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

Merge pull request #179 from ranjhith/master

Browse source 
Changes to import script
This commit is contained in:
Alexis Metaireau 2011-10-27 07:24:31 -07:00
commit 4da387127e
1 changed files with 27 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

36
tools/pelican-import
View file

@ -183,12 +183,13 @@ def build_markdown_header(title, date, author, categories, tags):
header += '\n' header += '\n'
return header return header
def fields2pelican(fields, output_path, dircat=False): def fields2pelican(fields, out_markup, output_path, dircat=False):
for title, content, filename, date, author, categories, tags, markup in fields: for title, content, filename, date, author, categories, tags, in_markup in fields:
if (markup == "markdown"): if (in_markup == "markdown") or (out_markup == "markdown") :
ext = '.md' ext = '.md'
header = build_markdown_header(title, date, author, categories, tags) header = build_markdown_header(title, date, author, categories, tags)
else: else:
out_markup = "rst"
ext = '.rst' ext = '.rst'
header = build_header(title, date, author, categories, tags) header = build_header(title, date, author, categories, tags)
@ -205,24 +206,31 @@ def fields2pelican(fields, output_path, dircat=False):
print out_filename print out_filename
if markup == "html": if in_markup == "html":
html_filename = os.path.join(output_path, filename+'.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:
# Replace simple newlines with <br />+newline so that the HTML file
# represents the original post more accurately
content = content.replace("\n", "<br />\n")
fp.write(content) fp.write(content)
os.system('pandoc --normalize --reference-links --from=html --to=rst -o "%s" "%s"' % (out_filename, html_filename)) os.system('pandoc --normalize --reference-links --from=html --to=%s -o "%s" "%s"' % (out_markup, out_filename, html_filename))
os.remove(html_filename) #os.remove(html_filename)
with open(out_filename, 'r', encoding='utf-8') as fs: with open(out_filename, 'r', encoding='utf-8') as fs:
content = fs.read() content = fs.read()
if out_markup == "markdown":
# In markdown, to insert a <br />, end a line with two or more spaces & then a end-of-line
content = content.replace("\\\n ", " \n")
content = content.replace("\\\n", " \n")
with open(out_filename, 'w', encoding='utf-8') as fs: with open(out_filename, 'w', encoding='utf-8') as fs:
fs.write(header + content) fs.write(header + content)
def main(input_type, input, output_path, dircat=False): def main(input_type, input, out_markup, output_path, dircat=False):
if input_type == 'wordpress': if input_type == 'wordpress':
fields = wp2fields(input) fields = wp2fields(input)
elif input_type == 'dotclear': elif input_type == 'dotclear':
@ -230,7 +238,7 @@ def main(input_type, input, output_path, dircat=False):
elif input_type == 'feed': elif input_type == 'feed':
fields = feed2fields(input) fields = feed2fields(input)
fields2pelican(fields, output_path, dircat=dircat) fields2pelican(fields, out_markup, output_path, dircat=dircat)
if __name__ == '__main__': if __name__ == '__main__':
@ -247,6 +255,8 @@ if __name__ == '__main__':
help='Feed to parse') help='Feed to parse')
parser.add_argument('-o', '--output', dest='output', default='output', parser.add_argument('-o', '--output', dest='output', default='output',
help='Output path') help='Output path')
parser.add_argument('-m', '--markup', dest='markup', default='rst',
help='Output markup format (supports rst & markdown)')
parser.add_argument('--dir-cat', action='store_true', dest='dircat', parser.add_argument('--dir-cat', action='store_true', dest='dircat',
help='Put files in directories with categories name') help='Put files in directories with categories name')
args = parser.parse_args() args = parser.parse_args()
@ -261,4 +271,12 @@ if __name__ == '__main__':
else: else:
print "you must provide either --wpfile, --dotclear or --feed options" print "you must provide either --wpfile, --dotclear or --feed options"
exit() exit()
main(input_type, args.input, args.output, dircat=args.dircat)
if not os.path.exists(args.output):
try:
os.mkdir(args.output)
except OSError:
error("Couldn't create the output folder: " + args.output)
exit()
main(input_type, args.input, args.markup, args.output, dircat=args.dircat)