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

Update wp2pelican script to extract date and author taken from wordpress xml file.

Browse source
This commit is contained in:
FELD Boris 2011-01-23 22:53:45 +01:00 • committed by Boris FELD
commit 3566bb6f5f
1 changed files with 9 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

11
tools/wp2pelican.py
View file

@ -15,7 +15,9 @@ def wp2html(xml):
title = item.title.contents[0] title = item.title.contents[0]
content = item.fetch('content:encoded')[0].contents[0] content = item.fetch('content:encoded')[0].contents[0]
filename = item.fetch('wp:post_name')[0].contents[0] filename = item.fetch('wp:post_name')[0].contents[0]
yield (title, content, filename) date = item.fetch('wp:post_date')[0].contents[0]
author = item.fetch('dc:creator')[0].contents[0].title()
yield (title, content, filename, date, author)
if __name__ == '__main__': if __name__ == '__main__':
parser = argparse.ArgumentParser(description="""Transform a wordpress xml export into rst files """) parser = argparse.ArgumentParser(description="""Transform a wordpress xml export into rst files """)
@ -24,7 +26,7 @@ if __name__ == '__main__':
parser.add_argument('-o', '--output', dest='output', default='output', help='Output path') parser.add_argument('-o', '--output', dest='output', default='output', help='Output path')
args = parser.parse_args() args = parser.parse_args()
for title, content, filename in wp2html(args.xml): for title, content, filename, date, author in wp2html(args.xml):
html_filename = os.path.join(args.output, filename+'.html') html_filename = os.path.join(args.output, filename+'.html')
rst_filename = os.path.join(args.output, filename+'.rst') rst_filename = os.path.join(args.output, filename+'.rst')
@ -32,3 +34,8 @@ if __name__ == '__main__':
fp.write(content) fp.write(content)
os.system('pandoc --from=html --to=rst -o %s %s' % (rst_filename, os.system('pandoc --from=html --to=rst -o %s %s' % (rst_filename,
html_filename)) 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:
header = '%s\n%s\n\n:date: %s\n:author: %s\n\n' % (title, '#' * len(title) ,date, author)
fs.write(header+content)