Skip to content

Instantly share code, notes, and snippets.

@arjunlol

arjunlol/scrape-stargazers.py

Created September 26, 2023 06:26
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save arjunlol/d2f2ff99a65754fbe0cfd99f8adb764b to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save arjunlol/d2f2ff99a65754fbe0cfd99f8adb764b to your computer and use it in GitHub Desktop.
Download ZIP

Revisions

  1. arjunlol created this gist Sep 26, 2023.
    54 changes: 54 additions & 0 deletions scrape-stargazers.py
    View file
    Original file line number Diff line number Diff line change
    @@ -0,0 +1,54 @@
    import requests
    import csv
    import os

    from dotenv import load_dotenv


    load_dotenv()
    token = os.getenv("GITHUB_TOKEN")
    headers = {"Authorization": f"Bearer {token}"}

    owner = "paper-trail-gem"
    repo = "paper_trail"

    page = 1
    has_next_page = True

    csv_filename = f"{owner}_{repo}_stargazers.csv"
    with open(csv_filename, mode="w", newline="") as csv_file:
    fieldnames = ["Name", "Organization", "Github Link", "Email"]
    writer = csv.DictWriter(csv_file, fieldnames=fieldnames)
    writer.writeheader()

    while has_next_page:
    response = requests.get(
    f"https://api.github.com/repos/{owner}/{repo}/stargazers?page={page}", headers=headers
    )
    if response.status_code != 200:
    raise
    stargazers = response.json()

    for stargazer in stargazers:
    username = stargazer["login"]

    user_response = requests.get(f"https://api.github.com/users/{username}", headers=headers)
    user_data = user_response.json()

    if user_data["company"] is not None:
    name = user_data.get("name", "")
    organization = user_data["company"]
    email = user_data.get("email")
    link = f"https://github.com/{username}"

    row = {"Name": name, "Organization": organization, "Github Link": link, "Email": email}
    writer.writerow(row)
    print(f"Checkpoint - scraped page {page}")

    link_header = response.headers.get("Link", "")
    if "rel=\"next\"" not in link_header:
    has_next_page = False
    else:
    page += 1

    print(f"Stargazers' information has been scraped and saved to {csv_filename}.")