wip: estado de trabajo pendiente antes de la vista grid (suite 230 verde)
This commit is contained in:
@@ -1 +1,44 @@
|
||||
{"0": "Webapp Frontend (JS)", "1": "Transcript Extraction & Parsing", "2": "Config & Discovery Pipeline", "3": "Store & Export Layer", "4": "CLI Command Layer", "5": "Platform Design & Proposals", "6": "Segments Search & Backfill", "7": "Store Platform Tests", "8": "Content Analysis", "9": "README & Config Docs", "10": "Server Start Script", "11": "Package Manifest", "12": "Server Stop Script", "13": "Webapp Package Init"}
|
||||
{
|
||||
"0": "Webapp Frontend (JS)",
|
||||
"1": "Transcript Extraction & Parsing",
|
||||
"2": "Config & Discovery Pipeline",
|
||||
"3": "Store & Export Layer",
|
||||
"4": "CLI Command Layer",
|
||||
"5": "Platform Design & Proposals",
|
||||
"6": "Segments Search & Backfill",
|
||||
"7": "Store Platform Tests",
|
||||
"8": "Content Analysis",
|
||||
"9": "README & Config Docs",
|
||||
"10": "Server Start Script",
|
||||
"11": "Package Manifest",
|
||||
"12": "Server Stop Script",
|
||||
"13": "Webapp Package Init",
|
||||
"14": "test_extract.py",
|
||||
"15": "Auditoría · Cómo la extensión obtiene la transcripción / información de vídeos de YouTube",
|
||||
"16": "api",
|
||||
"17": "pipeline.py",
|
||||
"18": "test_blocked_videos.py",
|
||||
"19": "config.py",
|
||||
"20": "setView",
|
||||
"21": "Discovery-Only Scrape Design",
|
||||
"22": "renderDashboardCharts",
|
||||
"23": "Global Constraints",
|
||||
"24": "Config",
|
||||
"25": "init",
|
||||
"26": "render.py",
|
||||
"27": "loadChannels",
|
||||
"28": "jobs.py",
|
||||
"29": "Segment",
|
||||
"30": "cookies.py",
|
||||
"31": "discover.py",
|
||||
"32": "export.py",
|
||||
"33": "pipeline.py",
|
||||
"34": "_channel_targets",
|
||||
"35": "test_features.py",
|
||||
"36": "VideoRow",
|
||||
"37": "test_since_filter.py",
|
||||
"38": ".reset_videos",
|
||||
"39": "._connect",
|
||||
"40": "re_render_cmd",
|
||||
"41": "handleFiles"
|
||||
}
|
||||
|
||||
@@ -1 +1 @@
|
||||
D:\yt-channel-scraper
|
||||
.
|
||||
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"0": "Webapp Frontend (JS)",
|
||||
"1": "Transcript Extraction & Parsing",
|
||||
"2": "Config & Discovery Pipeline",
|
||||
"3": "Store & Export Layer",
|
||||
"4": "CLI Command Layer",
|
||||
"5": "Platform Design & Proposals",
|
||||
"6": "Segments Search & Backfill",
|
||||
"7": "Store Platform Tests",
|
||||
"8": "Content Analysis",
|
||||
"9": "README & Config Docs",
|
||||
"10": "Server Start Script",
|
||||
"11": "Package Manifest",
|
||||
"12": "Server Stop Script",
|
||||
"13": "Webapp Package Init",
|
||||
"14": "test_extract.py",
|
||||
"15": "Auditoría · Cómo la extensión obtiene la transcripción / información de vídeos de YouTube",
|
||||
"16": "api",
|
||||
"17": "pipeline.py",
|
||||
"18": "render.py",
|
||||
"19": "config.py",
|
||||
"20": "setView",
|
||||
"21": "Discovery-Only Scrape Design",
|
||||
"22": "renderDashboardCharts",
|
||||
"23": "Global Constraints",
|
||||
"24": "loadJobs"
|
||||
}
|
||||
@@ -0,0 +1,182 @@
|
||||
# Graph Report - yt-channel-scraper (2026-07-31)
|
||||
|
||||
## Corpus Check
|
||||
- 45 files · ~46,603 words
|
||||
- Verdict: corpus is large enough that graph structure adds value.
|
||||
|
||||
## Summary
|
||||
- 612 nodes · 1392 edges · 25 communities (22 shown, 3 thin omitted)
|
||||
- Extraction: 91% EXTRACTED · 9% INFERRED · 0% AMBIGUOUS · INFERRED: 129 edges (avg confidence: 0.78)
|
||||
- Token cost: 0 input · 0 output
|
||||
|
||||
## Graph Freshness
|
||||
- Built from commit: `06497299`
|
||||
- Run `git rev-parse HEAD` and compare to check if the graph is stale.
|
||||
- Run `graphify update .` after code changes (no API cost).
|
||||
|
||||
## Community Hubs (Navigation)
|
||||
- Webapp Frontend (JS)
|
||||
- Transcript Extraction & Parsing
|
||||
- Config & Discovery Pipeline
|
||||
- Store & Export Layer
|
||||
- CLI Command Layer
|
||||
- Platform Design & Proposals
|
||||
- Segments Search & Backfill
|
||||
- Store Platform Tests
|
||||
- Content Analysis
|
||||
- README & Config Docs
|
||||
- Server Start Script
|
||||
- Package Manifest
|
||||
- Server Stop Script
|
||||
- test_extract.py
|
||||
- Auditoría · Cómo la extensión obtiene la transcripción / información de vídeos de YouTube
|
||||
- api
|
||||
- pipeline.py
|
||||
- render.py
|
||||
- config.py
|
||||
- setView
|
||||
- Discovery-Only Scrape Design
|
||||
- renderDashboardCharts
|
||||
- Global Constraints
|
||||
- loadJobs
|
||||
|
||||
## God Nodes (most connected - your core abstractions)
|
||||
1. `Store` - 96 edges
|
||||
2. `api()` - 36 edges
|
||||
3. `toast()` - 36 edges
|
||||
4. `Config` - 34 edges
|
||||
5. `Segment` - 32 edges
|
||||
6. `JobManager` - 26 edges
|
||||
7. `VideoRef` - 25 edges
|
||||
8. `discover_incremental()` - 21 edges
|
||||
9. `process_video()` - 19 edges
|
||||
10. `subscribeJob()` - 18 edges
|
||||
|
||||
## Surprising Connections (you probably didn't know these)
|
||||
- `test_config_languages_defaults_to_dict()` --calls--> `Config` [INFERRED]
|
||||
tests/test_extract.py → src/yt_scraper/config.py
|
||||
- `test_config_prefer_manual_defaults_true()` --calls--> `Config` [INFERRED]
|
||||
tests/test_extract.py → src/yt_scraper/config.py
|
||||
- `test_dashboard_aggregates()` --calls--> `Segment` [INFERRED]
|
||||
tests/test_store_platform.py → src/yt_scraper/parse.py
|
||||
- `test_store_and_search_segments()` --calls--> `Segment` [INFERRED]
|
||||
tests/test_store_platform.py → src/yt_scraper/parse.py
|
||||
- `test_store_segments_overwrites()` --calls--> `Segment` [INFERRED]
|
||||
tests/test_store_platform.py → src/yt_scraper/parse.py
|
||||
|
||||
## Import Cycles
|
||||
- None detected.
|
||||
|
||||
## Hyperedges (group relationships)
|
||||
- **Workstream B webapp stack (FastAPI + Alpine SPA + subagent)** — opencode_agent_webapp_builder, opencode_goals_webapp_build, src_yt_scraper_webapp_static_index, docs_superpowers_specs_2026_07_26_platform_design_dark_command_center, docs_superpowers_specs_2026_07_26_platform_design_sse_job_runner [EXTRACTED 0.95]
|
||||
- **FTS5 transcript search flow (proposal -> spec -> SPA view)** — opportunities_search_fts5, docs_superpowers_specs_2026_07_26_platform_design_transcript_fts5, src_yt_scraper_webapp_static_index [INFERRED 0.85]
|
||||
- **Cookie auth chain (vault -> resolve_active_path -> scrape job)** — docs_superpowers_specs_2026_07_26_platform_design_cookie_vault_ux, docs_superpowers_specs_2026_07_26_platform_design_sse_job_runner, docs_superpowers_specs_2026_07_26_platform_design_cookies_bug_fix, src_yt_scraper_webapp_static_index [INFERRED 0.85]
|
||||
|
||||
## Communities (25 total, 3 thin omitted)
|
||||
|
||||
### Community 0 - "Webapp Frontend (JS)"
|
||||
Cohesion: 0.07
|
||||
Nodes (20): _armAutoHide(), closeClip(), closeJobWidget(), closeSidebar(), closeStats(), _disarmAutoHide(), downloadClipTxt(), downloadFile() (+12 more)
|
||||
|
||||
### Community 1 - "Transcript Extraction & Parsing"
|
||||
Cohesion: 0.16
|
||||
Nodes (17): merge_adjacent(), parse_auto_dump(), parse_json3(), parse_vtt(), Segment, _vtt_ts_to_seconds(), store(), test_export_json_csv() (+9 more)
|
||||
|
||||
### Community 2 - "Config & Discovery Pipeline"
|
||||
Cohesion: 0.08
|
||||
Nodes (34): Config, Path, deep_channel_avatar(), Robust avatar recovery via non-flat yt-dlp call on the channel root URL., _extract_handle(), _keep_ref(), Same shorts/live rules the store was populated under — see jobs._keep_ref., Discover + process pending videos for a channel, optionally on an interval. (+26 more)
|
||||
|
||||
### Community 3 - "Store & Export Layer"
|
||||
Cohesion: 0.06
|
||||
Nodes (43): Connection, Cursor, Environment, Row, auto_import_dir(), cookies_dir(), delete(), import_file() (+35 more)
|
||||
|
||||
### Community 4 - "CLI Command Layer"
|
||||
Cohesion: 0.08
|
||||
Nodes (37): analyze_cmd(), _apply_filters(), audio_cmd(), _channel_targets(), channels_add(), cli(), export_cmd(), _extract_handle() (+29 more)
|
||||
|
||||
### Community 5 - "Platform Design & Proposals"
|
||||
Cohesion: 0.12
|
||||
Nodes (20): Platform Implementation Plan, Platform Design Spec, Cookie drag-and-drop vault UX, cli.py cookies scope bug fix, Design language: dark data command center, Architecture: Monorepo in-package webapp (Approach A), Scope rule: No AI features, Single-threaded scrape job runner + SSE event bus (+12 more)
|
||||
|
||||
### Community 6 - "Segments Search & Backfill"
|
||||
Cohesion: 0.10
|
||||
Nodes (26): APIRouter, FastAPI, cache_thumbnail(), Thumbnail URL for a video: stored URL, else the canonical YouTube one derived fr, Download + cache a video's thumbnail to <thumbnails_dir>/<video_id>.jpg. Returns, thumbnail_url_for(), backfill_from_markdown(), parse_markdown() (+18 more)
|
||||
|
||||
### Community 7 - "Store Platform Tests"
|
||||
Cohesion: 0.06
|
||||
Nodes (44): Collection, _channel_root_url(), discover_channel(), discover_incremental(), _flatten_entries(), IncrementalDiscovery, _pick_channel_avatar(), Any (+36 more)
|
||||
|
||||
### Community 8 - "Content Analysis"
|
||||
Cohesion: 0.27
|
||||
Nodes (10): _iter_texts(), Path, Return [(YYYY-MM, count)] of months where `term` appears in transcripts., render_timeline_chart(), render_top_words_chart(), render_wordcloud(), term_timeline(), _tokenize() (+2 more)
|
||||
|
||||
### Community 10 - "Server Start Script"
|
||||
Cohesion: 0.38
|
||||
Nodes (3): Open-Browser(), Out-Line(), Show-State()
|
||||
|
||||
### Community 14 - "test_extract.py"
|
||||
Cohesion: 0.08
|
||||
Nodes (46): Response, parse_languages(), Any, Normalise legacy list / new dict / None into ``{lang: mode}``., _coerce_languages(), _download_subtitle(), extract_video(), _normalize_lang() (+38 more)
|
||||
|
||||
### Community 15 - "Auditoría · Cómo la extensión obtiene la transcripción / información de vídeos de YouTube"
|
||||
Cohesion: 0.05
|
||||
Nodes (41): Arquitectura, Comandos, Cookies, Cualquier petición HTTP a CDNs de YouTube va por `_yt_http.yt_get()`, Documentos de referencia, El Markdown es fuente de datos, no solo salida, Frontend, Idiomas: dict por-idioma con compatibilidad legacy (+33 more)
|
||||
|
||||
### Community 16 - "api"
|
||||
Cohesion: 0.14
|
||||
Nodes (34): activateCookie(), addChannel(), api(), checkAudio(), copyClip(), copyText(), downloadAudio(), downloadAudioOne() (+26 more)
|
||||
|
||||
### Community 17 - "pipeline.py"
|
||||
Cohesion: 0.24
|
||||
Nodes (15): align_chapters(), Chapter, chapters_from_info(), Section, _normalize_date(), process_video(), Regenerate .md for done videos that have stored segments. Returns count re-rende, Extract + parse + store + render a single video. Returns final status string. (+7 more)
|
||||
|
||||
### Community 18 - "render.py"
|
||||
Cohesion: 0.20
|
||||
Nodes (16): build_filename_stem(), format_timestamp(), _make_env(), Path, quote_yaml(), render_markdown(), to_json(), test_build_filename_stem() (+8 more)
|
||||
|
||||
### Community 19 - "config.py"
|
||||
Cohesion: 0.27
|
||||
Nodes (13): _build_config(), DelayConfig, load_config(), Incremental channel sync — how far back a routine re-scan looks. The /video, SyncConfig, YtDlpConfig, Tests for the YAML config loader. Focuses on the ``languages`` and ``prefer_man, test_load_legacy_languages_list() (+5 more)
|
||||
|
||||
### Community 20 - "setView"
|
||||
Cohesion: 0.18
|
||||
Nodes (14): checkHealth(), cycleSort(), destroyCharts(), hydrateURL(), init(), loadFolders(), loadFormat(), loadSearch() (+6 more)
|
||||
|
||||
### Community 21 - "Discovery-Only Scrape Design"
|
||||
Cohesion: 0.22
|
||||
Nodes (8): Architecture, Discovery-Only Scrape Design, Error Handling, Existing Context, Goal, Persistence and Results, Testing, UI
|
||||
|
||||
### Community 22 - "renderDashboardCharts"
|
||||
Cohesion: 0.36
|
||||
Nodes (9): axisOpts(), barOpts(), fmtMonth(), lineOpts(), loadAnalysis(), makeChart(), renderDashboardCharts(), renderTimelineChart() (+1 more)
|
||||
|
||||
### Community 23 - "Global Constraints"
|
||||
Cohesion: 0.25
|
||||
Nodes (7): Discovery-Only Scrape Implementation Plan, Global Constraints, Task 1: Make catalog insertion counts accurate, Task 2: Add discovery-only job execution, Task 3: Expose the discovery mode through the API, Task 4: Add one-channel and all-channel UI controls, Task 5: Final verification and review
|
||||
|
||||
### Community 24 - "loadJobs"
|
||||
Cohesion: 0.29
|
||||
Nodes (7): cancelScrape(), clearJobHistory(), closeStream(), deleteJob(), jobActionLabel(), jobIsTerminal(), loadJobs()
|
||||
|
||||
## Knowledge Gaps
|
||||
- **57 isolated node(s):** `yt-channel-scraper`, `Qué es esto`, `Comandos`, `Orientación antes de leer código`, `Tres superficies, un solo pipeline` (+52 more)
|
||||
These have ≤1 connection - possible missing edges or undocumented components.
|
||||
- **3 thin communities (<3 nodes) omitted from report** — run `graphify query` to explore isolated nodes.
|
||||
|
||||
## Suggested Questions
|
||||
_Questions this graph is uniquely positioned to answer:_
|
||||
|
||||
- **Why does `Store` connect `Store & Export Layer` to `Transcript Extraction & Parsing`, `Config & Discovery Pipeline`, `CLI Command Layer`, `Segments Search & Backfill`, `Store Platform Tests`, `Content Analysis`, `pipeline.py`?**
|
||||
_High betweenness centrality (0.146) - this node is a cross-community bridge._
|
||||
- **Why does `Segment` connect `Transcript Extraction & Parsing` to `CLI Command Layer`, `Segments Search & Backfill`, `Store Platform Tests`, `test_extract.py`, `pipeline.py`, `render.py`?**
|
||||
_High betweenness centrality (0.035) - this node is a cross-community bridge._
|
||||
- **Why does `VideoRef` connect `Store Platform Tests` to `Transcript Extraction & Parsing`, `Config & Discovery Pipeline`, `Store & Export Layer`, `CLI Command Layer`?**
|
||||
_High betweenness centrality (0.027) - this node is a cross-community bridge._
|
||||
- **Are the 12 inferred relationships involving `Store` (e.g. with `ParsedMarkdown` and `store()`) actually correct?**
|
||||
_`Store` has 12 INFERRED edges - model-reasoned connections that need verification._
|
||||
- **Are the 9 inferred relationships involving `Config` (e.g. with `test_config_languages_defaults_to_dict()` and `test_config_prefer_manual_defaults_true()`) actually correct?**
|
||||
_`Config` has 9 INFERRED edges - model-reasoned connections that need verification._
|
||||
- **Are the 17 inferred relationships involving `Segment` (e.g. with `Chapter` and `Section`) actually correct?**
|
||||
_`Segment` has 17 INFERRED edges - model-reasoned connections that need verification._
|
||||
- **What connects `yt-channel-scraper`, `Qué es esto`, `Comandos` to the rest of the system?**
|
||||
_57 weakly-connected nodes found - possible documentation gaps or missing edges._
|
||||
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"runs": [
|
||||
{
|
||||
"date": "2026-07-27T05:54:56.822038+00:00",
|
||||
"input_tokens": 11800,
|
||||
"output_tokens": 4100,
|
||||
"files": 37
|
||||
}
|
||||
],
|
||||
"total_input_tokens": 11800,
|
||||
"total_output_tokens": 4100
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,237 @@
|
||||
{
|
||||
"pyproject.toml": {
|
||||
"mtime": 1785126752.9759955,
|
||||
"ast_hash": "f80dc007b3b67c7f7a78d9df01a81ead",
|
||||
"semantic_hash": "f80dc007b3b67c7f7a78d9df01a81ead"
|
||||
},
|
||||
"scripts/start-server.ps1": {
|
||||
"mtime": 1785132936.4055703,
|
||||
"ast_hash": "7390a228e676bff301ae85c5a4e7449e",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"scripts/stop-server.ps1": {
|
||||
"mtime": 1785132762.2959402,
|
||||
"ast_hash": "4a62db3fa3dca6b7109fcaadc1219226",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/__init__.py": {
|
||||
"mtime": 1785120608.3336751,
|
||||
"ast_hash": "4867131295172353fe6c2295851defc7",
|
||||
"semantic_hash": "4867131295172353fe6c2295851defc7"
|
||||
},
|
||||
"src/yt_scraper/analysis.py": {
|
||||
"mtime": 1785126463.1545029,
|
||||
"ast_hash": "c28d08131e6594e1e7c6111ff01b2d37",
|
||||
"semantic_hash": "c28d08131e6594e1e7c6111ff01b2d37"
|
||||
},
|
||||
"src/yt_scraper/chapters.py": {
|
||||
"mtime": 1785120675.3308973,
|
||||
"ast_hash": "1bf51b7c13486b9db9bcc3420fba2593",
|
||||
"semantic_hash": "1bf51b7c13486b9db9bcc3420fba2593"
|
||||
},
|
||||
"src/yt_scraper/cli.py": {
|
||||
"mtime": 1785555646.793181,
|
||||
"ast_hash": "36369eb5843535426c93cb5e0e14343a",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/config.py": {
|
||||
"mtime": 1785555391.6008003,
|
||||
"ast_hash": "b7a36354f41dbbaa3e4bbc7b635be4a2",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/cookies.py": {
|
||||
"mtime": 1785126417.4218228,
|
||||
"ast_hash": "dd5ec44bb4c6e6375be80f21307fc73d",
|
||||
"semantic_hash": "dd5ec44bb4c6e6375be80f21307fc73d"
|
||||
},
|
||||
"src/yt_scraper/discover.py": {
|
||||
"mtime": 1785555427.3430922,
|
||||
"ast_hash": "fce9799bd4076f35d4e5b4b1359b9782",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/export.py": {
|
||||
"mtime": 1785126439.6829402,
|
||||
"ast_hash": "f1cff31fb1004f08e997655f838e3a58",
|
||||
"semantic_hash": "f1cff31fb1004f08e997655f838e3a58"
|
||||
},
|
||||
"src/yt_scraper/extract.py": {
|
||||
"mtime": 1785134973.9585488,
|
||||
"ast_hash": "a9cff81702b263b80f72087a14864d7a",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/monitor.py": {
|
||||
"mtime": 1785555591.7611978,
|
||||
"ast_hash": "e7948e61b74b84b246708518f02dbcae",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/parse.py": {
|
||||
"mtime": 1785120665.3384771,
|
||||
"ast_hash": "25354365ac1ab52f1561c97256573806",
|
||||
"semantic_hash": "25354365ac1ab52f1561c97256573806"
|
||||
},
|
||||
"src/yt_scraper/pipeline.py": {
|
||||
"mtime": 1785134990.2165341,
|
||||
"ast_hash": "22d9c0d4630559f97ab68b652d9e1ef3",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/ratelimit.py": {
|
||||
"mtime": 1785120650.3795395,
|
||||
"ast_hash": "6082befe56d342fc43abd5299dd6c6ea",
|
||||
"semantic_hash": "6082befe56d342fc43abd5299dd6c6ea"
|
||||
},
|
||||
"src/yt_scraper/render.py": {
|
||||
"mtime": 1785120688.3247268,
|
||||
"ast_hash": "ff83764f3a8c8874557993e11eab1f89",
|
||||
"semantic_hash": "ff83764f3a8c8874557993e11eab1f89"
|
||||
},
|
||||
"src/yt_scraper/segments.py": {
|
||||
"mtime": 1785128385.6652262,
|
||||
"ast_hash": "09c7da35bc09a3f75fd0a627c0534746",
|
||||
"semantic_hash": "09c7da35bc09a3f75fd0a627c0534746"
|
||||
},
|
||||
"src/yt_scraper/store.py": {
|
||||
"mtime": 1785555451.541978,
|
||||
"ast_hash": "1821f8382f14edc0fe16e27c947caa3b",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/webapp/__init__.py": {
|
||||
"mtime": 1785126827.4957752,
|
||||
"ast_hash": "d41d8cd98f00b204e9800998ecf8427e",
|
||||
"semantic_hash": "d41d8cd98f00b204e9800998ecf8427e"
|
||||
},
|
||||
"src/yt_scraper/webapp/api.py": {
|
||||
"mtime": 1785555568.718664,
|
||||
"ast_hash": "be2bce8aacf98625a43edd840439a5a5",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/webapp/app.py": {
|
||||
"mtime": 1785126888.8032887,
|
||||
"ast_hash": "e0b1925b4318305dcf746d360373ff50",
|
||||
"semantic_hash": "e0b1925b4318305dcf746d360373ff50"
|
||||
},
|
||||
"src/yt_scraper/webapp/jobs.py": {
|
||||
"mtime": 1785555552.558772,
|
||||
"ast_hash": "8ca8f21136d8a4564f49927821244344",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/webapp/static/app.js": {
|
||||
"mtime": 1785555832.5020685,
|
||||
"ast_hash": "6932efd1a6044e66d227a2fc93042187",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_chapters.py": {
|
||||
"mtime": 1785120789.3300896,
|
||||
"ast_hash": "6d5303fa86de8dc99af6ae2ee17da033",
|
||||
"semantic_hash": "6d5303fa86de8dc99af6ae2ee17da033"
|
||||
},
|
||||
"tests/test_features.py": {
|
||||
"mtime": 1785126709.65728,
|
||||
"ast_hash": "21f9c44ce7cc1d618ece402ab7c2b057",
|
||||
"semantic_hash": "21f9c44ce7cc1d618ece402ab7c2b057"
|
||||
},
|
||||
"tests/test_parse.py": {
|
||||
"mtime": 1785120974.3283188,
|
||||
"ast_hash": "57ce74ee10fe6f9a90126ec7d9fd96b0",
|
||||
"semantic_hash": "57ce74ee10fe6f9a90126ec7d9fd96b0"
|
||||
},
|
||||
"tests/test_render.py": {
|
||||
"mtime": 1785120806.3260238,
|
||||
"ast_hash": "27125960e235813724fd669001faab59",
|
||||
"semantic_hash": "27125960e235813724fd669001faab59"
|
||||
},
|
||||
"tests/test_store_platform.py": {
|
||||
"mtime": 1785194588.4186954,
|
||||
"ast_hash": "44069db75a444906fb5001880dedf180",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
".opencode/agent/webapp-builder.md": {
|
||||
"mtime": 1785126783.7152567,
|
||||
"ast_hash": "58e92641724400370d7823dce1e02ca3",
|
||||
"semantic_hash": "58e92641724400370d7823dce1e02ca3"
|
||||
},
|
||||
".opencode/goals/webapp-build.md": {
|
||||
"mtime": 1785126796.8402326,
|
||||
"ast_hash": "478e7a2350ded2fd273cfdb0714d228d",
|
||||
"semantic_hash": "478e7a2350ded2fd273cfdb0714d228d"
|
||||
},
|
||||
"OPPORTUNITIES.md": {
|
||||
"mtime": 1785122706.3466253,
|
||||
"ast_hash": "4af60e3106b394664fbf5b5c5f645804",
|
||||
"semantic_hash": "4af60e3106b394664fbf5b5c5f645804"
|
||||
},
|
||||
"README.md": {
|
||||
"mtime": 1785121499.3282604,
|
||||
"ast_hash": "a0a8e6b62a991fce5d6c58171f80075e",
|
||||
"semantic_hash": "a0a8e6b62a991fce5d6c58171f80075e"
|
||||
},
|
||||
"config.example.yaml": {
|
||||
"mtime": 1785555848.8664799,
|
||||
"ast_hash": "f65a5089bf286e47326e916ad19ca572",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"docs/superpowers/plans/2026-07-26-platform-build.md": {
|
||||
"mtime": 1785126240.4211702,
|
||||
"ast_hash": "8097056ef23068f22c48151746de305b",
|
||||
"semantic_hash": "8097056ef23068f22c48151746de305b"
|
||||
},
|
||||
"docs/superpowers/specs/2026-07-26-platform-design.md": {
|
||||
"mtime": 1785126024.4879057,
|
||||
"ast_hash": "9b85f02fd45c93cdabfd2e1c6d1e0c9e",
|
||||
"semantic_hash": "9b85f02fd45c93cdabfd2e1c6d1e0c9e"
|
||||
},
|
||||
"src/yt_scraper/webapp/static/index.html": {
|
||||
"mtime": 1785555838.550363,
|
||||
"ast_hash": "372b8d77aae448ab1c478253782579ce",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/_yt_http.py": {
|
||||
"mtime": 1785134945.1512043,
|
||||
"ast_hash": "8af224580322df5aeeba10062592d961",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_config.py": {
|
||||
"mtime": 1785135145.3334274,
|
||||
"ast_hash": "5588a7ad8e1c866b1571a818d816f7a7",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_discover_incremental.py": {
|
||||
"mtime": 1785555704.1061945,
|
||||
"ast_hash": "e1c382a9b8f5c927a85d67814d3dbb09",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_extract.py": {
|
||||
"mtime": 1785135157.3141267,
|
||||
"ast_hash": "0bd7c2f3fb9f6bdfe855758b17e3bcf0",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_store_sync_watermark.py": {
|
||||
"mtime": 1785555725.6495814,
|
||||
"ast_hash": "9f9943f5b914078cee49bf4aaa060564",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_webapp_jobs.py": {
|
||||
"mtime": 1785555746.4912646,
|
||||
"ast_hash": "7688c701256ff0cdd2a7d78d7090c8b3",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"CLAUDE.md": {
|
||||
"mtime": 1785556046.8310063,
|
||||
"ast_hash": "631eba15392019298d5fbfcce89c6611",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"YOUTUBE-TRANSCRIPT-AUDIT.md": {
|
||||
"mtime": 1785116715.5118847,
|
||||
"ast_hash": "67c5b7e3b4661ca8c8a7280e63b13ba9",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"docs/superpowers/plans/2026-07-27-discovery-only-scrape.md": {
|
||||
"mtime": 1785192916.5353482,
|
||||
"ast_hash": "3cf41d6331bd67e39ccd96b0e6138cf2",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"docs/superpowers/specs/2026-07-27-discovery-only-scrape-design.md": {
|
||||
"mtime": 1785192898.2889626,
|
||||
"ast_hash": "529b39e9bd2adcafd17a2dc30263281c",
|
||||
"semantic_hash": ""
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"0": "Webapp Frontend (JS)",
|
||||
"1": "Transcript Extraction & Parsing",
|
||||
"2": "Config & Discovery Pipeline",
|
||||
"3": "Store & Export Layer",
|
||||
"4": "CLI Command Layer",
|
||||
"5": "Platform Design & Proposals",
|
||||
"6": "Segments Search & Backfill",
|
||||
"7": "Store Platform Tests",
|
||||
"8": "Content Analysis",
|
||||
"9": "README & Config Docs",
|
||||
"10": "Server Start Script",
|
||||
"11": "Package Manifest",
|
||||
"12": "Server Stop Script",
|
||||
"13": "Webapp Package Init",
|
||||
"14": "test_extract.py",
|
||||
"15": "Auditoría · Cómo la extensión obtiene la transcripción / información de vídeos de YouTube",
|
||||
"16": "api",
|
||||
"17": "pipeline.py",
|
||||
"20": "setView",
|
||||
"21": "Discovery-Only Scrape Design",
|
||||
"22": "renderDashboardCharts",
|
||||
"23": "Global Constraints",
|
||||
"25": "init",
|
||||
"27": "loadChannels"
|
||||
}
|
||||
@@ -0,0 +1,177 @@
|
||||
# Graph Report - yt-channel-scraper (2026-08-01)
|
||||
|
||||
## Corpus Check
|
||||
- 48 files · ~51,184 words
|
||||
- Verdict: corpus is large enough that graph structure adds value.
|
||||
|
||||
## Summary
|
||||
- 669 nodes · 1538 edges · 24 communities (21 shown, 3 thin omitted)
|
||||
- Extraction: 89% EXTRACTED · 11% INFERRED · 0% AMBIGUOUS · INFERRED: 162 edges (avg confidence: 0.78)
|
||||
- Token cost: 0 input · 0 output
|
||||
|
||||
## Graph Freshness
|
||||
- Built from commit: `06497299`
|
||||
- Run `git rev-parse HEAD` and compare to check if the graph is stale.
|
||||
- Run `graphify update .` after code changes (no API cost).
|
||||
|
||||
## Community Hubs (Navigation)
|
||||
- Webapp Frontend (JS)
|
||||
- Transcript Extraction & Parsing
|
||||
- Config & Discovery Pipeline
|
||||
- Store & Export Layer
|
||||
- CLI Command Layer
|
||||
- Platform Design & Proposals
|
||||
- Segments Search & Backfill
|
||||
- Store Platform Tests
|
||||
- Content Analysis
|
||||
- README & Config Docs
|
||||
- Server Start Script
|
||||
- Package Manifest
|
||||
- Server Stop Script
|
||||
- test_extract.py
|
||||
- Auditoría · Cómo la extensión obtiene la transcripción / información de vídeos de YouTube
|
||||
- api
|
||||
- pipeline.py
|
||||
- setView
|
||||
- Discovery-Only Scrape Design
|
||||
- renderDashboardCharts
|
||||
- Global Constraints
|
||||
- init
|
||||
- loadChannels
|
||||
|
||||
## God Nodes (most connected - your core abstractions)
|
||||
1. `Store` - 101 edges
|
||||
2. `VideoRef` - 42 edges
|
||||
3. `api()` - 39 edges
|
||||
4. `toast()` - 38 edges
|
||||
5. `Config` - 36 edges
|
||||
6. `Segment` - 32 edges
|
||||
7. `JobManager` - 26 edges
|
||||
8. `discover_incremental()` - 21 edges
|
||||
9. `process_video()` - 19 edges
|
||||
10. `reconcile_markdown()` - 19 edges
|
||||
|
||||
## Surprising Connections (you probably didn't know these)
|
||||
- `seeded_store()` --calls--> `VideoRef` [INFERRED]
|
||||
tests/test_store_platform.py → src/yt_scraper/store.py
|
||||
- `test_upload_sort_uses_discovered_time_when_date_is_missing()` --calls--> `VideoRef` [INFERRED]
|
||||
tests/test_store_platform.py → src/yt_scraper/store.py
|
||||
- `test_upsert_videos_reports_only_new_rows()` --calls--> `VideoRef` [INFERRED]
|
||||
tests/test_store_platform.py → src/yt_scraper/store.py
|
||||
- `store()` --calls--> `Store` [INFERRED]
|
||||
tests/test_store_platform.py → src/yt_scraper/store.py
|
||||
- `test_migration_idempotent()` --calls--> `Store` [INFERRED]
|
||||
tests/test_store_platform.py → src/yt_scraper/store.py
|
||||
|
||||
## Import Cycles
|
||||
- None detected.
|
||||
|
||||
## Hyperedges (group relationships)
|
||||
- **Workstream B webapp stack (FastAPI + Alpine SPA + subagent)** — opencode_agent_webapp_builder, opencode_goals_webapp_build, src_yt_scraper_webapp_static_index, docs_superpowers_specs_2026_07_26_platform_design_dark_command_center, docs_superpowers_specs_2026_07_26_platform_design_sse_job_runner [EXTRACTED 0.95]
|
||||
- **FTS5 transcript search flow (proposal -> spec -> SPA view)** — opportunities_search_fts5, docs_superpowers_specs_2026_07_26_platform_design_transcript_fts5, src_yt_scraper_webapp_static_index [INFERRED 0.85]
|
||||
- **Cookie auth chain (vault -> resolve_active_path -> scrape job)** — docs_superpowers_specs_2026_07_26_platform_design_cookie_vault_ux, docs_superpowers_specs_2026_07_26_platform_design_sse_job_runner, docs_superpowers_specs_2026_07_26_platform_design_cookies_bug_fix, src_yt_scraper_webapp_static_index [INFERRED 0.85]
|
||||
|
||||
## Communities (24 total, 3 thin omitted)
|
||||
|
||||
### Community 0 - "Webapp Frontend (JS)"
|
||||
Cohesion: 0.06
|
||||
Nodes (22): _armAutoHide(), cancelScrape(), closeClip(), closeJobWidget(), closeSidebar(), closeStats(), closeStream(), deleteJob() (+14 more)
|
||||
|
||||
### Community 1 - "Transcript Extraction & Parsing"
|
||||
Cohesion: 0.27
|
||||
Nodes (10): _iter_texts(), Path, Return [(YYYY-MM, count)] of months where `term` appears in transcripts., render_timeline_chart(), render_top_words_chart(), render_wordcloud(), term_timeline(), _tokenize() (+2 more)
|
||||
|
||||
### Community 2 - "Config & Discovery Pipeline"
|
||||
Cohesion: 0.06
|
||||
Nodes (46): _build_config(), Config, DelayConfig, load_config(), Path, Incremental channel sync — how far back a routine re-scan looks. The /video, SyncConfig, YtDlpConfig (+38 more)
|
||||
|
||||
### Community 3 - "Store & Export Layer"
|
||||
Cohesion: 0.05
|
||||
Nodes (46): Connection, Cursor, Environment, Row, auto_import_dir(), cookies_dir(), delete(), import_file() (+38 more)
|
||||
|
||||
### Community 4 - "CLI Command Layer"
|
||||
Cohesion: 0.07
|
||||
Nodes (44): analyze_cmd(), _apply_filters(), audio_cmd(), _channel_targets(), channels_add(), cli(), export_cmd(), _extract_handle() (+36 more)
|
||||
|
||||
### Community 5 - "Platform Design & Proposals"
|
||||
Cohesion: 0.12
|
||||
Nodes (20): Platform Implementation Plan, Platform Design Spec, Cookie drag-and-drop vault UX, cli.py cookies scope bug fix, Design language: dark data command center, Architecture: Monorepo in-package webapp (Approach A), Scope rule: No AI features, Single-threaded scrape job runner + SSE event bus (+12 more)
|
||||
|
||||
### Community 6 - "Segments Search & Backfill"
|
||||
Cohesion: 0.09
|
||||
Nodes (28): APIRouter, FastAPI, cache_channel_avatar(), cache_thumbnail(), Thumbnail URL for a video: stored URL, else the canonical YouTube one derived fr, Download + cache a video's thumbnail to <thumbnails_dir>/<video_id>.jpg. Returns, Download + cache a channel avatar to <avatars_dir>/<channel_id>.jpg. Returns Tru, thumbnail_url_for() (+20 more)
|
||||
|
||||
### Community 7 - "Store Platform Tests"
|
||||
Cohesion: 0.13
|
||||
Nodes (28): Collection, _channel_root_url(), deep_channel_avatar(), discover_channel(), discover_incremental(), _flatten_entries(), IncrementalDiscovery, _pick_channel_avatar() (+20 more)
|
||||
|
||||
### Community 8 - "Content Analysis"
|
||||
Cohesion: 0.10
|
||||
Nodes (41): Re-escanear data/markdown y hacer que la DB coincida con el disco., reconcile_cmd(), Make the DB agree with what is actually on disk. `backfill_from_markdown` f, reconcile_markdown(), VideoRef, Recovery paths: retryable statuses, recorded skip reasons, disk<->DB reconcile., The throttling message is the one that must stay retryable., The exact symptom the user reported: a .md exists but the row still shows a (+33 more)
|
||||
|
||||
### Community 10 - "Server Start Script"
|
||||
Cohesion: 0.38
|
||||
Nodes (3): Open-Browser(), Out-Line(), Show-State()
|
||||
|
||||
### Community 14 - "test_extract.py"
|
||||
Cohesion: 0.07
|
||||
Nodes (48): Response, parse_languages(), Any, Normalise legacy list / new dict / None into ``{lang: mode}``., _coerce_languages(), describe_missing_subtitle(), _download_subtitle(), extract_video() (+40 more)
|
||||
|
||||
### Community 15 - "Auditoría · Cómo la extensión obtiene la transcripción / información de vídeos de YouTube"
|
||||
Cohesion: 0.04
|
||||
Nodes (42): Arquitectura, Comandos, Cookies, Cualquier petición HTTP a CDNs de YouTube va por `_yt_http.yt_get()`, Documentos de referencia, El Markdown es fuente de datos, no solo salida, Estados terminales y frescura (la UI tiene que reflejar DB + disco), Frontend (+34 more)
|
||||
|
||||
### Community 16 - "api"
|
||||
Cohesion: 0.15
|
||||
Nodes (29): activateCookie(), api(), checkAudio(), clearJobHistory(), copyClip(), copyText(), downloadAudio(), downloadAudioOne() (+21 more)
|
||||
|
||||
### Community 17 - "pipeline.py"
|
||||
Cohesion: 0.05
|
||||
Nodes (56): align_chapters(), Chapter, chapters_from_info(), Section, merge_adjacent(), parse_auto_dump(), parse_json3(), parse_vtt() (+48 more)
|
||||
|
||||
### Community 20 - "setView"
|
||||
Cohesion: 0.24
|
||||
Nodes (10): cycleSort(), destroyCharts(), loadFolders(), loadFormat(), loadSearch(), loadVideos(), openChannel(), resetSearch() (+2 more)
|
||||
|
||||
### Community 21 - "Discovery-Only Scrape Design"
|
||||
Cohesion: 0.22
|
||||
Nodes (8): Architecture, Discovery-Only Scrape Design, Error Handling, Existing Context, Goal, Persistence and Results, Testing, UI
|
||||
|
||||
### Community 22 - "renderDashboardCharts"
|
||||
Cohesion: 0.36
|
||||
Nodes (9): axisOpts(), barOpts(), fmtMonth(), lineOpts(), loadAnalysis(), makeChart(), renderDashboardCharts(), renderTimelineChart() (+1 more)
|
||||
|
||||
### Community 23 - "Global Constraints"
|
||||
Cohesion: 0.25
|
||||
Nodes (7): Discovery-Only Scrape Implementation Plan, Global Constraints, Task 1: Make catalog insertion counts accurate, Task 2: Add discovery-only job execution, Task 3: Expose the discovery mode through the API, Task 4: Add one-channel and all-channel UI controls, Task 5: Final verification and review
|
||||
|
||||
### Community 25 - "init"
|
||||
Cohesion: 0.20
|
||||
Nodes (11): checkHealth(), hydrateURL(), init(), jobActive(), loadRetryable(), reconcile(), refreshLiveState(), resetVideos() (+3 more)
|
||||
|
||||
### Community 27 - "loadChannels"
|
||||
Cohesion: 0.32
|
||||
Nodes (8): addChannel(), downloadAvatarsScope(), loadChannelPending(), loadChannels(), loadDashboard(), removeChannel(), _setSyncResult(), syncChannels()
|
||||
|
||||
## Knowledge Gaps
|
||||
- **58 isolated node(s):** `yt-channel-scraper`, `Qué es esto`, `Comandos`, `Orientación antes de leer código`, `Tres superficies, un solo pipeline` (+53 more)
|
||||
These have ≤1 connection - possible missing edges or undocumented components.
|
||||
- **3 thin communities (<3 nodes) omitted from report** — run `graphify query` to explore isolated nodes.
|
||||
|
||||
## Suggested Questions
|
||||
_Questions this graph is uniquely positioned to answer:_
|
||||
|
||||
- **Why does `Store` connect `Store & Export Layer` to `Transcript Extraction & Parsing`, `Config & Discovery Pipeline`, `CLI Command Layer`, `Segments Search & Backfill`, `Content Analysis`, `pipeline.py`?**
|
||||
_High betweenness centrality (0.151) - this node is a cross-community bridge._
|
||||
- **Why does `VideoRef` connect `Content Analysis` to `Config & Discovery Pipeline`, `Store & Export Layer`, `CLI Command Layer`, `Store Platform Tests`, `pipeline.py`?**
|
||||
_High betweenness centrality (0.048) - this node is a cross-community bridge._
|
||||
- **Why does `Segment` connect `pipeline.py` to `CLI Command Layer`, `test_extract.py`, `Segments Search & Backfill`?**
|
||||
_High betweenness centrality (0.032) - this node is a cross-community bridge._
|
||||
- **Are the 13 inferred relationships involving `Store` (e.g. with `ParsedMarkdown` and `store()`) actually correct?**
|
||||
_`Store` has 13 INFERRED edges - model-reasoned connections that need verification._
|
||||
- **Are the 31 inferred relationships involving `VideoRef` (e.g. with `IncrementalDiscovery` and `store()`) actually correct?**
|
||||
_`VideoRef` has 31 INFERRED edges - model-reasoned connections that need verification._
|
||||
- **Are the 11 inferred relationships involving `Config` (e.g. with `test_config_languages_defaults_to_dict()` and `test_config_prefer_manual_defaults_true()`) actually correct?**
|
||||
_`Config` has 11 INFERRED edges - model-reasoned connections that need verification._
|
||||
- **What connects `yt-channel-scraper`, `Qué es esto`, `Comandos` to the rest of the system?**
|
||||
_58 weakly-connected nodes found - possible documentation gaps or missing edges._
|
||||
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"runs": [
|
||||
{
|
||||
"date": "2026-07-27T05:54:56.822038+00:00",
|
||||
"input_tokens": 11800,
|
||||
"output_tokens": 4100,
|
||||
"files": 37
|
||||
}
|
||||
],
|
||||
"total_input_tokens": 11800,
|
||||
"total_output_tokens": 4100
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,252 @@
|
||||
{
|
||||
"pyproject.toml": {
|
||||
"mtime": 1785126752.9759955,
|
||||
"ast_hash": "f80dc007b3b67c7f7a78d9df01a81ead",
|
||||
"semantic_hash": "f80dc007b3b67c7f7a78d9df01a81ead"
|
||||
},
|
||||
"scripts/start-server.ps1": {
|
||||
"mtime": 1785132936.4055703,
|
||||
"ast_hash": "7390a228e676bff301ae85c5a4e7449e",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"scripts/stop-server.ps1": {
|
||||
"mtime": 1785132762.2959402,
|
||||
"ast_hash": "4a62db3fa3dca6b7109fcaadc1219226",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/__init__.py": {
|
||||
"mtime": 1785120608.3336751,
|
||||
"ast_hash": "4867131295172353fe6c2295851defc7",
|
||||
"semantic_hash": "4867131295172353fe6c2295851defc7"
|
||||
},
|
||||
"src/yt_scraper/analysis.py": {
|
||||
"mtime": 1785126463.1545029,
|
||||
"ast_hash": "c28d08131e6594e1e7c6111ff01b2d37",
|
||||
"semantic_hash": "c28d08131e6594e1e7c6111ff01b2d37"
|
||||
},
|
||||
"src/yt_scraper/chapters.py": {
|
||||
"mtime": 1785120675.3308973,
|
||||
"ast_hash": "1bf51b7c13486b9db9bcc3420fba2593",
|
||||
"semantic_hash": "1bf51b7c13486b9db9bcc3420fba2593"
|
||||
},
|
||||
"src/yt_scraper/cli.py": {
|
||||
"mtime": 1785561823.2458293,
|
||||
"ast_hash": "100604834f369047b55641bd327333d0",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/config.py": {
|
||||
"mtime": 1785561416.2574291,
|
||||
"ast_hash": "712dddce27149cb3a5ceb34f78fac2fd",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/cookies.py": {
|
||||
"mtime": 1785126417.4218228,
|
||||
"ast_hash": "dd5ec44bb4c6e6375be80f21307fc73d",
|
||||
"semantic_hash": "dd5ec44bb4c6e6375be80f21307fc73d"
|
||||
},
|
||||
"src/yt_scraper/discover.py": {
|
||||
"mtime": 1785555427.3430922,
|
||||
"ast_hash": "fce9799bd4076f35d4e5b4b1359b9782",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/export.py": {
|
||||
"mtime": 1785126439.6829402,
|
||||
"ast_hash": "f1cff31fb1004f08e997655f838e3a58",
|
||||
"semantic_hash": "f1cff31fb1004f08e997655f838e3a58"
|
||||
},
|
||||
"src/yt_scraper/extract.py": {
|
||||
"mtime": 1785561382.7161057,
|
||||
"ast_hash": "a46b96123cfef40a10436e6e65b45d4b",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/monitor.py": {
|
||||
"mtime": 1785555591.7611978,
|
||||
"ast_hash": "e7948e61b74b84b246708518f02dbcae",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/parse.py": {
|
||||
"mtime": 1785120665.3384771,
|
||||
"ast_hash": "25354365ac1ab52f1561c97256573806",
|
||||
"semantic_hash": "25354365ac1ab52f1561c97256573806"
|
||||
},
|
||||
"src/yt_scraper/pipeline.py": {
|
||||
"mtime": 1785562085.460622,
|
||||
"ast_hash": "7dae8872284b33015654fb356c008e67",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/ratelimit.py": {
|
||||
"mtime": 1785120650.3795395,
|
||||
"ast_hash": "6082befe56d342fc43abd5299dd6c6ea",
|
||||
"semantic_hash": "6082befe56d342fc43abd5299dd6c6ea"
|
||||
},
|
||||
"src/yt_scraper/render.py": {
|
||||
"mtime": 1785120688.3247268,
|
||||
"ast_hash": "ff83764f3a8c8874557993e11eab1f89",
|
||||
"semantic_hash": "ff83764f3a8c8874557993e11eab1f89"
|
||||
},
|
||||
"src/yt_scraper/segments.py": {
|
||||
"mtime": 1785562183.2376134,
|
||||
"ast_hash": "902d851e321b83c99d4cae30c1ae39fc",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/store.py": {
|
||||
"mtime": 1785569257.9151454,
|
||||
"ast_hash": "fffc4c7aa5265bd53cd7ca2856b453ef",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/webapp/__init__.py": {
|
||||
"mtime": 1785126827.4957752,
|
||||
"ast_hash": "d41d8cd98f00b204e9800998ecf8427e",
|
||||
"semantic_hash": "d41d8cd98f00b204e9800998ecf8427e"
|
||||
},
|
||||
"src/yt_scraper/webapp/api.py": {
|
||||
"mtime": 1785569267.6258545,
|
||||
"ast_hash": "cadbcafc755f0e1daa574709bc54be84",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/webapp/app.py": {
|
||||
"mtime": 1785562107.3107448,
|
||||
"ast_hash": "80e375becb41e202f78239138252c5c8",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/webapp/jobs.py": {
|
||||
"mtime": 1785556090.2023566,
|
||||
"ast_hash": "45ba7f10b13b847c213f04441a5e741d",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/webapp/static/app.js": {
|
||||
"mtime": 1785561992.7035935,
|
||||
"ast_hash": "94250d573a31bf9bfb29cb54dc4c01e0",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_chapters.py": {
|
||||
"mtime": 1785120789.3300896,
|
||||
"ast_hash": "6d5303fa86de8dc99af6ae2ee17da033",
|
||||
"semantic_hash": "6d5303fa86de8dc99af6ae2ee17da033"
|
||||
},
|
||||
"tests/test_features.py": {
|
||||
"mtime": 1785126709.65728,
|
||||
"ast_hash": "21f9c44ce7cc1d618ece402ab7c2b057",
|
||||
"semantic_hash": "21f9c44ce7cc1d618ece402ab7c2b057"
|
||||
},
|
||||
"tests/test_parse.py": {
|
||||
"mtime": 1785120974.3283188,
|
||||
"ast_hash": "57ce74ee10fe6f9a90126ec7d9fd96b0",
|
||||
"semantic_hash": "57ce74ee10fe6f9a90126ec7d9fd96b0"
|
||||
},
|
||||
"tests/test_render.py": {
|
||||
"mtime": 1785120806.3260238,
|
||||
"ast_hash": "27125960e235813724fd669001faab59",
|
||||
"semantic_hash": "27125960e235813724fd669001faab59"
|
||||
},
|
||||
"tests/test_store_platform.py": {
|
||||
"mtime": 1785194588.4186954,
|
||||
"ast_hash": "44069db75a444906fb5001880dedf180",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
".opencode/agent/webapp-builder.md": {
|
||||
"mtime": 1785126783.7152567,
|
||||
"ast_hash": "58e92641724400370d7823dce1e02ca3",
|
||||
"semantic_hash": "58e92641724400370d7823dce1e02ca3"
|
||||
},
|
||||
".opencode/goals/webapp-build.md": {
|
||||
"mtime": 1785126796.8402326,
|
||||
"ast_hash": "478e7a2350ded2fd273cfdb0714d228d",
|
||||
"semantic_hash": "478e7a2350ded2fd273cfdb0714d228d"
|
||||
},
|
||||
"OPPORTUNITIES.md": {
|
||||
"mtime": 1785122706.3466253,
|
||||
"ast_hash": "4af60e3106b394664fbf5b5c5f645804",
|
||||
"semantic_hash": "4af60e3106b394664fbf5b5c5f645804"
|
||||
},
|
||||
"README.md": {
|
||||
"mtime": 1785121499.3282604,
|
||||
"ast_hash": "a0a8e6b62a991fce5d6c58171f80075e",
|
||||
"semantic_hash": "a0a8e6b62a991fce5d6c58171f80075e"
|
||||
},
|
||||
"config.example.yaml": {
|
||||
"mtime": 1785561451.814817,
|
||||
"ast_hash": "43661d5c00d05c922bcf884e8ac707c3",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"docs/superpowers/plans/2026-07-26-platform-build.md": {
|
||||
"mtime": 1785126240.4211702,
|
||||
"ast_hash": "8097056ef23068f22c48151746de305b",
|
||||
"semantic_hash": "8097056ef23068f22c48151746de305b"
|
||||
},
|
||||
"docs/superpowers/specs/2026-07-26-platform-design.md": {
|
||||
"mtime": 1785126024.4879057,
|
||||
"ast_hash": "9b85f02fd45c93cdabfd2e1c6d1e0c9e",
|
||||
"semantic_hash": "9b85f02fd45c93cdabfd2e1c6d1e0c9e"
|
||||
},
|
||||
"src/yt_scraper/webapp/static/index.html": {
|
||||
"mtime": 1785569275.8425553,
|
||||
"ast_hash": "4f3d8f27f4f663c6f741be3db2312df3",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/_yt_http.py": {
|
||||
"mtime": 1785134945.1512043,
|
||||
"ast_hash": "8af224580322df5aeeba10062592d961",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_config.py": {
|
||||
"mtime": 1785561477.3907576,
|
||||
"ast_hash": "46f3eefb24bcf44535c17977ac175509",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_discover_incremental.py": {
|
||||
"mtime": 1785555704.1061945,
|
||||
"ast_hash": "e1c382a9b8f5c927a85d67814d3dbb09",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_extract.py": {
|
||||
"mtime": 1785561483.422817,
|
||||
"ast_hash": "9949ef4f6e7fe8cbdf12bc8d1dc71e3f",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_store_sync_watermark.py": {
|
||||
"mtime": 1785555725.6495814,
|
||||
"ast_hash": "9f9943f5b914078cee49bf4aaa060564",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_webapp_jobs.py": {
|
||||
"mtime": 1785555746.4912646,
|
||||
"ast_hash": "7688c701256ff0cdd2a7d78d7090c8b3",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"CLAUDE.md": {
|
||||
"mtime": 1785569349.167527,
|
||||
"ast_hash": "a161232f286c0a4f674715f54b66fa76",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"YOUTUBE-TRANSCRIPT-AUDIT.md": {
|
||||
"mtime": 1785116715.5118847,
|
||||
"ast_hash": "67c5b7e3b4661ca8c8a7280e63b13ba9",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"docs/superpowers/plans/2026-07-27-discovery-only-scrape.md": {
|
||||
"mtime": 1785192916.5353482,
|
||||
"ast_hash": "3cf41d6331bd67e39ccd96b0e6138cf2",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"docs/superpowers/specs/2026-07-27-discovery-only-scrape-design.md": {
|
||||
"mtime": 1785192898.2889626,
|
||||
"ast_hash": "529b39e9bd2adcafd17a2dc30263281c",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_recovery.py": {
|
||||
"mtime": 1785569307.786051,
|
||||
"ast_hash": "53f25aeda88cbf3755f45f2377970b62",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_since_filter.py": {
|
||||
"mtime": 1785556104.7475204,
|
||||
"ast_hash": "1d827c61156ab488e838dac91261624f",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
".claude/settings.json": {
|
||||
"mtime": 1785569155.4443069,
|
||||
"ast_hash": "dc072413449915d630bc773c9fb57dc7",
|
||||
"semantic_hash": ""
|
||||
}
|
||||
}
|
||||
+200
-56
@@ -1,12 +1,18 @@
|
||||
# Graph Report - . (2026-07-26)
|
||||
# Graph Report - yt-channel-scraper (2026-08-01)
|
||||
|
||||
## Corpus Check
|
||||
- Corpus is ~28,854 words - fits in a single context window. You may not need a graph.
|
||||
- 49 files · ~52,574 words
|
||||
- Verdict: corpus is large enough that graph structure adds value.
|
||||
|
||||
## Summary
|
||||
- 392 nodes · 951 edges · 14 communities (12 shown, 2 thin omitted)
|
||||
- Extraction: 93% EXTRACTED · 7% INFERRED · 0% AMBIGUOUS · INFERRED: 65 edges (avg confidence: 0.76)
|
||||
- Token cost: 11,800 input · 4,100 output
|
||||
- 696 nodes · 1591 edges · 42 communities (37 shown, 5 thin omitted)
|
||||
- Extraction: 90% EXTRACTED · 10% INFERRED · 0% AMBIGUOUS · INFERRED: 163 edges (avg confidence: 0.78)
|
||||
- Token cost: 0 input · 0 output
|
||||
|
||||
## Graph Freshness
|
||||
- Built from commit: `06497299`
|
||||
- Run `git rev-parse HEAD` and compare to check if the graph is stale.
|
||||
- Run `graphify update .` after code changes (no API cost).
|
||||
|
||||
## Community Hubs (Navigation)
|
||||
- Webapp Frontend (JS)
|
||||
@@ -19,31 +25,61 @@
|
||||
- Store Platform Tests
|
||||
- Content Analysis
|
||||
- README & Config Docs
|
||||
- Server Start Script
|
||||
- Package Manifest
|
||||
- Server Stop Script
|
||||
- test_extract.py
|
||||
- Auditoría · Cómo la extensión obtiene la transcripción / información de vídeos de YouTube
|
||||
- api
|
||||
- pipeline.py
|
||||
- test_blocked_videos.py
|
||||
- config.py
|
||||
- setView
|
||||
- Discovery-Only Scrape Design
|
||||
- renderDashboardCharts
|
||||
- Global Constraints
|
||||
- Config
|
||||
- init
|
||||
- render.py
|
||||
- loadChannels
|
||||
- jobs.py
|
||||
- Segment
|
||||
- cookies.py
|
||||
- discover.py
|
||||
- export.py
|
||||
- pipeline.py
|
||||
- _channel_targets
|
||||
- test_features.py
|
||||
- VideoRow
|
||||
- test_since_filter.py
|
||||
- .reset_videos
|
||||
- ._connect
|
||||
- re_render_cmd
|
||||
- handleFiles
|
||||
|
||||
## God Nodes (most connected - your core abstractions)
|
||||
1. `Store` - 81 edges
|
||||
2. `Segment` - 32 edges
|
||||
3. `api()` - 31 edges
|
||||
4. `toast()` - 29 edges
|
||||
5. `Config` - 23 edges
|
||||
6. `process_video()` - 19 edges
|
||||
7. `JobManager` - 17 edges
|
||||
8. `resolve_active_path()` - 13 edges
|
||||
9. `discover_channel()` - 13 edges
|
||||
10. `backfill_from_markdown()` - 13 edges
|
||||
1. `Store` - 103 edges
|
||||
2. `VideoRef` - 43 edges
|
||||
3. `api()` - 39 edges
|
||||
4. `toast()` - 38 edges
|
||||
5. `Config` - 36 edges
|
||||
6. `Segment` - 32 edges
|
||||
7. `JobManager` - 26 edges
|
||||
8. `discover_incremental()` - 21 edges
|
||||
9. `process_video()` - 19 edges
|
||||
10. `reconcile_markdown()` - 19 edges
|
||||
|
||||
## Surprising Connections (you probably didn't know these)
|
||||
- `test_dashboard_aggregates()` --calls--> `Segment` [INFERRED]
|
||||
tests/test_store_platform.py → src/yt_scraper/parse.py
|
||||
- `test_store_and_search_segments()` --calls--> `Segment` [INFERRED]
|
||||
tests/test_store_platform.py → src/yt_scraper/parse.py
|
||||
- `test_store_segments_overwrites()` --calls--> `Segment` [INFERRED]
|
||||
tests/test_store_platform.py → src/yt_scraper/parse.py
|
||||
- `store()` --calls--> `Store` [INFERRED]
|
||||
tests/test_store_platform.py → src/yt_scraper/store.py
|
||||
- `test_migration_idempotent()` --calls--> `Store` [INFERRED]
|
||||
tests/test_store_platform.py → src/yt_scraper/store.py
|
||||
- `test_config_languages_defaults_to_dict()` --calls--> `Config` [INFERRED]
|
||||
tests/test_extract.py → src/yt_scraper/config.py
|
||||
- `test_config_prefer_manual_defaults_true()` --calls--> `Config` [INFERRED]
|
||||
tests/test_extract.py → src/yt_scraper/config.py
|
||||
- `test_export_json_csv()` --calls--> `Segment` [INFERRED]
|
||||
tests/test_features.py → src/yt_scraper/parse.py
|
||||
- `test_export_srt()` --calls--> `Segment` [INFERRED]
|
||||
tests/test_features.py → src/yt_scraper/parse.py
|
||||
- `test_term_timeline()` --calls--> `Segment` [INFERRED]
|
||||
tests/test_features.py → src/yt_scraper/parse.py
|
||||
|
||||
## Import Cycles
|
||||
- None detected.
|
||||
@@ -53,63 +89,171 @@
|
||||
- **FTS5 transcript search flow (proposal -> spec -> SPA view)** — opportunities_search_fts5, docs_superpowers_specs_2026_07_26_platform_design_transcript_fts5, src_yt_scraper_webapp_static_index [INFERRED 0.85]
|
||||
- **Cookie auth chain (vault -> resolve_active_path -> scrape job)** — docs_superpowers_specs_2026_07_26_platform_design_cookie_vault_ux, docs_superpowers_specs_2026_07_26_platform_design_sse_job_runner, docs_superpowers_specs_2026_07_26_platform_design_cookies_bug_fix, src_yt_scraper_webapp_static_index [INFERRED 0.85]
|
||||
|
||||
## Communities (14 total, 2 thin omitted)
|
||||
## Communities (42 total, 5 thin omitted)
|
||||
|
||||
### Community 0 - "Webapp Frontend (JS)"
|
||||
Cohesion: 0.06
|
||||
Nodes (59): activateCookie(), addChannel(), api(), axisOpts(), barOpts(), cancelScrape(), checkHealth(), closeStream() (+51 more)
|
||||
Nodes (22): _armAutoHide(), blockLabel(), blockTitle(), cancelScrape(), closeClip(), closeJobWidget(), closeSidebar(), closeStats() (+14 more)
|
||||
|
||||
### Community 1 - "Transcript Extraction & Parsing"
|
||||
Cohesion: 0.07
|
||||
Nodes (57): Environment, align_chapters(), Chapter, chapters_from_info(), Section, _parse_tags(), Regenerar Markdown desde segmentos almacenados., re_render_cmd() (+49 more)
|
||||
Cohesion: 0.27
|
||||
Nodes (10): _iter_texts(), Path, Return [(YYYY-MM, count)] of months where `term` appears in transcripts., render_timeline_chart(), render_top_words_chart(), render_wordcloud(), term_timeline(), _tokenize() (+2 more)
|
||||
|
||||
### Community 2 - "Config & Discovery Pipeline"
|
||||
Cohesion: 0.06
|
||||
Nodes (40): APIRouter, FastAPI, _build_config(), Config, DelayConfig, load_config(), Any, Path (+32 more)
|
||||
Cohesion: 0.17
|
||||
Nodes (10): _clone_config(), _handle(), JobManager, _keep_ref(), Any, Single-worker scrape job runner with an in-memory event log per job (SSE-polled), Refresh the catalog without extracting or downloading video content., Refresh one channel's catalog. Incremental by default: only the newest (+2 more)
|
||||
|
||||
### Community 3 - "Store & Export Layer"
|
||||
Cohesion: 0.07
|
||||
Nodes (28): Connection, Cursor, Row, is_expired(), list_vault(), export_csv(), export_html(), export_json() (+20 more)
|
||||
Cohesion: 0.10
|
||||
Nodes (10): Cursor, _now_iso(), Any, Every video id already recorded for a channel — the boundary an incremen, Newest known upload date (YYYYMMDD) for a channel, or None., Refresh a channel's counters from what is actually stored. Incremental, Update only the fields explicitly passed. Preserves last_scraped and video_count, Set a video's status, optionally recording why. `no_subtitles` used to (+2 more)
|
||||
|
||||
### Community 4 - "CLI Command Layer"
|
||||
Cohesion: 0.08
|
||||
Nodes (41): analyze_cmd(), _apply_filters(), audio_cmd(), _channel_targets(), channels_add(), cli(), export_cmd(), _extract_handle() (+33 more)
|
||||
Cohesion: 0.12
|
||||
Nodes (24): channels_add(), cli(), _extract_handle(), _fmt_date(), _fmt_duration(), _known_channel_for(), main(), _order_pending() (+16 more)
|
||||
|
||||
### Community 5 - "Platform Design & Proposals"
|
||||
Cohesion: 0.12
|
||||
Nodes (20): Platform Implementation Plan, Platform Design Spec, Cookie drag-and-drop vault UX, cli.py cookies scope bug fix, Design language: dark data command center, Architecture: Monorepo in-package webapp (Approach A), Scope rule: No AI features, Single-threaded scrape job runner + SSE event bus (+12 more)
|
||||
|
||||
### Community 6 - "Segments Search & Backfill"
|
||||
Cohesion: 0.26
|
||||
Nodes (11): backfill_from_markdown(), parse_markdown(), ParsedMarkdown, Path, Parse all done .md files under md_root, populate segments/FTS/metadata. Idempote, search(), store_segments(), _strip_quotes() (+3 more)
|
||||
Cohesion: 0.13
|
||||
Nodes (17): APIRouter, FastAPI, cache_channel_avatar(), cache_thumbnail(), Thumbnail URL for a video: stored URL, else the canonical YouTube one derived fr, Download + cache a video's thumbnail to <thumbnails_dir>/<video_id>.jpg. Returns, Download + cache a channel avatar to <avatars_dir>/<channel_id>.jpg. Returns Tru, thumbnail_url_for() (+9 more)
|
||||
|
||||
### Community 7 - "Store Platform Tests"
|
||||
Cohesion: 0.17
|
||||
Nodes (5): store(), test_dashboard_aggregates(), test_migration_idempotent(), test_store_and_search_segments(), test_store_segments_overwrites()
|
||||
Cohesion: 0.22
|
||||
Nodes (18): Collection, discover_incremental(), IncrementalDiscovery, Fetch only the newest slice of a channel instead of paginating all of it. A, Outcome of a windowed channel sync., _fake_channel(), Windowed channel sync: only fetch what is newer than what we already have. The, Shorts the store never recorded must not keep the window widening. (+10 more)
|
||||
|
||||
### Community 8 - "Content Analysis"
|
||||
Cohesion: 0.07
|
||||
Nodes (52): Re-escanear data/markdown y hacer que la DB coincida con el disco., reconcile_cmd(), backfill_from_markdown(), parse_markdown(), ParsedMarkdown, Path, Parse all done .md files under md_root, populate segments/FTS/metadata. Idempote, Make the DB agree with what is actually on disk. `backfill_from_markdown` f (+44 more)
|
||||
|
||||
### Community 10 - "Server Start Script"
|
||||
Cohesion: 0.38
|
||||
Nodes (3): Open-Browser(), Out-Line(), Show-State()
|
||||
|
||||
### Community 14 - "test_extract.py"
|
||||
Cohesion: 0.07
|
||||
Nodes (50): Response, parse_languages(), Any, Normalise legacy list / new dict / None into ``{lang: mode}``., _coerce_languages(), describe_missing_subtitle(), _download_subtitle(), extract_video() (+42 more)
|
||||
|
||||
### Community 15 - "Auditoría · Cómo la extensión obtiene la transcripción / información de vídeos de YouTube"
|
||||
Cohesion: 0.04
|
||||
Nodes (42): Arquitectura, Comandos, Cookies, Cualquier petición HTTP a CDNs de YouTube va por `_yt_http.yt_get()`, Documentos de referencia, El Markdown es fuente de datos, no solo salida, Estados terminales y frescura (la UI tiene que reflejar DB + disco), Frontend (+34 more)
|
||||
|
||||
### Community 16 - "api"
|
||||
Cohesion: 0.16
|
||||
Nodes (29): activateCookie(), api(), checkAudio(), clearJobHistory(), copyClip(), copyText(), deleteJob(), downloadAudio() (+21 more)
|
||||
|
||||
### Community 17 - "pipeline.py"
|
||||
Cohesion: 0.10
|
||||
Nodes (19): merge_adjacent(), parse_auto_dump(), parse_json3(), parse_vtt(), _vtt_ts_to_seconds(), test_merge_adjacent(), test_parse_json3_basic(), test_parse_json3_invalid_json() (+11 more)
|
||||
|
||||
### Community 18 - "test_blocked_videos.py"
|
||||
Cohesion: 0.23
|
||||
Nodes (18): Members-only / gated videos: identified from discovery, labelled, and kept out o, Buying the membership must not leave the video permanently stranded., `unlisted` downloads perfectly well — mislabelling it would hide videos the, Rows burned into `error` before availability was captured must still be iden, Bulk runs must not spend requests on videos that cannot be fetched., _ref(), _store(), test_a_blocked_video_is_still_reachable_by_id() (+10 more)
|
||||
|
||||
### Community 19 - "config.py"
|
||||
Cohesion: 0.24
|
||||
Nodes (14): _build_config(), DelayConfig, load_config(), Incremental channel sync — how far back a routine re-scan looks. The /video, SyncConfig, YtDlpConfig, Tests for the YAML config loader. Focuses on the ``languages`` and ``prefer_man, The default must fall back to auto captions. A manual-only default silently (+6 more)
|
||||
|
||||
### Community 20 - "setView"
|
||||
Cohesion: 0.24
|
||||
Nodes (10): cycleSort(), destroyCharts(), loadFolders(), loadFormat(), loadSearch(), loadVideos(), openChannel(), resetSearch() (+2 more)
|
||||
|
||||
### Community 21 - "Discovery-Only Scrape Design"
|
||||
Cohesion: 0.22
|
||||
Nodes (8): Architecture, Discovery-Only Scrape Design, Error Handling, Existing Context, Goal, Persistence and Results, Testing, UI
|
||||
|
||||
### Community 22 - "renderDashboardCharts"
|
||||
Cohesion: 0.36
|
||||
Nodes (9): axisOpts(), barOpts(), fmtMonth(), lineOpts(), loadAnalysis(), makeChart(), renderDashboardCharts(), renderTimelineChart() (+1 more)
|
||||
|
||||
### Community 23 - "Global Constraints"
|
||||
Cohesion: 0.25
|
||||
Nodes (7): Discovery-Only Scrape Implementation Plan, Global Constraints, Task 1: Make catalog insertion counts accurate, Task 2: Add discovery-only job execution, Task 3: Expose the discovery mode through the API, Task 4: Add one-channel and all-channel UI controls, Task 5: Final verification and review
|
||||
|
||||
### Community 24 - "Config"
|
||||
Cohesion: 0.23
|
||||
Nodes (11): Config, Path, _catalog_channel(), The window is 30 wide but the channel has 200 videos — video_count must not, test_all_channel_discovery_continues_after_one_error(), test_audio_job_downloads_into_audio_directory(), test_audio_job_with_video_ids_uses_audio_runner(), test_batch_job_reports_videos_without_transcripts() (+3 more)
|
||||
|
||||
### Community 25 - "init"
|
||||
Cohesion: 0.15
|
||||
Nodes (18): addChannel(), checkHealth(), downloadAvatarsScope(), hydrateURL(), init(), jobActive(), loadChannelPending(), loadChannels() (+10 more)
|
||||
|
||||
### Community 26 - "render.py"
|
||||
Cohesion: 0.25
|
||||
Nodes (12): Environment, format_timestamp(), _make_env(), Path, quote_yaml(), render_markdown(), to_json(), test_format_timestamp_hours() (+4 more)
|
||||
|
||||
### Community 27 - "loadChannels"
|
||||
Cohesion: 0.23
|
||||
Nodes (8): Row, is_expired(), list_vault(), CookieRow, JobRow, _row_to_cookierow(), _row_to_jobrow(), _sanitize_fts()
|
||||
|
||||
### Community 28 - "jobs.py"
|
||||
Cohesion: 0.23
|
||||
Nodes (10): resolve_active_path(), _extract_handle(), _keep_ref(), Same shorts/live rules the store was populated under — see jobs._keep_ref., Discover + process pending videos for a channel, optionally on an interval., _run_once(), watch_loop(), polite_sleep() (+2 more)
|
||||
|
||||
### Community 29 - "Segment"
|
||||
Cohesion: 0.37
|
||||
Nodes (11): align_chapters(), Chapter, chapters_from_info(), Section, Segment, test_align_no_chapters(), test_align_pre_chapter_segments(), test_align_with_chapters() (+3 more)
|
||||
|
||||
### Community 30 - "cookies.py"
|
||||
Cohesion: 0.35
|
||||
Nodes (11): auto_import_dir(), cookies_dir(), delete(), import_file(), import_text(), parse_netscape(), parse_netscape_file(), Path (+3 more)
|
||||
|
||||
### Community 31 - "discover.py"
|
||||
Cohesion: 0.27
|
||||
Nodes (10): _iter_texts(), Path, Return [(YYYY-MM, count)] of months where `term` appears in transcripts., render_timeline_chart(), render_top_words_chart(), render_wordcloud(), term_timeline(), _tokenize() (+2 more)
|
||||
Nodes (10): _channel_root_url(), deep_channel_avatar(), discover_channel(), _flatten_entries(), _pick_channel_avatar(), Any, Best-effort channel avatar URL from a yt-dlp channel info dict. Only source, Strip a tab suffix from a YouTube channel URL so yt-dlp extracts the channel (+2 more)
|
||||
|
||||
### Community 32 - "export.py"
|
||||
Cohesion: 0.38
|
||||
Nodes (10): export_csv(), export_html(), export_json(), export_srt(), export_srt_video(), Path, _segments_to_srt(), _srt_ts() (+2 more)
|
||||
|
||||
### Community 33 - "pipeline.py"
|
||||
Cohesion: 0.29
|
||||
Nodes (10): _normalize_date(), process_video(), Regenerate .md for done videos that have stored segments. Returns count re-rende, Extract + parse + store + render a single video. Returns final status string., re_render_videos(), _safe_dirname(), build_filename_stem(), test_build_filename_stem() (+2 more)
|
||||
|
||||
### Community 34 - "_channel_targets"
|
||||
Cohesion: 0.20
|
||||
Nodes (10): analyze_cmd(), audio_cmd(), _channel_targets(), export_cmd(), Devolver videos atascados en error/no_subtitles a 'pending' para reintentarlos., Export multi-formato., Descarga audio MP3 (requiere ffmpeg)., Analisis estadistico de contenido (frecuencia, timeline). (+2 more)
|
||||
|
||||
### Community 35 - "test_features.py"
|
||||
Cohesion: 0.20
|
||||
Nodes (5): store(), test_export_json_csv(), test_export_srt(), test_term_timeline(), test_word_frequency()
|
||||
|
||||
### Community 36 - "VideoRow"
|
||||
Cohesion: 0.33
|
||||
Nodes (4): Why this video can never be fetched, or None if it can. Prefers the dis, Pending videos, excluding ones discovery already told us we cannot fetch, _row_to_videorow(), VideoRow
|
||||
|
||||
### Community 37 - "test_since_filter.py"
|
||||
Cohesion: 0.52
|
||||
Nodes (6): _apply_filters(), `--since` / the scrape form's date filter must not eat undated entries. yt-dlp', _ref(), test_since_keeps_entries_with_no_upload_date(), test_since_still_drops_entries_that_are_provably_older(), test_without_since_nothing_is_dropped_on_date_grounds()
|
||||
|
||||
### Community 40 - "re_render_cmd"
|
||||
Cohesion: 0.50
|
||||
Nodes (4): _parse_tags(), Regenerar Markdown desde segmentos almacenados., re_render_cmd(), _safe_dirname()
|
||||
|
||||
### Community 41 - "handleFiles"
|
||||
Cohesion: 0.67
|
||||
Nodes (3): handleDrop(), handleFiles(), uploadCookies()
|
||||
|
||||
## Knowledge Gaps
|
||||
- **10 isolated node(s):** `yt-channel-scraper`, `OPPORTUNITIES.md - extension audit`, `Design language: dark data command center`, `yt-dlp InnerTube mechanism (ANDROID/IOS/WEB clients)`, `Feature proposal: search (FTS5 transcript search)` (+5 more)
|
||||
- **58 isolated node(s):** `yt-channel-scraper`, `Qué es esto`, `Comandos`, `Orientación antes de leer código`, `Tres superficies, un solo pipeline` (+53 more)
|
||||
These have ≤1 connection - possible missing edges or undocumented components.
|
||||
- **2 thin communities (<3 nodes) omitted from report** — run `graphify query` to explore isolated nodes.
|
||||
- **5 thin communities (<3 nodes) omitted from report** — run `graphify query` to explore isolated nodes.
|
||||
|
||||
## Suggested Questions
|
||||
_Questions this graph is uniquely positioned to answer:_
|
||||
|
||||
- **Why does `Store` connect `Store & Export Layer` to `Transcript Extraction & Parsing`, `Config & Discovery Pipeline`, `CLI Command Layer`, `Segments Search & Backfill`, `Store Platform Tests`, `Content Analysis`?**
|
||||
_High betweenness centrality (0.194) - this node is a cross-community bridge._
|
||||
- **Why does `Segment` connect `Transcript Extraction & Parsing` to `CLI Command Layer`, `Segments Search & Backfill`, `Store Platform Tests`?**
|
||||
_High betweenness centrality (0.057) - this node is a cross-community bridge._
|
||||
- **Why does `Config` connect `Config & Discovery Pipeline` to `Transcript Extraction & Parsing`, `CLI Command Layer`?**
|
||||
_High betweenness centrality (0.024) - this node is a cross-community bridge._
|
||||
- **Are the 4 inferred relationships involving `Store` (e.g. with `ParsedMarkdown` and `store()`) actually correct?**
|
||||
_`Store` has 4 INFERRED edges - model-reasoned connections that need verification._
|
||||
- **Are the 17 inferred relationships involving `Segment` (e.g. with `Chapter` and `Section`) actually correct?**
|
||||
_`Segment` has 17 INFERRED edges - model-reasoned connections that need verification._
|
||||
- **What connects `yt-channel-scraper`, `OPPORTUNITIES.md - extension audit`, `Design language: dark data command center` to the rest of the system?**
|
||||
_10 weakly-connected nodes found - possible documentation gaps or missing edges._
|
||||
- **Should `Webapp Frontend (JS)` be split into smaller, more focused modules?**
|
||||
_Cohesion score 0.062317429406037 - nodes in this community are weakly interconnected._
|
||||
- **Why does `Store` connect `Store & Export Layer` to `export.py`, `Transcript Extraction & Parsing`, `pipeline.py`, `Config & Discovery Pipeline`, `CLI Command Layer`, `VideoRow`, `.reset_videos`, `._connect`, `Content Analysis`, `Segments Search & Backfill`, `test_features.py`, `pipeline.py`, `test_blocked_videos.py`, `Config`, `loadChannels`, `jobs.py`, `cookies.py`?**
|
||||
_High betweenness centrality (0.162) - this node is a cross-community bridge._
|
||||
- **Why does `VideoRef` connect `Content Analysis` to `Store & Export Layer`, `CLI Command Layer`, `test_features.py`, `test_since_filter.py`, `Store Platform Tests`, `pipeline.py`, `test_blocked_videos.py`, `Config`, `loadChannels`, `jobs.py`, `discover.py`?**
|
||||
_High betweenness centrality (0.053) - this node is a cross-community bridge._
|
||||
- **Why does `Segment` connect `Segment` to `pipeline.py`, `test_features.py`, `CLI Command Layer`, `re_render_cmd`, `Content Analysis`, `test_extract.py`, `pipeline.py`?**
|
||||
_High betweenness centrality (0.031) - this node is a cross-community bridge._
|
||||
- **Are the 14 inferred relationships involving `Store` (e.g. with `ParsedMarkdown` and `_store()`) actually correct?**
|
||||
_`Store` has 14 INFERRED edges - model-reasoned connections that need verification._
|
||||
- **Are the 31 inferred relationships involving `VideoRef` (e.g. with `IncrementalDiscovery` and `store()`) actually correct?**
|
||||
_`VideoRef` has 31 INFERRED edges - model-reasoned connections that need verification._
|
||||
- **Are the 11 inferred relationships involving `Config` (e.g. with `test_config_languages_defaults_to_dict()` and `test_config_prefer_manual_defaults_true()`) actually correct?**
|
||||
_`Config` has 11 INFERRED edges - model-reasoned connections that need verification._
|
||||
- **What connects `yt-channel-scraper`, `Qué es esto`, `Comandos` to the rest of the system?**
|
||||
_58 weakly-connected nodes found - possible documentation gaps or missing edges._
|
||||
graphify-out/cache/ast/v0.9.22/01d12afbd0457e8960455bcdd1197204d149941168e4452768492f17e12057b7.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/055ece0cc9a7abdfdce29fc2fe1d94165bdcca87a236ba398c105e4f8641c676.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/138f2e349300764b2b5ca342295a12efbaa6de1ff8df332be58871b130570ed9.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/165fa89acf2585a34e4b07436faeb8f225d14bc1a699fdc4ee506d7619eb1d95.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/1b7bfeeef4294b3ebbdfafd1e791473299d1bc77ad5e2f6b8a7b9427ba76f5ec.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/1d0aa0749bad2a7c8c3670e18750ea9cc581a8ac338d00b6501bb7361cf24991.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/1e52d419bb392cebab1e9715bcb53d51cceaa71d68b9032227d4741695af6e28.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/2552d4d9a9cc2a1ed9040be2fef3d5c460f5df7680e5e25ae14ed6f75907918b.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/2b9367cdaf1ee8bcd08a752824a819d0139dadd53f59086cb4b19fd67f32b53b.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/3f8e7e91eb49c07fcdbe4286b8c15848443c4edc734e4418e3f481bf7482a008.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/45cf21d405c4221cb88b1147cf7e87d1e1e4cc3252111019deeaf27a6d7a8b6a.json
Vendored
+1
@@ -0,0 +1 @@
|
||||
{"nodes": [{"id": "d_yt_channel_scraper_scripts_stop_server_ps1", "label": "stop-server.ps1", "file_type": "code", "source_file": "scripts/stop-server.ps1", "source_location": "L1"}, {"id": "d_yt_channel_scraper_scripts_stop_server_out_line", "label": "Out-Line()", "file_type": "code", "source_file": "scripts/stop-server.ps1", "source_location": "L5"}, {"id": "d_yt_channel_scraper_scripts_stop_server_test_portopen", "label": "Test-PortOpen()", "file_type": "code", "source_file": "scripts/stop-server.ps1", "source_location": "L13"}, {"id": "d_yt_channel_scraper_scripts_stop_server_kill_portowner", "label": "Kill-PortOwner()", "file_type": "code", "source_file": "scripts/stop-server.ps1", "source_location": "L24"}], "edges": [{"source": "d_yt_channel_scraper_scripts_stop_server_ps1", "target": "d_yt_channel_scraper_scripts_stop_server_out_line", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/stop-server.ps1", "source_location": "L5", "weight": 1.0}, {"source": "d_yt_channel_scraper_scripts_stop_server_ps1", "target": "d_yt_channel_scraper_scripts_stop_server_test_portopen", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/stop-server.ps1", "source_location": "L13", "weight": 1.0}, {"source": "d_yt_channel_scraper_scripts_stop_server_ps1", "target": "d_yt_channel_scraper_scripts_stop_server_kill_portowner", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/stop-server.ps1", "source_location": "L24", "weight": 1.0}, {"source": "d_yt_channel_scraper_scripts_stop_server_kill_portowner", "target": "d_yt_channel_scraper_scripts_stop_server_out_line", "relation": "calls", "confidence": "EXTRACTED", "source_file": "scripts/stop-server.ps1", "source_location": "L27", "weight": 1.0}], "raw_calls": [{"caller_nid": "d_yt_channel_scraper_scripts_stop_server_out_line", "callee": "Write-Host", "is_member_call": false, "source_file": "scripts/stop-server.ps1", "source_location": "L6"}, {"caller_nid": "d_yt_channel_scraper_scripts_stop_server_out_line", "callee": "Write-Host", "is_member_call": false, "source_file": "scripts/stop-server.ps1", "source_location": "L7"}, {"caller_nid": "d_yt_channel_scraper_scripts_stop_server_test_portopen", "callee": "New-Object", "is_member_call": false, "source_file": "scripts/stop-server.ps1", "source_location": "L14"}, {"caller_nid": "d_yt_channel_scraper_scripts_stop_server_kill_portowner", "callee": "Get-NetTCPConnection", "is_member_call": false, "source_file": "scripts/stop-server.ps1", "source_location": "L25"}, {"caller_nid": "d_yt_channel_scraper_scripts_stop_server_kill_portowner", "callee": "ForEach-Object", "is_member_call": false, "source_file": "scripts/stop-server.ps1", "source_location": "L26"}, {"caller_nid": "d_yt_channel_scraper_scripts_stop_server_kill_portowner", "callee": "Stop-Process", "is_member_call": false, "source_file": "scripts/stop-server.ps1", "source_location": "L28"}]}
|
||||
graphify-out/cache/ast/v0.9.22/46f59277042b7eba1430abe6f302416a2f14834a2a39de944e7919afd30ea732.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/4cd4f80326c3df60abc579fa3be19eca6e08b8bdbe0ad936c8d42ee241b71edb.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/55d28bdb9e808d6e2ab2717ef307faedff76d2202f0d029621489c82b8fe3aa1.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/5ad53cd8158245cd67b3ea45dc7dad107636666bd957a76041a6e36c20b1b4df.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/60f9653b556213f971442048ebc563d916c6c2c8e7e729d1eb3f1f1ef9a6f74e.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/61e93a83b219449f61955a14b4f15ecfb5be4950adc7a90568e2d4c1af13dc00.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/651f8538a30ddaeddb38795a3eef200b5d426c33eea3812e578b532e09c13f45.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/65dfd9ff5b8d3db19bf1ef2b4eb7ff596e9f5647d010481376266dc63f1b083e.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/68dada94168c2b33eb99461b5db0bcf4ce8f2ef6c256effd5a1efa9a2f537a35.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/6d4af4049f6b3a40f7e0356cc1993dcaf22af164a35b080c55b6aabc001fd18d.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/718bb43705ffbaaabace8c1eacedaa69d89d34729ff65328d3dfe20f2d1098d3.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/73fd8d6e6d80e5ffd3e34ba7cd37ea93f8972f02d09533f44710b9f1e90e0803.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/7dbbf6b8f41b3db71cb97e7f5e9ac6bbdd326f835b96aa8be9ce255a3e7e33b4.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/84d78dabe5dd523c6f7de3c05844ac207347e04eb57939fbc1186894fb8fc334.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/8984317652a50a4ac2e8de007380ce35790d306453dff7053f8089b007349da3.json
Vendored
+1
@@ -0,0 +1 @@
|
||||
{"nodes": [{"id": "d_yt_channel_scraper_src_yt_scraper_yt_http_py", "label": "_yt_http.py", "file_type": "code", "source_file": "src/yt_scraper/_yt_http.py", "source_location": "L1"}, {"id": "d_yt_channel_scraper_src_yt_scraper_yt_http_yt_headers", "label": "yt_headers()", "file_type": "code", "source_file": "src/yt_scraper/_yt_http.py", "source_location": "L33", "_callable": true}, {"id": "d_yt_channel_scraper_src_yt_scraper_yt_http_yt_get", "label": "yt_get()", "file_type": "code", "source_file": "src/yt_scraper/_yt_http.py", "source_location": "L40", "_callable": true}, {"id": "any", "label": "Any", "file_type": "code", "source_file": "", "source_location": "", "origin_file": "D:\\yt-channel-scraper\\src\\yt_scraper\\_yt_http.py"}, {"id": "response", "label": "Response", "file_type": "code", "source_file": "", "source_location": "", "origin_file": "D:\\yt-channel-scraper\\src\\yt_scraper\\_yt_http.py"}, {"id": "d_yt_channel_scraper_src_yt_scraper_yt_http_rationale_1", "label": "Shared HTTP helpers for talking to YouTube CDNs. Single source of truth for the", "file_type": "rationale", "source_file": "src/yt_scraper/_yt_http.py", "source_location": "L1"}, {"id": "d_yt_channel_scraper_src_yt_scraper_yt_http_rationale_34", "label": "Return a copy of the YouTube CDN headers merged with ``extra``.", "file_type": "rationale", "source_file": "src/yt_scraper/_yt_http.py", "source_location": "L34"}, {"id": "d_yt_channel_scraper_src_yt_scraper_yt_http_rationale_43", "label": "GET ``url`` with the shared YouTube CDN headers. Centralising this lets eve", "file_type": "rationale", "source_file": "src/yt_scraper/_yt_http.py", "source_location": "L43"}], "edges": [{"source": "d_yt_channel_scraper_src_yt_scraper_yt_http_py", "target": "typing", "relation": "imports_from", "context": "import", "confidence": "EXTRACTED", "source_file": "src/yt_scraper/_yt_http.py", "source_location": "L10", "weight": 1.0}, {"source": "d_yt_channel_scraper_src_yt_scraper_yt_http_py", "target": "requests", "relation": "imports", "context": "import", "confidence": "EXTRACTED", "source_file": "src/yt_scraper/_yt_http.py", "source_location": "L12", "weight": 1.0}, {"source": "d_yt_channel_scraper_src_yt_scraper_yt_http_py", "target": "d_yt_channel_scraper_src_yt_scraper_yt_http_yt_headers", "relation": "contains", "confidence": "EXTRACTED", "source_file": "src/yt_scraper/_yt_http.py", "source_location": "L33", "weight": 1.0}, {"source": "d_yt_channel_scraper_src_yt_scraper_yt_http_py", "target": "d_yt_channel_scraper_src_yt_scraper_yt_http_yt_get", "relation": "contains", "confidence": "EXTRACTED", "source_file": "src/yt_scraper/_yt_http.py", "source_location": "L40", "weight": 1.0}, {"source": "d_yt_channel_scraper_src_yt_scraper_yt_http_yt_get", "target": "any", "relation": "references", "context": "generic_arg", "confidence": "EXTRACTED", "source_file": "src/yt_scraper/_yt_http.py", "source_location": "L40", "weight": 1.0}, {"source": "d_yt_channel_scraper_src_yt_scraper_yt_http_yt_get", "target": "response", "relation": "references", "context": "return_type", "confidence": "EXTRACTED", "source_file": "src/yt_scraper/_yt_http.py", "source_location": "L40", "weight": 1.0}, {"source": "d_yt_channel_scraper_src_yt_scraper_yt_http_yt_get", "target": "d_yt_channel_scraper_src_yt_scraper_yt_http_yt_headers", "relation": "calls", "context": "call", "confidence": "EXTRACTED", "source_file": "src/yt_scraper/_yt_http.py", "source_location": "L49", "weight": 1.0}, {"source": "d_yt_channel_scraper_src_yt_scraper_yt_http_rationale_1", "target": "d_yt_channel_scraper_src_yt_scraper_yt_http_py", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "src/yt_scraper/_yt_http.py", "source_location": "L1", "weight": 1.0}, {"source": "d_yt_channel_scraper_src_yt_scraper_yt_http_rationale_34", "target": "d_yt_channel_scraper_src_yt_scraper_yt_http_yt_headers", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "src/yt_scraper/_yt_http.py", "source_location": "L34", "weight": 1.0}, {"source": "d_yt_channel_scraper_src_yt_scraper_yt_http_rationale_43", "target": "d_yt_channel_scraper_src_yt_scraper_yt_http_yt_get", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "src/yt_scraper/_yt_http.py", "source_location": "L43", "weight": 1.0}], "raw_calls": [{"caller_nid": "d_yt_channel_scraper_src_yt_scraper_yt_http_yt_headers", "callee": "_YT_HEADERS", "is_member_call": false, "indirect": true, "context": "argument", "source_file": "src/yt_scraper/_yt_http.py", "source_location": "L37"}, {"caller_nid": "d_yt_channel_scraper_src_yt_scraper_yt_http_yt_get", "callee": "get", "is_member_call": true, "source_file": "src/yt_scraper/_yt_http.py", "source_location": "L49", "receiver": "requests"}]}
|
||||
graphify-out/cache/ast/v0.9.22/91e63e7a4a9cd9af19ab798569730680f8172995ff8eb74803b64de66bac1295.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/9804897ae7075e54c30e3ff644c5fb455a7c00e00c7af74ec141cacfe8a68c35.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/981149ba3a0875f62a1191a903e769cea97f4692897fe547800a6aa1fbe81508.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/9b69dde6b0a1aa81eb3e1f3629f71bb3398b89d8ac28bddfd66df8736dd7f841.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/a188993a249d683cc548d0a49630ad50fef9b9e01f50888c7737eb5beb278ed0.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/a23f32306d296829d2d5a3997e63e9c4f54452dfebfe13bf34d9ee6eb9b29ec3.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/ada75965055538556230762161fb5829df2e2bda12de82e24c9d0aec4de63e15.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/b76c96064d3a1eef8dbf2ad95c10e220da08be4b2203dbe3bed5e063090a164a.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/c7152e16af45313d40e6cd32591417d727f7f781e34cbd96cd3d0716d1a5fc8c.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/c73479f2c48be4ec998ffd20c079c22cbe23a523d7ee0e75e475544bcec1c8bf.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/cfd689ff36a543753dbb4069417b91b6ffadd87c1f2f535e8a9ca6e8f14c75cb.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/e3898b3c1015fcdf14b2ded9745068645e784bd58b6bdd07d46665dffeeee335.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/e5392d2b2097b1b3abe5e0cf8abd8c578f8c2ce31b6b6cc2d94f33e4f77011de.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/e78706ff4fb38d94863ba4a677a8e0924bc13bcf4f1a9e785d7329d141c9f5fb.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/e94e0430b251839d294e187004902d1dbe489bdffe5abc8d37ddabf5057b622d.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/e9f4e6a982201fc90e95acc8d10cd3279ec1fd92f33dda68976dcb0c88db272f.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/ee1d3dfe150c6f3ba8318bbfb1c8cbd0747a36b7590090dfc94540fe225535d0.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/ee93e837819a3a34757f24506b85165b97901af37eccb161b585053e90379120.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/f323a0f9a76830ce23bc882ee9bcc08d1f3043ef1b793a1b93b289b8e92b513a.json
Vendored
+1
File diff suppressed because one or more lines are too long
graphify-out/cache/ast/v0.9.22/f860e97e16ef806ce0f1473489eba58a4ab3df878e99456f492ccdd4c117fd76.json
Vendored
+1
@@ -0,0 +1 @@
|
||||
{"nodes": [{"id": "d_yt_channel_scraper_scripts_start_server_ps1", "label": "start-server.ps1", "file_type": "code", "source_file": "scripts/start-server.ps1", "source_location": "L1"}, {"id": "d_yt_channel_scraper_scripts_start_server_out_line", "label": "Out-Line()", "file_type": "code", "source_file": "scripts/start-server.ps1", "source_location": "L10"}, {"id": "d_yt_channel_scraper_scripts_start_server_open_browser", "label": "Open-Browser()", "file_type": "code", "source_file": "scripts/start-server.ps1", "source_location": "L17"}, {"id": "d_yt_channel_scraper_scripts_start_server_test_portopen", "label": "Test-PortOpen()", "file_type": "code", "source_file": "scripts/start-server.ps1", "source_location": "L31"}, {"id": "d_yt_channel_scraper_scripts_start_server_get_serverhealth", "label": "Get-ServerHealth()", "file_type": "code", "source_file": "scripts/start-server.ps1", "source_location": "L42"}, {"id": "d_yt_channel_scraper_scripts_start_server_is_pidalive", "label": "Is-PidAlive()", "file_type": "code", "source_file": "scripts/start-server.ps1", "source_location": "L50"}, {"id": "d_yt_channel_scraper_scripts_start_server_show_state", "label": "Show-State()", "file_type": "code", "source_file": "scripts/start-server.ps1", "source_location": "L56"}], "edges": [{"source": "d_yt_channel_scraper_scripts_start_server_ps1", "target": "d_yt_channel_scraper_scripts_start_server_out_line", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/start-server.ps1", "source_location": "L10", "weight": 1.0}, {"source": "d_yt_channel_scraper_scripts_start_server_ps1", "target": "d_yt_channel_scraper_scripts_start_server_open_browser", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/start-server.ps1", "source_location": "L17", "weight": 1.0}, {"source": "d_yt_channel_scraper_scripts_start_server_ps1", "target": "d_yt_channel_scraper_scripts_start_server_test_portopen", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/start-server.ps1", "source_location": "L31", "weight": 1.0}, {"source": "d_yt_channel_scraper_scripts_start_server_ps1", "target": "d_yt_channel_scraper_scripts_start_server_get_serverhealth", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/start-server.ps1", "source_location": "L42", "weight": 1.0}, {"source": "d_yt_channel_scraper_scripts_start_server_ps1", "target": "d_yt_channel_scraper_scripts_start_server_is_pidalive", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/start-server.ps1", "source_location": "L50", "weight": 1.0}, {"source": "d_yt_channel_scraper_scripts_start_server_ps1", "target": "d_yt_channel_scraper_scripts_start_server_show_state", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/start-server.ps1", "source_location": "L56", "weight": 1.0}, {"source": "d_yt_channel_scraper_scripts_start_server_open_browser", "target": "d_yt_channel_scraper_scripts_start_server_out_line", "relation": "calls", "confidence": "EXTRACTED", "source_file": "scripts/start-server.ps1", "source_location": "L22", "weight": 1.0}, {"source": "d_yt_channel_scraper_scripts_start_server_show_state", "target": "d_yt_channel_scraper_scripts_start_server_out_line", "relation": "calls", "confidence": "EXTRACTED", "source_file": "scripts/start-server.ps1", "source_location": "L57", "weight": 1.0}], "raw_calls": [{"caller_nid": "d_yt_channel_scraper_scripts_start_server_out_line", "callee": "Write-Host", "is_member_call": false, "source_file": "scripts/start-server.ps1", "source_location": "L11"}, {"caller_nid": "d_yt_channel_scraper_scripts_start_server_out_line", "callee": "Write-Host", "is_member_call": false, "source_file": "scripts/start-server.ps1", "source_location": "L12"}, {"caller_nid": "d_yt_channel_scraper_scripts_start_server_open_browser", "callee": "Start-Process", "is_member_call": false, "source_file": "scripts/start-server.ps1", "source_location": "L19"}, {"caller_nid": "d_yt_channel_scraper_scripts_start_server_test_portopen", "callee": "New-Object", "is_member_call": false, "source_file": "scripts/start-server.ps1", "source_location": "L32"}, {"caller_nid": "d_yt_channel_scraper_scripts_start_server_get_serverhealth", "callee": "Invoke-WebRequest", "is_member_call": false, "source_file": "scripts/start-server.ps1", "source_location": "L44"}, {"caller_nid": "d_yt_channel_scraper_scripts_start_server_is_pidalive", "callee": "Get-Process", "is_member_call": false, "source_file": "scripts/start-server.ps1", "source_location": "L52"}, {"caller_nid": "d_yt_channel_scraper_scripts_start_server_show_state", "callee": "Get-Date", "is_member_call": false, "source_file": "scripts/start-server.ps1", "source_location": "L57"}]}
|
||||
Vendored
+1
@@ -0,0 +1 @@
|
||||
1787443350.5198534
|
||||
Vendored
+1
-1
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
+12669
-1545
File diff suppressed because it is too large
Load Diff
+121
-51
@@ -5,14 +5,14 @@
|
||||
"semantic_hash": "f80dc007b3b67c7f7a78d9df01a81ead"
|
||||
},
|
||||
"scripts/start-server.ps1": {
|
||||
"mtime": 1785130613.533591,
|
||||
"ast_hash": "9baf397df6c14b7917ca59fbe6df61cc",
|
||||
"semantic_hash": "9baf397df6c14b7917ca59fbe6df61cc"
|
||||
"mtime": 1785132936.4055703,
|
||||
"ast_hash": "7390a228e676bff301ae85c5a4e7449e",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"scripts/stop-server.ps1": {
|
||||
"mtime": 1785127403.2329483,
|
||||
"ast_hash": "4398501c202a3eb624fb439f6d03fcf5",
|
||||
"semantic_hash": "4398501c202a3eb624fb439f6d03fcf5"
|
||||
"mtime": 1785132762.2959402,
|
||||
"ast_hash": "4a62db3fa3dca6b7109fcaadc1219226",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/__init__.py": {
|
||||
"mtime": 1785120608.3336751,
|
||||
@@ -30,14 +30,14 @@
|
||||
"semantic_hash": "1bf51b7c13486b9db9bcc3420fba2593"
|
||||
},
|
||||
"src/yt_scraper/cli.py": {
|
||||
"mtime": 1785126572.0575886,
|
||||
"ast_hash": "9734cedf7c1e045e1ab0e4a102860e29",
|
||||
"semantic_hash": "9734cedf7c1e045e1ab0e4a102860e29"
|
||||
"mtime": 1785561823.2458293,
|
||||
"ast_hash": "100604834f369047b55641bd327333d0",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/config.py": {
|
||||
"mtime": 1785120620.335521,
|
||||
"ast_hash": "2f3c8f7768a942e12c0a9e41b54891be",
|
||||
"semantic_hash": "2f3c8f7768a942e12c0a9e41b54891be"
|
||||
"mtime": 1785561416.2574291,
|
||||
"ast_hash": "712dddce27149cb3a5ceb34f78fac2fd",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/cookies.py": {
|
||||
"mtime": 1785126417.4218228,
|
||||
@@ -45,9 +45,9 @@
|
||||
"semantic_hash": "dd5ec44bb4c6e6375be80f21307fc73d"
|
||||
},
|
||||
"src/yt_scraper/discover.py": {
|
||||
"mtime": 1785120708.331971,
|
||||
"ast_hash": "8db06d0b131575f709b55467eabdc2a9",
|
||||
"semantic_hash": "8db06d0b131575f709b55467eabdc2a9"
|
||||
"mtime": 1785569683.6527412,
|
||||
"ast_hash": "6b626a24ae81406ea549e9989c9f5d5b",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/export.py": {
|
||||
"mtime": 1785126439.6829402,
|
||||
@@ -55,14 +55,14 @@
|
||||
"semantic_hash": "f1cff31fb1004f08e997655f838e3a58"
|
||||
},
|
||||
"src/yt_scraper/extract.py": {
|
||||
"mtime": 1785122183.7294595,
|
||||
"ast_hash": "3e2179db2f7fd316d2b3acedee536086",
|
||||
"semantic_hash": "3e2179db2f7fd316d2b3acedee536086"
|
||||
"mtime": 1785561382.7161057,
|
||||
"ast_hash": "a46b96123cfef40a10436e6e65b45d4b",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/monitor.py": {
|
||||
"mtime": 1785126496.288271,
|
||||
"ast_hash": "a64188f938dc4f8917335ef41d333ead",
|
||||
"semantic_hash": "a64188f938dc4f8917335ef41d333ead"
|
||||
"mtime": 1785555591.7611978,
|
||||
"ast_hash": "e7948e61b74b84b246708518f02dbcae",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/parse.py": {
|
||||
"mtime": 1785120665.3384771,
|
||||
@@ -70,9 +70,9 @@
|
||||
"semantic_hash": "25354365ac1ab52f1561c97256573806"
|
||||
},
|
||||
"src/yt_scraper/pipeline.py": {
|
||||
"mtime": 1785131195.7311583,
|
||||
"ast_hash": "ebce1b294140bf40f809848ef280c290",
|
||||
"semantic_hash": "ebce1b294140bf40f809848ef280c290"
|
||||
"mtime": 1785569737.341973,
|
||||
"ast_hash": "4e22e69083b15c4b937fca406134539c",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/ratelimit.py": {
|
||||
"mtime": 1785120650.3795395,
|
||||
@@ -85,14 +85,14 @@
|
||||
"semantic_hash": "ff83764f3a8c8874557993e11eab1f89"
|
||||
},
|
||||
"src/yt_scraper/segments.py": {
|
||||
"mtime": 1785128385.6652262,
|
||||
"ast_hash": "09c7da35bc09a3f75fd0a627c0534746",
|
||||
"semantic_hash": "09c7da35bc09a3f75fd0a627c0534746"
|
||||
"mtime": 1785562183.2376134,
|
||||
"ast_hash": "902d851e321b83c99d4cae30c1ae39fc",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/store.py": {
|
||||
"mtime": 1785131583.548138,
|
||||
"ast_hash": "9a3d4286214aa54ae4ac4df2097b643d",
|
||||
"semantic_hash": "9a3d4286214aa54ae4ac4df2097b643d"
|
||||
"mtime": 1785569922.3510046,
|
||||
"ast_hash": "ea9a69606929df7ff0508814f2733204",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/webapp/__init__.py": {
|
||||
"mtime": 1785126827.4957752,
|
||||
@@ -100,24 +100,24 @@
|
||||
"semantic_hash": "d41d8cd98f00b204e9800998ecf8427e"
|
||||
},
|
||||
"src/yt_scraper/webapp/api.py": {
|
||||
"mtime": 1785131595.9914868,
|
||||
"ast_hash": "e64174f04d6eab0747b1d2a7c2a96a01",
|
||||
"semantic_hash": "e64174f04d6eab0747b1d2a7c2a96a01"
|
||||
"mtime": 1785569846.188889,
|
||||
"ast_hash": "e63b87bc3804f92f9078cdf36d7181da",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/webapp/app.py": {
|
||||
"mtime": 1785126888.8032887,
|
||||
"ast_hash": "e0b1925b4318305dcf746d360373ff50",
|
||||
"semantic_hash": "e0b1925b4318305dcf746d360373ff50"
|
||||
"mtime": 1785562107.3107448,
|
||||
"ast_hash": "80e375becb41e202f78239138252c5c8",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/webapp/jobs.py": {
|
||||
"mtime": 1785131211.0397103,
|
||||
"ast_hash": "8b6c80001ff8c95eaaa16f7b61d1f207",
|
||||
"semantic_hash": "8b6c80001ff8c95eaaa16f7b61d1f207"
|
||||
"mtime": 1785556090.2023566,
|
||||
"ast_hash": "45ba7f10b13b847c213f04441a5e741d",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/webapp/static/app.js": {
|
||||
"mtime": 1785131664.8792574,
|
||||
"ast_hash": "f6b081fadc5884d379152abbd1e59700",
|
||||
"semantic_hash": "f6b081fadc5884d379152abbd1e59700"
|
||||
"mtime": 1785569873.551512,
|
||||
"ast_hash": "0f4fc27cfdde0a10ef3c568774b199a2",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_chapters.py": {
|
||||
"mtime": 1785120789.3300896,
|
||||
@@ -140,9 +140,9 @@
|
||||
"semantic_hash": "27125960e235813724fd669001faab59"
|
||||
},
|
||||
"tests/test_store_platform.py": {
|
||||
"mtime": 1785126662.4772756,
|
||||
"ast_hash": "bad13dcf37be7a414ffae8018c29e55b",
|
||||
"semantic_hash": "bad13dcf37be7a414ffae8018c29e55b"
|
||||
"mtime": 1785194588.4186954,
|
||||
"ast_hash": "44069db75a444906fb5001880dedf180",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
".opencode/agent/webapp-builder.md": {
|
||||
"mtime": 1785126783.7152567,
|
||||
@@ -165,9 +165,9 @@
|
||||
"semantic_hash": "a0a8e6b62a991fce5d6c58171f80075e"
|
||||
},
|
||||
"config.example.yaml": {
|
||||
"mtime": 1785120602.4114335,
|
||||
"ast_hash": "415b0fc8e71ecc305d21e9c3c08d585a",
|
||||
"semantic_hash": "415b0fc8e71ecc305d21e9c3c08d585a"
|
||||
"mtime": 1785561451.814817,
|
||||
"ast_hash": "43661d5c00d05c922bcf884e8ac707c3",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"docs/superpowers/plans/2026-07-26-platform-build.md": {
|
||||
"mtime": 1785126240.4211702,
|
||||
@@ -180,8 +180,78 @@
|
||||
"semantic_hash": "9b85f02fd45c93cdabfd2e1c6d1e0c9e"
|
||||
},
|
||||
"src/yt_scraper/webapp/static/index.html": {
|
||||
"mtime": 1785131695.7653384,
|
||||
"ast_hash": "13591b7c8c662d8e7c2540f3032ae26d",
|
||||
"semantic_hash": "13591b7c8c662d8e7c2540f3032ae26d"
|
||||
"mtime": 1785570599.948749,
|
||||
"ast_hash": "46b1cb57281f7683acc5b39714d74073",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/yt_scraper/_yt_http.py": {
|
||||
"mtime": 1785134945.1512043,
|
||||
"ast_hash": "8af224580322df5aeeba10062592d961",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_config.py": {
|
||||
"mtime": 1785561477.3907576,
|
||||
"ast_hash": "46f3eefb24bcf44535c17977ac175509",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_discover_incremental.py": {
|
||||
"mtime": 1785555704.1061945,
|
||||
"ast_hash": "e1c382a9b8f5c927a85d67814d3dbb09",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_extract.py": {
|
||||
"mtime": 1785561483.422817,
|
||||
"ast_hash": "9949ef4f6e7fe8cbdf12bc8d1dc71e3f",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_store_sync_watermark.py": {
|
||||
"mtime": 1785555725.6495814,
|
||||
"ast_hash": "9f9943f5b914078cee49bf4aaa060564",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_webapp_jobs.py": {
|
||||
"mtime": 1785555746.4912646,
|
||||
"ast_hash": "7688c701256ff0cdd2a7d78d7090c8b3",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"CLAUDE.md": {
|
||||
"mtime": 1785570018.086969,
|
||||
"ast_hash": "e478d29b66549d4a24cdd0f91ddfc2aa",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"YOUTUBE-TRANSCRIPT-AUDIT.md": {
|
||||
"mtime": 1785116715.5118847,
|
||||
"ast_hash": "67c5b7e3b4661ca8c8a7280e63b13ba9",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"docs/superpowers/plans/2026-07-27-discovery-only-scrape.md": {
|
||||
"mtime": 1785192916.5353482,
|
||||
"ast_hash": "3cf41d6331bd67e39ccd96b0e6138cf2",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"docs/superpowers/specs/2026-07-27-discovery-only-scrape-design.md": {
|
||||
"mtime": 1785192898.2889626,
|
||||
"ast_hash": "529b39e9bd2adcafd17a2dc30263281c",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_recovery.py": {
|
||||
"mtime": 1785569307.786051,
|
||||
"ast_hash": "53f25aeda88cbf3755f45f2377970b62",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_since_filter.py": {
|
||||
"mtime": 1785556104.7475204,
|
||||
"ast_hash": "1d827c61156ab488e838dac91261624f",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
".claude/settings.json": {
|
||||
"mtime": 1785569155.4443069,
|
||||
"ast_hash": "dc072413449915d630bc773c9fb57dc7",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_blocked_videos.py": {
|
||||
"mtime": 1785569898.4683661,
|
||||
"ast_hash": "674b087c46f1ee8de0e650295f0cb8cd",
|
||||
"semantic_hash": ""
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user