Created
October 3, 2011 07:03
-
-
Save fakechris/1258590 to your computer and use it in GitHub Desktop.
Export delicious export html format from delicious API
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
from StringIO import StringIO | |
from lxml import etree | |
import time | |
XML_BEGIN = """ | |
<!DOCTYPE NETSCAPE-Bookmark-file-1> | |
<META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=UTF-8"> | |
<!-- This is an automatically generated file. | |
It will be read and overwritten. | |
Do Not Edit! --> | |
<TITLE>Bookmarks</TITLE> | |
<H1>Bookmarks</H1> | |
<DL><p> | |
""" | |
XML_END = """ | |
</DL><p><!-- fe03.secure.del.ac4.yahoo.net uncompressed/chunked Mon Sep 26 02:05:19 UTC 2011 --> | |
""" | |
ITEM = """<DT><A HREF="%s" ADD_DATE="%s" PRIVATE="%s" TAGS="%s">%s</A>""" | |
all = open("all.xml", "r").read() | |
t = etree.parse(StringIO(all)) | |
posts = t.findall('//post') | |
result = XML_BEGIN | |
for p in posts: | |
tag = ",".join(p.get("tag").encode("utf-8").split(" ")) | |
href = p.get("href").encode("utf-8") | |
description = p.get("description").encode("utf-8") | |
if p.get("private") == "yes": | |
private = 1 | |
else: | |
private = 0 | |
ts = int(time.mktime(time.strptime(p.get("time"), "%Y-%m-%dT%H:%M:%SZ"))) | |
result += ITEM % (href, ts, private, tag, description) | |
result += XML_END | |
print result | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment