4=8D=E6=8A=96=E9=9F=B3?=
 =?UTF-8?q?=E5=85=B3=E9=94=AE=E8=AF=8D=E6=90=9C=E7=B4=A2bug?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 media_platform/douyin/client.py | 5 ++++-
 media_platform/douyin/core.py   | 6 ++++--
 2 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/media_platform/douyin/client.py b/media_platform/douyin/client.py
index 7e2a78ed..e760697b 100644
--- a/media_platform/douyin/client.py
+++ b/media_platform/douyin/client.py
@@ -126,7 +126,8 @@ async def search_info_by_keyword(
             offset: int = 0,
             search_channel: SearchChannelType = SearchChannelType.GENERAL,
             sort_type: SearchSortType = SearchSortType.GENERAL,
-            publish_time: PublishTimeType = PublishTimeType.UNLIMITED
+            publish_time: PublishTimeType = PublishTimeType.UNLIMITED,
+            search_id: str = ""
     ):
         """
         DouYin Web Search API
@@ -135,6 +136,7 @@ async def search_info_by_keyword(
         :param search_channel:
         :param sort_type:
         :param publish_time: ·
+        :param search_id: ·
         :return:
         """
         query_params = {
@@ -149,6 +151,7 @@ async def search_info_by_keyword(
             'count': '15',
             'need_filter_settings': '1',
             'list_type': 'multi',
+            'search_id': search_id,
         }
         if sort_type.value != SearchSortType.GENERAL.value or publish_time.value != PublishTimeType.UNLIMITED.value:
             query_params["filter_selected"] = json.dumps({
diff --git a/media_platform/douyin/core.py b/media_platform/douyin/core.py
index 19b3ad1a..395d7c0d 100644
--- a/media_platform/douyin/core.py
+++ b/media_platform/douyin/core.py
@@ -83,6 +83,7 @@ async def search(self) -> None:
             utils.logger.info(f"[DouYinCrawler.search] Current keyword: {keyword}")
             aweme_list: List[str] = []
             page = 0
+            dy_search_id = ""
             while (page - start_page + 1) * dy_limit_count <= config.CRAWLER_MAX_NOTES_COUNT:
                 if page < start_page:
                     utils.logger.info(f"[DouYinCrawler.search] Skip {page}")
@@ -92,7 +93,8 @@ async def search(self) -> None:
                     utils.logger.info(f"[DouYinCrawler.search] search douyin keyword: {keyword}, page: {page}")
                     posts_res = await self.dy_client.search_info_by_keyword(keyword=keyword,
                                                                             offset=page * dy_limit_count - dy_limit_count,
-                                                                            publish_time=PublishTimeType(config.PUBLISH_TIME_TYPE)
+                                                                            publish_time=PublishTimeType(config.PUBLISH_TIME_TYPE),
+                                                                            search_id=dy_search_id
                                                                             )
                 except DataFetchError:
                     utils.logger.error(f"[DouYinCrawler.search] search douyin keyword: {keyword} failed")
@@ -103,7 +105,7 @@ async def search(self) -> None:
                     utils.logger.error(
                         f"[DouYinCrawler.search] search douyin keyword: {keyword} failed，账号也许被风控了。")
                     break
-
+                dy_search_id = posts_res.get("extra", {}).get("logid", "")
                 for post_item in posts_res.get("data"):
                     try:
                         aweme_info: Dict = post_item.get("aweme_info") or \