Created
May 15, 2014 00:51
-
-
Save philipn/20f24bea0b58575f7668 to your computer and use it in GitHub Desktop.
Test (doesn't work any longer) export to static html from LocalWiki
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import slumber | |
| import requests | |
| import os | |
| import lxml.html | |
| import urllib | |
| from urlparse import urljoin | |
| from utils import all, quote_fs | |
| SITE = 'https://trianglewiki.org' | |
| api = slumber.API(urljoin(SITE, '/api/')) | |
| dump_path = os.path.join(os.path.split(os.path.abspath(__file__))[0], 'dump') | |
| if not os.path.exists(dump_path): | |
| os.mkdir(dump_path) | |
| PROTOCOLS = ['http://', 'https://', 'mailto:'] | |
| def process_content(s): | |
| def _page_relative(link): | |
| if [True for p in PROTOCOLS if link.startswith(p)]: | |
| return link | |
| if link.startswith('_files/'): | |
| return link | |
| enc_link = quote_fs(urllib.unquote(link).decode('utf-8')) | |
| return (u"../%s" % enc_link) | |
| try: | |
| html = lxml.html.fromstring(s) | |
| except lxml.etree.ParserError: | |
| return '' | |
| html.rewrite_links(_page_relative) | |
| content = lxml.html.tostring(html) | |
| content = u"""<html> | |
| <head> | |
| <link href="../_static/css/base.css" rel="stylesheet" type="text/css"> | |
| <script type="text/javascript" src="../_static/js/base.js"></script> | |
| </head> | |
| <body> | |
| %s | |
| </body> | |
| </html>""" % content | |
| return content.encode('utf-8') | |
| def save_page_content(page): | |
| fsname = quote_fs(page['name']) | |
| page_dir = os.path.join(dump_path, fsname) | |
| if not os.path.exists(page_dir): | |
| os.mkdir(page_dir) | |
| content = process_content(page['content']) | |
| f = open(os.path.join(page_dir, 'index.html'), 'w') | |
| f.write(content) | |
| f.close() | |
| def save_files(page): | |
| fsname = quote_fs(page['name']) | |
| page_dir = os.path.join(dump_path, fsname) | |
| files_dir = os.path.join(page_dir, '_files') | |
| if not os.path.exists(files_dir): | |
| os.mkdir(files_dir) | |
| # Get files on page | |
| for file in all(api.file.get, slug=page['slug']): | |
| print " getting file %s" % file['name'] | |
| r = requests.get(urljoin(SITE, file['file'])) | |
| f = open(os.path.join(files_dir, file['name']), 'w') | |
| f.write(r.content) | |
| f.close() | |
| for page in all(api.page.get): | |
| print 'Getting page %s' % page['name'].encode('utf-8') | |
| save_page_content(page) | |
| save_files(page) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment