feat: logger record current search page

README.md

@@ -87,7 +87,6 @@
 - 知识星球：沉淀高质量常见问题、最佳实践文档、多年编程+爬虫经验分享，提供付费知识星球服务，主动提问，作者会定期回答问题
   <p>
   <img alt="xingqiu" src="https://nm.zizhi1.com/static/img/8e1312d1f52f2e0ff436ea7196b4e27b.15555424244122T1.webp" style="width: auto;height: 400px" >
-  <img alt="xingqiu_yhq" src="https://nm.zizhi1.com/static/img/c14da73f0dd9351e7169a36368d5037b.yhq.webp" style="width: auto;height: 400px" >
   </p>
   
   星球精选文章： 
@@ -95,6 +94,7 @@
   - [【独创】使用Playwright低成本获取某书X-s参数流程分析（当年的回忆录）](https://articles.zsxq.com/id_u4lcrvqakuc7.html)
   - [ MediaCrawler-基于抽象类设计重构项目缓存](https://articles.zsxq.com/id_4ju73oxewt9j.html)
   - [ 手把手带你撸一个自己的IP代理池](https://articles.zsxq.com/id_38fza371ladm.html)
+  - 每天 1 快钱订阅我的知识服务
   
   
   

media_platform/bilibili/core.py

@@ -106,6 +106,7 @@ class BilibiliCrawler(AbstractCrawler):
                     page += 1
                     continue
 
+                utils.logger.info(f"[BilibiliCrawler.search] search bilibili keyword: {keyword}, page: {page}")
                 video_id_list: List[str] = []
                 videos_res = await self.bili_client.search_video_by_keyword(
                     keyword=keyword,
@@ -126,7 +127,6 @@ class BilibiliCrawler(AbstractCrawler):
                     if video_item:
                         video_id_list.append(video_item.get("View").get("aid"))
                         await bilibili_store.update_bilibili_video(video_item)
-
                 page += 1
                 await self.batch_get_video_comments(video_id_list)
 

media_platform/douyin/core.py

@@ -90,6 +90,7 @@ class DouYinCrawler(AbstractCrawler):
                     page += 1
                     continue
                 try:
+                    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)

media_platform/kuaishou/core.py

@@ -92,7 +92,7 @@ class KuaishouCrawler(AbstractCrawler):
                     utils.logger.info(f"[KuaishouCrawler.search] Skip page: {page}")
                     page += 1
                     continue
-                
+                utils.logger.info(f"[KuaishouCrawler.search] search kuaishou keyword: {keyword}, page: {page}")
                 video_id_list: List[str] = []
                 videos_res = await self.ks_client.search_info_by_keyword(
                     keyword=keyword,

media_platform/weibo/core.py

@@ -108,7 +108,7 @@ class WeiboCrawler(AbstractCrawler):
                     utils.logger.info(f"[WeiboCrawler.search] Skip page: {page}")
                     page += 1
                     continue
-                
+                utils.logger.info(f"[WeiboCrawler.search] search weibo keyword: {keyword}, page: {page}")
                 search_res = await self.wb_client.get_note_by_keyword(
                     keyword=keyword,
                     page=page,

media_platform/xhs/core.py

@@ -102,6 +102,7 @@ class XiaoHongShuCrawler(AbstractCrawler):
                     continue
 
                 try:
+                    utils.logger.info(f"[XiaoHongShuCrawler.search] search xhs keyword: {keyword}, page: {page}")
                     note_id_list: List[str] = []
                     notes_res = await self.xhs_client.get_note_by_keyword(
                         keyword=keyword,