Created
May 3, 2015 06:17
-
-
Save janpipek/4529baa89ee58cf674b4 to your computer and use it in GitHub Desktop.
Export documents from old instiki database
This file contains hidden or 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
def export_from_instiki(file_name, output_dir, extension="md"): | |
"""Export data from instiki database to external files.""" | |
import sqlite3 | |
import os | |
import codecs | |
db = sqlite3.connect(file_name) | |
cur = db.execute("SELECT * from pages") | |
if not os.path.exists(output_dir): | |
os.makedirs(output_dir) | |
while True: | |
row = cur.fetchone() | |
if not row: | |
break | |
pid = row[0] | |
name = row[5] | |
cur2 = db.execute("SELECT * from revisions WHERE page_id=%d order by id DESC" % pid) | |
row2 = cur2.fetchone() | |
page_id = name.lower().encode('ascii', 'ignore').replace(" ", "_").replace("#", "sharp").replace("+", "plus") | |
page_file = os.path.join(output_dir, "%s.%s" % (page_id, extension)) | |
content = "# " + name + u"\n\n" + row2[5] | |
print page_file, name, len(content) | |
with codecs.open(page_file, "w", encoding="utf-8") as f: | |
f.write(content) | |
db.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I had one old instiki database in a version probably not supported now. This script enabled me to parse the database file and export all pages to separate documents.