jiazhizhong/MediaCrawler
1
0
Fork 0
mirror of https://github.com/NanmiCoder/MediaCrawler.git synced 2026-06-06 18:07:26 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: #107

Browse Source
This commit is contained in:
Relakkes
2024-01-03 23:08:30 +08:00
parent 38d6f10bf0
commit 80ecc53cd3
2 changed files with 3 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
media_platform/bilibili/core.py
View File

@@ -147,32 +147,12 @@ class BilibiliCrawler(AbstractCrawler):
async with semaphore:
try:
utils.logger.info(f"[BilibiliCrawler.get_comments] begin get video_id: {video_id} comments ...")
# Read keyword and quantity from config
keywords = config.COMMENT_KEYWORDS
max_comments = config.MAX_COMMENTS_PER_POST
# Download comments
all_comments = await self.bili_client.get_video_all_comments(
await self.bili_client.get_video_all_comments(
video_id=video_id,
crawl_interval=random.random(),
callback=bilibili.batch_update_bilibili_video_comments
)
# Filter comments by keyword
if keywords:
filtered_comments = [
comment for comment in all_comments if
any(keyword in comment["content"]["message"] for keyword in keywords)
]
else:
filtered_comments = all_comments
# Limit the number of comments
if max_comments > 0:
filtered_comments = filtered_comments[:max_comments]
# Update bilibili video comments
await bilibili.batch_update_bilibili_video_comments(video_id, filtered_comments)
except DataFetchError as ex:
utils.logger.error(f"[BilibiliCrawler.get_comments] get video_id: {video_id} comment error: {ex}")
except Exception as e: