mirror of
https://github.com/NanmiCoder/MediaCrawler.git
synced 2026-02-06 23:21:33 +08:00
Features: - Excel export with formatted multi-sheet workbooks (Contents, Comments, Creators) - Professional styling: blue headers, auto-width columns, borders, text wrapping - Smart export: empty sheets automatically removed - Support for all platforms (xhs, dy, ks, bili, wb, tieba, zhihu) Testing: - Added pytest framework with asyncio support - Unit tests for Excel store functionality - Unit tests for store factory pattern - Shared fixtures for test data - Test coverage for edge cases Documentation: - Comprehensive Excel export guide (docs/excel_export_guide.md) - Updated README.md and README_en.md with Excel examples - Updated config comments to include excel option Dependencies: - Added openpyxl>=3.1.2 for Excel support - Added pytest>=7.4.0 and pytest-asyncio>=0.21.0 for testing This contribution adds immediate value for users who need data analysis capabilities and establishes a testing foundation for future development.
46 lines
1.1 KiB
TOML
46 lines
1.1 KiB
TOML
[project]
|
|
name = "mediacrawler"
|
|
author = "程序员阿江-Relakkes <relakkes@gmail.com>"
|
|
version = "0.1.0"
|
|
description = "A social media crawler project, support Xiaohongshu, Weibo, Zhihu, Bilibili, Douyin, BaiduTieBa etc."
|
|
readme = "README.md"
|
|
requires-python = ">=3.11"
|
|
dependencies = [
|
|
"aiofiles~=23.2.1",
|
|
"aiomysql==0.2.0",
|
|
"aiosqlite>=0.21.0",
|
|
"alembic>=1.16.5",
|
|
"asyncmy>=0.2.10",
|
|
"cryptography>=45.0.7",
|
|
"fastapi==0.110.2",
|
|
"httpx==0.28.1",
|
|
"jieba==0.42.1",
|
|
"matplotlib==3.9.0",
|
|
"motor>=3.3.0",
|
|
"opencv-python>=4.11.0.86",
|
|
"pandas==2.2.3",
|
|
"parsel==1.9.1",
|
|
"pillow==9.5.0",
|
|
"playwright==1.45.0",
|
|
"pydantic==2.5.2",
|
|
"pyexecjs==1.5.1",
|
|
"pyhumps>=3.8.0",
|
|
"python-dotenv==1.0.1",
|
|
"redis~=4.6.0",
|
|
"requests==2.32.3",
|
|
"sqlalchemy>=2.0.43",
|
|
"tenacity==8.2.2",
|
|
"typer>=0.12.3",
|
|
"uvicorn==0.29.0",
|
|
"wordcloud==1.9.3",
|
|
"xhshow>=0.1.3",
|
|
"pre-commit>=3.5.0",
|
|
"openpyxl>=3.1.2",
|
|
"pytest>=7.4.0",
|
|
"pytest-asyncio>=0.21.0",
|
|
]
|
|
|
|
[[tool.uv.index]]
|
|
url = "https://pypi.tuna.tsinghua.edu.cn/simple"
|
|
default = true
|