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
|
#!/usr/bin/env python3
#
# Legacy Daily Bulletin components that need to be replaced
# Copyright (C) 2024 Runxi Yu <https://runxiyu.org>
# Copyright (C) 2023-2024 Albert Tan <albert-tan@qq.com>
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program. If not, see <https://www.gnu.org/licenses/>.
#
from __future__ import annotations
import re
import os
import copy
import datetime
import logging
import argparse
import configparser
import requests
import bs4
logger = logging.getLogger(__name__)
def get_on_this_day_zh() -> None:
months = list(map(lambda x: str(x) + "月", range(1, 13)))
for index in range(12):
month = months[index]
day = 1
url = "https://zh.m.wikipedia.org/zh-cn/Wikipedia:历史上的今天/" + month
response = requests.get(url, timeout=15)
html = response.text
soup = bs4.BeautifulSoup(html, "html.parser")
div_elements = soup.find_all("div", class_="selected-anniversary")
for div_element in div_elements:
datetime_time = datetime.datetime(2000, index + 1, day)
formatted_time_yearless = datetime_time.strftime("%m-%d")
p_element = div_element.find("p")
dl_element = div_element.find("dl")
event_elements = dl_element.find_all("div", class_="event")
ul_element = soup.new_tag("ul")
for event in event_elements:
li_element = soup.new_tag("li")
li_element.append(event)
ul_element.append(li_element)
result = str(p_element).replace("/wiki", "https://zh.wikipedia.org/zh-cn").replace('<span class="otd-year">', "<b>").replace("</span>：", "：</b>") + str(ul_element).replace("/wiki", "https://zh.wikipedia.org/zh-cn").replace("</dt><dd>", " – ").replace('<div class="event">\n<dt>', "").replace("</dd>\n</div>", "")
result = re.sub(r"<small>.*?图.*?</small>", "", result)
with open("otd_zh-" + formatted_time_yearless + ".html", "w") as file:
file.write(result)
file.close()
day += 1
def get_on_this_day_en() -> None:
months = [
"January",
"February",
"March",
"April",
"May",
"June",
"July",
"August",
"September",
"October",
"November",
"December",
]
for index in range(12):
month = months[index]
day = 1
url = "https://en.m.wikipedia.org/wiki/Wikipedia:Selected_anniversaries/" + month
response = requests.get(url, timeout=15)
html = response.text
soup = bs4.BeautifulSoup(html, "html.parser")
p_elements = soup.find_all("p")
for p_element in p_elements:
try:
datetime_time = datetime.datetime(2000, index + 1, day)
formatted_time_yearless = datetime_time.strftime("%m-%d")
except ValueError:
break
if not re.search(
f'<p><b><a href="/wiki/{month}_\\d+" title="{month} \\d+">{month} \\d+</a></b',
str(p_element),
):
continue
div_element = p_element.find_next("div")
ul_element = div_element.find_next_sibling("ul")
ul_element_2 = ul_element.find_next("ul")
p_element_2 = soup.new_tag("p")
li_contents = list(ul_element_2.find_all("li"))
for li in li_contents:
p_element_2.append(li)
result = str(p_element).replace("/wiki", "https://en.wikipedia.org/wiki") + str(ul_element).replace("/wiki", "https://en.wikipedia.org/wiki") + "\n" + str(p_element_2).replace("</li><li>", "; ").replace("<li>", "<b>Births and Deaths: </b>").replace("</li>", "").replace("/wiki", "https://en.wikipedia.org/wiki")
result = re.sub(r" <i>.*?icture.*?</i>", "", result)
with open("otd_en-" + formatted_time_yearless + ".html", "w") as file:
file.write(result)
file.close()
day += 1
def get_in_the_news_en() -> str:
url = "https://en.m.wikipedia.org/wiki/Main_Page"
response = requests.get(url, timeout=15)
html = response.text
soup = bs4.BeautifulSoup(html, "html.parser")
h2_element = soup.find("div", id="mp-itn")
assert h2_element
ul_element = h2_element.find_next("ul")
assert ul_element
ul_element_2 = ul_element.find_next("ul")
assert ul_element_2
div_element = ul_element_2.find_next("div")
assert div_element
ul_element_3 = div_element.find_next("ul")
assert ul_element_3
p_element_2 = soup.new_tag("p")
p_element_3 = soup.new_tag("p")
assert isinstance(ul_element_2, bs4.Tag)
assert isinstance(ul_element_3, bs4.Tag)
li_contents_2 = list(ul_element_2.find_all("li"))
li_contents_3 = list(ul_element_3.find_all("li"))
skip = False
for li in li_contents_2:
if skip:
skip = False
continue
if li.find("ul"):
new_li = copy.deepcopy(li)
new_li.find("ul").decompose()
p_element_2.append(new_li)
skip = True
else:
p_element_2.append(li)
for li in li_contents_3:
if skip:
skip = False
continue
if li.find("ul"):
new_li = copy.deepcopy(li)
new_li.find("ul").decompose()
p_element_3.append(new_li)
skip = True
else:
p_element_3.append(li)
result = str(ul_element).replace("/wiki", "https://en.wikipedia.org/wiki") + str(p_element_2).replace("</li><li>", "; ").replace("<li>", "<b>Ongoing: </b>").replace("</li>", "").replace("\n;", ";").replace("/wiki", "https://en.wikipedia.org/wiki").replace("</p>", "<br>") + str(p_element_3).replace("</li><li>", "; ").replace("<li>", "<b>Recent deaths: </b>").replace("</li>", "").replace("\n;", ";").replace("/wiki", "https://en.wikipedia.org/wiki").replace("<p>", "")
result = re.sub(r" <i>\(.*?\)</i>", "", result)
return result
def get_in_the_news_zh() -> str:
url = "https://zh.m.wikipedia.org/zh-cn/Wikipedia:%E9%A6%96%E9%A1%B5"
response = requests.get(url, timeout=15)
html = response.text
soup = bs4.BeautifulSoup(html, "html.parser")
div_element = soup.find("div", id="column-itn")
assert div_element
ul_element = div_element.find("ul")
assert isinstance(ul_element, bs4.Tag)
ul_element_2 = ul_element.find_next("ul")
assert isinstance(ul_element_2, bs4.Tag)
ul_element_3 = ul_element_2.find_next("ul")
assert isinstance(ul_element_3, bs4.Tag)
span_element_2 = ul_element_2.find("span", class_="hlist inline")
span_element_3 = ul_element_3.find("span", class_="hlist inline")
assert span_element_2 and span_element_3
p_element_2 = soup.new_tag("p")
p_element_3 = soup.new_tag("p")
p_element_2.append(span_element_2)
p_element_3.append(span_element_3)
result = (
str(ul_element).replace("/wiki", "https://zh.wikipedia.org/zh-cn")
+ str(p_element_2)
.replace('<span class="hlist inline">', "<b>正在发生：</b>")
.replace("</span>", "")
.replace("－", "；")
.replace(
'（<a href="/wiki/%E4%BF%84%E7%BE%85%E6%96%AF%E5%85%A5%E4%BE%B5%E7%83%8F%E5%85%8B%E8%98%AD%E6%99%82%E9%96%93%E8%BB%B8" title="俄罗斯入侵乌克兰时间轴">时间轴</a>）',
"",
)
.replace("/wiki", "https://zh.wikipedia.org/zh-cn")
+ str(p_element_3).replace('<span class="hlist inline">', "<b>最近逝世：</b>").replace("</span>", "").replace("－", "；").replace("/wiki", "https://zh.wikipedia.org/zh-cn")
).replace("</p><p>", "<br>")
result = re.sub(r"<small.*?>.*?</small>", "", result)
return result
def main() -> None:
parser = argparse.ArgumentParser(description="Legacy Wikipedia script for the Daily Bulletin")
parser.add_argument("--config", default="config.ini", help="path to the configuration file")
args = parser.parse_args()
config = configparser.ConfigParser()
config.read(args.config)
build_path = config["general"]["build_path"]
os.chdir(build_path)
logging.basicConfig(level=logging.DEBUG)
logger.warning("Running main() only grabs On This Day")
logger.info("get_on_this_day_en()")
get_on_this_day_en()
logger.info("get_on_this_day_zh()")
get_on_this_day_zh()
# logger.info("get_in_the_news_en()")
# get_in_the_news_en()
# logger.info("get_in_the_news_zh()")
# get_in_the_news_zh()
if __name__ == "__main__":
main()
|
