Created
May 2, 2020 10:24
-
-
Save Lusitaniae/d15e573317bdfa3f09fd71d990735146 to your computer and use it in GitHub Desktop.
Convert WordPress dump into Hugo content yml files
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
#!/usr/bin/env python | |
# -*- coding: utf-8 -*- | |
import xmltodict | |
import time | |
import hashlib | |
total_count = 0 | |
m = hashlib.md5() | |
with open('wp.xml', 'rt', encoding="utf-8") as fd: | |
cfg = xmltodict.parse(fd.read()) | |
for item in cfg['rss']['channel']['item']: | |
try: | |
for comment in item['wp:comment']: | |
if comment['wp:comment_approved'] == "1": | |
total_count += 1 | |
try: | |
date_time = comment['wp:comment_date_gmt'] | |
pattern = '%Y-%m-%d %H:%M:%S' | |
epoch = int(time.mktime(time.strptime(date_time, pattern))) | |
file = "comment-" + str(epoch) + ".yml" | |
except Exception as e: | |
print(e) | |
pass | |
try: | |
title = item['title'] | |
except Exception as e: | |
print(e) | |
pass | |
try: | |
id = comment['wp:comment_id'] | |
except Exception as e: | |
print(e) | |
pass | |
try: | |
name = comment['wp:comment_author'] | |
except Exception as e: | |
print(e) | |
pass | |
try: | |
reply_to = "" | |
if comment['wp:comment_parent'] != '0': | |
reply_to = comment['wp:comment_parent'] | |
except Exception as e: | |
print(e) | |
pass | |
try: | |
temp_email = comment['wp:comment_author_email'] | |
temp_email = temp_email.strip() | |
temp_email = temp_email.lower() | |
temp_email = temp_email.encode('utf-8') | |
m.update(temp_email) | |
email = m.hexdigest() | |
except Exception as e: | |
print(e) | |
pass | |
try: | |
body = comment['wp:comment_content'].replace('\n', '\n ') | |
except Exception as e: | |
print(e) | |
pass | |
try: | |
date = comment['wp:comment_date_gmt'] | |
except Exception as e: | |
print(e) | |
pass | |
content = """--- | |
_id: %s | |
post_title: %s | |
name: %s | |
reply_to: %s | |
email: %s | |
date: %s | |
body: | | |
%s | |
""" % (id, title, name, reply_to, email, date, body) | |
print("creating " + file) | |
with open ('tmp/'+file, 'w', encoding="utf-8") as f: f.write (content) | |
except Exception as e: | |
print(e) | |
pass | |
print("Total Count: " + str(total_count)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment