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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
|
# -*- 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 print_function, absolute_import, unicode_literals
import codecs
import datetime
import os
try:
from urlparse import urljoin, urlparse
import robotparser as robotparser
except ImportError:
from urllib.parse import urljoin, urlparse # NOQA
import urllib.robotparser as robotparser # NOQA
from nikola.plugin_categories import LateTask
from nikola.utils import config_changed
urlset_header = """<?xml version="1.0" encoding="UTF-8"?>
<urlset
xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://www.sitemaps.org/schemas/sitemap/0.9
http://www.sitemaps.org/schemas/sitemap/0.9/sitemap.xsd">
"""
loc_format = """ <url>
<loc>{0}</loc>
<lastmod>{1}</lastmod>
</url>
"""
urlset_footer = "</urlset>"
sitemapindex_header = """<?xml version="1.0" encoding="UTF-8"?>
<sitemapindex
xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://www.sitemaps.org/schemas/sitemap/0.9
http://www.sitemaps.org/schemas/sitemap/0.9/sitemap.xsd">
"""
sitemap_format = """ <sitemap>
<loc>{0}</loc>
<lastmod>{1}</lastmod>
</sitemap>
"""
sitemapindex_footer = "</sitemapindex>"
def get_base_path(base):
"""returns the path of a base URL if it contains one.
>>> get_base_path('http://some.site') == '/'
True
>>> get_base_path('http://some.site/') == '/'
True
>>> get_base_path('http://some.site/some/sub-path') == '/some/sub-path/'
True
>>> get_base_path('http://some.site/some/sub-path/') == '/some/sub-path/'
True
"""
# first parse the base_url for some path
base_parsed = urlparse(base)
if not base_parsed.path:
sub_path = ''
else:
sub_path = base_parsed.path
if sub_path.endswith('/'):
return sub_path
else:
return sub_path + '/'
class Sitemap(LateTask):
"""Generate a sitemap."""
name = "sitemap"
def gen_tasks(self):
"""Generate a sitemap."""
kw = {
"base_url": self.site.config["BASE_URL"],
"site_url": self.site.config["SITE_URL"],
"output_folder": self.site.config["OUTPUT_FOLDER"],
"strip_indexes": self.site.config["STRIP_INDEXES"],
"index_file": self.site.config["INDEX_FILE"],
"sitemap_include_fileless_dirs": self.site.config["SITEMAP_INCLUDE_FILELESS_DIRS"],
"mapped_extensions": self.site.config.get('MAPPED_EXTENSIONS', ['.html', '.htm', '.xml', '.rss']),
"robots_exclusions": self.site.config["ROBOTS_EXCLUSIONS"]
}
output = kw['output_folder']
base_url = kw['base_url']
mapped_exts = kw['mapped_extensions']
output_path = kw['output_folder']
sitemapindex_path = os.path.join(output_path, "sitemapindex.xml")
sitemap_path = os.path.join(output_path, "sitemap.xml")
base_path = get_base_path(kw['base_url'])
sitemapindex = {}
urlset = {}
def scan_locs():
for root, dirs, files in os.walk(output, followlinks=True):
if not dirs and not files and not kw['sitemap_include_fileless_dirs']:
continue # Totally empty, not on sitemap
path = os.path.relpath(root, output)
# ignore the current directory.
path = (path.replace(os.sep, '/') + '/').replace('./', '')
lastmod = self.get_lastmod(root)
loc = urljoin(base_url, base_path + path)
if kw['index_file'] in files and kw['strip_indexes']: # ignore folders when not stripping urls
urlset[loc] = loc_format.format(loc, lastmod)
for fname in files:
if kw['strip_indexes'] and fname == kw['index_file']:
continue # We already mapped the folder
if os.path.splitext(fname)[-1] in mapped_exts:
real_path = os.path.join(root, fname)
path = os.path.relpath(real_path, output)
if path.endswith(kw['index_file']) and kw['strip_indexes']:
# ignore index files when stripping urls
continue
if not robot_fetch(path):
continue
if path.endswith('.html') or path.endswith('.htm'):
try:
if u'<!doctype html' not in codecs.open(real_path, 'r', 'utf8').read(1024).lower():
# ignores "html" files without doctype
# alexa-verify, google-site-verification, etc.
continue
except UnicodeDecodeError:
# ignore ancient files
# most non-utf8 files are worthless anyways
continue
""" put RSS in sitemapindex[] instead of in urlset[], sitemap_path is included after it is generated """
if path.endswith('.xml') or path.endswith('.rss'):
if u'<rss' in codecs.open(real_path, 'r', 'utf8').read(512) or u'<urlset'and path != sitemap_path:
path = path.replace(os.sep, '/')
lastmod = self.get_lastmod(real_path)
loc = urljoin(base_url, base_path + path)
sitemapindex[loc] = sitemap_format.format(loc, lastmod)
continue
else:
continue # ignores all XML files except those presumed to be RSS
post = self.site.post_per_file.get(path)
if post and (post.is_draft or post.is_private or post.publish_later):
continue
path = path.replace(os.sep, '/')
lastmod = self.get_lastmod(real_path)
loc = urljoin(base_url, base_path + path)
urlset[loc] = loc_format.format(loc, lastmod)
def robot_fetch(path):
for rule in kw["robots_exclusions"]:
robot = robotparser.RobotFileParser()
robot.parse(["User-Agent: *", "Disallow: {0}".format(rule)])
if not robot.can_fetch("*", '/' + path):
return False # not robot food
return True
def write_sitemap():
# Have to rescan, because files may have been added between
# task dep scanning and task execution
with codecs.open(sitemap_path, 'wb+', 'utf8') as outf:
outf.write(urlset_header)
for k in sorted(urlset.keys()):
outf.write(urlset[k])
outf.write(urlset_footer)
sitemap_url = urljoin(base_url, base_path + "sitemap.xml")
sitemapindex[sitemap_url] = sitemap_format.format(sitemap_url, self.get_lastmod(sitemap_path))
def write_sitemapindex():
with codecs.open(sitemapindex_path, 'wb+', 'utf8') as outf:
outf.write(sitemapindex_header)
for k in sorted(sitemapindex.keys()):
outf.write(sitemapindex[k])
outf.write(sitemapindex_footer)
# Yield a task to calculate the dependencies of the sitemap
# Other tasks can depend on this output, instead of having
# to scan locations.
def scan_locs_task():
scan_locs()
return {'locations': list(urlset.keys()) + list(sitemapindex.keys())}
yield {
"basename": "_scan_locs",
"name": "sitemap",
"actions": [(scan_locs_task)]
}
yield self.group_task()
yield {
"basename": "sitemap",
"name": sitemap_path,
"targets": [sitemap_path],
"actions": [(write_sitemap,)],
"uptodate": [config_changed(kw)],
"clean": True,
"task_dep": ["render_site"],
"calc_dep": ["_scan_locs:sitemap"],
}
yield {
"basename": "sitemap",
"name": sitemapindex_path,
"targets": [sitemapindex_path],
"actions": [(write_sitemapindex,)],
"uptodate": [config_changed(kw)],
"clean": True,
"file_dep": [sitemap_path]
}
def get_lastmod(self, p):
if self.site.invariant:
return '2014-01-01'
else:
return datetime.datetime.fromtimestamp(os.stat(p).st_mtime).isoformat().split('T')[0]
if __name__ == '__main__':
import doctest
doctest.testmod()
|
