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

some improvements for importers:

Browse source 
- for dotclear: remove seconds in date, remove \\n
- fix categories for wordpress (categories is a list a string)
- refactor a bit the code between markdown and rst
This commit is contained in:
Simon 2011-08-03 17:04:39 +02:00
commit 3b37b42633
1 changed files with 33 additions and 26 deletions
Download patch file Download diff file Expand all files Collapse all files

63
tools/importer.py
View file

@ -27,7 +27,9 @@ def wp2fields(xml):
date = time.strftime("%Y-%m-%d %H:%M", date_object) date = time.strftime("%Y-%m-%d %H:%M", date_object)
author = item.fetch('dc:creator')[0].contents[0].title() author = item.fetch('dc:creator')[0].contents[0].title()
categories = [(cat['nicename'],cat.contents[0]) for cat in item.fetch(domain='category')]
categories = [cat.contents[0] for cat in item.fetch(domain='category')]
# caturl = [cat['nicename'] for cat in item.fetch(domain='category')]
tags = [tag.contents[0].title() for tag in item.fetch(domain='tag', nicename=None)] tags = [tag.contents[0].title() for tag in item.fetch(domain='tag', nicename=None)]
@ -101,16 +103,22 @@ def dc2fields(file):
# post_meta = fields[27] # post_meta = fields[27]
# redirect_url = fields[28][:-1] # redirect_url = fields[28][:-1]
# remove seconds
post_creadt = ':'.join(post_creadt.split(':')[0:2])
author = "" author = ""
categories = "" categories = []
tags = []
if cat_id: if cat_id:
categories = category_list[cat_id] categories = [category_list[id].strip() for id in cat_id.split(',')]
tags = ""
if post_format == "markdown": if post_format == "markdown":
content = post_excerpt + post_content content = post_excerpt + post_content
else: else:
content = post_excerpt_xhtml + post_content_xhtml content = post_excerpt_xhtml + post_content_xhtml
content = content.replace('\\n', '')
post_format = "html"
yield (post_title, content, post_url, post_creadt, author, categories, tags, post_format) yield (post_title, content, post_url, post_creadt, author, categories, tags, post_format)
@ -135,7 +143,7 @@ def build_header(title, date, author, categories, tags):
if date: if date:
header += ':date: %s\n' % date header += ':date: %s\n' % date
if categories: if categories:
header += ':category: %s\n' % categories header += ':category: %s\n' % ', '.join(categories)
if tags: if tags:
header += ':tags: %s\n' % ', '.join(tags) header += ':tags: %s\n' % ', '.join(tags)
header += '\n' header += '\n'
@ -147,7 +155,7 @@ def build_markdown_header(title, date, author, categories, tags):
if date: if date:
header += 'Date: %s\n' % date header += 'Date: %s\n' % date
if categories: if categories:
header += 'Category: %s\n' % categories header += 'Category: %s\n' % ', '.join(categories)
if tags: if tags:
header += 'Tags: %s\n' % ', '.join(tags) header += 'Tags: %s\n' % ', '.join(tags)
header += '\n' header += '\n'
@ -156,40 +164,39 @@ def build_markdown_header(title, date, author, categories, tags):
def fields2pelican(fields, output_path): def fields2pelican(fields, output_path):
for title, content, filename, date, author, categories, tags, markup in fields: for title, content, filename, date, author, categories, tags, markup in fields:
if markup == "markdown": if markup == "markdown":
md_filename = os.path.join(output_path, filename+'.md') ext = '.md'
header = build_markdown_header(title, date, author, categories, tags) header = build_markdown_header(title, date, author, categories, tags)
# content.replace('\r\n', '\n')
with open(md_filename, 'w', encoding='utf-8') as fp:
fp.write(header+content)
else: else:
filename = os.path.basename(filename) ext = '.rst'
html_filename = os.path.join(output_path, filename+'.html') header = build_header(title, date, author, categories, tags)
# if(len(categories) == 1): # TODO: add options to put files in directories by categories
# rst_filename = os.path.join(output_path, categories[0][0], filename+'.rst') # if(len(categories) == 1):
# if not os.path.isdir(os.path.join(output_path, categories[0][0])): # out_filename = os.path.join(output_path, categories[0], filename+'.rst')
# os.mkdir(os.path.join(output_path, categories[0][0])) # if not os.path.isdir(os.path.join(output_path, categories[0])):
# else: # os.mkdir(os.path.join(output_path, categories[0]))
rst_filename = os.path.join(output_path, filename+'.rst') # else:
filename = os.path.basename(filename)
out_filename = os.path.join(output_path, filename+ext)
print out_filename
if markup == "html":
html_filename = os.path.join(output_path, filename+'.html')
with open(html_filename, 'w', encoding='utf-8') as fp: with open(html_filename, 'w', encoding='utf-8') as fp:
fp.write(content) fp.write(content)
print rst_filename os.system('pandoc --normalize --reference-links --from=html --to=rst -o %s %s' % (out_filename,
os.system('pandoc --normalize --reference-links --from=html --to=rst -o %s %s' % (rst_filename,
html_filename)) html_filename))
os.remove(html_filename) os.remove(html_filename)
with open(rst_filename, 'r', encoding='utf-8') as fs: with open(out_filename, 'r', encoding='utf-8') as fs:
content = fs.read() content = fs.read()
with open(rst_filename, 'w', encoding='utf-8') as fs:
# categories = [x[1] for x in categories] with open(out_filename, 'w', encoding='utf-8') as fs:
header = build_header(title, date, author, categories, tags) fs.write(header + content)
fs.write(header + content)
def main(input_type, input, output_path): def main(input_type, input, output_path):