-
Notifications
You must be signed in to change notification settings - Fork 4
/
generate_news.py
executable file
·168 lines (142 loc) · 6.43 KB
/
generate_news.py
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
#!./env/bin/python
# -*- coding: utf-8 -*-
from datetime import datetime
import collections
from feedgen.feed import FeedGenerator
import glob
import json
from lxml import etree
import re
import os.path
I2P_OS = os.getenv("I2P_OS", "")
I2P_BRANCH = os.getenv("I2P_BRANCH", "")
DATA_DIR = os.path.join('data')
RELEASE_DIR = os.path.join(DATA_DIR, I2P_OS, I2P_BRANCH)
ENTRIES_FILE = os.path.join(DATA_DIR, 'entries.html')
PLATFORM_ENTRIES_FILE = os.path.join(DATA_DIR, I2P_OS, I2P_BRANCH, 'entries.html')
TRANSLATED_ENTRIES_FILES = os.path.join(DATA_DIR, 'translations/entries.*.html')
TRANSLATED_PLATFORM_ENTRIES_FILES = os.path.join(DATA_DIR, I2P_OS, I2P_BRANCH, 'translations/entries.*.html')
RELEASES_FILE = os.path.join(RELEASE_DIR, 'releases.json')
CRL_FILES = os.path.join(DATA_DIR, 'crls/*.crl')
BLOCKLIST_FILE = os.path.join(DATA_DIR, 'blocklist.xml')
BUILD_DIR = os.path.join('build', I2P_OS, I2P_BRANCH)
NEWS_FILE = os.path.join(BUILD_DIR, 'news.atom.xml')
TRANSLATED_NEWS_FILE = os.path.join(BUILD_DIR, 'news_%s.atom.xml')
def load_feed_metadata(fg):
fg.id('urn:uuid:60a76c80-d399-11d9-b91C-543213999af6')
fg.link( href='http://i2p-projekt.i2p/' )
fg.link( href='http://tc73n4kivdroccekirco7rhgxdg5f3cjvbaapabupeyzrqwv5guq.b32.i2p/news.atom.xml', rel='self' )
fg.link( href='http://dn3tvalnjz432qkqsvpfdqrwpqkw3ye4n4i2uyfr4jexvo3sp5ka.b32.i2p/news/news.atom.xml', rel='alternate' )
def load_entries(fg, entries_file, platform_entries_file=None):
metadatas = {}
finalentries = {}
print('Loading entries from %s' % entries_file)
entries = prepare_entries_file(fg, entries_file)
# split() creates a junk final element with trailing </div>
for entry_str in entries[:-1]:
entry_parts = entry_str.split('</details>', 1)
md = extract_entry_metadata(entry_parts[0])
metadatas[md['published']] = md
finalentries[md['id']] = entry_parts[1]
if os.path.exists(platform_entries_file) and platform_entries_file != entries_file and platform_entries_file is not None and platform_entries_file != "data/entries.html":
print('Loading platform entries from %s' % platform_entries_file)
entries = prepare_entries_file(fg, platform_entries_file)
for entry_str in entries[:-1]:
entry_parts = entry_str.split('</details>', 1)
md = extract_entry_metadata(entry_parts[0])
metadatas[md['updated']] = md
finalentries[md['id']] = entry_parts[1]
sorted_metadata = collections.OrderedDict(sorted(metadatas.items()))
for metadata in sorted_metadata.values():
fe = fg.add_entry()
fe.id(metadata['id'])
fe.title(metadata['title'])
fe.summary(metadata['summary'])
fe.link( href=metadata['href'] )
fe.author( name=metadata['author'] )
fe.published(metadata['published'])
fe.updated(metadata['updated'])
fe.content(finalentries[metadata['id']], type='xhtml')
def prepare_entries_file(fg, entries_file=None):
with open(entries_file) as f:
entries_data = f.read().strip('\n')
# Replace HTML non-breaking space with unicode
entries_data = entries_data.replace(' ', '\u00a0')
# Strip the leading <div> from translations
if entries_data.startswith('<div>'):
entries_data = entries_data[5:]
entries_parts = entries_data.split('</header>')
fg.title(re.findall(r'title="(.*?)"', entries_parts[0])[0])
fg.subtitle(entries_parts[0].split('>')[1])
entries = entries_parts[1].split('</article>')
return entries
def extract_entry_metadata(s):
m = {k:v.strip('"') for k,v in re.findall(r'(\S+)=(".*?"|\S+)', s)}
summary = re.findall(r'<summary>(.*)</summary>', s, re.DOTALL)
if len(summary) > 0:
m['summary'] = summary[0]
return m
def load_releases(fg):
with open(RELEASES_FILE) as json_data:
d = json.load(json_data)
for release in d:
r = fg.i2p.add_release()
r.date(release['date'])
r.version(release['version'])
if 'minVersion' in release:
r.min_version(release['minVersion'])
if 'minJavaVersion' in release:
r.min_java_version(release['minJavaVersion'])
for update_type, update in release['updates'].items():
u = r.add_update(update_type)
if 'clearnet' in update:
for url in update['clearnet']:
u.clearnet(url)
if 'clearnetssl' in update:
for url in update['clearnetssl']:
u.clearnetssl(url)
if 'torrent' in update:
u.torrent(update['torrent'])
if 'url' in update:
for url in update['url']:
u.url(url)
def load_revocations(fg):
# Only add a revocations element if there are CRLs
r = None
for crl in glob.glob(CRL_FILES):
if r is None:
r = fg.i2p.add_revocations()
crl_id = os.path.splitext(os.path.basename(crl))[0]
c = r.add_crl(crl_id)
c.updated(datetime.fromtimestamp(os.path.getmtime(crl)))
with open(crl) as f:
crl_content = f.read().decode('utf8').strip()
c.content('\n%s\n' % crl_content)
def load_blocklist(fg):
# Only add a blocklist element if there is content
b = None
if os.path.isfile(BLOCKLIST_FILE):
with open(BLOCKLIST_FILE) as f:
content = '<xml xmlns:i2p="http://geti2p.net/en/docs/spec/updates">%s</xml>' % f.read()
root = etree.fromstring(content)
b = fg.i2p.add_blocklist()
b.from_xml(root.getchildren()[0])
def generate_feed(entries_file=None, platform_entries_file=None):
language = entries_file and entries_file.split('.')[1] or 'en'
fg = FeedGenerator()
fg.load_extension('i2p')
fg.language(language)
load_feed_metadata(fg)
load_entries(fg, entries_file and entries_file or ENTRIES_FILE, platform_entries_file and platform_entries_file or PLATFORM_ENTRIES_FILE)
load_releases(fg)
load_revocations(fg)
load_blocklist(fg)
if not os.path.exists(BUILD_DIR):
os.makedirs(BUILD_DIR)
fg.atom_file(entries_file and TRANSLATED_NEWS_FILE % language or NEWS_FILE, pretty=True)
if __name__ == '__main__':
# Standard feed
generate_feed()
# Translated feeds
for entries_file in glob.glob(TRANSLATED_ENTRIES_FILES):
generate_feed(entries_file)