# coding=utf-8 import logging from pprint import pprint from atlassian import Confluence CONFLUENCE_URL = "http://conlfuence.example.com" CONFLUENCE_LOGIN = "******" CONFLUENCE_PASSWORD = "******" logging.basicConfig(level=logging.DEBUG) confluence = Confluence( url=CONFLUENCE_URL, username=CONFLUENCE_LOGIN, password=CONFLUENCE_PASSWORD, timeout=180, ) pgs = confluence.get_space_content("SPACE") pprint(pgs["page"]["results"])
if __name__ == "__main__": if not verify_environment_variables(): sys.exit( "Make sure that the environment variables ATLASSIAN_EMAIL and " "ATLASSIAN_API_TOKEN are set." ) confluence = Confluence( url="https://pyconjp.atlassian.net", username=os.getenv("ATLASSIAN_EMAIL"), password=os.getenv("ATLASSIAN_API_TOKEN"), ) space_content = confluence.get_space_content("pyconjp") pages = space_content["page"]["results"] print(f"{len(pages)} pages") print("-" * 40) for page in pages: title = page["title"] html_body = page["body"]["storage"]["value"] content = trim_html_tags(html_body) print(f"{title} ({len(content)} characters)") urls = extract_anchor_urls(html_body) for url in urls: # 共有ドライブへの直リンクと思しきリンクを洗い出す if re.match(r"https?://(docs|drive).google.com/.*", url): print(url)