urieljareth
621bbc5f5c
Scraper de canales de YouTube hacia notas Markdown para base de conocimiento (Obsidian-ready), con plataforma web local. Engine + CLI (Workstream A): - Modular pipeline: discover/extract/parse/chapters/render/store + ratelimit - SQLite store con migración idempotente: FTS5 (transcript search), columnas de metadata enriquecida, tablas cookies_meta y scrape_jobs - Módulos: segments, cookies (Netscape vault), export (json/csv/srt/html), analysis (word freq/timeline/wordcloud), monitor (watch loop), pipeline - CLI Click group: search, export, audio, channels, watch, analyze, re-render - Fix del bug de scoping de cookies en cli.py Webapp local (Workstream B): - FastAPI backend: dashboard, channels, videos facetado, transcript, search FTS, analysis, scrape jobs con SSE, cookies drag-and-drop, exports, folders (abrir en OS), tools (re-render, formato) - SPA no-build (Alpine.js + Tailwind + Chart.js por CDN): 9 vistas, tema dark command-center con acento rojo→rosa, cookie vault drag-drop, consola de scrapeo con progreso live vía SSE Launcher + subagentes (Workstream C): - start-server.bat / stop-server.bat con auto port-scan + browser open - .opencode/agent/webapp-builder.md + .opencode/goals/webapp-build.md Tests: 38 pytest verdes. Sin funcionalidad de IA (enfoque data-mining).
59 lines
1.8 KiB
Python
59 lines
1.8 KiB
Python
from __future__ import annotations
|
|
|
|
from yt_scraper.chapters import align_chapters, chapters_from_info, Chapter, Section
|
|
from yt_scraper.parse import Segment
|
|
|
|
|
|
def test_align_no_chapters():
|
|
segs = [Segment(0.0, 1.0, "a"), Segment(1.0, 2.0, "b")]
|
|
sections = align_chapters(segs, [])
|
|
assert len(sections) == 1
|
|
assert sections[0].title == "Transcripcion"
|
|
assert len(sections[0].segments) == 2
|
|
|
|
|
|
def test_align_with_chapters():
|
|
segs = [
|
|
Segment(0.0, 1.0, "intro"),
|
|
Segment(5.0, 6.0, "mid"),
|
|
Segment(20.0, 21.0, "end"),
|
|
]
|
|
chapters = [
|
|
Chapter(title="Intro", start_time=0.0, end_time=10.0),
|
|
Chapter(title="Desarrollo", start_time=10.0, end_time=30.0),
|
|
]
|
|
sections = align_chapters(segs, chapters)
|
|
assert len(sections) == 2
|
|
assert sections[0].title == "Intro"
|
|
assert len(sections[0].segments) == 2
|
|
assert sections[1].title == "Desarrollo"
|
|
assert len(sections[1].segments) == 1
|
|
assert sections[1].segments[0].text == "end"
|
|
|
|
|
|
def test_align_pre_chapter_segments():
|
|
segs = [Segment(0.0, 1.0, "antes")]
|
|
chapters = [Chapter(title="Cap 1", start_time=5.0, end_time=10.0)]
|
|
sections = align_chapters(segs, chapters)
|
|
assert len(sections) == 2
|
|
assert sections[0].title == "Inicio"
|
|
assert sections[0].segments[0].text == "antes"
|
|
|
|
|
|
def test_chapters_from_info():
|
|
info = {
|
|
"chapters": [
|
|
{"title": "Cap 1", "start_time": 0, "end_time": 60},
|
|
{"title": "Cap 2", "start_time": 60, "end_time": 120},
|
|
]
|
|
}
|
|
chapters = chapters_from_info(info)
|
|
assert len(chapters) == 2
|
|
assert chapters[0].title == "Cap 1"
|
|
assert chapters[1].start_time == 60.0
|
|
|
|
|
|
def test_chapters_from_info_empty():
|
|
assert chapters_from_info({}) == []
|
|
assert chapters_from_info({"chapters": []}) == []
|