X-Git-Url: https://projects.mako.cc/source/kuro5hin_to_wordpress/blobdiff_plain/5de5b8f8fb9e044d3149b3c4e91369e43586cd5b..67dc510ff5b8776de8d688f8ed5486d3d1359fe2:/k5_to_wordpress_diary_importer.py

diff --git a/k5_to_wordpress_diary_importer.py b/k5_to_wordpress_diary_importer.py
new file mode 100755
index 0000000..c41cb95
--- /dev/null
+++ b/k5_to_wordpress_diary_importer.py
@@ -0,0 +1,84 @@
+#!/usr/bin/python3
+# -*- coding: utf-8  -*-
+""" Script to parse raw HTML pages that reflect Kuro5hin diaries and repost them to a Wordpress blog using in the Wordpress XML RPC API. """
+
+# © Benjamin Mako Hill, 2018
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+
+from subprocess import check_output
+import sys
+from lxml import html
+import re
+from dateutil import parser
+
+from wordpress_xmlrpc import Client, WordPressPost
+from wordpress_xmlrpc.methods.posts import GetPosts, NewPost
+from wordpress_xmlrpc.methods.users import GetUserInfo
+
+## EDIT THIS SECTION BEFORE RUNNING!
+#########################################################
+
+wp_user = "mako"
+wp_password = check_output(["gpg", "--quiet", "--batch", "--decrypt", "/home/mako/.copyrighteous_password.gpg.asc"]).decode("utf-8").strip()
+wp_xmlrpc_endpoint = 'https://mako.cc/copyrighteous/xmlrpc.php'
+wp_terms = {'post_tag': ['reflections', 'kuro5hin'],
+            'category': ['Blog Posts']}
+archive_base_url = "https://mako.cc/copyrighteous/extra/kuro5hin_archives/"
+footer_html = """<hr />\n<p><i>Originally posted as a diary entry on <a href="https://en.wikipedia.org/wiki/Kuro5hin">Kuro5hin</a>. Although Kuro5hin is now defunct, <a href="%(base)s%(filename)s">an archived copy of the post</a> includes a series of comments from the Kuro5hin community.</i></p>"""
+##########################################################
+
+wp = Client(wp_xmlrpc_endpoint, wp_user, wp_password)
+
+def process_file(input_text, filename):
+    sub = html.fromstring(input_text)
+    
+    # grab the title of the post
+    title = sub.xpath("//title")[0].text
+    title = re.sub(" \|\| kuro5hin\.org$", "", title)
+
+    # timestamp
+    sub_metadata = sub.xpath('//font[text()="%s"]/../../../../font[2]' % title)[0]
+    date_string = re.sub(r"^.*((Mon|Tue|Wed|Thu|Fri|Sat|Sun).*?EST).*$", r"\1", sub_metadata.text_content())
+    post_date = parser.parse(date_string)
+    
+    # post_html
+    sub_text = sub_metadata.xpath("../../../tr[2]/td[2]/p/font")[0]
+
+    # step1: add any material not in a sub_tag
+    post_html = sub_text.text
+    if not re.match(r'^\s*$', post_html):
+        post_html = "<p>%s</p>" % post_html.strip()
+
+    # add all the subtags
+    post_html += "\n".join([html.tostring(x).strip().decode("utf-8") for x in sub_text.getchildren()])
+    post_html = re.sub(r'<[Bb][Rr]>', '', post_html)
+    post_html = re.sub(r'[\t ]*(<[Pp]>)\s*', r'\1', post_html)
+    post_html = re.sub(r'\s*(</[Pp]>)[\t ]*', r'\1', post_html)
+    post_html = post_html.strip()
+
+    post_html = post_html + "\n\n" + (footer_html % {'base' : archive_base_url, 'filename' : filename })
+    
+    # DEBUG CODE: you might want to uncomment this while testing
+    # list of comments
+    # print("***********OUTPUT: %s" % date_string)
+    # print(post_html)
+    # return
+
+    post = WordPressPost()
+    post.title = title
+    post.content = post_html
+    post.date = post_date
+    post.terms_names = wp_terms 
+    post.post_status = "pending"
+
+    wp.call(NewPost(post))
+    
+    
+for filename in sys.argv[1:]:
+    with open(filename, "r", encoding="latin1") as f:
+        process_file(f.read(), filename)
+