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
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
|
# -*- coding: utf-8 -*-
# Copyright © 2012-2014 Roberto Alsina and others.
# Permission is hereby granted, free of charge, to any
# person obtaining a copy of this software and associated
# documentation files (the "Software"), to deal in the
# Software without restriction, including without limitation
# the rights to use, copy, modify, merge, publish,
# distribute, sublicense, and/or sell copies of the
# Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice
# shall be included in all copies or substantial portions of
# the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY
# KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE
# WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR
# PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS
# OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
# OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
from __future__ import unicode_literals, print_function
import datetime
import os
import time
try:
from urlparse import urlparse
except ImportError:
from urllib.parse import urlparse # NOQA
try:
import feedparser
except ImportError:
feedparser = None # NOQA
from nikola.plugin_categories import Command
from nikola import utils
from nikola.utils import req_missing
from nikola.plugins.basic_import import ImportMixin
from nikola.plugins.command.init import SAMPLE_CONF, prepare_config
LOGGER = utils.get_logger('import_feed', utils.STDERR_HANDLER)
class CommandImportFeed(Command, ImportMixin):
"""Import a feed dump."""
name = "import_feed"
needs_config = False
doc_usage = "[options] feed_file"
doc_purpose = "import a RSS/Atom dump"
cmd_options = ImportMixin.cmd_options
def _execute(self, options, args):
'''
Import Atom/RSS feed
'''
if feedparser is None:
req_missing(['feedparser'], 'import feeds')
return
if not args:
print(self.help())
return
options['filename'] = args[0]
self.feed_export_file = options['filename']
self.output_folder = options['output_folder']
self.import_into_existing_site = False
self.url_map = {}
channel = self.get_channel_from_file(self.feed_export_file)
self.context = self.populate_context(channel)
conf_template = self.generate_base_site()
self.context['REDIRECTIONS'] = self.configure_redirections(
self.url_map)
self.import_posts(channel)
self.write_configuration(self.get_configuration_output_path(
), conf_template.render(**prepare_config(self.context)))
@classmethod
def get_channel_from_file(cls, filename):
return feedparser.parse(filename)
@staticmethod
def populate_context(channel):
context = SAMPLE_CONF.copy()
context['DEFAULT_LANG'] = channel.feed.title_detail.language \
if channel.feed.title_detail.language else 'en'
context['BLOG_TITLE'] = channel.feed.title
context['BLOG_DESCRIPTION'] = channel.feed.get('subtitle', '')
context['SITE_URL'] = channel.feed.get('link', '').rstrip('/')
context['BLOG_EMAIL'] = channel.feed.author_detail.get('email', '') if 'author_detail' in channel.feed else ''
context['BLOG_AUTHOR'] = channel.feed.author_detail.get('name', '') if 'author_detail' in channel.feed else ''
context['POSTS'] = '''(
("posts/*.html", "posts", "post.tmpl"),
)'''
context['PAGES'] = '''(
("stories/*.html", "stories", "story.tmpl"),
)'''
context['COMPILERS'] = '''{
"rest": ('.txt', '.rst'),
"markdown": ('.md', '.mdown', '.markdown', '.wp'),
"html": ('.html', '.htm')
}
'''
return context
def import_posts(self, channel):
for item in channel.entries:
self.process_item(item)
def process_item(self, item):
self.import_item(item, 'posts')
def import_item(self, item, out_folder=None):
"""Takes an item from the feed and creates a post file."""
if out_folder is None:
out_folder = 'posts'
# link is something like http://foo.com/2012/09/01/hello-world/
# So, take the path, utils.slugify it, and that's our slug
link = item.link
link_path = urlparse(link).path
title = item.title
# blogger supports empty titles, which Nikola doesn't
if not title:
LOGGER.warn("Empty title in post with URL {0}. Using NO_TITLE "
"as placeholder, please fix.".format(link))
title = "NO_TITLE"
if link_path.lower().endswith('.html'):
link_path = link_path[:-5]
slug = utils.slugify(link_path)
if not slug: # should never happen
LOGGER.error("Error converting post:", title)
return
description = ''
post_date = datetime.datetime.fromtimestamp(time.mktime(
item.published_parsed))
if item.get('content'):
for candidate in item.get('content', []):
content = candidate.value
break
# FIXME: handle attachments
elif item.get('summary'):
content = item.get('summary')
tags = []
for tag in item.get('tags', []):
tags.append(tag.term)
if item.get('app_draft'):
tags.append('draft')
is_draft = True
else:
is_draft = False
self.url_map[link] = self.context['SITE_URL'] + '/' + \
out_folder + '/' + slug + '.html'
if is_draft and self.exclude_drafts:
LOGGER.notice('Draft "{0}" will not be imported.'.format(title))
elif content.strip():
# If no content is found, no files are written.
content = self.transform_content(content)
self.write_metadata(os.path.join(self.output_folder, out_folder,
slug + '.meta'),
title, slug, post_date, description, tags)
self.write_content(
os.path.join(self.output_folder, out_folder, slug + '.html'),
content)
else:
LOGGER.warn('Not going to import "{0}" because it seems to contain'
' no content.'.format(title))
@staticmethod
def write_metadata(filename, title, slug, post_date, description, tags):
ImportMixin.write_metadata(filename,
title,
slug,
post_date.strftime(r'%Y/%m/%d %H:%m:%S'),
description,
tags)
|
