11 lines
380 B
Python
11 lines
380 B
Python
import re
|
|
with open('/tmp/comm.html', encoding='utf-8') as f:
|
|
html = f.read()
|
|
|
|
# 查找板块名
|
|
names = re.findall(r'>([^<>]{2,15})</a>', html)
|
|
keywords = ['赚钱', '副业', '电商', 'AI', '金融', '房产', '餐饮', '健康', '教育', '内容', '本地', '跨境', '求职']
|
|
for n in names:
|
|
if any(k in n for k in keywords) and len(n) < 20:
|
|
print(repr(n))
|