mirror of
https://github.com/NanmiCoder/MediaCrawler.git
synced 2026-02-19 05:21:24 +08:00
157ddfb21b
Comprehensive translation of Chinese text to English across the entire codebase: - api/: FastAPI server documentation and logger messages - cache/: Cache abstraction layer comments and docstrings - database/: Database models and MongoDB store documentation - media_platform/: All platform crawlers (Bilibili, Douyin, Kuaishou, Tieba, Weibo, Xiaohongshu, Zhihu) - model/: Data model documentation - proxy/: Proxy pool and provider documentation - store/: Data storage layer comments - tools/: Utility functions and browser automation - test/: Test file documentation Preserved: Chinese disclaimer header (lines 10-18) for legal compliance 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
46 lines
1.6 KiB
Python
46 lines
1.6 KiB
Python
# -*- 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/help.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。
|
|
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
|
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
|
# 5. 不得用于任何非法或不当的用途。
|
|
#
|
|
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
|
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
|
|
|
|
|
# -*- coding: utf-8 -*-
|
|
# @Author : relakkes@gmail.com
|
|
# @Time : 2023/12/24 17:37
|
|
# @Desc :
|
|
|
|
from typing import Dict, List
|
|
|
|
|
|
def filter_search_result_card(card_list: List[Dict]) -> List[Dict]:
|
|
"""
|
|
Filter Weibo search results, only keep data with card_type of 9
|
|
:param card_list: List of card items from search results
|
|
:return: Filtered list of note items
|
|
"""
|
|
note_list: List[Dict] = []
|
|
for card_item in card_list:
|
|
if card_item.get("card_type") == 9:
|
|
note_list.append(card_item)
|
|
if len(card_item.get("card_group", [])) > 0:
|
|
card_group = card_item.get("card_group")
|
|
for card_group_item in card_group:
|
|
if card_group_item.get("card_type") == 9:
|
|
note_list.append(card_group_item)
|
|
|
|
return note_list
|