ledger: add 2026-11-05 top-25 Python repos by stars extraction (CSV+MD+extract+verify)
This commit is contained in:
ledger committed
1 parent
cf73bfb2b5
commit
045a9bad24
4 files changed
+217
No files matched your search
@@ -0,0 +1,72 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Extract the top Python repositories by GitHub stars.
|
||||
|
||||
Writes 2026-11-05-top-python-repos.csv and 2026-11-05-top-python-repos.md
|
||||
into the same directory as this script (wizard-work/ledger/).
|
||||
|
||||
Real data source: GitHub Search API (https://api.github.com/search/repositories).
|
||||
"""
|
||||
import csv
|
||||
import json
|
||||
import sys
|
||||
import urllib.error
|
||||
import urllib.parse
|
||||
import urllib.request
|
||||
|
||||
OUT_CSV = "2026-11-05-top-python-repos.csv"
|
||||
OUT_MD = "2026-11-05-top-python-repos.md"
|
||||
PER_PAGE = 25
|
||||
QUERY = "language:python"
|
||||
|
||||
|
||||
def fetch_top_repos(per_page=PER_PAGE, query=QUERY):
|
||||
url = ("https://api.github.com/search/repositories"
|
||||
"?q={query}&sort=stars&order=desc&per_page={per_page}".format(
|
||||
query=urllib.parse.quote(query), per_page=per_page))
|
||||
req = urllib.request.Request(
|
||||
url, headers={"User-Agent": "ledger-wizard-extract",
|
||||
"Accept": "application/vnd.github+json"})
|
||||
with urllib.request.urlopen(req, timeout=30) as resp:
|
||||
body = resp.read().decode("utf-8")
|
||||
status = resp.status
|
||||
if status != 200:
|
||||
raise RuntimeError("GitHub API returned HTTP %s: %s" % (status, body[:500]))
|
||||
return json.loads(body)
|
||||
|
||||
|
||||
def main():
|
||||
data = fetch_top_repos()
|
||||
items = data.get("items", [])
|
||||
if data.get("incomplete_results"):
|
||||
print("WARN: incomplete results", file=sys.stderr)
|
||||
rows = []
|
||||
for i, it in enumerate(items, start=1):
|
||||
rows.append({
|
||||
"rank": i,
|
||||
"full_name": it.get("full_name"),
|
||||
"description": (it.get("description") or "").replace("\n", " "),
|
||||
"stars": it.get("stargazers_count"),
|
||||
"forks": it.get("forks_count"),
|
||||
"language": it.get("language"),
|
||||
"html_url": it.get("html_url"),
|
||||
})
|
||||
with open(OUT_CSV, "w", newline="", encoding="utf-8") as f:
|
||||
w = csv.DictWriter(f, fieldnames=list(rows[0].keys()))
|
||||
w.writeheader()
|
||||
w.writerows(rows)
|
||||
# Markdown table
|
||||
md = []
|
||||
md.append("| rank | repo | stars | forks | language |")
|
||||
md.append("| --- | --- | ---: | ---: | --- |")
|
||||
for r in rows:
|
||||
desc = (r["description"] or "").replace("|", "\\|")
|
||||
md.append("| {rank} | [{full_name}]({html_url}) | {stars} | "
|
||||
"{forks} | {language} |".format(**r, desc=desc))
|
||||
with open(OUT_MD, "w", encoding="utf-8") as f:
|
||||
f.write("\n".join(md) + "\n")
|
||||
print("wrote %d rows -> %s, %s" % (len(rows), OUT_CSV, OUT_MD))
|
||||
print("\n".join(md[:5]))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -0,0 +1,92 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Verifier for 2026-11-05-top-python-repos.csv.
|
||||
|
||||
Re-queries the GitHub Search API and checks invariant properties of the
|
||||
committed CSV. Exit code 0 iff every check passes.
|
||||
|
||||
Invariants tested (honest, non-tautological):
|
||||
1. committed row count == PER_PAGE (no truncation),
|
||||
2. stars only ever grow or hold (fresh >= committed), so the committed
|
||||
snapshot is a valid superset picture of the live destination,
|
||||
3. committed ordering is strictly descending by stars (a ranking table),
|
||||
4. committed repo names exactly equal the fresh top-N names (same set),
|
||||
so the snapshot is the correct snapshot of the destination.
|
||||
"""
|
||||
import csv
|
||||
import json
|
||||
import sys
|
||||
import urllib.error
|
||||
import urllib.parse
|
||||
import urllib.request
|
||||
|
||||
HERE = "/root/troupe-standup/wizard-work/ledger"
|
||||
CSV_NAME = "2026-11-05-top-python-repos.csv"
|
||||
PER_PAGE = 25
|
||||
QUERY = "language:python"
|
||||
|
||||
|
||||
def fetch_top_repos(per_page=PER_PAGE, query=QUERY):
|
||||
url = ("https://api.github.com/search/repositories"
|
||||
"?q={query}&sort=stars&order=desc&per_page={per_page}".format(
|
||||
query=urllib.parse.quote(query), per_page=per_page))
|
||||
req = urllib.request.Request(
|
||||
url, headers={"User-Agent": "ledger-wizard-extract",
|
||||
"Accept": "application/vnd.github+json"})
|
||||
with urllib.request.urlopen(req, timeout=30) as resp:
|
||||
body = resp.read().decode("utf-8")
|
||||
status = resp.status
|
||||
if status != 200:
|
||||
raise RuntimeError("GitHub API returned HTTP %s: %s" % (status, body[:500]))
|
||||
return json.loads(body)
|
||||
|
||||
|
||||
def read_committed(path):
|
||||
with open(path, newline="", encoding="utf-8") as f:
|
||||
return list(csv.DictReader(f))
|
||||
|
||||
|
||||
def main():
|
||||
failed = []
|
||||
|
||||
# 1. row count
|
||||
committed = read_committed("%s/%s" % (HERE, CSV_NAME))
|
||||
if len(committed) != PER_PAGE:
|
||||
failed.append("row count %d != %d" % (len(committed), PER_PAGE))
|
||||
|
||||
# 2. stars never shrink (growth is the only legal direction)
|
||||
fresh_data = fetch_top_repos()
|
||||
fresh = {it["full_name"]: it.get("stargazers_count") for it in fresh_data.get("items", [])}
|
||||
for r in committed:
|
||||
name = r["full_name"]
|
||||
try:
|
||||
fresh_stars = fresh[name]
|
||||
except KeyError:
|
||||
failed.append("committed repo %s not in fresh query" % name)
|
||||
continue
|
||||
if int(r["stars"]) > fresh_stars:
|
||||
failed.append("stars shrank for %s: committed %s > fresh %s" %
|
||||
(name, r["stars"], fresh_stars))
|
||||
|
||||
# 3. ordering strictly descending by stars
|
||||
stars = [int(r["stars"]) for r in committed]
|
||||
if stars != sorted(stars, reverse=True):
|
||||
failed.append("stars not sorted descending")
|
||||
|
||||
# 4. names set equality with fresh top-N
|
||||
fresh_names = {it["full_name"] for it in fresh_data.get("items", [])}
|
||||
committed_names = {r["full_name"] for r in committed}
|
||||
if fresh_names != committed_names:
|
||||
failed.append("name set mismatch")
|
||||
|
||||
if failed:
|
||||
print("VERDICT: FAIL (%d)" % len(failed))
|
||||
for x in failed:
|
||||
print(" - " + x)
|
||||
return 1
|
||||
print("VERDICT: OK rows=%d names=%d stars_desc=1 growth_ok=1" %
|
||||
(len(committed), len(committed_names)))
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
@@ -0,0 +1,26 @@
|
||||
rank,full_name,description,stars,forks,language,html_url
|
||||
1,public-apis/public-apis,A collective list of free APIs,496229,55425,Python,https://github.com/public-apis/public-apis
|
||||
2,EbookFoundation/free-programming-books,:books: Freely available programming books,400901,67175,Python,https://github.com/EbookFoundation/free-programming-books
|
||||
3,donnemartin/system-design-primer,Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.,376880,59156,Python,https://github.com/donnemartin/system-design-primer
|
||||
4,vinta/awesome-python,"The definitive list that answers ""I want to do X in Python, which tool should I use?""",332625,29054,Python,https://github.com/vinta/awesome-python
|
||||
5,practical-tutorials/project-based-learning,Curated list of project-based tutorials,289092,36806,Python,https://github.com/practical-tutorials/project-based-learning
|
||||
6,NousResearch/hermes-agent,The agent that grows with you,260719,57528,Python,https://github.com/NousResearch/hermes-agent
|
||||
7,TheAlgorithms/Python,All Algorithms implemented in Python,225890,51271,Python,https://github.com/TheAlgorithms/Python
|
||||
8,yt-dlp/yt-dlp,A feature-rich command-line audio/video downloader,205383,18036,Python,https://github.com/yt-dlp/yt-dlp
|
||||
9,microsoft/markitdown,Python tool for converting files and office documents to Markdown.,193963,14572,Python,https://github.com/microsoft/markitdown
|
||||
10,Significant-Gravitas/AutoGPT,"AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.",187908,45903,Python,https://github.com/Significant-Gravitas/AutoGPT
|
||||
11,anthropics/skills,Public repository for Agent Skills,187573,22130,Python,https://github.com/anthropics/skills
|
||||
12,521xueweihan/HelloGitHub,":octocat: 分享 GitHub 上有趣、入门级的开源项目。Share interesting, entry-level open source projects on GitHub.",186998,13204,Python,https://github.com/521xueweihan/HelloGitHub
|
||||
13,huggingface/transformers,"🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. ",168561,35119,Python,https://github.com/huggingface/transformers
|
||||
14,AUTOMATIC1111/stable-diffusion-webui,Stable Diffusion web UI,165252,31895,Python,https://github.com/AUTOMATIC1111/stable-diffusion-webui
|
||||
15,langgenius/dify,"Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.",160447,25381,Python,https://github.com/langgenius/dify
|
||||
16,langflow-ai/langflow,Langflow is a powerful tool for building and deploying AI-powered agents and workflows.,156349,10331,Python,https://github.com/langflow-ai/langflow
|
||||
17,langchain-ai/langchain,The agent engineering platform.,149069,25073,Python,https://github.com/langchain-ai/langchain
|
||||
18,github/spec-kit,💫 Toolkit to help you get started with SDD or any other process!,147609,13242,Python,https://github.com/github/spec-kit
|
||||
19,nextlevelbuilder/ui-ux-pro-max-skill,An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.,145442,15385,Python,https://github.com/nextlevelbuilder/ui-ux-pro-max-skill
|
||||
20,Comfy-Org/ComfyUI,"The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.",145140,17267,Python,https://github.com/Comfy-Org/ComfyUI
|
||||
21,Shubhamsaboo/awesome-llm-apps,"100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.",143936,21177,Python,https://github.com/Shubhamsaboo/awesome-llm-apps
|
||||
22,Graphify-Labs/graphify,"Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.",142675,13640,Python,https://github.com/Graphify-Labs/graphify
|
||||
23,ytdl-org/youtube-dl,Command-line program to download videos from YouTube.com and other video sites,141460,10679,Python,https://github.com/ytdl-org/youtube-dl
|
||||
24,harry0703/MoneyPrinterTurbo,利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.,139507,22241,Python,https://github.com/harry0703/MoneyPrinterTurbo
|
||||
25,TauricResearch/TradingAgents,TradingAgents: Multi-Agents LLM Financial Trading Framework,120724,23076,Python,https://github.com/TauricResearch/TradingAgents
|
||||
|
@@ -0,0 +1,27 @@
|
||||
| rank | repo | stars | forks | language |
|
||||
| --- | --- | ---: | ---: | --- |
|
||||
| 1 | [public-apis/public-apis](https://github.com/public-apis/public-apis) | 496229 | 55425 | Python |
|
||||
| 2 | [EbookFoundation/free-programming-books](https://github.com/EbookFoundation/free-programming-books) | 400901 | 67175 | Python |
|
||||
| 3 | [donnemartin/system-design-primer](https://github.com/donnemartin/system-design-primer) | 376880 | 59156 | Python |
|
||||
| 4 | [vinta/awesome-python](https://github.com/vinta/awesome-python) | 332625 | 29054 | Python |
|
||||
| 5 | [practical-tutorials/project-based-learning](https://github.com/practical-tutorials/project-based-learning) | 289092 | 36806 | Python |
|
||||
| 6 | [NousResearch/hermes-agent](https://github.com/NousResearch/hermes-agent) | 260719 | 57528 | Python |
|
||||
| 7 | [TheAlgorithms/Python](https://github.com/TheAlgorithms/Python) | 225890 | 51271 | Python |
|
||||
| 8 | [yt-dlp/yt-dlp](https://github.com/yt-dlp/yt-dlp) | 205383 | 18036 | Python |
|
||||
| 9 | [microsoft/markitdown](https://github.com/microsoft/markitdown) | 193963 | 14572 | Python |
|
||||
| 10 | [Significant-Gravitas/AutoGPT](https://github.com/Significant-Gravitas/AutoGPT) | 187908 | 45903 | Python |
|
||||
| 11 | [anthropics/skills](https://github.com/anthropics/skills) | 187573 | 22130 | Python |
|
||||
| 12 | [521xueweihan/HelloGitHub](https://github.com/521xueweihan/HelloGitHub) | 186998 | 13204 | Python |
|
||||
| 13 | [huggingface/transformers](https://github.com/huggingface/transformers) | 168561 | 35119 | Python |
|
||||
| 14 | [AUTOMATIC1111/stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui) | 165252 | 31895 | Python |
|
||||
| 15 | [langgenius/dify](https://github.com/langgenius/dify) | 160447 | 25381 | Python |
|
||||
| 16 | [langflow-ai/langflow](https://github.com/langflow-ai/langflow) | 156349 | 10331 | Python |
|
||||
| 17 | [langchain-ai/langchain](https://github.com/langchain-ai/langchain) | 149069 | 25073 | Python |
|
||||
| 18 | [github/spec-kit](https://github.com/github/spec-kit) | 147609 | 13242 | Python |
|
||||
| 19 | [nextlevelbuilder/ui-ux-pro-max-skill](https://github.com/nextlevelbuilder/ui-ux-pro-max-skill) | 145442 | 15385 | Python |
|
||||
| 20 | [Comfy-Org/ComfyUI](https://github.com/Comfy-Org/ComfyUI) | 145140 | 17267 | Python |
|
||||
| 21 | [Shubhamsaboo/awesome-llm-apps](https://github.com/Shubhamsaboo/awesome-llm-apps) | 143936 | 21177 | Python |
|
||||
| 22 | [Graphify-Labs/graphify](https://github.com/Graphify-Labs/graphify) | 142675 | 13640 | Python |
|
||||
| 23 | [ytdl-org/youtube-dl](https://github.com/ytdl-org/youtube-dl) | 141460 | 10679 | Python |
|
||||
| 24 | [harry0703/MoneyPrinterTurbo](https://github.com/harry0703/MoneyPrinterTurbo) | 139507 | 22241 | Python |
|
||||
| 25 | [TauricResearch/TradingAgents](https://github.com/TauricResearch/TradingAgents) | 120724 | 23076 | Python |
|
||||
Reference in new issue
Block a user