How to download pull request metadata using the GitHub GraphQL API

This is a TypeScript Node.js script to download GitHub pull request information (title, body, comments, etc.) using the GitHub GraphQL API. The data is saved in a JSON file.

The GitHub repo is here: download-github-prs.

Create a GitHub personal access token

Create a GitHub personal access token as described here (no checkboxes need to be selected for public repos): https://docs.github.com/en/free-pro-team@latest/github/authenticating-to-github/creating-a-personal-access-token This is used to access the GitHub GraphQL API.

Intall libraries

• Create a directory and cd into it

  $ mkdir -p /tmp/my-prs
  $ cd /tmp/my-prs 
  

• Create package.json file:

  {
    "scripts": {
      "download": "ts-node index.ts"
    },
    "dependencies": {
      "node-fetch": "^2.6.1"
    },
    "devDependencies": {
      "@types/node-fetch": "^2.5.7",
      "ts-node": "^9.0.0",
      "typescript": "^4.1.2"
    }
  }
  

• Install

  $ npm install 
  

Create script

Creat a file, /tmp/my-prs/index.ts, replacing XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX with the GitHub personal access token described above.

import * as fs from "fs";
import fetch from "node-fetch";

const GITHUB_TOKEN = "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX";
const GITHUB_GRAPHQL_API_URL = "https://api.github.com/graphql";
const OUTPUT_DIR = "/tmp/my-prs";
const REPO_OWNER = "facebookexperimental";
const REPO_NAME = "Recoil";

fetchPullRequest(1);

/**
 * fetchPullRequest
 */
async function fetchPullRequest(prNumber: number) {
  const reactionFragment = `
    content
    user {
      login
    }
  `;
  const userContentEditFragment = `
    createdAt
    deletedAt
    deletedBy {
      login
    }
    diff
    editedAt
    editor {
      login
    }
    updatedAt
  `;
  const commentFragment = `
    author {
      login
    }
    body
    createdAt
    reactions(first: 100) {
      nodes {
        ${reactionFragment}
      }
    }
    userContentEdits(first: 100) {
      nodes {
        ${userContentEditFragment}
      }
    }
  `;
  const query = `
  query {
    repository(owner: "${REPO_OWNER}", name: "${REPO_NAME}") {
      nameWithOwner
      pullRequest(number: ${prNumber}) {
        author { login }
        baseRefName
        baseRefOid
        body
        closedAt
        comments(first: 100) {
          nodes {
            ${commentFragment}
          }
        }
        commits(first: 250) {
          nodes {
            commit {
              oid
            }
          }
        }
        createdAt
        files(first: 100) {
          nodes { path }
        }
        headRefName
        headRefOid
        mergeCommit { oid }
        merged
        mergedAt
        mergedBy { login }
        number
        publishedAt
        reactions(first: 10) {
          nodes {
            ${reactionFragment}
          }
        }
        reviews(first: 10) {
          nodes {
            author { login }
            body
            comments(first: 10) {
              nodes {
                ${commentFragment}
              }
            }
            commit {
              oid
            }
            createdAt
            editor { login }
            publishedAt
            reactions(first: 10) {
              nodes {
                ${reactionFragment}
              }
            }
            resourcePath
            submittedAt
            updatedAt
            userContentEdits(first: 10) {
              nodes {
                ${userContentEditFragment}
              }
            }
          }
        }
        state
        title
        updatedAt
        userContentEdits(first: 10) {
          nodes {
            ${userContentEditFragment}
          }
        }
      }
    }
  }
  `;

  // make graphql query and strigify the response
  const resp = await fetchQuery(query);
  const respStr = JSON.stringify(resp, null, 2);

  // save json file
  const filepath = [
    `${OUTPUT_DIR}/`,
    `${REPO_NAME}-pr-${String(prNumber).padStart(4, "0")}.json`,
  ].join("");
  console.log(`Saving ${filepath}...`);
  fs.writeFileSync(filepath, respStr);
}

/**
 * fetchQuery
 */
function fetchQuery(query: string, variables: Record<string, any> = {}) {
  return fetch(GITHUB_GRAPHQL_API_URL, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      Authorization: `bearer ${GITHUB_TOKEN}`,
    },
    body: JSON.stringify({
      query,
      variables,
    }),
  }).then((response) => {
    return response.json();
  });
}

Run it

$ npm run download 

Output

This produces the following JSON file

$ cat /tmp/my-prs/Recoil-pr-0001.json
{
  "data": {
    "repository": {
      "nameWithOwner": "facebookexperimental/Recoil",
      "pullRequest": {
        "author": {
          "login": "facebook-github-bot"
        },
        "baseRefName": "master",
        "baseRefOid": "40e870caadc159a87e81be291ff641410ab32e8f",
        "body": "This is pull request was created automatically because we noticed your project was missing a Contributing file.\n\nCONTRIBUTING files explain how a developer can contribute to the project - which you should actively encourage.\n\nThis PR was crafted with love by Facebook's Open Source Team.",
        "closedAt": "2020-05-13T04:12:15Z",
        "comments": {
          "nodes": [
            {
              "author": {
                "login": "davidmccabe"
              },
              "body": "Already added this manually.",
              "createdAt": "2020-05-13T04:12:15Z",
              "reactions": {
                "nodes": []
              },
              "userContentEdits": {
                "nodes": []
              }
            }
          ]
        },
        "commits": {
          "nodes": [
            {
              "commit": {
                "oid": "96f91679540362fa96a6c92611a8ef5621447b42"
              }
            }
          ]
        },
        "createdAt": "2020-05-06T22:31:01Z",
        "files": {
          "nodes": [
            {
              "path": "CONTRIBUTING.md"
            }
          ]
        },
        "headRefName": "automated_fixup_contributing_file_exists",
        "headRefOid": "96f91679540362fa96a6c92611a8ef5621447b42",
        "mergeCommit": null,
        "merged": false,
        "mergedAt": null,
        "mergedBy": null,
        "number": 1,
        "publishedAt": "2020-05-06T22:31:01Z",
        "reactions": {
          "nodes": []
        },
        "reviews": {
          "nodes": []
        },
        "state": "CLOSED",
        "title": "Adding Contributing file",
        "updatedAt": "2020-10-07T20:23:05Z",
        "userContentEdits": {
          "nodes": []
        }
      }
    }
  }
}