1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
|
import codecs
import os
from urlparse import urlparse
from urllib import urlopen
from lxml import etree, html
from mako.template import Template
from nikola.plugin_categories import Command
from nikola import utils
links = {}
class CommandImportWordpress(Command):
"""Import a wordpress dump."""
name = "import_wordpress"
def run(self, fname=None):
# Parse the data
if fname is None:
print "Usage: nikola import_wordpress wordpress_dump.xml"
return
context = {}
with open(fname) as fd:
xml = []
for line in fd:
# These explode etree and are useless
if '<atom:link rel=' in line:
continue
xml.append(line)
xml = '\n'.join(xml)
tree = etree.fromstring(xml)
channel = tree.find('channel')
context['DEFAULT_LANG'] = get_text_tag(channel, 'language', 'en')[:2]
context['BLOG_TITLE'] = get_text_tag(
channel, 'title', 'PUT TITLE HERE')
context['BLOG_DESCRIPTION'] = get_text_tag(
channel, 'description', 'PUT DESCRIPTION HERE')
context['BLOG_URL'] = get_text_tag(channel, 'link', '#')
author = channel.find('{http://wordpress.org/export/1.2/}author')
context['BLOG_EMAIL'] = get_text_tag(
author,
'{http://wordpress.org/export/1.2/}author_email',
"joe@example.com")
context['BLOG_AUTHOR'] = get_text_tag(
author,
'{http://wordpress.org/export/1.2/}author_display_name',
"Joe Example")
context['POST_PAGES'] = '''(
("posts/*.wp", "posts", "post.tmpl", True),
("stories/*.wp", "stories", "story.tmpl", False),
)'''
context['POST_COMPILERS'] = '''{
"rest": ('.txt', '.rst'),
"markdown": ('.md', '.mdown', '.markdown', '.wp'),
"html": ('.html', '.htm')
}
'''
# Generate base site
os.system('nikola init new_site')
conf_template = Template(filename=os.path.join(
os.path.dirname(utils.__file__), 'data', 'samplesite', 'conf.py.in'))
with codecs.open(os.path.join('new_site', 'conf.py'),
'w+', 'utf8') as fd:
fd.write(conf_template.render(**context))
# Import posts
for item in channel.findall('item'):
import_attachment(item)
for item in channel.findall('item'):
import_item(item)
def replacer(dst):
return links.get(dst, dst)
def get_text_tag(tag, name, default):
t = tag.find(name)
if t is not None:
return t.text
else:
return default
def import_attachment(item):
post_type = get_text_tag(item,
'{http://wordpress.org/export/1.2/}post_type', 'post')
if post_type == 'attachment':
url = get_text_tag(item,
'{http://wordpress.org/export/1.2/}attachment_url', 'foo')
link = get_text_tag(item,
'{http://wordpress.org/export/1.2/}link', 'foo')
path = urlparse(url).path
dst_path = os.path.join(*(['new_site', 'files']
+ list(path.split('/'))))
dst_dir = os.path.dirname(dst_path)
if not os.path.isdir(dst_dir):
os.makedirs(dst_dir)
print "Downloading %s => %s" % (url, dst_path)
with open(dst_path, 'wb+') as fd:
fd.write(urlopen(url).read())
dst_url = '/'.join(dst_path.split(os.sep)[2:])
links[link] = '/' + dst_url
links[url] = '/' + dst_url
return
def import_item(item):
"""Takes an item from the feed and creates a post file."""
title = get_text_tag(item, 'title', 'NO TITLE')
# link is something like http://foo.com/2012/09/01/hello-world/
# So, take the path, utils.slugify it, and that's our slug
slug = utils.slugify(urlparse(get_text_tag(item, 'link', None)).path)
description = get_text_tag(item, 'description', '')
post_date = get_text_tag(item,
'{http://wordpress.org/export/1.2/}post_date', None)
post_type = get_text_tag(item,
'{http://wordpress.org/export/1.2/}post_type', 'post')
status = get_text_tag(item,
'{http://wordpress.org/export/1.2/}status', 'publish')
content = get_text_tag(item,
'{http://purl.org/rss/1.0/modules/content/}encoded', '')
tags = []
if status != 'publish':
tags.append('draft')
for tag in item.findall('category'):
text = tag.text
if text == 'Uncategorized':
continue
tags.append(text)
if post_type == 'attachment':
return
elif post_type == 'post':
out_folder = 'posts'
else:
out_folder = 'stories'
# Write metadata
with codecs.open(os.path.join('new_site', out_folder, slug + '.meta'),
"w+", "utf8") as fd:
fd.write(u'%s\n' % title)
fd.write(u'%s\n' % slug)
fd.write(u'%s\n' % post_date)
fd.write(u'%s\n' % ','.join(tags))
fd.write(u'\n')
fd.write(u'%s\n' % description)
with open(os.path.join(
'new_site', out_folder, slug + '.wp'), "wb+") as fd:
if content.strip():
try:
doc = html.document_fromstring(content)
doc.rewrite_links(replacer)
fd.write(html.tostring(doc, encoding='utf8'))
except:
import pdb
pdb.set_trace()
|
