GitHub: scrapers and the official API, compared

from apify_client import ApifyClient

client = ApifyClient("<YOUR_APIFY_TOKEN>")
run_input = {
    "mode": "search",
    "searchQuery": "stars:>10000 language:python",
    "repositoryUrls": [
        "https://github.com/apify/crawlee"
    ],
    "sortBy": "stars",
    "sortOrder": "desc",
    "minStars": 0,
    "minForks": 0,
    "includeForks": False,
    "includeArchived": True,
    "maxResults": 30,
    "includeReadme": True,
    "includeTopics": True,
    "includeLanguages": True,
    "includeRepoDetails": False,
    "includeReleases": False,
    "releasesLimit": 10,
    "includeContributors": False,
    "contributorsLimit": 30,
    "includeActivity": False
}

run = client.actor("nimbryxo-studio/github-repository-metadata-and-readme-extractor").call(run_input=run_input)
if run is None:
    raise RuntimeError("The Actor run was not found.")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

import { ApifyClient } from "apify-client";

const client = new ApifyClient({ token: "<YOUR_APIFY_TOKEN>" });
const input = {
    "mode": "search",
    "searchQuery": "stars:>10000 language:python",
    "repositoryUrls": [
        "https://github.com/apify/crawlee"
    ],
    "sortBy": "stars",
    "sortOrder": "desc",
    "minStars": 0,
    "minForks": 0,
    "includeForks": false,
    "includeArchived": true,
    "maxResults": 30,
    "includeReadme": true,
    "includeTopics": true,
    "includeLanguages": true,
    "includeRepoDetails": false,
    "includeReleases": false,
    "releasesLimit": 10,
    "includeContributors": false,
    "contributorsLimit": 30,
    "includeActivity": false
};

const run = await client.actor("nimbryxo-studio/github-repository-metadata-and-readme-extractor").call(input);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items);

curl -X POST "https://api.apify.com/v2/actors/nimbryxo-studio~github-repository-metadata-and-readme-extractor/run-sync-get-dataset-items"   -H "Authorization: Bearer $APIFY_TOKEN"   -H "Content-Type: application/json"   -d '{"mode":"search","searchQuery":"stars:>10000 language:python","repositoryUrls":["https://github.com/apify/crawlee"],"sortBy":"stars","sortOrder":"desc","minStars":0,"minForks":0,"includeForks":false,"includeArchived":true,"maxResults":30,"includeReadme":true,"includeTopics":true,"includeLanguages":true,"includeRepoDetails":false,"includeReleases":false,"releasesLimit":10,"includeContributors":false,"contributorsLimit":30,"includeActivity":false}'

{
  "mcpServers": {
    "apify": {
      "url": "https://mcp.apify.com?tools=nimbryxo-studio/github-repository-metadata-and-readme-extractor",
      "headers": {
        "Authorization": "Bearer <YOUR_APIFY_TOKEN>"
      }
    }
  }
}