mirror of
https://github.com/muhac/chinese-holidays-calendar.git
synced 2024-11-27 01:50:00 +08:00
113 lines
4.1 KiB
Python
113 lines
4.1 KiB
Python
"""从国务院官网抓取放假信息"""
|
||
|
||
import os
|
||
import re
|
||
from datetime import datetime, timezone, timedelta
|
||
from typing import Iterator, Tuple
|
||
|
||
import requests
|
||
|
||
|
||
def main():
|
||
"""更新节假日信息"""
|
||
comments: list[str] = [
|
||
"// automatically generated by crawler.py",
|
||
"// manually checked by DATA NOT VERIFIED",
|
||
]
|
||
|
||
for year, link, holidays in data():
|
||
print(year, link, holidays, sep='\n')
|
||
file = f'./data/{year}.txt'
|
||
|
||
if os.path.isfile(file):
|
||
with open(file, encoding='utf-8') as f_obj:
|
||
existing = f_obj.read()
|
||
if comments[0] in existing and comments[1] not in existing:
|
||
continue # 数据已人工确认
|
||
|
||
with open(file, 'w', encoding='utf-8') as f_obj:
|
||
f_obj.write(
|
||
f"{comments[0]} ({beijing_time().strftime('%-m/%-d/%Y')})\n"
|
||
f"{comments[1]}\n// source: {link}\n\n{holidays}"
|
||
)
|
||
|
||
with open('./README.md', 'r', encoding='utf-8') as f_obj:
|
||
content = f_obj.read().split('\n')
|
||
|
||
update_info = "> Calendar data updated "
|
||
for i, line in enumerate(content):
|
||
if line.startswith(update_info):
|
||
content[i] = update_info + beijing_time().strftime("at %-H:%M on %B %-d, %Y")
|
||
|
||
with open('./README.md', 'w', encoding='utf-8') as f_obj:
|
||
f_obj.write('\n'.join(content))
|
||
|
||
|
||
def data() -> Iterator[Tuple[str, str, str]]:
|
||
"""爬取国务院网站数据"""
|
||
for year, link in source():
|
||
print(f"\n\n{year}: {link}")
|
||
results: list[str] = []
|
||
|
||
response = requests.get(link, timeout=(5, 10))
|
||
response.encoding = response.apparent_encoding
|
||
|
||
line_regex = r"(?P<id>.)、(?P<name>.*)：(</.*?>)?(?P<detail>.*放假.*。)"
|
||
for line in response.text.replace('<br/>', '\n').split('\n'):
|
||
if match := re.search(line_regex, line):
|
||
work, rest, *_ = match.group('detail').split('。')
|
||
dates = ';'.join((match.group('name'), parse(work), parse(rest)))
|
||
print(dates) # 已知需要人工干预如下情况: 1.与周末连休, 2.补休
|
||
results.append(f"{dates:30} // {match.group('detail')}")
|
||
|
||
yield year, link, '\n'.join(results)
|
||
|
||
|
||
def parse(text: str) -> str:
|
||
"""解析节假日安排数据"""
|
||
results: list[str] = []
|
||
range_type_a = r"(?P<m1>\d?\d)月(?P<d1>\d?\d)日至(?P<m2>\d?\d)月(?P<d2>\d?\d)日"
|
||
range_type_b = r"(?P<m1>\d?\d)月(?P<d1>\d?\d)日至(?P<d2>\d?\d)日"
|
||
single_date = r"(?P<m1>\d?\d)月(?P<d1>\d?\d)日"
|
||
|
||
for item in text.split('、'):
|
||
if match := re.search(range_type_a, item):
|
||
results.append(f"{match.group('m1')}.{match.group('d1')}-"
|
||
f"{match.group('m2')}.{match.group('d2')}")
|
||
print(f"\tA: {results[-1]:15} {item}")
|
||
|
||
elif match := re.search(range_type_b, item):
|
||
results.append(f"{match.group('m1')}.{match.group('d1')}-"
|
||
f"{match.group('m1')}.{match.group('d2')}")
|
||
print(f"\tB: {results[-1]:15} {item}")
|
||
|
||
elif match := re.search(single_date, item):
|
||
results.append(f"{match.group('m1')}.{match.group('d1')}")
|
||
print(f"\tS: {results[-1]:15} {item}")
|
||
|
||
else:
|
||
print(f"\tX: {'':15} {item}")
|
||
|
||
return ','.join(results)
|
||
|
||
|
||
def source() -> Iterator[Tuple[str, str]]:
|
||
"""获取官网发布通知列表"""
|
||
search_url = "http://sousuo.gov.cn/s.htm?t=paper&advance=false&n=&codeYear=&codeCode=" \
|
||
"&searchfield=title&sort=&q=%E8%8A%82%E5%81%87%E6%97%A5%E5%AE%89%E6%8E%92"
|
||
link_regex = r"href=['\"](?P<link>.*?)['\"].*国务院办公厅关于(?P<year>20\d\d)年.*通知"
|
||
|
||
for line in requests.get(search_url, timeout=(5, 10)).text.split('\n'):
|
||
if match := re.search(link_regex, line):
|
||
yield match.group('year'), match.group('link')
|
||
|
||
|
||
def beijing_time() -> datetime:
|
||
"""获取当前北京时间"""
|
||
utc_time = datetime.utcnow().replace(tzinfo=timezone.utc)
|
||
return utc_time.astimezone(timezone(timedelta(hours=8)))
|
||
|
||
|
||
if __name__ == '__main__':
|
||
main()
|