| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172 |
- """原生整段视频提取离线测试：注入假 http_post 返回 segments，断言段卡 + 内容。"""
- from __future__ import annotations
- import json
- from creation_knowledge.config import PgConfig, Settings
- from creation_knowledge.integrations.video_extract import extract_video
- from creation_knowledge.models import Post
- SEGMENTS = json.dumps({
- "video_title": "AI视频教程", "overall": "教 AI 出片",
- "segments": [
- {"start": "00:00", "end": "00:18", "title": "问题与简介",
- "knowledge_types": ["what"], "what": "常见翻车", "why": None, "how": None},
- {"start": "00:19", "end": "00:48", "title": "去噪原理",
- "knowledge_types": ["why"], "what": None, "why": "噪声去噪类似雕刻", "how": None},
- ]}, ensure_ascii=False)
- class _Resp:
- def __init__(self, content): self._c = content
- def raise_for_status(self): return None
- def json(self): return {"choices": [{"message": {"content": self._c}}]}
- def _settings() -> Settings:
- return Settings(
- pg=PgConfig(host="h", port=5432, user="u", password="p", database="d"),
- crawler_base_url="x", crawler_key="", crawler_timeout=30,
- video_model="google/gemini-3-flash-preview", gemini_api_key="",
- openrouter_base_url="https://openrouter.ai/api/v1", openrouter_api_key="k",
- llm_model="m", knowhub_api="x", ingest_enabled=False, max_cards=12,
- frames_dir="runtime/frames", douyin_ratio="540p")
- def _fake_post():
- captured = {}
- def post(url, headers=None, json=None, timeout=None):
- captured["url"] = url
- captured["json"] = json
- return _Resp(SEGMENTS)
- return post, captured
- def test_video_extract_makes_segment_cards(tmp_path):
- vf = tmp_path / "v.mp4"
- vf.write_bytes(b"\x00\x00\x00\x18ftypmp42fakevideobytes")
- fake, captured = _fake_post()
- post = Post(id="dy_1", platform="douyin", url="u", content_id="1",
- content_type="video", video_urls=["http://x/play?ratio=default"])
- out = extract_video(post, settings=_settings(), http_post=fake, video_path=str(vf))
- # ExtractedContent.cards = 每段一条内容
- assert len(out.cards) == 2
- assert out.cards[0].index == 1 and "问题" in out.cards[0].content
- assert out.is_empty is False and out.text # overall 进 text
- # post.cards = 段卡，带 start/end（秒）
- assert len(post.cards) == 2
- assert post.cards[0].kind == "segment"
- assert post.cards[0].start == 0.0 and post.cards[1].start == 19.0
- assert post.cards[1].end == 48.0
- assert post.cards[0].url is None # 段卡默认无图
- # 请求体含 base64 video_url
- parts = captured["json"]["messages"][0]["content"]
- assert any(p["type"] == "video_url"
- and p["video_url"]["url"].startswith("data:video/mp4;base64,")
- for p in parts)
|
