# 脚本名称：片库影院 # 作者：小柱子 # 创建时间：2026‑09‑11 # 文件编码utf‑8，防止中文乱码【固定，不要改】 # -*- coding: utf-8 -*- import sys # 系统模块【固定】 import re # 正则，解析html【固定】 import json # json处理【固定】 import requests from urllib.parse import quote # url编码，搜索关键词编码【固定】 sys.path.append('..') # 导入上级模块路径【固定】 from base.spider import Spider # 继承壳爬虫基类【固定】 # 类名Spider：壳识别爬虫脚本入口【类名固定，禁止修改】 class Spider(Spider): # ===================== 接口1：init 初始化接口【函数名、参数固定】 ===================== def init(self, extend=""): #接口用途：源初始化，打开该爬虫源时执行一次；可修改字段：self.host、self.headers""" # 【可修改】请求头，模拟浏览器，反爬网站可修改UA、Accept等 self.headers = { # 【可修改】浏览器标识，网站校验UA就改这里 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/140.0.0.0 Safari/537.36', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7', 'Accept-Language': 'zh-CN,zh;q=0.9,en-US;q=0.8,en;q=0.7', 'Upgrade-Insecure-Requests': '1', 'sec-ch-ua': '"Not A;Brand";v="99", "Chromium";v="140", "Google Chrome";v="140"', 'sec-ch-ua-mobile': '?1', 'sec-ch-ua-platform': '"Android"', 'x-requested-with': 'XBrowser', 'Sec-Fetch-Site': 'none', 'Sec-Fetch-Mode': 'navigate', 'Sec-Fetch-User': '?1', 'Sec-Fetch-Dest': 'document', } # 【已改】固定内容站域名，不再调用 _get_host() 从导航页获取 self.host = 'https://4k01.pianku.online' # 解析接口固定域名 self.auth_host = "https://svip.qlplayer.cyou" # 初始化访问首页建立会话，全局搜索不经过homeContent，必须在此建立 try: self.fetch(self.host, headers=self.headers, timeout=15, verify=False) except Exception: pass # ===================== 接口2：getName 源名称接口【函数名固定】 ===================== def getName(self): #接口用途：返回源名称，展示在壳源列表；可修改字段：return返回的字符串""" # 【可修改】修改引号内文字，更改源显示名字 return '片库影院' # ===================== 壳内部回调钩子【全部固定，禁止改动】 ===================== def isVideoFormat(self, url): return False def manualVideoCheck(self): return True # ===================== 解析列表公共工具函数 _parse_vodlist ===================== def _parse_vodlist(self, html): #工具用途：首页/分类/搜索 共用解析影片列表；可修改：re.findall正则，适配不同网站的影片列表html""" videos = [] # 【可修改】正则，匹配单条影片：链接、标题、封面，根据网页标签改写 items = re.findall( r']*>\s*
]*>\s*]*>\s*([^<]*)', html ) for href, title, pic, remark in items: # 【可修改】正则提取影片id，根据网站详情链接格式改写 vod_id_match = re.search(r'/voddetail/(\d+)\.html', href) if not vod_id_match: continue vod_id = vod_id_match.group(1) # 补全相对图片地址【逻辑固定】 if pic.startswith('/'): pic = self.host + pic # 返回字典key壳固定，value为解析数据 videos.append({ 'vod_id': vod_id, 'vod_name': title, 'vod_pic': pic, 'vod_remarks': remark, }) return videos def homeVideoContent(self): """壳钩子，本源未使用，保留占位""" return '' # ===================== 接口3：homeContent 首页接口【函数名、参数固定】 ===================== def homeContent(self, filter): #接口用途：加载源首页，返回分类列表 + 首页影片列表；可修改：首页url、分类抓取正则、异常兜底分类；返回格式固定 {"class":分类数组,"list":影片数组}""" try: # 【可修改】首页网页地址 r = self.fetch(self.host, headers=self.headers, timeout=15, verify=False) html = r.text # 【可修改】抓取导航整块html正则，匹配导航标签 nav_match = re.search(r'', html, re.DOTALL) if nav_match: nav_html = nav_match.group(1) # 【可修改】提取分类id、分类名称正则，适配网站a标签 categories = re.findall(r']*>]*>([^<]+)', nav_html) else: categories = [] seen = set() classes = [] for tid, name in categories: if tid not in seen: seen.add(tid) classes.append({'type_name': name, 'type_id': tid}) if not classes: raise Exception('No categories found') video_list = self._parse_vodlist(html) except Exception: # 兜底写死分类，防止源直接空白崩溃【可修改按需修改】 classes = [ {'type_name': '电影', 'type_id': '20'}, {'type_name': '剧集', 'type_id': '37'}, {'type_name': '动漫', 'type_id': '43'}, {'type_name': '综艺', 'type_id': '45'} ] video_list = [] # ========= CAT分组绑定式筛选【筛选值为独立分类id，按大类tid分组绑定】 ========= filters = { "20": [ { "key": "cateId", "name": "类型", "value": [ {"n": "全部", "v": "20"}, {"n": "动作片", "v": "21"}, {"n": "喜剧片", "v": "22"}, {"n": "爱情片", "v": "23"}, {"n": "科幻片", "v": "24"}, {"n": "恐怖片", "v": "25"}, {"n": "剧情片", "v": "26"}, {"n": "战争片", "v": "27"}, {"n": "惊悚片", "v": "28"}, {"n": "犯罪片", "v": "29"}, {"n": "冒险篇", "v": "30"}, {"n": "动画片", "v": "31"}, {"n": "悬疑片", "v": "32"}, {"n": "武侠片", "v": "33"}, {"n": "奇幻片", "v": "34"}, {"n": "纪录片", "v": "35"}, {"n": "其他片", "v": "36"} ] } ], "37": [ { "key": "cateId", "name": "类型", "value": [ {"n": "全部", "v": "37"}, {"n": "国产剧", "v": "38"}, {"n": "港台剧", "v": "39"}, {"n": "欧美剧", "v": "40"}, {"n": "日韩剧", "v": "41"}, {"n": "其他剧", "v": "42"} ] } ] } return {"class": classes, "list": video_list, "filters": filters} # ===================== 接口4：categoryContent 分类接口【函数名、参数固定】 ===================== def categoryContent(self, tid, pg, filter, extend): #接口用途：点击分类，加载分类页面数据；tid：分类id，pg：页码；可修改：分类页面url模板；返回key全部壳固定不可修改""" pg = int(pg) # 【可修改】分类页面url模板，未翻页 vodtype/{tid}.html，已翻页 vodtype/{tid}-{pg}.html # CAT协议：筛选值存放在extend，key为cateId；无筛选沿用原始tid cateId = extend.get("cateId", tid) if extend else tid url = f'{self.host}/vodtype/{cateId}.html' if pg == 1 else f'{self.host}/vodtype/{cateId}-{pg}.html' try: r = self.fetch(url, headers=self.headers, timeout=15, verify=False) html = r.text video_list = self._parse_vodlist(html) return { "list": video_list, "page": pg, "pagecount": 9999, # 9999=无限分页【可修改，设置真实总页数】 "limit": 30, # 每页条数【可修改】 "total": len(video_list), } except Exception: return {"list": [], "page": pg, "pagecount": 1, "limit": 90, "total": 0} # ===================== 接口5：detailContent 详情接口【函数名、参数固定】 ===================== def detailContent(self, ids): #接口用途：点击影片，加载详情页面，获取标题、演员、简介、播放线路集数；ids：壳传入影片id列表；可修改：详情url、各个字段截取正则；返回格式固定 {"list":[详情字典]}""" # ----------------------【可修改 线路配置区】---------------------- # 【已移除】line_rename手动重命名字典，改为下方自动编号逻辑，无需逐个写原始名映射 del_line_list = [""] # 【可修改】需要屏蔽的线路原始名称 sort_order = [""] # 【可修改】自定义线路显示排序，优先顺序 # ---------------------------------------------------------------- vod_id = ids[0] if isinstance(ids, list) else ids try: # 【可修改】详情页面url模板 url = f'{self.host}/voddetail/{vod_id}.html' r = self.fetch(url, headers=self.headers, timeout=15, verify=False) html = r.text # 【可修改】截取影片标题正则 title_match = re.search(r'

]*>([^<]+)', html) vod_name = title_match.group(1).strip() if title_match else '' # 【可修改】截取封面图片正则 pic_match = re.search(r'
]*>\s*]*>([^<]+)\s*]*>地区：([^<]+)\s*]*>年份：(\d{4})', html, re.S|re.DOTALL) type_name = info_match.group(1).strip() if info_match else '' vod_area = info_match.group(2).strip() if info_match else '' vod_year = info_match.group(3).strip() if info_match else '' # 【可修改】截取导演正则 director_match = re.search(r']*>导演：(.*?)', html, re.DOTALL) vod_director = '' if director_match: vod_director = re.sub(r'<[^>]+>', '', director_match.group(1)).strip() vod_director = vod_director.replace(' ', '').strip() # 【可修改】截取主演正则（彻底清理 空格实体） actor_match = re.search(r']*>主演：(.*?)', html, re.DOTALL) vod_actor = '' if actor_match: vod_actor = re.sub(r'<[^>]+>', '', actor_match.group(1)).strip() vod_actor = vod_actor.replace(' ', ' ').strip() # 【可修改】截取剧情简介正则 desc_match = re.search(r'
]*>.*?]*>(.*?)

', html, re.DOTALL) vod_content = desc_match.group(1).strip() if desc_match else '' # =====================线路抓取===================== # 正则抓取线路序号和名称，序号取自data-target，与显示顺序无关 source_tabs = re.findall(r']*>([^<]+)', html) temp_line_data = {} # 存放 线路名:集数串 for source_id, source_name in source_tabs: # 命中屏蔽的线路跳过 if source_name in del_line_list: continue # 正则抓取该线路的集数列表整块，id属性前有class等属性，需从div开头放宽匹配 play_block = re.search( f']*id="playlist-{source_id}"[^>]*>.*?
]*>(.*?)
', html, re.DOTALL ) if play_block: play_html = play_block.group(1) # 正则抓取每一集的链接和名称 ep_items = re.findall(r']*>([^<]*)', play_html) ep_list = [] for ep_url, ep_name in ep_items: full_url = self.host + ep_url # 补全集数完整地址 # $ 分隔集名和地址 ep_list.append(f'{ep_name}${full_url}') # # 分隔集与集 temp_line_data[source_name] = '#'.join(ep_list) # =========【原始名称层面做sort_order排序，填网站原始线路名称】========= play_from_raw = [] # 线路名列表 play_url_raw = [] # 集数串列表 temp_raw_keys = list(temp_line_data.keys()) for raw_name in sort_order: # 先排优先线路 if raw_name in temp_raw_keys: play_from_raw.append(raw_name) play_url_raw.append(temp_line_data[raw_name]) temp_raw_keys.remove(raw_name) for remain_raw_name in temp_raw_keys: # 剩余线路追加在后 play_from_raw.append(remain_raw_name) play_url_raw.append(temp_line_data[remain_raw_name]) # =========【原站名称自动命名】========= renamed_play_from = [] renamed_play_url = [] for raw_name, ep_str in zip(play_from_raw, play_url_raw): # 空集数跳过，不占位 if not (ep_str and len(ep_str.strip()) > 0): continue # 【可修改】展示名模板，直接用原站线路名 new_name = f'📡{raw_name}┃广告勿信！' renamed_play_from.append(new_name) renamed_play_url.append(ep_str) # 地址原样不动 # $$$ 分隔线路与线路 vod_play_from = '$$$'.join(renamed_play_from) if renamed_play_from else '' vod_play_url = '$$$'.join(renamed_play_url) if renamed_play_url else '' vod_info = { 'vod_id': vod_id, # 影片id 'vod_name': vod_name, # 影片名 'vod_pic': vod_pic, # 封面 'vod_year': vod_year, # 年份 'vod_area': vod_area, # 地区 'type_name': type_name, # 类型 'vod_director': vod_director, # 导演 'vod_actor': vod_actor, # 主演 'vod_content': vod_content, # 简介 'vod_play_from': vod_play_from, # 线路名 'vod_play_url': vod_play_url, # 各线路集数 } return {"list": [vod_info]} except Exception: return {"list": []} # ===================== 接口6：searchContent 搜索接口【函数名、参数固定】 ===================== def searchContent(self, key, quick, pg="1"): #接口用途：执行搜索，返回搜索影片列表；key：搜索关键词，pg：搜索页码；可修改：搜索页面url地址；返回key全部壳固定不可修改""" pg = int(pg) # 【可修改】搜索url模板，quote(key)关键词编码不可删除 # 走联想搜索接口（站点搜索框下拉提示入口，无验证码），mid=1 为视频模型，limit=50 单次返回上限 url = f'{self.host}/index.php/ajax/suggest?mid=1&wd={quote(key)}&limit=50' try: # 搜索请求头，照抓包补全浏览器指纹，UA与sec-ch-ua版本对齐，会话cookie由壳自动携带 search_headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/140.0.0.0 Safari/537.36', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7', 'Accept-Language': 'zh-CN,zh;q=0.9,en-US;q=0.8,en;q=0.7', 'Upgrade-Insecure-Requests': '1', 'sec-ch-ua': '"Not A;Brand";v="99", "Chromium";v="140", "Google Chrome";v="140"', 'sec-ch-ua-mobile': '?1', 'sec-ch-ua-platform': '"Android"', 'X-Requested-With': 'com.mmbox.xbrowser', 'Sec-Fetch-Site': 'same-origin', 'Sec-Fetch-Mode': 'navigate', 'Sec-Fetch-User': '?1', 'Sec-Fetch-Dest': 'document', 'Referer': f'{self.host}/', } video_list = [] try: import json as _json sug_headers = dict(search_headers) sug_headers['X-Requested-With'] = 'XMLHttpRequest' sug_headers['Accept'] = 'application/json, text/javascript, */*; q=0.01' r = self.fetch(url, headers=sug_headers, timeout=15, verify=False) data = _json.loads(r.text) for it in (data or {}).get('list') or []: vid = it.get('id') name = (it.get('name') or '').strip() if not (vid and name): continue video_list.append({ "vod_id": str(vid), "vod_name": name, "vod_pic": it.get('pic') or '', "vod_remarks": '', }) except Exception: video_list = [] return { "list": video_list, "page": pg, "pagecount": 1, "limit": 50, "total": len(video_list), } except Exception: return {"list": [], "page": pg, "pagecount": 1, "limit": 50, "total": 0} # ===================== 接口7：playerContent 播放解析接口 ===================== def playerContent(self, flag, id, vipFlags): result = {"parse": 0, "url": "", "header": {}} try: # 1.请求播放页，用壳fetch带cookie，提取播放源url play_page_resp = self.fetch(id, headers=self.headers, timeout=15, verify=False) play_page_html = play_page_resp.text player_aaaa_match = re.search(r'player_aaaa\s*=\s*\{.*?"url"\s*:\s*"([^"]+)"', play_page_html, re.S) if not player_aaaa_match: raise Exception("播放页未匹配到player_aaaa.url") raw_qq_url = player_aaaa_match.group(1) qq_real_url = raw_qq_url.replace(r'\/', '/') # 下面三个接口统一用的请求头 parse_api_headers = { "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36", "Origin": "https://4k01.pianku.online", # 与内容站域名保持一致 "Accept": "*/*", } # 2.中转接口，拿apiToken，裸请求不带cookie mid_url = f"{self.auth_host}/?url={quote(qq_real_url)}" mid_resp = self.fetch(mid_url, headers=parse_api_headers, cookies={}, timeout=15, verify=False) mid_html = mid_resp.text token_match = re.search(r'apiToken\s*:\s*"([^"]+)"', mid_html) if not token_match: raise Exception("中转页面未提取apiToken") api_token = token_match.group(1) # 3.鉴权接口，传内容站域名，裸请求不带cookie auth_param_host = '4k01.pianku.online' auth_url = f"{self.auth_host}/api/auth.php?host={auth_param_host}" self.fetch(auth_url, headers=parse_api_headers, cookies={}, timeout=15, verify=False) # 4.解析接口，用token换直链，裸请求不带cookie resolve_url = f"{self.auth_host}/api/resolve.php?token={quote(api_token)}" resolve_resp = self.fetch(resolve_url, headers=parse_api_headers, cookies={}, timeout=15, verify=False) resolve_data = json.loads(resolve_resp.text) if resolve_data.get("code") != 200: raise Exception("解析接口返回失败") play_url = resolve_data.get("url") if not play_url: raise Exception("未获取有效播放地址") result = { "parse": 0, # 0=直链播放，1=嗅探播放 "url": play_url, "header": parse_api_headers } except Exception as e: # 异常统一捕获，返回空result pass return result # 壳必备占位函数，禁止删除修改 def localProxy(self, param): return [200, {}, ""] def destroy(self): pass