结构调整

视频解析多图/多媒体结构 消息体适配
This commit is contained in:
2026-09-08 14:25:32 +08:00
parent 30899688a7
commit 131b92b319
72 changed files with 433 additions and 186 deletions
@@ -68,13 +68,18 @@ async def parse_douyin(
logger.info(f"短链重定向: {target_url} -> {resolved}")
target_url = resolved
else:
# 全链接: www.douyin.com/note/xxx 或 www.douyin.com/video/xxx
# 全链接: www.douyin.com/note/xxx、www.douyin.com/video/xxx,
# 以及抖音复制出的 iesdouyin.com/share/video|note/xxx(弱网/无网下 App
# 生成的恢复连接同样会是这个形态)。统一提取出作品 id 后再交给 SSR / playwright。
m = re.search(
r"(https?://(?:www\.)?douyin\.com/(?:note|video)/\d+)", url
r"(https?://(?:www\.)?(?:m\.)?(?:ies)?douyin\.com/(?:share/)?(note|video)/(\d+))",
url,
)
if not m:
return None, None, False
target_url = m.group(1)
# 统一规范化为 www.douyin.com/{note|video}/{id},避免 iesdouyin 分享页
# 在无登录态/弱网下只返回壳页,直接落到浏览器可正常打开的作品页。
target_url = f"https://www.douyin.com/{m.group(2)}/{m.group(3)}"
try:
is_img_post = False