Convert GitHub API JSON to CSV

Export all issues from a repository (handles pagination and rate limits)

import requests
import pandas as pd
import time

TOKEN = "ghp_..."  # GitHub personal access token
OWNER = "torvalds"
REPO  = "linux"

headers = {
    "Authorization": f"Bearer {TOKEN}",
    "Accept": "application/vnd.github+json",
    "X-GitHub-Api-Version": "2022-11-28",
}

issues = []
page = 1

while True:
    r = requests.get(
        f"https://api.github.com/repos/{OWNER}/{REPO}/issues",
        headers=headers,
        params={"state": "all", "per_page": 100, "page": page},
    )
    r.raise_for_status()

    # Check rate limit
    remaining = int(r.headers.get("X-RateLimit-Remaining", 1))
    if remaining < 5:
        reset_at = int(r.headers.get("X-RateLimit-Reset", time.time() + 60))
        wait = max(0, reset_at - time.time()) + 2
        print(f"Rate limit low — waiting {wait:.0f}s")
        time.sleep(wait)

    batch = r.json()
    if not batch:
        break

    issues.extend(batch)
    page += 1
    time.sleep(0.1)  # be polite

print(f"Fetched {len(issues)} issues/PRs")

# Flatten
rows = []
for issue in issues:
    rows.append({
        "number":        issue["number"],
        "title":         issue["title"],
        "state":         issue["state"],
        "author":        issue["user"]["login"] if issue.get("user") else "",
        "labels":        ", ".join(l["name"] for l in issue.get("labels", [])),
        "assignee":      issue["assignee"]["login"] if issue.get("assignee") else "",
        "milestone":     issue["milestone"]["title"] if issue.get("milestone") else "",
        "comments":      issue.get("comments", 0),
        "is_pr":         "pull_request" in issue,  # PRs appear in issues endpoint
        "created_at":    issue.get("created_at", "")[:10],
        "updated_at":    issue.get("updated_at", "")[:10],
        "closed_at":     (issue.get("closed_at") or "")[:10],
    })

df = pd.DataFrame(rows)
df.to_csv(f"{OWNER}_{REPO}_issues.csv", index=False, encoding="utf-8-sig")
print(f"Exported {len(df)} rows")

Export pull requests with review status and merge info

import requests
import pandas as pd

TOKEN = "ghp_..."
OWNER = "your-org"
REPO  = "your-repo"

headers = {
    "Authorization": f"Bearer {TOKEN}",
    "Accept": "application/vnd.github+json",
}

prs = []
page = 1
while True:
    r = requests.get(
        f"https://api.github.com/repos/{OWNER}/{REPO}/pulls",
        headers=headers,
        params={"state": "all", "per_page": 100, "page": page},
    )
    batch = r.json()
    if not batch:
        break
    prs.extend(batch)
    page += 1

rows = []
for pr in prs:
    rows.append({
        "pr_number":     pr["number"],
        "title":         pr["title"],
        "state":         pr["state"],
        "author":        pr["user"]["login"] if pr.get("user") else "",
        "base_branch":   pr.get("base", {}).get("ref"),
        "head_branch":   pr.get("head", {}).get("ref"),
        "draft":         pr.get("draft", False),
        "merged":        pr.get("merged_at") is not None,
        "labels":        ", ".join(l["name"] for l in pr.get("labels", [])),
        "reviewers":     ", ".join(r["login"] for r in pr.get("requested_reviewers", [])),
        "created_at":    (pr.get("created_at") or "")[:10],
        "merged_at":     (pr.get("merged_at") or "")[:10],
        "closed_at":     (pr.get("closed_at") or "")[:10],
        "additions":     pr.get("additions", 0),
        "deletions":     pr.get("deletions", 0),
        "changed_files": pr.get("changed_files", 0),
    })

pd.DataFrame(rows).to_csv(f"{OWNER}_{REPO}_prs.csv", index=False, encoding="utf-8-sig")
print(f"Exported {len(rows)} pull requests")