weidu

$url = "<wx-url>"
$out = "$env:TEMP\wx_raw.html"

$req = [System.Net.HttpWebRequest]::Create($url)
$req.UserAgent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
$req.Headers.Add("Accept-Language","zh-CN,zh;q=0.9")
$req.Timeout = 30000

$resp = $req.GetResponse()
$ms = New-Object System.IO.MemoryStream
$resp.GetResponseStream().CopyTo($ms)
[System.IO.File]::WriteAllBytes($out, $ms.ToArray())
$resp.Close()

"len=" + $ms.Length
"sha8=" + (Get-FileHash $out -Algorithm SHA256).Hash.Substring(0,8)

$h = [System.IO.File]::ReadAllText("$env:TEMP\wx_raw.html", [System.Text.Encoding]::UTF8)
"js_content present? " + $h.Contains('id="js_content"')
"content_noencode present? " + $h.Contains('content_noencode:')

import re, html, sys, io
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')

with open(r"<path-to-html>", encoding="utf-8") as f:
    h = f.read()

def find_meta(name):
    m = re.search(r'<meta[^>]+(?:property|name)="' + name + r'"[^>]+content="([^"]*)"', h)
    return html.unescape(m.group(1)) if m else None

title = find_meta("og:title")

# 路径 A：旧版 js_content（优先）
m = re.search(r'<div[^>]*id="js_content"[^>]*>(.*?)</div>\s*<script', h, re.S)
body_html = ""

if m:
    body_html = m.group(1)
else:
    # 路径 B：新版 content_noencode JS string
    i = h.find("content_noencode:")
    if i > 0:
        i = h.find("'", i)
        j = i + 1
        buf = []
        while j < len(h):
            c = h[j]
            if c == "\\" and j + 1 < len(h):
                nx = h[j+1]
                if nx == "x" and j + 3 < len(h):
                    buf.append(chr(int(h[j+2:j+4], 16))); j += 4; continue
                if nx == "u" and j + 5 < len(h):
                    buf.append(chr(int(h[j+2:j+6], 16))); j += 6; continue
                buf.append({'n':'\n','t':'\t','r':'\r',"'":"'",'"':'"','\\':'\\','/':'/'}.get(nx, nx))
                j += 2; continue
            if c == "'":
                break
            buf.append(c); j += 1
        body_html = "".join(buf)

# 班规：chars=0 不是成功
assert body_html, "FATAL: 两个容器都没匹配上——可能是新版变体或反爬命中"

# 去标签
body = re.sub(r'<br[^>]*>', '\n', body_html)
body = re.sub(r'</p>', '\n\n', body)
body = re.sub(r'</(h[1-6]|li|blockquote|section|div)>', '\n', body)
body = re.sub(r'<style[^>]*>.*?</style>', '', body, flags=re.S)
body = re.sub(r'<script[^>]*>.*?</script>', '', body, flags=re.S)
body = re.sub(r'<[^>]+>', '', body)
body = html.unescape(body)
body = re.sub(r'\n{3,}', '\n\n', body).strip()

print(f"TITLE: {title}")
print(f"chars: {len(body)}")