jiazhizhong/MediaCrawler
1
0
Fork 0
mirror of https://github.com/NanmiCoder/MediaCrawler.git synced 2026-06-05 17:37:35 +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

23
media_platform/weibo/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/weibo/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。
@@ -86,7 +95,7 @@ class WeiboCrawler(AbstractCrawler):
await self.context_page.goto(self.index_url)
await asyncio.sleep(2)
# Create a client to interact with the xiaohongshu website.
self.wb_client = await self.create_weibo_client(httpx_proxy_format)
if not await self.wb_client.pong():
@@ -169,11 +178,11 @@ class WeiboCrawler(AbstractCrawler):
await self.get_note_images(mblog)
page += 1
# Sleep after page navigation
await asyncio.sleep(config.CRAWLER_MAX_SLEEP_SEC)
utils.logger.info(f"[WeiboCrawler.search] Sleeping for {config.CRAWLER_MAX_SLEEP_SEC} seconds after page {page-1}")
await self.batch_get_notes_comments(note_id_list)
async def get_specified_notes(self):
@@ -199,11 +208,11 @@ class WeiboCrawler(AbstractCrawler):
async with semaphore:
try:
result = await self.wb_client.get_note_info_by_id(note_id)
# Sleep after fetching note details
await asyncio.sleep(config.CRAWLER_MAX_SLEEP_SEC)
utils.logger.info(f"[WeiboCrawler.get_note_info_task] Sleeping for {config.CRAWLER_MAX_SLEEP_SEC} seconds after fetching note details {note_id}")
return result
except DataFetchError as ex:
utils.logger.error(f"[WeiboCrawler.get_note_info_task] Get note detail error: {ex}")
@@ -240,11 +249,11 @@ class WeiboCrawler(AbstractCrawler):
async with semaphore:
try:
utils.logger.info(f"[WeiboCrawler.get_note_comments] begin get note_id: {note_id} comments ...")
# Sleep before fetching comments
await asyncio.sleep(config.CRAWLER_MAX_SLEEP_SEC)
utils.logger.info(f"[WeiboCrawler.get_note_comments] Sleeping for {config.CRAWLER_MAX_SLEEP_SEC} seconds before fetching comments for note {note_id}")
await self.wb_client.get_note_all_comments(
note_id=note_id,
crawl_interval=config.CRAWLER_MAX_SLEEP_SEC, # Use fixed interval instead of random