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
|
#!/usr/bin/env python3
from datetime import datetime
import json
import re
from sys import argv
from urllib.parse import urljoin
from lxml.builder import E
from lxml.etree import CDATA, XML, indent, tostring
from helpers import (
DATE_FORMATTERS,
guess_language,
read_concerts,
tmplocale,
touchup_plaintext,
)
# TODO: handle timezones correctly.
# Places to disambiguate:
#
# - concerts.in:
# either add the zone explicitly, or deduce it from the place,
# assuming all times in concerts.in are local times.
#
# - concerts-pubdates.json:
# just add the zone explicitly.
#
# Until then, assume all these "naive times" describe the same timezone
# (CET/CEST).
TIMEZONE = datetime.now().astimezone().tzinfo
NOW = datetime.now(tz=TIMEZONE)
DATE_FORMAT = '%-d %b %Y %H:%M %z'
# TODO: add item pubDate
LOCALIZED_TEXT = {
'en': {
'title': 'Bellefeuille Quartet',
'indexpath': 'en/',
'description': 'News from the Bellefeuille quartet',
},
'fr': {
'title': 'Quatuor Bellefeuille',
'indexpath': '/',
'description': 'Des nouvelles du quatuor Bellefeuille',
},
}
LOCALIZED_FORMATS = {
'en': {
'title': lambda c: f'{c.time.strftime("%B %-d %Y")} in {c.place}',
},
'fr': {
'title': lambda c: f'{c.time.strftime("%-d %B %Y")} à {c.place}',
},
}
def join(sequence, joiner_factory):
# There's got to be a standard itertools/functools thingy to do that…
result = []
for i, item in enumerate(sequence, start=1):
result.append(item)
if i == len(sequence):
return result
result.append(joiner_factory())
def cdata_concert(concert, lang):
formatters = DATE_FORMATTERS[lang]
blocks = []
if concert.warning is not None:
blocks.append(E.p(concert.warning))
with tmplocale(lang):
blocks.extend((
E.p(formatters['date'](concert.time)),
E.p(formatters['time'](concert.time)),
))
blocks.extend((
E.p(*join(concert.address.splitlines(), E.br)),
E.ol(
*(XML(f'<li>{touchup_plaintext(p)}</li>')
for p in concert.pieces.splitlines())
),
*(E.p(line) for line in concert.instructions.splitlines()),
))
# Do a silly dance to indent CDATA correctly.
for b in blocks:
indent(b)
html_blocks = (tostring(b, encoding='utf-8').decode() for b in blocks)
cdata = '\n'.join(html_blocks) + '\n'
cdata = re.sub('^', 8*' ', cdata, flags=re.MULTILINE)
return CDATA('\n' + cdata)
def generate_concert(concert, concerts_url, pubdates, lang):
formatters = LOCALIZED_FORMATS[lang]
with tmplocale(lang):
title = formatters['title'](concert)
anchor = f'concert-{concert.time.strftime("%F")}'
item = E.item(
E.title(title),
E.link(f'{concerts_url}#{anchor}'),
E.description(cdata_concert(concert, lang)),
)
pubdate_str = pubdates[concert.time.isoformat(timespec='minutes')]
if pubdate_str is not None:
pubdate = datetime.fromisoformat(pubdate_str).replace(tzinfo=TIMEZONE)
item.append(E.pubDate(pubdate.strftime(DATE_FORMAT)))
return item
def generate_concerts(concerts_src, concerts_url, concerts_pubdates, lang):
with open(concerts_pubdates) as pubdates_file:
pubdates = json.load(pubdates_file)
return tuple(
generate_concert(c, concerts_url, pubdates, lang)
for c in read_concerts(concerts_src)
)
def main(concerts_src, feed_dst, concerts_pubdates, domain):
lang = guess_language(concerts_src)
text = LOCALIZED_TEXT[lang]
url = f'https://{domain}'
index_url = urljoin(url, text['indexpath'])
concerts_url = urljoin(index_url, 'concerts.html')
now_formatted = NOW.strftime(DATE_FORMAT)
concerts = generate_concerts(
concerts_src, concerts_url, concerts_pubdates, lang
)
rss = E.rss(
E.channel(
E.title(text['title']),
E.link(index_url),
E.description(text['description']),
E.image(
E.url(urljoin(url, 'images/logo.svg')),
E.link(concerts_url),
),
E.lastBuildDate(now_formatted),
E.pubDate(now_formatted),
E.language(lang),
*concerts,
),
version='2.0',
)
indent(rss)
with open(feed_dst, 'wb') as feed:
feed.write(tostring(rss, encoding='utf-8', xml_declaration=True))
if __name__ == '__main__':
main(*argv[1:])
|
