github/pelican
1
0
Fork 1
mirror of https://github.com/getpelican/pelican.git synced 2025-10-15 20:28:56 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add a way to import from RSS/Atom feeds. Fixes #55

Browse source
This commit is contained in:
Alexis Metaireau 2011-02-10 01:27:28 +00:00
commit a07fe2abee
1 changed files with 0 additions and 72 deletions
Download patch file Download diff file Expand all files Collapse all files

72
tools/wp2pelican.py
View file

@ -1,72 +0,0 @@
#! /usr/bin/env python
from BeautifulSoup import BeautifulStoneSoup
from codecs import open
import os
import argparse
import time
def wp2html(xml):
xmlfile = open(xml, encoding='utf-8').read()
soup = BeautifulStoneSoup(xmlfile)
items = soup.rss.channel.findAll('item')
for item in items:
if item.fetch('wp:status')[0].contents[0] == "publish":
title = item.title.contents[0]
content = item.fetch('content:encoded')[0].contents[0]
filename = item.fetch('wp:post_name')[0].contents[0]
raw_date = item.fetch('wp:post_date')[0].contents[0]
date_object = time.strptime(raw_date, "%Y-%m-%d %H:%M:%S")
date = time.strftime("%Y-%m-%d %H:%M", date_object)
author = item.fetch('dc:creator')[0].contents[0].title()
categories = [(cat['nicename'],cat.contents[0]) for cat in item.fetch(domain='category')]
tags = [tag.contents[0].title() for tag in item.fetch(domain='tag', nicename=None)]
yield (title, content, filename, date, author, categories, tags)
def buildHeader(title, date, author, categories, tags):
header = '%s\n%s\n' % (title, '#' * len(title))
if (date != None):
header += ':date: %s\n' % (date)
if (categories != []):
header += ':category: %s\n' % (', '.join(categories))
if (tags != []):
header += ':tags: %s\n' % (', '.join(tags))
header += '\n'
return header
if __name__ == '__main__':
parser = argparse.ArgumentParser(description="""Transform a wordpress xml export into rst files """)
parser.add_argument(dest='xml', help='The xml filepath')
parser.add_argument('-o', '--output', dest='output', default='output', help='Output path')
args = parser.parse_args()
for title, content, filename, date, author, categories in wp2html(args.xml):
html_filename = os.path.join(args.output, filename+'.html')
if(len(categories) == 1):
rst_filename = os.path.join(args.output, categories[0][0], filename+'.rst.dr')
if not os.path.isdir(os.path.join(args.output, categories[0][0])):
os.mkdir(os.path.join(args.output, categories[0][0]))
else:
rst_filename = os.path.join(args.output, filename+'.rst.dr')
with open(html_filename, 'w', encoding='utf-8') as fp:
fp.write(content)
os.system('pandoc --from=html --to=rst -o %s %s' % (rst_filename,
html_filename))
os.remove(html_filename)
with open(rst_filename, 'r', encoding='utf-8') as fs:
content = fs.read()
with open(rst_filename, 'w', encoding='utf-8') as fs:
categories = [x[1] for x in categories]
header = buildHeader(title, date, author, categories, tags)
fs.write(header+content)