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
248
|
# -*- coding: utf-8 -*-
# Copyright (c) 2012 Roberto Alsina y otros.
# 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, unicode_literals
import codecs
import datetime
import hashlib
from optparse import OptionParser
import os
from doit.tools import timeout
import feedparser
import peewee
from nikola.plugin_categories import Command, Task
from nikola.utils import config_changed
class Feed(peewee.Model):
name = peewee.CharField()
url = peewee.CharField(max_length=200)
last_status = peewee.CharField(null=True)
etag = peewee.CharField(max_length=200)
last_modified = peewee.DateTimeField()
class Entry(peewee.Model):
date = peewee.DateTimeField()
feed = peewee.ForeignKeyField(Feed)
content = peewee.TextField(max_length=20000)
link = peewee.CharField(max_length=200)
title = peewee.CharField(max_length=200)
guid = peewee.CharField(max_length=200)
class Planetoid(Command, Task):
"""Maintain a planet-like thing."""
name = "planetoid"
def init_db(self):
# setup database
Feed.create_table(fail_silently=True)
Entry.create_table(fail_silently=True)
def gen_tasks(self):
self.init_db()
for task in self.task_load_feeds():
yield task
for task in self.task_update_feeds():
yield task
for task in self.task_generate_posts():
yield task
def run(self, *args):
self.init_db()
parser = OptionParser(usage="nikola %s [options]" % self.name)
(options, args) = parser.parse_args(list(args))
def task_load_feeds(self):
"Read the feeds file, add it to the database."
feeds = []
feed = name = None
for line in codecs.open('feeds', 'r', 'utf-8'):
line = line.strip()
if line.startswith("#"):
continue
elif line.startswith('http'):
feed = line
elif line:
name = line
if feed and name:
feeds.append([feed, name])
feed = name = None
def add_feed(name, url):
f = Feed.create(
name=name,
url=url,
etag='foo',
last_modified=datetime.datetime(1970, 1, 1),
)
f.save()
def update_feed_url(feed, url):
feed.url = url
feed.save()
for feed, name in feeds:
f = Feed.select().where(Feed.name == name)
if not list(f):
yield {
'basename': self.name,
'name': name.encode('utf8'),
'actions': ((add_feed, (name, feed)), ),
'file_dep': ['feeds'],
}
elif list(f)[0].url != feed:
yield {
'basename': self.name,
'name': ('updating_' + name).encode('utf8'),
'actions': ((update_feed_url, (list(f)[0], feed)), ),
}
def task_update_feeds(self):
"""Download feed contents, add entries to the database."""
def update_feed(feed):
modified = feed.last_modified.timetuple()
etag = feed.etag
try:
parsed = feedparser.parse(
feed.url,
etag=etag,
modified=modified
)
feed.last_status = str(parsed.status)
except: # Probably a timeout
# TODO: log failure
return
if parsed.feed.get('title'):
print(parsed.feed.title)
else:
print(feed.url)
feed.etag = parsed.get('etag', 'foo')
modified = tuple(parsed.get('date_parsed', (1970, 1, 1)))[:6]
print("==========>", modified)
modified = datetime.datetime(*modified)
feed.last_modified = modified
feed.save()
# No point in adding items from missinfg feeds
if parsed.status > 400:
# TODO log failure
return
for entry_data in parsed.entries:
print("=========================================")
date = entry_data.get('published_parsed', None)
if date is None:
date = entry_data.get('updated_parsed', None)
if date is None:
print("Can't parse date from:")
print(entry_data)
return False
print("DATE:===>", date)
date = datetime.datetime(*(date[:6]))
title = "%s: %s" % (feed.name, entry_data.get('title', 'Sin título'))
content = entry_data.get('content', None)
if content:
content = content[0].value
if not content:
content = entry_data.get('description', None)
if not content:
content = entry_data.get('summary', 'Sin contenido')
guid = str(entry_data.get('guid', entry_data.link))
link = entry_data.link
print(repr([date, title]))
e = list(Entry.select().where(Entry.guid == guid))
print(
repr(dict(
date=date,
title=title,
content=content,
guid=guid,
feed=feed,
link=link,
))
)
if not e:
entry = Entry.create(
date=date,
title=title,
content=content,
guid=guid,
feed=feed,
link=link,
)
else:
entry = e[0]
entry.date = date
entry.title = title
entry.content = content
entry.link = link
entry.save()
for feed in Feed.select():
task = {
'basename': self.name,
'name': str(feed.url),
'actions': [(update_feed, (feed, ))],
'uptodate': [timeout(datetime.timedelta(minutes=
self.site.config.get('PLANETOID_REFRESH', 60)))],
}
yield task
def task_generate_posts(self):
"""Generate post files for the blog entries."""
def gen_id(entry):
h = hashlib.md5()
h.update(entry.feed.name.encode('utf8'))
h.update(entry.guid)
return h.hexdigest()
def generate_post(entry):
unique_id = gen_id(entry)
meta_path = os.path.join('posts', unique_id + '.meta')
post_path = os.path.join('posts', unique_id + '.txt')
with codecs.open(meta_path, 'wb+', 'utf8') as fd:
fd.write('%s\n' % entry.title.replace('\n', ' '))
fd.write('%s\n' % unique_id)
fd.write('%s\n' % entry.date.strftime('%Y/%m/%d %H:%M'))
fd.write('\n')
fd.write('%s\n' % entry.link)
with codecs.open(post_path, 'wb+', 'utf8') as fd:
fd.write('.. raw:: html\n\n')
content = entry.content
if not content:
content = 'Sin contenido'
for line in content.splitlines():
fd.write(' %s\n' % line)
for entry in Entry.select().order_by(Entry.date.desc()):
entry_id = gen_id(entry)
yield {
'basename': self.name,
'targets': [os.path.join('posts', entry_id + '.meta'), os.path.join('posts', entry_id + '.txt')],
'name': entry_id,
'actions': [(generate_post, (entry,))],
'uptodate': [config_changed({1: entry})]
}
|
