mirror of
https://github.com/NanmiCoder/MediaCrawler.git
synced 2026-09-20 03:17:55 +08:00
旧实现只覆盖 4 个平台,且把整个文件读进内存、无重试与完整性校验,
代码按平台复制粘贴了 4 份。本次用统一下载器替换:
- 新增 media_downloader/:流式写入、Range 续传、指数退避重试、大小校验、
路径穿越防护;B 站 DASH 音视频分轨下载后交由 ffmpeg 无损合流
- 新增 media_platform/<平台>/media.py:从平台原始响应提取媒体地址,
与下载器解耦;快手首次接入下载能力
- 开关:config.ENABLE_GET_MEDIA 与 --get_media,并打通 API/WebUI;
同时修正旧配置项 ENABLE_GET_MEIDAS 的拼写
- 落盘按帖子聚合:{SAVE_DATA_PATH 或 data}/{platform}/media/{内容ID}/
- B 站装好 ffmpeg 时走 DASH 最高画质,否则降级 mp4 直链(产物 video-durl.mp4,
避免低清文件阻塞后续的高清路径)
- 删除 4 个 *_store_media.py、AbstractStoreImage/Video 及各 client 的媒体 GET 方法
媒体下载失败只记录日志,不中断爬取主流程。
167 lines
5.4 KiB
Python
167 lines
5.4 KiB
Python
# -*- coding: utf-8 -*-
|
|
import pytest
|
|
import config
|
|
from unittest.mock import AsyncMock, patch
|
|
from fastapi.testclient import TestClient
|
|
from cmd_arg import parse_cmd
|
|
from api.schemas import CrawlerStartRequest, PlatformEnum, LoginTypeEnum, CrawlerTypeEnum
|
|
from api.services.crawler_manager import CrawlerManager
|
|
from api.main import app
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_cmd_arg_crawler_max_notes_count():
|
|
# Store original values
|
|
orig_notes = config.CRAWLER_MAX_NOTES_COUNT
|
|
orig_comments = config.CRAWLER_MAX_COMMENTS_COUNT_SINGLENOTES
|
|
|
|
try:
|
|
await parse_cmd([
|
|
"--platform", "xhs",
|
|
"--crawler_max_notes_count", "42",
|
|
"--max_comments_count_singlenotes", "24"
|
|
])
|
|
assert config.CRAWLER_MAX_NOTES_COUNT == 42
|
|
assert config.CRAWLER_MAX_COMMENTS_COUNT_SINGLENOTES == 24
|
|
finally:
|
|
config.CRAWLER_MAX_NOTES_COUNT = orig_notes
|
|
config.CRAWLER_MAX_COMMENTS_COUNT_SINGLENOTES = orig_comments
|
|
|
|
def test_crawler_manager_build_command():
|
|
cm = CrawlerManager()
|
|
|
|
# 1. No max limits passed in API request
|
|
req1 = CrawlerStartRequest(
|
|
platform=PlatformEnum.XHS,
|
|
login_type=LoginTypeEnum.QRCODE,
|
|
crawler_type=CrawlerTypeEnum.SEARCH,
|
|
keywords="test",
|
|
max_notes_count=None,
|
|
max_comments_count=None
|
|
)
|
|
cmd1 = cm._build_command(req1)
|
|
# Check that the custom arguments are NOT present
|
|
assert "--crawler_max_notes_count" not in cmd1
|
|
assert "--max_comments_count_singlenotes" not in cmd1
|
|
|
|
# 2. Both limits passed in API request
|
|
req2 = CrawlerStartRequest(
|
|
platform=PlatformEnum.XHS,
|
|
login_type=LoginTypeEnum.QRCODE,
|
|
crawler_type=CrawlerTypeEnum.SEARCH,
|
|
keywords="test",
|
|
max_notes_count=50,
|
|
max_comments_count=5
|
|
)
|
|
cmd2 = cm._build_command(req2)
|
|
# Check that they are correctly added
|
|
assert "--crawler_max_notes_count" in cmd2
|
|
idx_notes = cmd2.index("--crawler_max_notes_count")
|
|
assert cmd2[idx_notes + 1] == "50"
|
|
|
|
assert "--max_comments_count_singlenotes" in cmd2
|
|
idx_comments = cmd2.index("--max_comments_count_singlenotes")
|
|
assert cmd2[idx_comments + 1] == "5"
|
|
|
|
|
|
def test_crawler_manager_passes_media_switch():
|
|
cm = CrawlerManager()
|
|
|
|
req_off = CrawlerStartRequest(
|
|
platform=PlatformEnum.XHS,
|
|
login_type=LoginTypeEnum.QRCODE,
|
|
crawler_type=CrawlerTypeEnum.DETAIL,
|
|
specified_ids="note-1",
|
|
)
|
|
cmd_off = cm._build_command(req_off)
|
|
idx_off = cmd_off.index("--get_media")
|
|
assert cmd_off[idx_off + 1] == "false"
|
|
|
|
req_on = CrawlerStartRequest(
|
|
platform=PlatformEnum.XHS,
|
|
login_type=LoginTypeEnum.QRCODE,
|
|
crawler_type=CrawlerTypeEnum.DETAIL,
|
|
specified_ids="note-1",
|
|
enable_media=True,
|
|
)
|
|
cmd_on = cm._build_command(req_on)
|
|
idx_on = cmd_on.index("--get_media")
|
|
assert cmd_on[idx_on + 1] == "true"
|
|
|
|
|
|
def test_api_schema_exposes_media_switch_default_off():
|
|
assert CrawlerStartRequest(platform=PlatformEnum.XHS).enable_media is False
|
|
|
|
def test_api_start_crawler_with_limits():
|
|
client = TestClient(app)
|
|
|
|
with patch("api.routers.crawler.crawler_manager.start", new_callable=AsyncMock) as mock_start:
|
|
mock_start.return_value = True
|
|
|
|
# Test case 1: with limits
|
|
response = client.post("/api/crawler/start", json={
|
|
"platform": "xhs",
|
|
"login_type": "qrcode",
|
|
"crawler_type": "search",
|
|
"keywords": "test",
|
|
"max_notes_count": 50,
|
|
"max_comments_count": 5
|
|
})
|
|
|
|
assert response.status_code == 200
|
|
assert response.json() == {"status": "ok", "message": "Crawler started successfully"}
|
|
|
|
mock_start.assert_called_once()
|
|
called_request = mock_start.call_args[0][0]
|
|
assert called_request.platform == PlatformEnum.XHS
|
|
assert called_request.max_notes_count == 50
|
|
assert called_request.max_comments_count == 5
|
|
|
|
def test_api_start_crawler_without_limits():
|
|
client = TestClient(app)
|
|
|
|
with patch("api.routers.crawler.crawler_manager.start", new_callable=AsyncMock) as mock_start:
|
|
mock_start.return_value = True
|
|
|
|
# Test case 2: without limits
|
|
response = client.post("/api/crawler/start", json={
|
|
"platform": "xhs",
|
|
"login_type": "qrcode",
|
|
"crawler_type": "search",
|
|
"keywords": "test"
|
|
})
|
|
|
|
assert response.status_code == 200
|
|
mock_start.assert_called_once()
|
|
called_request = mock_start.call_args[0][0]
|
|
assert called_request.platform == PlatformEnum.XHS
|
|
assert called_request.max_notes_count is None
|
|
assert called_request.max_comments_count is None
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("field_name", "value"),
|
|
[
|
|
("max_notes_count", 0),
|
|
("max_notes_count", -1),
|
|
("max_notes_count", 10001),
|
|
("max_comments_count", 0),
|
|
("max_comments_count", -1),
|
|
("max_comments_count", 10001),
|
|
],
|
|
)
|
|
def test_api_rejects_invalid_limits(field_name, value):
|
|
client = TestClient(app)
|
|
payload = {
|
|
"platform": "xhs",
|
|
"login_type": "qrcode",
|
|
"crawler_type": "search",
|
|
"keywords": "test",
|
|
field_name: value,
|
|
}
|
|
|
|
with patch("api.routers.crawler.crawler_manager.start", new_callable=AsyncMock) as mock_start:
|
|
response = client.post("/api/crawler/start", json=payload)
|
|
|
|
assert response.status_code == 422
|
|
mock_start.assert_not_called()
|