mirror of
https://github.com/JefferyHcool/BiliNote.git
synced 2026-08-30 04:27:02 +08:00
pumpkinperson996andClaude Fable 5
b85d7bc1ff
从"稍后再看"（/list/watchlater/?bvid=BV...）、收藏夹播放页等场景 复制的链接会被判为无效链接，尽管其中包含完整 BV 号；校验通过的 链接也会带着追踪参数原样传给 yt-dlp。 在请求入口新增 normalize_video_url()：提取 BV 号重建标准 /video/BVxxx 链接，保留分 P 参数（?p=N），丢弃其余查询参数。 b23.tv 短链与其他平台行为不变，无 BV 号链接仍按原逻辑拒绝。 Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
107 lines
3.2 KiB
Python
107 lines
3.2 KiB
Python
import re
|
||
from typing import Optional
|
||
import requests
|
||
|
||
|
||
def extract_video_id(url: str, platform: str) -> Optional[str]:
|
||
"""
|
||
从视频链接中提取视频 ID
|
||
|
||
:param url: 视频链接
|
||
:param platform: 平台名（bilibili / youtube / douyin）
|
||
:return: 提取到的视频 ID 或 None
|
||
"""
|
||
if platform == "bilibili":
|
||
# 如果是短链接，则解析真实链接
|
||
if "b23.tv" in url:
|
||
resolved_url = resolve_bilibili_short_url(url)
|
||
if resolved_url:
|
||
url = resolved_url
|
||
|
||
# 匹配 BV号（如 BV1vc411b7Wa）
|
||
match = re.search(r"BV([0-9A-Za-z]+)", url)
|
||
return f"BV{match.group(1)}" if match else None
|
||
|
||
elif platform == "youtube":
|
||
# 匹配 v=xxxxx、youtu.be/xxxxx 或 shorts/xxxxx，ID 长度通常为 11
|
||
match = re.search(r"(?:v=|youtu\.be/|shorts/)([0-9A-Za-z_-]{11})", url)
|
||
return match.group(1) if match else None
|
||
|
||
elif platform == "douyin":
|
||
# 匹配 douyin.com/video/1234567890123456789
|
||
match = re.search(r"/video/(\d+)", url)
|
||
return match.group(1) if match else None
|
||
|
||
return None
|
||
|
||
|
||
def normalize_video_url(url: str) -> str:
|
||
"""
|
||
将任意包含 BV 号的 B 站链接规范化为标准视频链接。
|
||
|
||
支持稍后再看（/list/watchlater/?bvid=BV...）、收藏夹播放页（/list/mlXXX?bvid=BV...）、
|
||
带追踪参数的分享链接等。保留分 P 参数，丢弃其余查询参数。
|
||
|
||
b23.tv 短链与无 BV 号的链接原样返回（后者交由校验器拒绝）。
|
||
"""
|
||
if "b23.tv" in url:
|
||
return url
|
||
|
||
match = re.search(r"BV([0-9A-Za-z]+)", url)
|
||
if not match:
|
||
return url
|
||
|
||
normalized = f"https://www.bilibili.com/video/BV{match.group(1)}"
|
||
p = extract_bilibili_p_number(url)
|
||
if p:
|
||
normalized += f"?p={p}"
|
||
return normalized
|
||
|
||
|
||
def resolve_bilibili_short_url(short_url: str) -> Optional[str]:
|
||
"""
|
||
解析哔哩哔哩短链接以获取真实视频链接
|
||
|
||
:param short_url: Bilibili短链接（如"https://b23.tv/xxxxxx"）
|
||
:return: 真实的视频链接或None
|
||
"""
|
||
try:
|
||
response = requests.head(short_url, allow_redirects=True)
|
||
return response.url
|
||
except requests.RequestException as e:
|
||
print(f"Error resolving short URL: {e}")
|
||
return None
|
||
|
||
|
||
def extract_bilibili_p_number(url: str) -> Optional[int]:
|
||
"""
|
||
从 B 站分 P 视频 URL 中提取 p 参数（分 P 序号）。
|
||
|
||
支持格式：
|
||
- https://www.bilibili.com/video/BVxxx/?p=36
|
||
- https://www.bilibili.com/video/BVxxx?p=5
|
||
- https://b23.tv/xxxxx?p=10
|
||
- https://www.bilibili.com/video/BVxxx/pN (尾缀形式)
|
||
|
||
:param url: B 站视频链接
|
||
:return: 分 P 序号（从 1 开始），非分 P 视频返回 None
|
||
"""
|
||
if "b23.tv" in url:
|
||
url = resolve_bilibili_short_url(url) or url
|
||
|
||
# 匹配 ?p=NNN 或 &p=NNN
|
||
match = re.search(r'[?&]p=(\d+)', url)
|
||
if match:
|
||
p = int(match.group(1))
|
||
if p >= 1:
|
||
return p
|
||
|
||
# 匹配 /pN 尾缀形式（较少见）
|
||
match = re.search(r'/p(\d+)(?:/?$|\?|&)', url)
|
||
if match:
|
||
p_val = int(match.group(1))
|
||
if p_val >= 1:
|
||
return p_val
|
||
|
||
return None
|