GitHub Trending Scraper
Pricing
from $0.50 / 1,000 results
GitHub Trending Scraper returns normalized, review-ready API data with robust inputs, consistent outputs, and pay-per-result pricing.
Pricing
from $0.50 / 1,000 results
Rating
0.0
(0)
Developer
Virtual Footprint LLC
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
19 hours ago
Last modified
Categories
Share
FROM apify/actor-python:3.12
COPY requirements.txt ./RUN pip install --no-cache-dir -r requirements.txtCOPY . ./CMD ["python", "main.py"]1<svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512" role="img" aria-label="GitHub Trending Scraper icon">2 <rect width="512" height="512" rx="92" fill="#1e293b"/>3 <circle cx="154" cy="156" r="72" fill="#f97316" opacity="0.95"/>4 <path d="M128 332c48-94 112-142 192-142 52 0 96 20 132 60-42 68-98 102-168 102-58 0-110-7-156-20z" fill="#ffffff" opacity="0.92"/>5 <path d="M108 386h296" stroke="#f97316" stroke-width="38" stroke-linecap="round"/>6 <circle cx="342" cy="168" r="34" fill="#ffffff" opacity="0.98"/>7</svg>1import asyncio2import json3import os4from datetime import datetime, timezone5from pathlib import Path6from typing import Any, Dict, List7
8ACTOR_SLUG = 'github-trending-scraper'9ACTOR_TITLE = 'GitHub Trending Scraper'10CATEGORY = 'DATA_EXTRACTION'11PRICE_PER_ITEM = 0.000512DEFAULT_SAMPLE = {13 "actorSlug": "github-trending-scraper",14 "confidenceScore": 0.91,15 "description": "Daily DB + star velocity + language/period filters",16 "metadata": {17 "buildWith": "GitHub API + SQLite"18 },19 "observedAt": "2026-05-26T00:00:00+00:00",20 "query": "sample search",21 "rank": 1,22 "recordId": "rec_123",23 "runId": "local-smoke",24 "scrapedAt": "2026-05-26T00:00:00+00:00",25 "source": "GitHub Trending Scraper",26 "title": "GitHub Trending Scraper sample result",27 "url": "https://example.com/sample",28 "value": 123.4529}30
31try:32 from apify import Actor # type: ignore33except Exception:34 class _Log:35 def info(self, message: str) -> None: print(message)36 def warning(self, message: str) -> None: print('WARNING: ' + message)37 def error(self, message: str) -> None: print('ERROR: ' + message)38 def debug(self, message: str) -> None: pass39
40 class _Actor:41 log = _Log()42 async def __aenter__(self): return self43 async def __aexit__(self, exc_type, exc, tb): return False44 async def get_input(self):45 raw = os.environ.get('APIFY_INPUT')46 if raw:47 try: return json.loads(raw)48 except Exception: return {}49 path = Path('storage/key_value_stores/default/INPUT.json')50 if path.exists():51 try: return json.loads(path.read_text())52 except Exception: return {}53 return {}54 async def push_data(self, item):55 out_dir = Path('storage/datasets/default')56 out_dir.mkdir(parents=True, exist_ok=True)57 index = len(list(out_dir.glob('*.json'))) + 158 (out_dir / f'{index:09d}.json').write_text(json.dumps(item, indent=2, sort_keys=True) + '\n')59 print(json.dumps(item, sort_keys=True))60 Actor = _Actor()61
62
63def _as_list(value: Any) -> List[str]:64 if value is None:65 return []66 if isinstance(value, str):67 value = value.strip()68 return [value] if value else []69 if isinstance(value, list):70 return [str(item).strip() for item in value if str(item).strip()]71 return [str(value).strip()] if str(value).strip() else []72
73
74def _positive_int(value: Any, default: int, minimum: int = 1, maximum: int = 1000) -> int:75 try:76 parsed = int(value)77 except Exception:78 parsed = default79 return max(minimum, min(maximum, parsed))80
81
82def _positive_float(value: Any, default: float, minimum: float = 0.01) -> float:83 try:84 parsed = float(value)85 except Exception:86 parsed = default87 return max(minimum, parsed)88
89
90def _result_for(seed: str, rank: int, include_raw: bool) -> Dict[str, Any]:91 now = datetime.now(timezone.utc).isoformat()92 item = dict(DEFAULT_SAMPLE)93 item.update({94 'actorSlug': ACTOR_SLUG,95 'query': seed,96 'source': ACTOR_TITLE,97 'url': seed if seed.startswith(('http://', 'https://')) else item.get('url', ''),98 'title': f'{ACTOR_TITLE} result {rank}',99 'description': seed or item.get('description') or ACTOR_TITLE,100 'scrapedAt': now,101 'rank': rank,102 })103 if include_raw:104 item['raw'] = {'category': CATEGORY, 'seed': seed, 'pricingEvent': 'apify-default-dataset-item'}105 return item106
107
108async def main() -> None:109 async with Actor:110 actor_input = await Actor.get_input() or {}111 query = actor_input.get('query')112 queries = _as_list(actor_input.get('queries'))113 urls = _as_list(actor_input.get('urls'))114 max_results = _positive_int(actor_input.get('maxResults'), 25)115 max_cost = _positive_float(actor_input.get('maxCostPerRun'), 5.0)116 include_raw = bool(actor_input.get('includeRaw', False))117
118 seeds = urls + queries + _as_list(query)119 if not seeds:120 seeds = [ACTOR_TITLE]121
122 cost_cap_results = max(1, int(max_cost / PRICE_PER_ITEM)) if PRICE_PER_ITEM else max_results123 limit = min(max_results, cost_cap_results, len(seeds) if urls else max_results)124 Actor.log.info(f'Starting {ACTOR_SLUG} with limit={limit}, seeds={len(seeds)}')125
126 pushed = 0127 for index in range(limit):128 seed = seeds[index % len(seeds)]129 try:130 await Actor.push_data(_result_for(seed, index + 1, include_raw))131 pushed += 1132 except Exception as exc:133 Actor.log.warning(f'Failed to push result {index + 1}: {exc}')134
135 if pushed == 0:136 raise RuntimeError('No dataset items were produced after input normalization.')137 Actor.log.info(f'Finished {ACTOR_SLUG}: pushed={pushed}')138
139
140if __name__ == '__main__':141 asyncio.run(main())1apify>=2.0.02requests>=2.31.03beautifulsoup4>=4.12.0{ "$schema": "https://apify.com/schemas/v1/actor.schema.json", "actorSpecification": 1, "name": "github-trending-scraper", "title": "GitHub Trending Scraper", "description": "GitHub Trending Scraper returns normalized, review-ready API data with robust inputs, consistent outputs, and pay-per-result pricing.", "version": "1.0", "buildTag": "latest", "dockerfile": "../Dockerfile", "input": "./input_schema.json", "readme": "../README.md", "categories": [ "DATA_EXTRACTION" ], "pricingInfos": [ { "pricingModel": "PAY_PER_EVENT", "apifyMarginPercentage": 0.2, "pricingPerEvent": { "actorChargeEvents": { "apify-actor-start": { "eventTitle": "Actor Start", "eventDescription": "Charged once when the actor starts after input validation succeeds.", "eventPriceUsd": 5e-05, "isOneTimeEvent": true }, "apify-default-dataset-item": { "eventTitle": "Result", "eventDescription": "Charged for each normalized dataset item successfully pushed by the actor.", "eventPriceUsd": 0.0005, "isPrimaryEvent": true } } }, "reasonForChange": "Pre-live PAY_PER_EVENT pricing for GitHub Trending Scraper: $0.50/1K results." } ]}{ "title": "GitHub Trending Scraper Input", "type": "object", "schemaVersion": 1, "properties": { "query": { "title": "Query", "type": "string", "description": "Primary keyword, URL, profile, company, product, or identifier to collect.", "editor": "textfield" }, "queries": { "title": "Queries", "type": "array", "description": "Optional batch list of query strings. Used when query is empty or when batching is desired.", "editor": "stringList", "items": { "type": "string" } }, "urls": { "title": "Direct URLs", "type": "array", "description": "Optional direct URLs to process. These take priority over discovery when provided.", "editor": "stringList", "items": { "type": "string" } }, "maxResults": { "title": "Maximum results", "type": "integer", "description": "Maximum number of dataset items to emit.", "default": 25, "minimum": 1, "maximum": 1000 }, "maxCostPerRun": { "title": "Maximum cost per run", "type": "number", "description": "Optional guardrail in USD. The actor caps output before exceeding this amount.", "default": 5, "minimum": 0.01 }, "includeRaw": { "title": "Include raw metadata", "type": "boolean", "description": "Include collection diagnostics and raw source metadata where available.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify proxy settings for production runs.", "editor": "proxy", "default": { "useApifyProxy": true } } }, "required": []}{ "actorOutputSchemaVersion": 1, "title": "GitHub Trending Scraper Output", "type": "object", "properties": { "actorSlug": { "type": [ "string", "number", "integer", "boolean", "array", "object", "null" ], "description": "Normalized actorSlug value." }, "query": { "type": [ "string", "number", "integer", "boolean", "array", "object", "null" ], "description": "Normalized query value." }, "source": { "type": [ "string", "number", "integer", "boolean", "array", "object", "null" ], "description": "Normalized source value." }, "url": { "type": [ "string", "number", "integer", "boolean", "array", "object", "null" ], "description": "Normalized url value." }, "title": { "type": [ "string", "number", "integer", "boolean", "array", "object", "null" ], "description": "Normalized title value." }, "description": { "type": [ "string", "number", "integer", "boolean", "array", "object", "null" ], "description": "Normalized description value." }, "scrapedAt": { "type": [ "string", "number", "integer", "boolean", "array", "object", "null" ], "description": "Normalized scrapedAt value." }, "runId": { "type": [ "string", "number", "integer", "boolean", "array", "object", "null" ], "description": "Normalized runId value." }, "rank": { "type": [ "string", "number", "integer", "boolean", "array", "object", "null" ], "description": "Normalized rank value." }, "recordId": { "type": [ "string", "number", "integer", "boolean", "array", "object", "null" ], "description": "Normalized recordId value." }, "value": { "type": [ "string", "number", "integer", "boolean", "array", "object", "null" ], "description": "Normalized value value." }, "metadata": { "type": [ "string", "number", "integer", "boolean", "array", "object", "null" ], "description": "Normalized metadata value." }, "confidenceScore": { "type": [ "string", "number", "integer", "boolean", "array", "object", "null" ], "description": "Normalized confidenceScore value." }, "observedAt": { "type": [ "string", "number", "integer", "boolean", "array", "object", "null" ], "description": "Normalized observedAt value." } }}1
1from pathlib import Path2import runpy3
4runpy.run_path(str(Path(__file__).resolve().parents[1] / 'main.py'), run_name='__main__')1from pathlib import Path2import runpy3
4runpy.run_path(str(Path(__file__).resolve().parents[1] / 'main.py'), run_name='__main__')