From af5a393a7afe4a8b8c1c4fa931d0671b7da524eb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E7=BF=9F=E6=8C=81=E6=B1=9F?= <129171955+2513502304@users.noreply.github.com> Date: Sat, 19 Apr 2025 04:34:24 +0800 Subject: [PATCH] =?UTF-8?q?Update=20core.py=EF=BC=8C=E5=88=A0=E9=99=A4?= =?UTF-8?q?=E4=BA=86=E5=85=B6=E5=AE=83=E4=BB=A3=E7=A0=81=E8=B4=A1=E7=8C=AE?= =?UTF-8?q?=E8=80=85=E6=89=80=E6=B7=BB=E5=8A=A0=E7=9A=84try-catch=E8=AF=AD?= =?UTF-8?q?=E5=8F=A5=EF=BC=8C=E8=AF=A5=E6=AE=B5try-catch=E8=AF=AD=E5=8F=A5?= =?UTF-8?q?=E5=B0=86=E4=BC=9A=E5=BD=B1=E5=93=8D=E5=85=B6=E4=BB=A3=E7=A0=81?= =?UTF-8?q?=E7=9A=84=E6=9C=80=E7=BB=88=E9=80=BB=E8=BE=91=E5=B9=B6=E4=BB=A4?= =?UTF-8?q?=E5=85=B6=E5=A4=B1=E6=95=88=EF=BC=8C=E4=BD=BF=E5=85=B6=E4=BB=85?= =?UTF-8?q?=E8=83=BD=E7=88=AC=E5=8F=96=E5=BD=93=E5=A4=A9=E4=B8=80=E5=A4=A9?= =?UTF-8?q?=E6=95=B0=E6=8D=AE=E8=80=8C=E6=97=A0=E6=B3=95=E8=B7=B3=E8=BD=AC?= =?UTF-8?q?=E5=88=B0=E4=B8=8B=E4=B8=80=E5=A4=A9=EF=BC=88=E5=8E=9F=E5=85=88?= =?UTF-8?q?=E7=9A=84=E9=80=BB=E8=BE=91=E5=B0=B1=E6=98=AFtry-catch=E6=8D=95?= =?UTF-8?q?=E8=8E=B7=E5=BC=82=E5=B8=B8=E4=BB=8E=E8=80=8C=E8=BF=9B=E5=85=A5?= =?UTF-8?q?=E4=B8=8B=E4=B8=80=E5=A4=A9=EF=BC=8C=E4=B8=8D=E8=A6=81=E5=86=8D?= =?UTF-8?q?=E5=90=91=E8=AF=A5=E8=AF=AD=E5=8F=A5=E4=B8=AD=E6=B7=BB=E5=8A=A0?= =?UTF-8?q?=E6=8D=95=E8=8E=B7=E5=BC=82=E5=B8=B8=E6=93=8D=E4=BD=9C=E6=88=96?= =?UTF-8?q?=E8=80=85finally=E8=AF=AD=E5=8F=A5=EF=BC=81=EF=BC=89?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- media_platform/bilibili/core.py | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) diff --git a/media_platform/bilibili/core.py b/media_platform/bilibili/core.py index 649fe19..5c7949a 100644 --- a/media_platform/bilibili/core.py +++ b/media_platform/bilibili/core.py @@ -164,10 +164,8 @@ class BilibiliCrawler(AbstractCrawler): task_list = [] try: task_list = [self.get_video_info_task(aid=video_item.get("aid"), bvid="", semaphore=semaphore) for video_item in video_list] - except Exception as e : - utils.logger.warning( - f"[BilibiliCrawler.search] error in the task list. The video for this page will not be included. {e}" - ) + except Exception as e: + utils.logger.warning(f"[BilibiliCrawler.search] error in the task list. The video for this page will not be included. {e}") video_items = await asyncio.gather(*task_list) for video_item in video_items: if video_item: @@ -177,16 +175,19 @@ class BilibiliCrawler(AbstractCrawler): await self.get_bilibili_video(video_item, semaphore) page += 1 await self.batch_get_video_comments(video_id_list) - # 按照 START_DAY 至 END_DAY 按照每一天进行筛选，这样能够突破 1000 条视频的限制，最大程度爬取该关键词下的所有视频 + # 按照 START_DAY 至 END_DAY 按照每一天进行筛选，这样能够突破 1000 条视频的限制，最大程度爬取该关键词下每一天的所有视频 else: for day in pd.date_range(start=config.START_DAY, end=config.END_DAY, freq='D'): # 按照每一天进行爬取的时间戳参数 pubtime_begin_s, pubtime_end_s = await self.get_pubtime_datetime(start=day.strftime('%Y-%m-%d'), end=day.strftime('%Y-%m-%d')) page = 1 + #!该段 while 语句在发生异常时（通常情况下为当天数据为空时）会自动跳转到下一天，以实现最大程度爬取该关键词下当天的所有视频 + #!除了仅保留现在原有的 try, except Exception 语句外，不要再添加其他的异常处理！！！否则将使该段代码失效，使其仅能爬取当天一天数据而无法跳转到下一天 + #!除非将该段代码的逻辑进行重构以实现相同的功能，否则不要进行修改！！！ while (page - start_page + 1) * bili_limit_count <= config.CRAWLER_MAX_NOTES_COUNT: - # ! Catch any error if response return nothing, go to next day + #! Catch any error if response return nothing, go to next day try: - # ! Don't skip any page, to make sure gather all video in one day + #! Don't skip any page, to make sure gather all video in one day # if page < start_page: # utils.logger.info(f"[BilibiliCrawler.search] Skip page: {page}") # page += 1 @@ -205,11 +206,7 @@ class BilibiliCrawler(AbstractCrawler): video_list: List[Dict] = videos_res.get("result") semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM) - task_list = [] - try: - task_list = [self.get_video_info_task(aid=video_item.get("aid"), bvid="", semaphore=semaphore) for video_item in video_list] - finally: - pass + task_list = [self.get_video_info_task(aid=video_item.get("aid"), bvid="", semaphore=semaphore) for video_item in video_list] video_items = await asyncio.gather(*task_list) for video_item in video_items: if video_item: