github_api.py 文件源码

def paged_github_json_request(url, headers=None):

    response = requests.get(url, headers=headers)
    assert response.ok, response.content
    results = response.json()

    if 'Link' in response.headers:

        links = response.headers['Link']

        # There are likely better ways to parse/extract the link information
        # but here we just find the last page number mentioned in the header
        # 'Link' section and then loop over all pages to get the comments
        last_match = list(re.finditer('page=[0-9]+', links))[-1]
        last_page = int(links[last_match.start():last_match.end()].split('=')[1])

        # If there are other pages, just loop over them and get all the
        # comments
        if last_page > 1:
            for page in range(2, last_page + 1):
                response = requests.get(url + '?page={0}'.format(page), headers=headers)
                assert response.ok, response.content
                results += response.json()

    return results