34 lines
1.2 KiB
Python
34 lines
1.2 KiB
Python
import re
|
||
import urllib.request
|
||
|
||
req = urllib.request.Request('https://www.zhuig.com/community', headers={'User-Agent': 'Mozilla/5.0', 'Cache-Control': 'no-cache'})
|
||
html = urllib.request.urlopen(req, timeout=15).read().decode('utf-8')
|
||
|
||
# 板块区域附近
|
||
idx_q = html.find('全部板块')
|
||
idx_z = html.find('最新话题')
|
||
section = html[idx_q:idx_z] if idx_z > 0 else html[idx_q:idx_q+15000]
|
||
|
||
# 找"<a " 出现位置（不是RSC payload里的"a"组件，是真实HTML）
|
||
real_a = re.findall(r'<a\s', section)
|
||
real_a_in_quotes = re.findall(r'\\"a\\",', section)
|
||
print(f'真实<a>标签: {len(real_a)}')
|
||
print(f'RSC \\"a\\" 组件: {len(real_a_in_quotes)}')
|
||
|
||
# 看section里"$" RSC payload 数量
|
||
dollar_count = section.count('"$"')
|
||
print(f'RSC payload "$" 数量: {dollar_count}')
|
||
|
||
# 找第一个 RSC "a" 组件
|
||
m = re.search(r'\["\$","a",[^]]+\]', section)
|
||
if m:
|
||
print(f'\n第一个RSC a组件示例:\n{m.group()[:500]}')
|
||
|
||
# 看板块区域最后部分(应该是RSC结束+可能HTML)
|
||
print(f'\n板块区域最后200字符:')
|
||
print(section[-300:])
|
||
|
||
# 板块区域有多少个 [$,"a" 出现
|
||
rsc_a = re.findall(r'\["\$","a"', section)
|
||
print(f'\nRSC "a" 组件数: {len(rsc_a)}')
|