little-things/github-list-repos

#!/usr/bin/env python3
import logging
import re
import requests
import sys


users = sys.argv[1:]
assert users, 'Usage: github-list-repos USER [USER...]'


def get(url):
	while True:
		logging.info(f'Fetching {url}')
		r = requests.get(url, headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; rv:60.0) Gecko/20100101 Firefox/60.0'})
		if r.status_code == 429:
			logging.warning(f'Got 429, sleeping and retrying')
			time.sleep(5)
		else:
			break
	return r


for user in users:
	r = get(f'https://github.com/{user}')
	if '<div id="org-repositories"' in r.text:
		# Organisation, ?page=2 pagination
		page = 1
		while True:
			for m in re.finditer(r'<a itemprop="name codeRepository"\s(?:[^>]*\s)?data-hovercard-url="/([^/>"]+/[^/>"]+)/hovercard"', r.text):
				print(f'https://github.com/{m.group(1)}')
			if '<a class="next_page"' not in r.text:
				# End of pagination
				break
			page += 1
			r = get(f'https://github.com/{user}?page={page}')
	else:
		# User, ?tab=repositories + cursor pagination
		r = get(f'https://github.com/{user}?tab=repositories')
		while True:
			for m in re.finditer(r'<a href="/([^/>"]+/[^/>"]+)" itemprop="name codeRepository"(\s[^>]*)?>', r.text):
				print(f'https://github.com/{m.group(1)}')
			if not (m := re.search(r'<a\s(?:[^>]*\s)?href="https://github\.com/[^/?"]+\?after=([^&]+)&amp;tab=repositories"(?:\s[^>]*)?>', r.text)):
				# End of pagination
				break
			r = get(f'https://github.com/{user}?after={m.group(1)}&tab=repositories')