\s*]*>]*href=\"([^\"]+)\"[^>]*>([^<]+)", text):
+ href, title = m.groups()
+ mm = re.search(r'/([^/]+)_content/(\d+)/([^/]+)\.html', href)
+ if not mm: continue
+ ctype, vid, slug = mm.group(1), mm.group(2), mm.group(3)
+ items.append({
+ 'vod_id': f'{ctype}#{vid}#{slug}',
+ 'vod_name': title.strip(),
+ 'vod_pic': '',
+ 'vod_remarks': '',
+ })
+ return items
+
+ def _parse_posts(self, text, tid=''):
+ """根据分类解析列表：小说单独处理，其他统一按带图 post 处理"""
+ if _is_novel(tid):
+ return self._parse_text_posts(text)
+
+ items = []
+ for m in re.finditer(r"(.*?) ', h)
+ if tn:
+ d["vod_name"] = tn.group(1).split("-")[0].strip()
+
+ # === 封面: 详情页中 data-src ===
+ p = re.search(r'data-src="(https?://[^"]+)"', h)
+ if not p:
+ p = re.search(r'src="(https?://[^"]+\.(?:jpg|jpeg|png|webp))"', h, re.I)
+ if p:
+ d["vod_pic"] = self._clean_pic(p.group(1))
+
+ # === slide-info 区域提取年份/地区/类型/导演/演员/备注/更新时间 ===
+ # 结构:
+ #
+ #
+ #
+ #
+ #
+
+ # 提取slide-info区域中的标签(年份、地区、类型)
+ slide_info_tags = re.findall(
+ r'',
+ h, re.S
+ )
+ if slide_info_tags:
+ tag_text = re.sub(r'<[^>]+>', ' ', slide_info_tags[0])
+ tag_text = re.sub(r'\s+', ' ', tag_text).strip()
+ parts = [t.strip() for t in tag_text.split() if t.strip()]
+ # 第一个通常是年份
+ for p_text in parts:
+ if re.match(r'^\d{4}$', p_text) and not d["vod_year"]:
+ d["vod_year"] = p_text
+ # 地区关键词
+ elif p_text in ("大陆", "香港", "台湾", "美国", "韩国", "日本", "英国",
+ "法国", "德国", "泰国", "印度", "加拿大", "其他",
+ "意大利", "西班牙", "未知"):
+ if not d["vod_area"]:
+ d["vod_area"] = p_text
+ elif not d["vod_area"] and re.match(r'^[\u4e00-\u9fff]{2,3}$', p_text):
+ d["vod_area"] = p_text
+ # 剩余的是类型
+ type_parts = []
+ year_done = False
+ area_done = False
+ for p_text in parts:
+ if re.match(r'^\d{4}$', p_text):
+ year_done = True
+ continue
+ if p_text in ("大陆", "香港", "台湾", "美国", "韩国", "日本", "英国",
+ "法国", "德国", "泰国", "印度", "加拿大", "其他",
+ "意大利", "西班牙", "未知"):
+ area_done = True
+ continue
+ if year_done and area_done:
+ type_parts.append(p_text)
+ if type_parts:
+ d["vod_class"] = " ".join(type_parts)
+
+ # 备注: 备注 :蓝光
+ rm = re.search(r'备注\s*[：:]\s*\s*([^<\s]+)', h)
+ if rm:
+ d["vod_remarks"] = rm.group(1).strip()
+
+ # 导演: 导演 :巨兴茂
+ dm = re.search(r'导演\s*[：:]\s*([\s\S]*?)(?:
)', h)
+ if dm:
+ d["vod_director"] = re.sub(r'<[^>]+>', '', dm.group(1)).replace("/", ",").strip().rstrip(",").strip()
+
+ # 演员: 演员 :杨旭文/杨志刚/...
+ am = re.search(r'演员\s*[：:]\s*([\s\S]*?)(?:\s*]*href=\"([^\"]+)\"[^>]*>]*src='([^']+)'[^>]*>\s*\s*]*class="[^"]*data[^"]*"[^>]*>([\s\S]*?)', h)
+ for item in info_items:
+ clean = re.sub(r'<[^>]+>', '', item).strip()
+ if '导演' in item and not d["vod_director"]:
+ d["vod_director"] = clean.replace('导演', '').strip().rstrip('，').strip()
+ elif '主演' in item and not d["vod_actor"]:
+ d["vod_actor"] = clean.replace('主演', '').strip().rstrip('，').strip()
+ elif '类型' in item and not d["vod_class"]:
+ d["vod_class"] = clean.replace('类型', '').strip()
+ elif '地区' in item and not d["vod_area"]:
+ d["vod_area"] = clean.replace('地区', '').strip()
+ # 备注
+ rm = re.search(r'class="[^"]*remarks?[^"]*"[^>]*>([^<]+)<', h)
+ if rm: d["vod_remarks"] = rm.group(1).strip()
+ # 播放源（只保留m3u8直链线路）
+ try:
+ pf, pu = [], []
+ line_map = {}
+ for sid, name in re.findall(r'id="#con_playlist_(\d+)"[^>]*class="gico[^"]*"[^>]*>([^<]+)', h):
+ line_map[sid] = name.strip()
+ for m in re.finditer(r']*id="con_playlist_(\d+)"[^>]*>([\s\S]*?)', h):
+ sid = m.group(1)
+ content = m.group(2)
+ eps = re.findall(r'href="(/index\.php/vod/play/id/\d+/sid/\d+/nid/\d+\.html)"[^>]*>([\s\S]*?)', content)
+ if not eps:
+ continue
+ line_name = line_map.get(sid, f"线路{sid}")
+ # 预检第1集：只保留返回m3u8直链的线路
+ first_url = urljoin(HOST, eps[0][0])
+ try:
+ rp = self.fetch(first_url, headers={"User-Agent": UA}, timeout=10000)
+ hp = rp.text if hasattr(rp, 'text') else str(rp)
+ pd = re.search(r'player_data\s*=\s*(\{[\s\S]*?\})\s*[;<]', hp)
+ if not pd:
+ continue
+ pdata = json.loads(pd.group(1))
+ purl = pdata.get("url", "")
+ if not purl or not purl.startswith("http") or ".m3u8" not in purl:
+ continue
+ except:
+ continue
+ ep_list = []
+ for url, name in eps:
+ clean_name = re.sub(r'<[^>]+>', '', name).strip()
+ ep_list.append(f"{clean_name}${urljoin(HOST, url)}")
+ if ep_list:
+ pf.append(line_name)
+ pu.append("#".join(ep_list))
+ if pf:
+ d["vod_play_from"] = "$$$".join(pf)
+ d["vod_play_url"] = "$$$".join(pu)
+ except:
+ pass
+ return {"list": [d]}
+
+ def searchContent(self, key, quick=False, pg="1"):
+ try:
+ pn = 1
+ try: pn = int(str(pg))
+ except: pass
+ url = f"{HOST}/index.php/vod/search/wd/{quote(key)}"
+ if pn > 1:
+ url += f"/page/{pn}"
+ url += ".html"
+ r = self.fetch(url, headers={"User-Agent": UA}, timeout=30000)
+ html = r.text if hasattr(r, 'text') else str(r)
+ items = self._items(html)
+ return {"list": items, "page": pn}
+ except:
+ return {"list": []}
+
+ def playerContent(self, flag, id, vipFlags=None):
+ url = str(id) if id else str(flag)
+ if url.startswith("http") and ".m3u8" in url:
+ return {"url": url}
+ if url.startswith("http"):
+ full_url = url
+ else:
+ if not url.startswith("/"):
+ url = "/" + url
+ full_url = urljoin(HOST, url)
+ try:
+ r = self.fetch(full_url, headers={"User-Agent": UA}, timeout=30000)
+ h = r.text if hasattr(r, 'text') else str(r)
+ except:
+ return {"url": ""}
+ pd = re.search(r'player_data\s*=\s*(\{[\s\S]*?\})\s*[;<]', h)
+ if pd:
+ try:
+ data = json.loads(pd.group(1))
+ play_url = data.get("url", "")
+ if play_url:
+ return {"url": play_url}
+ except:
+ pass
+ m3u8 = re.search(r'(https?://[^\s"\'<>]+\.m3u8)', h)
+ if m3u8:
+ return {"url": m3u8.group(1)}
+ return {"url": ""}
+
+ def localProxy(self, param):
+ pass
+
+ def _filter_items(self, items):
+ """过滤：去掉没封面的 + 并发检查线路，去掉没有LZ/YZ的"""
+ if not items:
+ return items
+ # 先去掉没封面的
+ items = [it for it in items if it.get("vod_pic")]
+ if not items:
+ return items
+ # 并发检查每个影片是否有LZ/YZ线路
+ playable_ids = set()
+ def check(it):
+ return it["vod_id"], self._check_playable(it["vod_id"])
+ with ThreadPoolExecutor(max_workers=10) as executor:
+ futures = {executor.submit(check, it): it for it in items}
+ for future in as_completed(futures):
+ try:
+ vid, ok = future.result()
+ if ok:
+ playable_ids.add(vid)
+ except:
+ pass
+ return [it for it in items if it["vod_id"] in playable_ids]
+
+ def _check_playable(self, vid):
+ """检查详情页是否有LZ或YZ线路名"""
+ try:
+ r = self.fetch(f"{HOST}/index.php/vod/detail/id/{vid}.html", headers={"User-Agent": UA}, timeout=5000)
+ h = r.text if hasattr(r, 'text') else str(r)
+ lines = re.findall(r'id="#con_playlist_\d+"[^>]*class="gico[^"]*"[^>]*>([^<]+)', h)
+ for name in lines:
+ if "LZ" in name or "YZ" in name:
+ return True
+ return False
+ except:
+ return False
+
+ def _pagecount(self, html, current_page=1):
+ # 匹配分页链接: /index.php/vod/show/.../page/2/...
+ pages = re.findall(r'/page/(\d+)/', html)
+ max_page = current_page
+ for p in pages:
+ try:
+ n = int(p)
+ if n > max_page:
+ max_page = n
+ except:
+ pass
+ # 如果当前页是最大且还有下一页
+ has_next = re.search(r'>下一页<', html)
+ if has_next and max_page <= current_page + 5:
+ max_page = current_page + 5
+ return max_page
+
+ def _items(self, html, cat_filter=""):
+ items, seen = [], set()
+ # 分类过滤关键词映射
+ ANIME_KEYWORDS = {'动漫', '动画', '卡通', '番剧', '番'}
+ TV_KEYWORDS = {'电视剧', '国产剧', '港台剧', '日韩剧', '欧美剧', '海外剧'}
+ MOVIE_KEYWORDS = {'电影', '动作片', '喜剧片', '爱情片', '科幻片', '恐怖片', '剧情片', '战争片', '纪录片'}
+ for m in re.finditer(r'href="(/index\.php/vod/detail/id/(\d+)\.html)"[^>]*title="([^"]*)"', html):
+ vid = m.group(2)
+ if vid in seen:
+ continue
+ name = m.group(3).strip()
+ if not name or len(name) > 100:
+ continue
+ after = html[m.end():m.end()+2000]
+ # 封面: 优先 data-original，再 data-src，再 src。HTTP升级为HTTPS
+ cover = re.search(r'data-original="(https?://[^"]+)"', after)
+ if not cover:
+ cover = re.search(r'data-src="(https?://[^"]+)"', after)
+ if not cover:
+ cover = re.search(r'src="(https?://[^"]+\.(?:jpg|jpeg|png|webp))"', after, re.I)
+ pic_url = cover.group(1) if cover else ""
+ if pic_url.startswith("http://"):
+ pic_url = pic_url.replace("http://", "https://", 1)
+ # 过滤失效图床域名
+ if pic_url:
+ host = urlparse(pic_url).hostname or ""
+ if host in DEAD_IMG_HOSTS:
+ pic_url = ""
+ # 备注
+ remark = re.search(r'class="titles"[^>]*>([^<]+)<', after)
+ if not remark:
+ remark = re.search(r'class="[^"]*prb[^"]*"[^>]*>([^<]+)<', after)
+ # 分类过滤: 从 mcat 提取分类标签（注意span内可能有换行）
+ mcat_raw = re.search(r'class="mcat">([\s\S]*?)
', after)
+ if mcat_raw and cat_filter:
+ mcat_text = re.sub(r'<[^>]+>', '', mcat_raw.group(1)).strip()
+ if cat_filter == "电视剧":
+ if any(k in mcat_text for k in ANIME_KEYWORDS):
+ continue
+ elif cat_filter == "动漫":
+ if any(k in mcat_text for k in TV_KEYWORDS):
+ continue
+ seen.add(vid)
+ items.append({
+ "vod_id": vid,
+ "vod_name": name[:50],
+ "vod_pic": pic_url,
+ "vod_remarks": remark.group(1).strip() if remark else "",
+ })
+ return items
diff --git a/FGBLH/py/兄弟影视.py b/FGBLH/py/兄弟影视.py
new file mode 100644
index 00000000..d232d4b8
--- /dev/null
+++ b/FGBLH/py/兄弟影视.py
@@ -0,0 +1,640 @@
+# -*- coding: utf-8 -*-
+import sys
+import re
+import json
+from urllib.parse import urljoin, quote, unquote, urlparse
+from html import unescape as html_unescape
+sys.path.append('..')
+try:
+ from base.spider import Spider
+except ImportError:
+ class Spider:
+ def fetch(self, url, headers=None, **kw):
+ import requests as rq
+ kw.pop('timeout', None)
+ r = rq.get(url, headers=headers, timeout=15, **kw)
+ r.encoding = 'utf-8'
+ return r
+
+HOST = "https://www.brovod.com"
+UA = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
+
+# 封面URL中这些域名已失效，对应影片会被过滤掉
+DEAD_IMG_HOSTS = {"image.caiji.cyou", "wim.xrc888.com"}
+# 分类映射: tid -> 中文名
+CATEGORIES = {
+ "Movies": "电影",
+ "TV": "剧集",
+ "Anime": "动漫",
+ "Documentaries": "纪录片",
+ "Snaps": "短剧",
+ "Shows": "综艺",
+}
+
+# weserv.nl 代理前缀，需要去掉以获取原始URL
+WESERV_PREFIX = "https://images.weserv.nl/?url="
+
+# from值 -> 线路显示名 (来自 playerconfig.js)
+# 蓝光①(xdxl/xdyy)和蓝光④(xdjp)已禁用（无法播放）
+FROM_DISPLAY = {
+ "xdrs": "蓝光②", "xdac": "蓝光③", "xd5": "蓝光⑤",
+ "bfzym3u8": "极速①", "1080zyk": "极速②", "jsm3u8": "极速③",
+}
+# 禁用的from值，对应的线路会被过滤掉
+BLOCKED_FROMS = {"xdxl", "xdyy", "xdjp"}
+
+
+class Spider(Spider):
+ def init(self, extend=""):
+ global HOST
+ try:
+ r = self.fetch(HOST, headers={"User-Agent": UA}, timeout=15000)
+ if hasattr(r, 'url') and r.url and r.url != HOST.rstrip("/"):
+ HOST = r.url.rstrip("/")
+ except:
+ pass
+
+ def homeContent(self, filter=False):
+ r = {"class": []}
+ for k, v in CATEGORIES.items():
+ r["class"].append({"type_id": k, "type_name": v})
+ return r
+
+ def homeVideoContent(self):
+ try:
+ r = self.fetch(HOST, headers={"User-Agent": UA}, timeout=15000)
+ html = r.text if hasattr(r, 'text') else str(r)
+ return {"list": [it for it in self._items(html) if it.get("vod_pic")]}
+ except:
+ return {"list": []}
+
+ def categoryContent(self, tid, pg=1, filter=False, extend=""):
+ pn = 1
+ try:
+ pn = max(int(str(pg)), 1)
+ except:
+ pass
+ cat = str(tid)
+ if cat not in CATEGORIES:
+ return {"page": pn, "pagecount": 1, "limit": 36, "total": 0, "list": []}
+ try:
+ url = self._build_category_url(cat, pn, extend)
+ r = self.fetch(url, headers={"User-Agent": UA}, timeout=30000)
+ html = r.text if hasattr(r, 'text') else str(r)
+ items = [it for it in self._items(html) if it.get("vod_pic")]
+ pc = self._pagecount(html, pn)
+ return {"page": pn, "pagecount": pc, "limit": 36, "total": len(items), "list": items}
+ except:
+ return {"page": pn, "pagecount": 1, "limit": 36, "total": 0, "list": []}
+
+ def _build_category_url(self, cat, pn, extend=""):
+ """构建分类URL
+ 网站URL实际格式为12段（以-分隔）:
+ /show/{类名}-{地区}-{排序}-{类型}-{语言}-{字母}-----{页码}---{年份}/
+ 段位说明（0-indexed）:
+ 0: 类名 (Movies/TV/Anime/Documentaries/Snaps/Shows)
+ 1: 地区 (大陆/香港/美国/...)
+ 2: 排序 (time/hits/score)
+ 3: 类型 (喜剧/爱情/动作/...)
+ 4: 语言 (国语/英语/粤语/...)
+ 5: 字母 (A/B/C/.../0-9)
+ 6-7: 空
+ 8: 页码 (1/2/3/...)
+ 9-10: 空
+ 11: 年份 (2026/2025/...)
+ 示例: /show/Movies-----------/ (无筛选,首页)
+ 示例: /show/Movies--------1---/ (第1页) 注意首页无筛选时不需要页码
+ 示例: /show/Movies--------2---/ (第2页)
+ 示例: /show/Movies-%E5%A4%A7%E9%99%86----------/ (地区=大陆)
+ 示例: /show/Movies---%E5%96%9C%E5%89%A7--------/ (类型=喜剧)
+ 示例: /show/Movies-----------2026/ (年份=2026)
+ 示例: /show/Movies--time---------/ (按时间排序)
+ """
+ ext = {}
+ if extend and isinstance(extend, str) and extend.strip():
+ try:
+ ext = json.loads(extend)
+ except:
+ pass
+
+ area = ext.get("area") or ""
+ sort = ext.get("sort") or ""
+ genre = ext.get("class") or ""
+ lang = ext.get("lang") or ""
+ letter = ext.get("letter") or ""
+ year = ext.get("year") or ""
+
+ # 12段: [类名, 地区, 排序, 类型, 语言, 字母, "", "", 页码, "", "", 年份]
+ parts = [cat, "", "", "", "", "", "", "", "", "", "", ""]
+ if area and area != "全部":
+ parts[1] = quote(area)
+ if sort:
+ parts[2] = sort
+ if genre and genre != "全部":
+ parts[3] = quote(genre)
+ if lang and lang != "全部":
+ parts[4] = quote(lang)
+ if letter and letter != "全部":
+ parts[5] = letter
+ if pn > 1:
+ parts[8] = str(pn)
+ if year and year != "全部":
+ parts[11] = str(year)
+
+ url = "/show/" + "-".join(parts) + "/"
+ return HOST + url
+
+ def detailContent(self, ids):
+ if isinstance(ids, list):
+ vid = ids[0] if ids else ""
+ else:
+ vid = str(ids) if ids else ""
+ if not vid:
+ return {"list": []}
+ detail_id = vid
+
+ # 构建详情页URL
+ if "/" in vid:
+ detail_url = vid if vid.startswith("http") else urljoin(HOST, vid)
+ else:
+ detail_url = f"{HOST}/detail/{vid}/"
+
+ try:
+ r = self.fetch(detail_url, headers={"User-Agent": UA}, timeout=30000)
+ h = r.text if hasattr(r, 'text') else str(r)
+ except:
+ return {"list": []}
+
+ d = {
+ "vod_id": detail_id,
+ "vod_name": "",
+ "vod_pic": "",
+ "vod_year": "",
+ "vod_area": "",
+ "vod_class": "",
+ "vod_director": "",
+ "vod_actor": "",
+ "vod_content": "",
+ "vod_remarks": "",
+ "vod_play_from": "",
+ "vod_play_url": "",
+ }
+
+ # === 标题: \s*]*>]*>([^<]+)(?:\s*)?", text):
+ href, pic, title, date = m.groups()
+ date = date or ''
+ mm = re.search(r'/([^/]+)_content/(\d+)/([^/]+)\.html', href)
+ if not mm: continue
+ ctype, vid, slug = mm.group(1), mm.group(2), mm.group(3)
+ items.append({
+ 'vod_id': f'{ctype}#{vid}#{slug}',
+ 'vod_name': title.strip(),
+ 'vod_pic': self._proxy_url(pic),
+ 'vod_remarks': date.strip(),
+ })
+ return items
+
+ def _build_cat_url(self, tid, page, extend=None):
+ if extend and extend.get('sub'):
+ sub = quote(unquote(extend['sub']), safe='/()')
+ return f'{self.host}/zh/{sub}/{page}.html'
+ if tid.startswith('search_'):
+ kw = tid[7:]
+ return f'{self.host}/zh/chinese_search/all/{kw}/{page}.html'
+ # TVBox 可能截断 type_id，自动补全
+ if tid.endswith('_random'):
+ tid = tid + '/all'
+ elif '/' not in tid:
+ tid = tid + '_random/all'
+ if page == 1:
+ return f'{self.host}/zh/{tid}/index.html'
+ return f'{self.host}/zh/{tid}/index_{page}.html'
+
+ # ===== 接口 =====
+ def homeContent(self, filter):
+ classes = [
+ {'type_id': 'chinese_random/all', 'type_name': '中文字幕'},
+ {'type_id': 'censored_random/all', 'type_name': '有码'},
+ {'type_id': 'uncensored_random/all', 'type_name': '无码'},
+ {'type_id': 'reducing-mosaic_random/all', 'type_name': '无码破解'},
+ {'type_id': 'amateurjav_random/all', 'type_name': '素人'},
+ {'type_id': 'animation_random/all', 'type_name': 'H动画'},
+ {'type_id': 'dt_random/all', 'type_name': '国产自拍'},
+ {'type_id': '18H_random/all', 'type_name': '18H漫画'},
+ {'type_id': 'cg_random/all', 'type_name': '写真图集'},
+ {'type_id': 'cwp_random/all', 'type_name': '国产写真'},
+ {'type_id': 'novel_random/all', 'type_name': '小说'},
+ ]
+
+ filter = self._build_filters()
+ return {'class': classes, 'filters': filter, 'type': '影视'}
+
+ def _build_filters(self):
+ """构造 TVBox filter 格式（网站左侧导航真实子分类）"""
+ filters = {}
+ chinese_opts = [
+ {'n': '全部', 'v': ''},
+ {'n': '随机', 'v': 'chinese_randomall/all'},
+ {'n': '类别清单', 'v': 'chinese_categorylist/list'},
+ ]
+ filters['chinese_random/all'] = [{'key': 'sub', 'name': '中文字幕', 'value': chinese_opts}]
+ uncensored_opts: list[dict[str, str]] = [
+ {'n': '全部', 'v': ''},
+ {'n': '一本道(1pondo)', 'v': 'uncensored_makersr/32/一本道(1pondo)'},
+ {'n': 'カリビアンコム(Caribbeancom)', 'v': 'uncensored_makersr/30/カリビアンコム(Caribbeancom)'},
+ {'n': 'カリビアンコムPPV', 'v': 'uncensored_makersr/40/カリビアンコムPPV(Caribbeancompr)'},
+ {'n': '天然むすめ(10musume)', 'v': 'uncensored_makersr/31/天然むすめ(10musume)'},
+ {'n': 'HEYZO', 'v': 'uncensored_makersr/17/HEYZO'},
+ {'n': '東京熱(Tokyo Hot)', 'v': 'uncensored_makersr/29/東京熱(Tokyo Hot)'},
+ {'n': 'ガチん娘！(Gachinco)', 'v': 'uncensored_makersr/35/ガチん娘！(Gachinco)'},
+ {'n': 'パコパコママ(pacopacomama)', 'v': 'uncensored_makersr/36/パコパコママ(pacopacomama)'},
+ {'n': 'エッチな4610', 'v': 'uncensored_makersr/34/エッチな4610'},
+ {'n': '人妻斬り0930', 'v': 'uncensored_makersr/38/人妻斬り0930'},
+ {'n': 'エッチな0930', 'v': 'uncensored_makersr/39/エッチな0930'},
+ {'n': 'トリプルエックス(XXX-AV)', 'v': 'uncensored_makersr/126/トリプルエックス (XXX-AV)'},
+ ]
+ filters['uncensored_random/all'] = [{'key': 'sub', 'name': '厂商', 'value': uncensored_opts}]
+
+ animation_opts = [
+ {'n': '全部', 'v': ''},
+ {'n': 'H有码动画', 'v': 'CensoredAnimation_random/all'},
+ {'n': 'H无码动画', 'v': 'UncensoredAnimation_random/all'},
+ {'n': 'H_3D动画', 'v': 'tdAnimation_random/all'},
+ ]
+ filters['animation_random/all'] = [{'key': 'sub', 'name': '动漫', 'value': animation_opts}]
+
+ comic_opts = [
+ {'n': '全部', 'v': ''},
+ {'n': '短篇同人', 'v': 'doujin_random/all'},
+ ]
+ filters['18H_random/all'] = [{'key': 'sub', 'name': '漫画', 'value': comic_opts}]
+
+ cg_opts = [
+ {'n': '全部', 'v': ''},
+ {'n': 'Bejean On Line', 'v': 'cg_search/all/Bejean On Line'},
+ {'n': 'Bomb.tv', 'v': 'cg_search/all/Bomb.tv'},
+ {'n': 'DGC', 'v': 'cg_search/all/DGC'},
+ {'n': 'Graphis Gals', 'v': 'cg_search/all/Graphis Gals'},
+ {'n': 'Graphis Hatsunugi', 'v': 'cg_search/all/Graphis Hatsunugi'},
+ {'n': 'image.tv', 'v': 'cg_search/all/image.tv'},
+ {'n': 'Sabra.net', 'v': 'cg_search/all/Sabra.net'},
+ {'n': 'S-Cute', 'v': 'cg_search/all/S-Cute'},
+ {'n': 'X-City', 'v': 'cg_search/all/X-City'},
+ {'n': 'YS Web', 'v': 'cg_search/all/YS Web'},
+ ]
+ filters['cg_random/all'] = [{'key': 'sub', 'name': '系列', 'value': cg_opts}]
+
+ cwp_opts = [
+ {'n': '全部', 'v': ''},
+ {'n': '3AGirl AAA女郎', 'v': 'cwp_search/all/3AGirl AAA女郎'},
+ {'n': 'ROSI寫真', 'v': 'cwp_search/all/ROSI寫真'},
+ {'n': 'RU1MM 如壹寫真', 'v': 'cwp_search/all/RU1MM 如壹寫真'},
+ {'n': 'DISI第四印象', 'v': 'cwp_search/all/DISI第四印象'},
+ ]
+ filters['cwp_random/all'] = [{'key': 'sub', 'name': '系列', 'value': cwp_opts}]
+
+ novel_opts = [
+ {'n': '全部', 'v': ''},
+ {'n': '學生校園', 'v': 'novel_search/all/學生校園'},
+ {'n': '職場激情', 'v': 'novel_search/all/職場激情'},
+ {'n': '經驗故事', 'v': 'novel_search/all/經驗故事'},
+ {'n': '暴力虐待', 'v': 'novel_search/all/暴力虐待'},
+ {'n': '不倫戀情', 'v': 'novel_search/all/不倫戀情'},
+ {'n': '群體換伴', 'v': 'novel_search/all/群體換伴'},
+ {'n': '人妻熟女', 'v': 'novel_search/all/人妻熟女'},
+ {'n': '科學幻想', 'v': 'novel_search/all/科學幻想'},
+ {'n': '其他故事', 'v': 'novel_search/all/其他故事'},
+ {'n': '玄幻仙俠', 'v': 'novel_search/all/玄幻仙俠'},
+ {'n': '動漫修改', 'v': 'novel_search/all/動漫修改'},
+ {'n': '長篇連載', 'v': 'novel_search/all/長篇連載'},
+ ]
+ filters['novel_random/all'] = [{'key': 'sub', 'name': '主题', 'value': novel_opts}]
+ return filters
+
+ def homeVideoContent(self):
+ text = self._fetch(f'{self.host}/zh/chinese_IamOverEighteenYearsOld/19/index.html')
+ items = self._parse_posts(text, 'content_news/all')
+ return {'list': items}
+
+ def categoryContent(self, tid, pg, filter, extend):
+ try:
+ return self._categoryContent_inner(tid, pg, filter, extend)
+ except Exception:
+ return {'list': [], 'page': int(pg) if pg else 1, 'pagecount': 1, 'limit': 0, 'total': 0}
+
+ def _categoryContent_inner(self, tid, pg, filter, extend):
+ if isinstance(extend, str):
+ try:
+ extend = json.loads(extend)
+ except Exception:
+ extend = {}
+ if not extend:
+ extend = {}
+ page = int(pg) if pg else 1
+ # ===== 类别清单（中文字幕的子分类）: 文件夹形式（仿 18av） =====
+ if extend.get('sub') == 'chinese_categorylist/list':
+ return self._category_folder(page)
+ if '@' in str(tid):
+ return self._folder_detail(tid, page)
+ url = self._build_cat_url(tid, page, extend)
+ # 子分类筛选时按子分类内容类型解析
+ parse_tid = tid
+ if parse_tid.endswith('_random'):
+ parse_tid = parse_tid + '/all'
+ elif '/' not in parse_tid:
+ parse_tid = parse_tid + '_random/all'
+ if extend and extend.get('sub'):
+ sub = extend['sub']
+ if _is_novel(sub):
+ parse_tid = 'novel_random/all'
+ elif _is_image(sub):
+ parse_tid = sub.split('_')[0] + '_random/all' if '_' in sub else 'cg_random/all'
+ text = self._fetch(url)
+ items = self._parse_posts(text, parse_tid)
+ return {'list': items, 'page': page, 'pagecount': page + 1,
+ 'limit': len(items), 'total': page * len(items) + 1}
+
+ # ===== 类别清单（文件夹形式，仿 18av） =====
+ def _category_folder(self, pg):
+ """类别清单: 抓取子分类索引页，以 folder 形式返回，点文件夹进入视频列表"""
+ html = self._fetch(f'{self.host}/zh/chinese_categorylist/list/index.html')
+ lst = []
+ for m in re.finditer(
+ r"]+href=[\"']([^\"']*chinese_category/(\d+)/([^\"'/]+)/[^\"']*)[\"'][^>]*>([^<]+)",
+ html, re.I):
+ category_url = m.group(1).strip()
+ category_name = m.group(4).strip()
+ if category_url.startswith(self.host):
+ category_url = category_url[len(self.host):]
+ lst.append({
+ 'vod_id': category_url + '@',
+ 'vod_name': category_name,
+ 'vod_pic': self.host.rstrip('/') + '/images/1v.jpg',
+ 'vod_tag': 'folder',
+ 'vod_remarks': '分类',
+ })
+ return {'list': lst, 'page': 1, 'pagecount': 1,
+ 'limit': len(lst), 'total': len(lst)}
+
+ def _folder_detail(self, tid, pg):
+ """@ 文件夹: 去掉 @, 把子分类链接当作真实 URL 拉取视频列表（支持翻页）"""
+ tid = str(tid).replace('@', '')
+ url = self.host.rstrip('/') + tid
+ if re.search(r'/\d+\.html$', url):
+ url = re.sub(r'/\d+\.html$', '/' + str(pg) + '.html', url)
+ else:
+ base = url.rstrip('/')
+ url = base + ('/index.html' if pg <= 1 else f'/index_{pg}.html')
+ html = self._fetch(url)
+ lst = self._parse_posts(html, 'chinese_category')
+ return {'list': lst, 'page': pg, 'pagecount': 9999,
+ 'limit': len(lst), 'total': 9999}
+
+ def detailContent(self, ids):
+ try:
+ return self._detailContent_inner(ids)
+ except Exception:
+ return {'list': []}
+
+ def _detailContent_inner(self, ids):
+ vid = str(ids[0] if isinstance(ids, list) else ids)
+ ctype, num, slug = vid.split('#', 2)
+ if _is_novel(ctype):
+ return self._novel_detail(vid, ctype, num, slug)
+ elif _is_image(ctype):
+ return self._image_detail(vid, ctype, num, slug)
+ else:
+ return self._video_detail(vid, ctype, num, slug)
+
+ def _video_detail(self, vid, ctype, num, slug):
+ """视频详情（有播放器解密）"""
+ url = f'{self.host}/zh/{ctype}_content/{num}/{slug}.html'
+ text = self._fetch(url)
+ if not text: return {'list': []}
+
+ title = ''
+ m = re.search(r']*>(.*?)', text, re.S)
+ if m: title = re.sub(r'<[^>]+>', '', m.group(1)).strip()
+ if not title:
+ m = re.search(r'([^<]+) ', text)
+ if m: title = m.group(1).strip()
+
+ cover = ''
+ m = re.search(r'"thumbnailUrl"\s*:\s*"([^"]+)"', text)
+ if m: cover = m.group(1)
+ if not cover:
+ m = re.search(r"]*property=\"og:image\"[^>]*content=\"([^\"]+)\"", text)
+ if m: cover = m.group(1)
+ if not cover:
+ m = re.search(r"
', h)
+ if desc_m:
+ d["vod_content"] = re.sub(r'\s+', ' ', re.sub(r'<[^>]+>', '', desc_m.group(1))).strip()[:500]
+ # 年份
+ ym = re.search(r'(\d{4})', d.get("vod_name", ""))
+ if ym: d["vod_year"] = ym.group(1)
+ # 地区/分类/导演/主演等
+ info_items = re.findall(r'.*?]*src='([^']+)'", text, re.S)
+ if m: cover = m.group(1)
+
+ m = re.search(r'hadeedg252=(\d+)', text)
+ if not m: return {'list': []}
+ hadeedg252 = int(m.group(1))
+ m = re.search(r'hcdeedg252=(\d+)', text)
+ if not m: return {'list': []}
+ hcdeedg252 = int(m.group(1))
+ m = re.search(r"var argdeqweqweqwe = '([^']+)'", text)
+ if not m: return {'list': []}
+ aes_key = m.group(1)
+ m = re.search(r"var hdddedg252 = '([^']+)'", text)
+ if not m: return {'list': []}
+ aes_iv = m.group(1)
+
+ mm = re.search(r"mvarr\['10_1'\]=(\[.*?\]);", text, re.S)
+ if not mm: return {'list': []}
+ mvarr_str = mm.group(1)
+ items = re.findall(r"\['([^']*)','([^']*)','([^']*)','([^']*)','([^']*)','([^']*)'\]", mvarr_str)
+ if not items: return {'list': []}
+
+ urls = []
+ for iframe_id, enc, html, prefix, empty, label in items:
+ if not enc or not prefix: continue
+ pid = self._decrypt_id(enc, hadeedg252, hcdeedg252, aes_key, aes_iv)
+ if not pid: continue
+ for res, label_name in [('1080', '1080P'), ('720', '720P'), ('480', '480P')]:
+ urls.append(f'{label_name}${num}|{slug}|{pid}|{res}')
+
+ if not urls: return {'list': []}
+
+ vod = {
+ 'vod_id': vid,
+ 'vod_name': title,
+ 'vod_pic': self._proxy_url(cover),
+ 'vod_content': '',
+ 'vod_remarks': '',
+ 'vod_play_from': 'mjv011',
+ 'vod_play_url': '#'.join(urls),
+ }
+ return {'list': [vod]}
+
+ def _novel_detail(self, vid, ctype, num, slug):
+ """小说详情"""
+ url = f'{self.host}/zh/{ctype}_content/{num}/{slug}.html'
+ text = self._fetch(url)
+ if not text: return {'list': []}
+
+ title = ''
+ m = re.search(r']*>(.*?)', text, re.S)
+ if m: title = re.sub(r'<[^>]+>', '', m.group(1)).strip()
+
+ content = ''
+ m = re.search(r"id=['\"]novel_content_txtsize['\"][^>]*>(.*?)
", text, re.S)
+ if m:
+ raw = m.group(1)
+ content = re.sub(r'<[^>]+>', '', raw)
+ content = re.sub(r' ', ' ', content)
+ content = re.sub(r'\s+', ' ', content).strip()
+ if not content:
+ m = re.search(r"([\s\S]*?)\s*]+>', '', raw)
+ content = re.sub(r' ', ' ', content)
+ content = re.sub(r'\s+', ' ', content).strip()
+
+ if len(content) > 3000:
+ content = content[:3000] + '...'
+
+ novel_json = json.dumps({'title': title, 'content': content}, ensure_ascii=False)
+ play_url = f'阅读$novel://{novel_json}'
+
+ vod = {
+ 'vod_id': vid,
+ 'vod_name': title,
+ 'vod_pic': '',
+ 'vod_content': '',
+ 'vod_remarks': '',
+ 'vod_play_from': '小说',
+ 'vod_play_url': play_url,
+ 'vod_tag': 'text',
+ 'vod_player': '书',
+ }
+ return {'list': [vod]}
+
+ def _image_detail(self, vid, ctype, num, slug):
+ """图片详情（写真/漫画）"""
+ url = f'{self.host}/zh/{ctype}_content/{num}/{slug}.html'
+ text = self._fetch(url)
+ if not text: return {'list': []}
+
+ title = ''
+ m = re.search(r']*>(.*?)', text, re.S)
+ if m: title = re.sub(r'<[^>]+>', '', m.group(1)).strip()
+
+ cover = ''
+ m = re.search(r'"thumbnailUrl"\s*:\s*"([^"]+)"', text)
+ if m: cover = m.group(1)
+
+ # 提取详情页所有大图（第一页已包含全部）
+ all_imgs = re.findall(r"src=['\"]([^'\"]*eemmhh02\.com/[^'\"]+\.(?:jpg|png|webp))['\"]", text, re.I)
+ big_imgs = []
+ seen = set()
+ for img in all_imgs:
+ if img in seen:
+ continue
+ seen.add(img)
+ big_imgs.append(self._proxy_url(img))
+
+ if not big_imgs:
+ return {'list': []}
+
+ pics = '&&'.join(big_imgs)
+ play_url = f'查看$pics://{pics}'
+
+ vod = {
+ 'vod_id': vid,
+ 'vod_name': title,
+ 'vod_pic': self._proxy_url(cover),
+ 'vod_content': f'共 {len(big_imgs)} 张图片',
+ 'vod_remarks': str(len(big_imgs)) + 'P',
+ 'vod_play_from': '图片',
+ 'vod_play_url': play_url,
+ 'vod_tag': 'image',
+ 'vod_player': '画',
+ }
+ return {'list': [vod]}
+
+ def _decrypt_id(self, enc, xor_key, base, aes_key, aes_iv):
+ try:
+ sep = chr(base + 97)
+ parts = enc.split(sep)
+ s1 = ''.join(chr(int(p, base) ^ xor_key) for p in parts if p)
+ data = base64.b64decode(s1)
+ plain = _aes_cbc_decrypt(data, aes_key.encode(), aes_iv.encode())
+ return plain.decode('utf-8')
+ except Exception:
+ return ''
+
+ def searchContent(self, key, quick, pg="1"):
+ try:
+ return self._searchContent_inner(key, quick, pg)
+ except Exception:
+ return {'list': [], 'page': int(pg) if pg else 1, 'pagecount': 1, 'limit': 0, 'total': 0}
+
+ def _searchContent_inner(self, key, quick, pg="1"):
+ page = int(pg) if pg else 1
+ return self._categoryContent_inner(f'search_{key}', page, False, {})
+
+ def playerContent(self, flag, id, vipFlags=None):
+ try:
+ return self._playerContent_inner(flag, id, vipFlags)
+ except Exception:
+ return {'parse': 0, 'url': '', 'header': {}, 'position': '0'}
+
+ def _playerContent_inner(self, flag, id, vipFlags=None):
+ # 小说
+ if id.startswith('novel://'):
+ return {'parse': 0, 'url': id, 'header': '', 'vod_player': '书'}
+ # 图片
+ if id.startswith('pics://'):
+ return {'parse': 0, 'playUrl': '', 'url': id, 'header': self.headers}
+ # 视频播放
+ num, slug, pid, res = id.split('|', 3)
+ url = f'{self.host}/js/player/play.php?numresolution={res}&lo=on&id={pid}'
+ text = self._fetch(url)
+ m3u8 = ''
+ if text:
+ mm = re.search(r'videoSources\s*=\s*(\[.*?\]);', text, re.S)
+ if mm:
+ arr = mm.group(1)
+ sources = re.findall(r"src:\s*'([^']+)'[^}]*?size:\s*(\d+)", arr, re.S)
+ if sources:
+ target = int(res) if str(res).isdigit() else 0
+ for u, s in sources:
+ if int(s) == target:
+ m3u8 = u
+ break
+ if not m3u8:
+ m3u8 = sources[0][0]
+ if not m3u8:
+ mm = re.search(r'https?://[^\s"<>\']+?\.m3u8', text)
+ if mm: m3u8 = mm.group(0)
+ return {'parse': 0, 'url': m3u8, 'header': {'Referer': self.host + '/'}, 'position': '0'}
\ No newline at end of file
diff --git a/FGBLH/py/58影视.py b/FGBLH/py/58影视.py
new file mode 100644
index 00000000..6d39fbf3
--- /dev/null
+++ b/FGBLH/py/58影视.py
@@ -0,0 +1,385 @@
+# -*- coding: utf-8 -*-
+import sys
+import re
+import json
+from urllib.parse import urljoin, quote, unquote, urlparse
+from concurrent.futures import ThreadPoolExecutor, as_completed
+
+sys.path.append('..')
+try:
+ from base.spider import Spider
+except ImportError:
+ class Spider:
+ def fetch(self, url, headers=None, **kw):
+ import requests as rq
+ kw.pop('timeout', None)
+ r = rq.get(url, headers=headers, timeout=15, **kw)
+ r.encoding = 'utf-8'
+ return r
+
+HOST = "https://www.58hu.com"
+UA = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
+
+# 封面URL中这些域名已失效，对应影片会被过滤掉
+DEAD_IMG_HOSTS = {"image.caiji.cyou", "wim.xrc888.com"}
+
+CATEGORIES = {
+ "1": "电影", "2": "电视剧", "3": "综艺",
+ "4": "动漫", "21": "体育",
+}
+
+# 子分类: {父分类ID: {子分类ID: 名称}}
+SUB_CATS = {
+ "1": {"6": "动作片", "7": "喜剧片", "8": "爱情片", "9": "科幻片", "10": "恐怖片",
+ "11": "剧情片", "12": "战争片", "22": "纪录片"},
+ "2": {"13": "国产剧", "14": "港台剧", "15": "日韩剧", "16": "欧美剧", "24": "海外剧",
+ "29": "BI番剧", "30": "BI国创", "31": "BI电影"},
+ "3": {"28": "最新综艺"},
+ "4": {"27": "最新动漫"},
+ "21": {"26": "体育赛事"},
+}
+
+class Spider(Spider):
+ def init(self, extend=""):
+ global HOST
+ try:
+ r = self.fetch(HOST, headers={"User-Agent": UA}, timeout=15000)
+ if hasattr(r, 'url') and r.url and r.url != HOST.rstrip("/"):
+ HOST = r.url.rstrip("/")
+ except:
+ pass
+
+ def homeContent(self, filter=False):
+ r = {"class": [], "list": []}
+ for k, v in CATEGORIES.items():
+ r["class"].append({"type_id": k, "type_name": v})
+ return r
+
+ def homeVideoContent(self):
+ try:
+ r = self.fetch(HOST, headers={"User-Agent": UA}, timeout=15000)
+ html = r.text if hasattr(r, 'text') else str(r)
+ return {"list": self._items(html)}
+ except:
+ return {"list": []}
+
+ def categoryContent(self, tid, pg=1, filter=False, extend=""):
+ pn = 1
+ try: pn = max(int(str(pg)), 1)
+ except: pass
+ cat = str(tid)
+ try:
+ url = self._build_category_url(cat, pn, extend)
+ r = self.fetch(url, headers={"User-Agent": UA}, timeout=30000)
+ html = r.text if hasattr(r, 'text') else str(r)
+ cat_name = CATEGORIES.get(cat, "")
+ items = self._items(html, cat_filter=cat_name)
+ # 过滤掉没有封面或没有可播放线路的影片（并发检查）
+ items = self._filter_items(items)
+ pc = self._pagecount(html, pn)
+ return {"page": pn, "pagecount": pc, "limit": 30, "total": len(items), "list": items}
+ except:
+ return {"page": pn, "pagecount": 1, "limit": 30, "total": 0, "list": []}
+
+ def _build_category_url(self, cat, pn, extend=""):
+ """构建分类URL，支持筛选参数"""
+ # 解析extend中的筛选条件
+ ext = {}
+ if extend and isinstance(extend, str) and extend.strip():
+ try:
+ ext = json.loads(extend)
+ except:
+ pass
+
+ # 判断是否为子分类（在SUB_CATS中）
+ is_sub = False
+ for parent, subs in SUB_CATS.items():
+ if cat in subs:
+ is_sub = True
+ break
+
+ # 所有分类用 vod/show 模式
+ parts = []
+ # class/类型
+ cls = ext.get("class") or ""
+ if cls and cls != "全部":
+ parts.append(f"class/{quote(cls)}")
+ # area/地区
+ area = ext.get("area") or ""
+ if area and area != "全部":
+ parts.append(f"area/{quote(area)}")
+ # year/年代
+ year = ext.get("year") or ""
+ if year and year != "全部":
+ parts.append(f"year/{quote(year)}")
+ # letter/字母
+ letter = ext.get("letter") or ""
+ if letter and letter != "全部":
+ parts.append(f"letter/{quote(letter)}")
+ # sort/排序
+ sort = ext.get("sort") or ""
+ if sort:
+ parts.append(f"by/{quote(sort)}")
+ # page
+ if pn > 1:
+ parts.append(f"page/{pn}")
+ filters = "/".join(parts)
+ if filters:
+ return f"{HOST}/index.php/vod/show/{filters}/id/{cat}.html"
+ else:
+ return f"{HOST}/index.php/vod/show/id/{cat}.html"
+
+ def detailContent(self, ids):
+ if isinstance(ids, list):
+ vid = ids[0] if ids else ""
+ else:
+ vid = str(ids) if ids else ""
+ m = re.search(r'(\d+)', str(vid))
+ vid = m.group(1) if m else ""
+ if not vid:
+ return {"list": []}
+ try:
+ r = self.fetch(f"{HOST}/index.php/vod/detail/id/{vid}.html", headers={"User-Agent": UA}, timeout=30000)
+ h = r.text if hasattr(r, 'text') else str(r)
+ except:
+ return {"list": []}
+ d = {"vod_id": vid, "vod_name": "", "vod_pic": "", "vod_year": "",
+ "vod_area": "", "vod_class": "", "vod_director": "", "vod_actor": "",
+ "vod_content": "", "vod_remarks": "", "vod_play_from": "", "vod_play_url": ""}
+ # 标题
+ tn = re.search(r']*>(.*?)', h)
+ if tn:
+ d["vod_name"] = re.sub(r'<[^>]+>', '', tn.group(1)).strip()
+ if not d["vod_name"]:
+ tn = re.search(r'(.*?) ', h)
+ if tn:
+ d["vod_name"] = tn.group(1).split("-")[0].strip()
+ # 封面: 优先 class="pic-img video-pic" 里的img
+ p = re.search(r'class="pic-img video-pic"[\s\S]{0,100}?]*src="(https?://[^"]+)"', h, re.I)
+ if not p:
+ p = re.search(r'data-src="(https?://[^"]+)"', h)
+ if not p:
+ p = re.search(r'src="(https?://[^"]+\.(?:jpg|jpeg|png|webp))"', h, re.I)
+ if p:
+ pic_url = p.group(1)
+ if pic_url.startswith("http://"):
+ pic_url = pic_url.replace("http://", "https://", 1)
+ d["vod_pic"] = pic_url
+ # 简介
+ desc_m = re.search(r'简介[\s\S]{0,30}?>([\s\S]*?)
', h)
+ if desc_m:
+ d["vod_content"] = re.sub(r'\s+', ' ', re.sub(r'<[^>]+>', '', desc_m.group(1))).strip()[:500]
+ if not d["vod_content"]:
+ desc_m = re.search(r'class="[^"]*desc[^"]*"[^>]*>([\s\S]*?)