1
|
|
|
#!/usr/bin/env python |
2
|
|
|
# -*- coding: utf8 -*- |
3
|
|
|
# |
4
|
|
|
# common.py : common tools used by versions.py modules |
5
|
|
|
# |
6
|
|
|
# (C) Copyright 2016 - 2018 Olivier Delhomme |
7
|
|
|
# e-mail : [email protected] |
8
|
|
|
# |
9
|
|
|
# This program is free software; you can redistribute it and/or modify |
10
|
|
|
# it under the terms of the GNU General Public License as published by |
11
|
|
|
# the Free Software Foundation; either version 3, or (at your option) |
12
|
|
|
# any later version. |
13
|
|
|
# |
14
|
|
|
# This program is distributed in the hope that it will be useful, |
15
|
|
|
# but WITHOUT ANY WARRANTY; without even the implied warranty of |
16
|
|
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
17
|
|
|
# GNU General Public License for more details. |
18
|
|
|
# |
19
|
|
|
# You should have received a copy of the GNU General Public License |
20
|
|
|
# along with this program; if not, write to the Free Software Foundation, |
21
|
|
|
# Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. |
22
|
|
|
# |
23
|
|
|
import feedparser |
24
|
|
|
import time |
25
|
|
|
|
26
|
|
|
|
27
|
|
|
def get_entry_published_date(entry): |
28
|
|
|
""" |
29
|
|
|
Returns the published date of an entry. |
30
|
|
|
Selects the right field to do so |
31
|
|
|
""" |
32
|
|
|
published_date = None |
33
|
|
|
field_name = '' |
34
|
|
|
|
35
|
|
|
if 'published_parsed' in entry: |
36
|
|
|
published_date = entry.published_parsed |
37
|
|
|
field_name = 'published_parsed' |
38
|
|
|
elif 'updated_parsed' in entry: |
39
|
|
|
published_date = entry.updated_parsed |
40
|
|
|
field_name = 'updated_parsed' |
41
|
|
|
elif 'pubDate' in entry: # rss-0.91.dtd (netscape) |
42
|
|
|
published_date = entry.pubDate |
43
|
|
|
field_name = 'pubDate' |
44
|
|
|
|
45
|
|
|
return (published_date, field_name) |
46
|
|
|
|
47
|
|
|
# End of get_entry_published_date() function |
48
|
|
|
|
49
|
|
|
|
50
|
|
|
def make_list_of_newer_feeds(feed, feed_info, debug): |
51
|
|
|
""" |
52
|
|
|
Compares feed entries and keep those that are newer than the latest |
53
|
|
|
check we've done and inserting the newer ones in reverse order in |
54
|
|
|
a list to be returned |
55
|
|
|
""" |
56
|
|
|
|
57
|
|
|
feed_list = [] |
58
|
|
|
|
59
|
|
|
# inserting into a list in reverse order to keep the most recent |
60
|
|
|
# version in case of multiple release of the same project in the |
61
|
|
|
# feeds |
62
|
|
|
for a_feed in feed.entries: |
63
|
|
|
|
64
|
|
|
if a_feed: |
65
|
|
|
(published_date, field_name) = get_entry_published_date(a_feed) |
66
|
|
|
|
67
|
|
|
print_debug(debug, u'\tFeed entry ({0}): Feed title: "{1:16}"'.format(time.strftime('%x %X', published_date), a_feed.title)) |
68
|
|
|
|
69
|
|
|
if feed_info.is_newer(published_date): |
70
|
|
|
feed_list.insert(0, a_feed) |
71
|
|
|
else: |
72
|
|
|
print(u'Warning: empty feed in {}'.format(feed)) |
73
|
|
|
|
74
|
|
|
return feed_list |
75
|
|
|
|
76
|
|
|
# End of make_list_of_newer_feeds() function |
77
|
|
|
|
78
|
|
|
|
79
|
|
|
def manage_http_status(feed, url): |
80
|
|
|
""" |
81
|
|
|
Manages http status code present in feed and prints |
82
|
|
|
an error in case of a 3xx, 4xx or 5xx and stops |
83
|
|
|
doing anything for the feed by returning None. |
84
|
|
|
""" |
85
|
|
|
|
86
|
|
|
err = feed.status / 100 |
87
|
|
|
|
88
|
|
|
if err > 2: |
89
|
|
|
print(u'Error {} while fetching "{}".'.format(feed.status, url)) |
90
|
|
|
feed = None |
91
|
|
|
|
92
|
|
|
return feed |
93
|
|
|
|
94
|
|
|
# End of manage_http_status() function |
95
|
|
|
|
96
|
|
|
|
97
|
|
|
def manage_non_http_errors(feed, url): |
98
|
|
|
""" |
99
|
|
|
Tries to manage non http errors and gives |
100
|
|
|
a message to the user. |
101
|
|
|
""" |
102
|
|
|
|
103
|
|
|
if feed.bozo: |
104
|
|
|
if feed.bozo_exception: |
105
|
|
|
exc = feed.bozo_exception |
106
|
|
|
if hasattr(exc, 'reason'): |
107
|
|
|
message = exc.reason |
108
|
|
|
else: |
109
|
|
|
message = 'unaddressed' |
110
|
|
|
|
111
|
|
|
print(u'Error {} while fetching "{}".'.format(message, url)) |
112
|
|
|
|
113
|
|
|
else: |
114
|
|
|
print(u'Error while fetching url "{}".'.format(url)) |
115
|
|
|
|
116
|
|
|
# End of manage_non_http_errors() function |
117
|
|
|
|
118
|
|
|
|
119
|
|
|
def get_feed_entries_from_url(url): |
120
|
|
|
""" |
121
|
|
|
Gets feed entries from an url that should be an |
122
|
|
|
RSS or Atom feed. |
123
|
|
|
>>> get_feed_entries_from_url("http://delhomme.org/notfound.html") |
124
|
|
|
Error 404 while fetching "http://delhomme.org/notfound.html". |
125
|
|
|
>>> feed = get_feed_entries_from_url("http://blog.delhomme.org/index.php?feed/atom") |
126
|
|
|
>>> feed.status |
127
|
|
|
200 |
128
|
|
|
""" |
129
|
|
|
|
130
|
|
|
feed = feedparser.parse(url) |
131
|
|
|
|
132
|
|
|
if 'status' in feed: |
133
|
|
|
feed = manage_http_status(feed, url) |
134
|
|
|
else: |
135
|
|
|
# An error happened such that the feed does not contain an HTTP answer. |
136
|
|
|
manage_non_http_errors(feed, url) |
137
|
|
|
feed = None |
138
|
|
|
|
139
|
|
|
return feed |
140
|
|
|
|
141
|
|
|
# End of get_feed_entries_from_url() function |
142
|
|
|
|
143
|
|
|
|
144
|
|
|
def print_project_version(project, version): |
145
|
|
|
""" |
146
|
|
|
Prints to the standard output project name and it's version. |
147
|
|
|
""" |
148
|
|
|
|
149
|
|
|
print(u'{} {}'.format(project, version)) |
150
|
|
|
|
151
|
|
|
# End of print_project_version() function |
152
|
|
|
|
153
|
|
|
|
154
|
|
|
def print_debug(debug, message): |
155
|
|
|
""" |
156
|
|
|
Prints 'message' if debug mode is True |
157
|
|
|
""" |
158
|
|
|
|
159
|
|
|
if debug: |
160
|
|
|
print(u'{}'.format(message)) |
161
|
|
|
|
162
|
|
|
# End of print_debug() function |
163
|
|
|
|