jiazhizhong/MediaCrawler
1
0
Fork 0
mirror of https://github.com/NanmiCoder/MediaCrawler.git synced 2026-06-09 03:17:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

chore: add copyright to every file

Browse Source
This commit is contained in:
程序员阿江(Relakkes)
2025-11-18 12:24:02 +08:00
parent 5288bddb42
commit ff8c92daad
137 changed files with 2569 additions and 810 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
media_platform/xhs/core.py
View File

@@ -1,3 +1,12 @@
# -*- coding: utf-8 -*-
# Copyright (c) 2025 relakkes@gmail.com
#
# This file is part of MediaCrawler project.
# Repository: https://github.com/NanmiCoder/MediaCrawler/blob/main/media_platform/xhs/core.py
# GitHub: https://github.com/NanmiCoder
# Licensed under NON-COMMERCIAL LEARNING LICENSE 1.1
#
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
# 1. 不得用于任何商业用途。
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
@@ -164,7 +173,7 @@ class XiaoHongShuCrawler(AbstractCrawler):
page += 1
utils.logger.info(f"[XiaoHongShuCrawler.search] Note details: {note_details}")
await self.batch_get_note_comments(note_ids, xsec_tokens)
# Sleep after each page navigation
await asyncio.sleep(config.CRAWLER_MAX_SLEEP_SEC)
utils.logger.info(f"[XiaoHongShuCrawler.search] Sleeping for {config.CRAWLER_MAX_SLEEP_SEC} seconds after page {page-1}")
@@ -296,11 +305,11 @@ class XiaoHongShuCrawler(AbstractCrawler):
raise Exception(f"[get_note_detail_async_task] Failed to get note detail, Id: {note_id}")
note_detail.update({"xsec_token": xsec_token, "xsec_source": xsec_source})
# Sleep after fetching note detail
await asyncio.sleep(config.CRAWLER_MAX_SLEEP_SEC)
utils.logger.info(f"[get_note_detail_async_task] Sleeping for {config.CRAWLER_MAX_SLEEP_SEC} seconds after fetching note {note_id}")
return note_detail
except DataFetchError as ex:
@@ -340,7 +349,7 @@ class XiaoHongShuCrawler(AbstractCrawler):
callback=xhs_store.batch_update_xhs_note_comments,
max_count=CRAWLER_MAX_COMMENTS_COUNT_SINGLENOTES,
)
# Sleep after fetching comments
await asyncio.sleep(crawl_interval)
utils.logger.info(f"[XiaoHongShuCrawler.get_comments] Sleeping for {crawl_interval} seconds after fetching comments for note {note_id}")