From 71ed5778feb1e732f6e839defadbb459e8e234af Mon Sep 17 00:00:00 2001 From: Harold <8866033@gmail.com> Date: Mon, 20 Apr 2026 14:42:30 +0800 Subject: [PATCH] =?UTF-8?q?Revert=20"=E7=8E=A9=E5=81=B6=E8=81=9A=E5=90=88"?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit 8d1ad1f82d769d19ff808435789d37a146ea3d4f. --- py/tests/test_玩偶聚合.py | 357 ++++++++++++++++++++++++++ py/玩偶聚合.py | 516 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 873 insertions(+) create mode 100644 py/tests/test_玩偶聚合.py create mode 100644 py/玩偶聚合.py diff --git a/py/tests/test_玩偶聚合.py b/py/tests/test_玩偶聚合.py new file mode 100644 index 0000000..51b6536 --- /dev/null +++ b/py/tests/test_玩偶聚合.py @@ -0,0 +1,357 @@ +import base64 +import json +import unittest +from importlib.machinery import SourceFileLoader +from pathlib import Path +from types import SimpleNamespace +from unittest.mock import patch + + +ROOT = Path(__file__).resolve().parents[1] +MODULE = SourceFileLoader("wanou_aggregate_spider", str(ROOT / "玩偶聚合.py")).load_module() +Spider = MODULE.Spider + + +class TestWanouAggregateSpider(unittest.TestCase): + def setUp(self): + Spider._instance = None + self.spider = Spider() + self.spider.init() + + def test_home_content_exposes_site_classes_and_category_filter(self): + content = self.spider.homeContent(False) + self.assertEqual( + [item["type_id"] for item in content["class"][:3]], + ["site_wanou", "site_muou", "site_labi"], + ) + self.assertEqual(content["class"][0]["type_name"], "玩偶") + self.assertEqual(content["filters"]["site_wanou"][0]["key"], "categoryId") + self.assertEqual(content["filters"]["site_wanou"][0]["value"][1], {"n": "电影", "v": "1"}) + + @patch.object( + Spider, + "_load_local_filter_groups", + return_value=[ + { + "key": "year", + "name": "年份", + "init": "", + "value": [{"n": "全部", "v": ""}, {"n": "2025", "v": "2025"}], + } + ], + ) + def test_home_content_appends_local_filter_groups_after_category_filter(self, mock_load_local_filter_groups): + content = self.spider.homeContent(False) + self.assertEqual( + [item["key"] for item in content["filters"]["site_wanou"][:2]], + ["categoryId", "year"], + ) + + def test_encode_and_decode_site_vod_id_round_trip(self): + vod_id = self.spider._encode_site_vod_id("wanou", "/voddetail/12345.html") + self.assertEqual(vod_id, "site:wanou:/voddetail/12345.html") + self.assertEqual( + self.spider._decode_site_vod_id(vod_id), + {"site": "wanou", "path": "/voddetail/12345.html"}, + ) + + def test_encode_and_decode_aggregate_vod_id_round_trip(self): + payload = [ + {"site": "wanou", "path": "/voddetail/1.html", "name": "繁花", "year": "2024"}, + {"site": "muou", "path": "/voddetail/2.html", "name": "繁花", "year": "2024"}, + ] + vod_id = self.spider._encode_aggregate_vod_id(payload) + self.assertTrue(vod_id.startswith("agg:")) + decoded = self.spider._decode_aggregate_vod_id(vod_id) + self.assertEqual(decoded, payload) + + def test_normalize_title_removes_spaces_punctuation_and_resolution_tags(self): + self.assertEqual( + self.spider._normalize_title(" 繁花 4K.HDR-玩偶 "), + "繁花", + ) + + def test_is_same_title_rejects_year_conflict(self): + left = {"vod_name": "繁花", "vod_year": "2024"} + right = {"vod_name": "繁花", "vod_year": "2023"} + self.assertFalse(self.spider._is_same_title(left, right)) + + def test_build_category_url_uses_selected_category_and_filters(self): + site = { + "id": "wanou", + "domains": ["https://www.wogg.net"], + "category_url": "/vodshow/{categoryId}--------{page}---.html", + "category_url_with_filters": "/vodshow/{categoryId}-{area}-{by}-{class}-----{page}---{year}.html", + } + url = self.spider._build_category_url( + site, + "1", + "2", + {"categoryId": "1", "area": "香港", "by": "score", "class": "动作", "year": "2025"}, + ) + self.assertEqual( + url, + "https://www.wogg.net/vodshow/1-%E9%A6%99%E6%B8%AF-score-%E5%8A%A8%E4%BD%9C-----2---2025.html", + ) + + @patch.object(Spider, "fetch") + def test_request_with_failover_tries_next_domain_when_first_fails(self, mock_fetch): + def fake_fetch(url, headers=None, timeout=10): + if url.startswith("https://bad.example"): + raise RuntimeError("boom") + return SimpleNamespace(status_code=200, text="ok") + + mock_fetch.side_effect = fake_fetch + site = {"domains": ["https://bad.example", "https://good.example"]} + html = self.spider._request_with_failover(site, "/vodshow/1--------1---.html") + self.assertIn("ok", html) + self.assertEqual(site["domains"][0], "https://good.example") + + def test_parse_cards_extracts_short_site_vod_id_title_cover_and_remarks(self): + site = {"id": "wanou", "domains": ["https://www.wogg.net"], "list_xpath": "//*[contains(@class,'module-item')]"} + html = """ +
+
+ + 示例影片 +
+
HD
+
+ """ + cards = self.spider._parse_cards(site, html) + self.assertEqual( + cards, + [ + { + "vod_id": "site:wanou:/voddetail/123.html", + "vod_name": "示例影片", + "vod_pic": "https://www.wogg.net/poster.jpg", + "vod_remarks": "HD", + "vod_year": "", + "_site": "wanou", + "_detail_path": "/voddetail/123.html", + } + ], + ) + + @patch.object(Spider, "_request_with_failover") + def test_category_content_uses_default_category_when_extend_missing(self, mock_request_with_failover): + mock_request_with_failover.return_value = """ +
+
+ + 分类影片 +
+
更新至10集
+
+ """ + result = self.spider.categoryContent("site_wanou", "2", False, {}) + self.assertEqual(result["page"], 2) + self.assertEqual(result["list"][0]["vod_name"], "分类影片") + + def test_aggregate_search_results_merges_same_title_and_keeps_highest_priority_source(self): + raw_results = [ + { + "vod_id": "site:muou:/voddetail/2.html", + "vod_name": "繁花", + "vod_pic": "https://img.example/m.jpg", + "vod_remarks": "木偶版", + "vod_year": "2024", + "_site": "muou", + "_detail_path": "/voddetail/2.html", + }, + { + "vod_id": "site:wanou:/voddetail/1.html", + "vod_name": "繁花", + "vod_pic": "https://img.example/w.jpg", + "vod_remarks": "玩偶版", + "vod_year": "2024", + "_site": "wanou", + "_detail_path": "/voddetail/1.html", + }, + ] + aggregated = self.spider._aggregate_search_results(raw_results) + self.assertEqual(len(aggregated), 1) + self.assertEqual(aggregated[0]["vod_name"], "繁花") + self.assertEqual(aggregated[0]["vod_pic"], "https://img.example/w.jpg") + self.assertEqual(aggregated[0]["vod_remarks"], "玩偶版") + self.assertTrue(aggregated[0]["vod_id"].startswith("agg:")) + + def test_aggregate_search_results_keeps_year_conflict_as_two_items(self): + raw_results = [ + { + "vod_id": "site:wanou:/voddetail/1.html", + "vod_name": "倚天屠龙记", + "vod_year": "2019", + "_site": "wanou", + "_detail_path": "/voddetail/1.html", + }, + { + "vod_id": "site:muou:/voddetail/2.html", + "vod_name": "倚天屠龙记", + "vod_year": "2022", + "_site": "muou", + "_detail_path": "/voddetail/2.html", + }, + ] + aggregated = self.spider._aggregate_search_results(raw_results) + self.assertEqual(len(aggregated), 2) + + @patch.object(Spider, "_fetch_site_search") + def test_search_content_queries_sites_and_returns_aggregated_items(self, mock_fetch_site_search): + mock_fetch_site_search.side_effect = [ + [ + { + "vod_id": "site:wanou:/voddetail/1.html", + "vod_name": "繁花", + "vod_pic": "https://img.example/w.jpg", + "vod_remarks": "玩偶版", + "vod_year": "2024", + "_site": "wanou", + "_detail_path": "/voddetail/1.html", + } + ], + [ + { + "vod_id": "site:muou:/voddetail/2.html", + "vod_name": "繁花", + "vod_pic": "https://img.example/m.jpg", + "vod_remarks": "木偶版", + "vod_year": "2024", + "_site": "muou", + "_detail_path": "/voddetail/2.html", + } + ], + [], + ] + result = self.spider.searchContent("繁花", False, "1") + self.assertEqual(len(result["list"]), 1) + self.assertEqual(result["list"][0]["vod_name"], "繁花") + self.assertNotIn("pagecount", result) + + def test_parse_detail_page_extracts_meta_and_netdisk_links(self): + site = { + "id": "wanou", + "name": "玩偶", + "domains": ["https://www.wogg.net"], + "detail_pan_xpath": "//*[contains(@class,'module-row-info')]//p", + } + html = """ +
示例剧
+
+
导演
导演甲
+
主演
演员甲演员乙
+
剧情

一段剧情简介

+
+

https://pan.quark.cn/s/q1

+

https://pan.baidu.com/s/b1

+
+ """ + detail = self.spider._parse_detail_page(site, "/voddetail/123.html", html) + self.assertEqual(detail["vod_name"], "示例剧") + self.assertEqual(detail["vod_pic"], "https://www.wogg.net/poster.jpg") + self.assertEqual(detail["vod_director"], "导演甲") + self.assertEqual(detail["vod_actor"], "演员甲,演员乙") + self.assertEqual(detail["pan_urls"], ["https://pan.quark.cn/s/q1", "https://pan.baidu.com/s/b1"]) + + @patch.object(Spider, "_fetch_site_detail") + def test_detail_content_for_aggregate_id_merges_lines_from_multiple_sites(self, mock_fetch_site_detail): + mock_fetch_site_detail.side_effect = [ + { + "vod_name": "繁花", + "vod_pic": "https://img.example/w.jpg", + "vod_year": "2024", + "vod_director": "导演甲", + "vod_actor": "演员甲", + "vod_content": "玩偶简介", + "pan_urls": ["https://pan.baidu.com/s/b1", "https://pan.quark.cn/s/q1"], + "_site_name": "玩偶", + }, + { + "vod_name": "繁花", + "vod_pic": "https://img.example/m.jpg", + "vod_year": "2024", + "vod_director": "导演乙", + "vod_actor": "演员乙", + "vod_content": "木偶简介", + "pan_urls": ["https://pan.quark.cn/s/q2", "https://pan.baidu.com/s/b1"], + "_site_name": "木偶", + }, + ] + payload = [ + {"site": "wanou", "path": "/voddetail/1.html", "name": "繁花", "year": "2024"}, + {"site": "muou", "path": "/voddetail/2.html", "name": "繁花", "year": "2024"}, + ] + result = self.spider.detailContent([self.spider._encode_aggregate_vod_id(payload)]) + vod = result["list"][0] + self.assertEqual(vod["vod_name"], "繁花") + self.assertEqual(vod["vod_pic"], "https://img.example/w.jpg") + self.assertEqual(vod["vod_play_from"], "baidu#玩偶$$$quark#玩偶$$$quark#木偶") + self.assertEqual( + vod["vod_play_url"], + "百度资源$https://pan.baidu.com/s/b1$$$夸克资源$https://pan.quark.cn/s/q1$$$夸克资源$https://pan.quark.cn/s/q2", + ) + + def test_player_content_passthroughs_known_pan_domains(self): + self.assertEqual( + self.spider.playerContent("quark#玩偶", "https://pan.quark.cn/s/demo", {}), + {"parse": 0, "playUrl": "", "url": "https://pan.quark.cn/s/demo"}, + ) + self.assertEqual( + self.spider.playerContent("baidu#玩偶", "https://pan.baidu.com/s/demo", {}), + {"parse": 0, "playUrl": "", "url": "https://pan.baidu.com/s/demo"}, + ) + + def test_player_content_rejects_non_pan_url(self): + self.assertEqual( + self.spider.playerContent("zxzj", "/vodplay/1-1-1.html", {}), + {"parse": 0, "playUrl": "", "url": ""}, + ) + + @patch.object(Spider, "_request_with_failover") + def test_fetch_site_search_builds_search_url_and_parses_results(self, mock_request_with_failover): + mock_request_with_failover.return_value = """ +
+
+
搜索影片
+
抢先版
+
+ """ + site = { + "id": "wanou", + "domains": ["https://www.wogg.net"], + "list_xpath": "//*[contains(@class,'module-item')]", + "search_xpath": "//*[contains(@class,'module-search-item')]", + "search_url": "/vodsearch/-------------.html?wd={keyword}&page={page}", + } + results = self.spider._fetch_site_search(site, "繁花", 1) + self.assertEqual(results[0]["vod_id"], "site:wanou:/voddetail/789.html") + self.assertEqual(results[0]["vod_name"], "搜索影片") + + @patch.object(Spider, "_fetch_site_search") + def test_search_content_skips_site_errors(self, mock_fetch_site_search): + mock_fetch_site_search.side_effect = [ + RuntimeError("boom"), + [ + { + "vod_id": "site:muou:/voddetail/2.html", + "vod_name": "繁花", + "vod_pic": "", + "vod_remarks": "", + "vod_year": "2024", + "_site": "muou", + "_detail_path": "/voddetail/2.html", + } + ], + [], + ] + result = self.spider.searchContent("繁花", False, "1") + self.assertEqual(result["total"], 1) + self.assertEqual(result["list"][0]["vod_name"], "繁花") + + def test_home_content_does_not_expose_content_first_categories(self): + content = self.spider.homeContent(False) + self.assertNotIn("movie", [item["type_id"] for item in content["class"]]) + + def test_search_content_returns_empty_list_for_blank_keyword(self): + self.assertEqual(self.spider.searchContent("", False, "1"), {"page": 1, "total": 0, "list": []}) diff --git a/py/玩偶聚合.py b/py/玩偶聚合.py new file mode 100644 index 0000000..a4732f5 --- /dev/null +++ b/py/玩偶聚合.py @@ -0,0 +1,516 @@ +# coding=utf-8 +import base64 +import json +import os +import re +import sys +from urllib.parse import quote + +from base.spider import Spider as BaseSpider + +sys.path.append("..") + + +class Spider(BaseSpider): + def __init__(self): + self.name = "玩偶聚合" + self.filter_root = os.path.join(os.path.dirname(__file__), "../筛选") + self.headers = { + "User-Agent": ( + "Mozilla/5.0 (Windows NT 10.0; Win64; x64) " + "AppleWebKit/537.36 (KHTML, like Gecko) " + "Chrome/136.0.0.0 Safari/537.36" + ) + } + self.site_priority = [ + "wanou", + "muou", + "labi", + "zhizhen", + "erxiao", + "huban", + "kuaiying", + "shandian", + "ouge", + ] + self.pan_priority = { + "baidu": 1, + "a139": 2, + "a189": 3, + "a123": 4, + "a115": 5, + "quark": 6, + "xunlei": 7, + "aliyun": 8, + "uc": 9, + } + self.sites = [ + { + "id": "wanou", + "name": "玩偶", + "domains": ["https://wogg.xxooo.cf"], + "filter_files": ["wogg.json"], + "list_xpath": "//*[contains(@class,'module-item')]", + "search_xpath": "//*[contains(@class,'module-search-item')]", + "detail_pan_xpath": "//*[contains(@class,'module-row-info')]//p", + "category_url": "/vodshow/{categoryId}--------{page}---.html", + "category_url_with_filters": "/vodshow/{categoryId}-{area}-{by}-{class}-----{page}---{year}.html", + "search_url": "/vodsearch/-------------.html?wd={keyword}&page={page}", + "default_categories": [("1", "电影"), ("2", "电视剧"), ("3", "动漫"), ("4", "综艺")], + }, + { + "id": "muou", + "name": "木偶", + "domains": ["https://www.muou.site", "http://123.666291.xyz"], + "filter_files": ["mogg.json"], + "list_xpath": "//*[contains(@class,'module-item')]", + "search_xpath": "//*[contains(@class,'module-search-item')]", + "detail_pan_xpath": "//*[contains(@class,'module-row-info')]//p", + "category_url": "/vodshow/{categoryId}--------{page}---.html", + "search_url": "/vodsearch/-------------.html?wd={keyword}&page={page}", + "default_categories": [("1", "电影"), ("2", "电视剧"), ("3", "动漫"), ("29", "综艺")], + }, + { + "id": "labi", + "name": "蜡笔", + "domains": ["http://xiaocge.fun"], + "filter_files": ["labi.json"], + "list_xpath": "//*[contains(@class,'module-item')]", + "search_xpath": "//*[contains(@class,'module-search-item')]", + "detail_pan_xpath": "//*[contains(@class,'module-row-info')]//p", + "category_url": "/vodshow/{categoryId}--------{page}---.html", + "search_url": "/vodsearch/-------------.html?wd={keyword}&page={page}", + "default_categories": [("1", "电影"), ("2", "电视剧"), ("3", "动漫"), ("4", "综艺")], + }, + ] + + def init(self, extend=""): + return None + + def getName(self): + return self.name + + def homeVideoContent(self): + return {"list": []} + + def _load_local_filter_groups(self, site): + return [] + + def _build_site_filters(self, site): + groups = [ + { + "key": "categoryId", + "name": "分类", + "init": site["default_categories"][0][0], + "value": [{"n": "全部", "v": ""}] + + [{"n": name, "v": cid} for cid, name in site["default_categories"]], + } + ] + groups.extend(self._load_local_filter_groups(site)) + return groups + + def homeContent(self, filter): + classes = [{"type_id": f"site_{site['id']}", "type_name": site["name"]} for site in self.sites] + filters = {f"site_{site['id']}": self._build_site_filters(site) for site in self.sites} + return {"class": classes, "filters": filters} + + def _encode_site_vod_id(self, site_id, path): + return f"site:{site_id}:{path}" + + def _decode_site_vod_id(self, value): + prefix, site_id, path = str(value).split(":", 2) + if prefix != "site": + raise ValueError("not site vod id") + return {"site": site_id, "path": path} + + def _encode_aggregate_vod_id(self, payload): + raw = json.dumps(payload, ensure_ascii=False, separators=(",", ":")).encode("utf-8") + return "agg:" + base64.urlsafe_b64encode(raw).decode("utf-8").rstrip("=") + + def _decode_aggregate_vod_id(self, value): + encoded = str(value)[4:] + padded = encoded + "=" * (-len(encoded) % 4) + return json.loads(base64.urlsafe_b64decode(padded.encode("utf-8")).decode("utf-8")) + + def _normalize_title(self, value): + text = str(value or "").lower() + text = re.sub(r"(4k|hdr|2160p|1080p|720p|玩偶|木偶|蜡笔)", "", text, flags=re.I) + text = re.sub(r"[\s\-_.·,，。!！?:：()（）\[\]]+", "", text) + return text + + def _is_same_title(self, left, right): + left_year = str(left.get("vod_year") or "").strip() + right_year = str(right.get("vod_year") or "").strip() + if left_year and right_year and left_year != right_year: + return False + return self._normalize_title(left.get("vod_name")) == self._normalize_title(right.get("vod_name")) + + def _get_site(self, site_id): + for site in self.sites: + if site["id"] == site_id: + return site + return None + + def _build_absolute_url(self, base, path): + raw = str(path or "").strip() + if not raw: + return "" + if raw.startswith(("http://", "https://")): + return raw + if raw.startswith("//"): + return "https:" + raw + return str(base).rstrip("/") + "/" + raw.lstrip("/") + + def _build_category_url(self, site, category_id, pg, extend): + values = dict(extend or {}) + values.setdefault("categoryId", category_id) + values.setdefault("area", "") + values.setdefault("by", values.get("sort", "")) + values.setdefault("class", "") + values.setdefault("year", "") + if site.get("category_url_with_filters") and any(values.get(key) for key in ("area", "by", "class", "year")): + path = site["category_url_with_filters"].format( + **{ + "categoryId": values["categoryId"], + "area": quote(str(values["area"])), + "by": quote(str(values["by"])), + "class": quote(str(values["class"])), + "page": int(pg), + "year": quote(str(values["year"])), + } + ) + else: + path = site["category_url"].format(categoryId=values["categoryId"], page=int(pg)) + return self._build_absolute_url(site["domains"][0], path) + + def _request_with_failover(self, site, path_or_url, referer=None): + last_error = None + for index, domain in enumerate(list(site["domains"])): + target = path_or_url if str(path_or_url).startswith("http") else self._build_absolute_url(domain, path_or_url) + try: + headers = dict(self.headers) + headers["Referer"] = referer or self._build_absolute_url(domain, "/") + response = self.fetch(target, headers=headers, timeout=10) + if response.status_code == 200 and response.text: + if index > 0: + site["domains"].insert(0, site["domains"].pop(index)) + return response.text + except Exception as exc: + last_error = exc + raise RuntimeError(str(last_error or "all domains failed")) + + def _parse_cards(self, site, html): + root = self.html(html) + if root is None: + return [] + + items = [] + seen = set() + for card in root.xpath(site["list_xpath"]): + href = ((card.xpath(".//a[@href][1]/@href") or [""])[0]).strip() + title = ( + ((card.xpath(".//img[@alt][1]/@alt") or [""])[0]).strip() + or ((card.xpath(".//a[@title][1]/@title") or [""])[0]).strip() + ) + pic = ( + ((card.xpath(".//img[@data-src][1]/@data-src") or [""])[0]).strip() + or ((card.xpath(".//img[@src][1]/@src") or [""])[0]).strip() + ) + remarks = "".join(card.xpath(".//*[contains(@class,'module-item-text')][1]//text()")).strip() + if not href or not title or href in seen: + continue + seen.add(href) + items.append( + { + "vod_id": self._encode_site_vod_id(site["id"], href), + "vod_name": title, + "vod_pic": self._build_absolute_url(site["domains"][0], pic), + "vod_remarks": remarks, + "vod_year": "", + "_site": site["id"], + "_detail_path": href, + } + ) + return items + + def categoryContent(self, tid, pg, filter, extend): + site_id = str(tid).replace("site_", "", 1) + site = self._get_site(site_id) + values = extend if isinstance(extend, dict) else {} + category_id = values.get("categoryId") or site["default_categories"][0][0] + html = self._request_with_failover(site, self._build_category_url(site, category_id, pg, values)) + items = self._parse_cards(site, html) + return {"list": items, "page": int(pg), "limit": len(items), "total": int(pg) * 20 + len(items)} + + def _site_rank(self, site_id): + try: + return self.site_priority.index(site_id) + except ValueError: + return 999 + + def _parse_search_cards(self, site, html): + root = self.html(html) + if root is None: + return [] + + items = [] + seen = set() + xpath = site.get("search_xpath") or site["list_xpath"] + for card in root.xpath(xpath): + href = ( + ((card.xpath(".//*[contains(@class,'video-serial')][1]/@href") or [""])[0]).strip() + or ((card.xpath(".//*[@href][1]/@href") or [""])[0]).strip() + ) + title = ( + ((card.xpath(".//*[contains(@class,'video-serial')][1]/@title") or [""])[0]).strip() + or ((card.xpath(".//img[@alt][1]/@alt") or [""])[0]).strip() + or ((card.xpath(".//*[@title][1]/@title") or [""])[0]).strip() + ) + pic = ( + ((card.xpath(".//img[@data-src][1]/@data-src") or [""])[0]).strip() + or ((card.xpath(".//img[@src][1]/@src") or [""])[0]).strip() + ) + remarks = "".join(card.xpath(".//*[contains(@class,'module-item-text')][1]//text()")).strip() + if not href or not title or href in seen: + continue + seen.add(href) + items.append( + { + "vod_id": self._encode_site_vod_id(site["id"], href), + "vod_name": title, + "vod_pic": self._build_absolute_url(site["domains"][0], pic), + "vod_remarks": remarks, + "vod_year": "", + "_site": site["id"], + "_detail_path": href, + } + ) + return items + + def _fetch_site_search(self, site, keyword, pg): + search_path = site["search_url"].format(keyword=quote(str(keyword)), page=int(pg)) + html = self._request_with_failover(site, search_path) + return self._parse_search_cards(site, html) + + def _aggregate_search_results(self, items): + groups = [] + for item in items: + matched_group = None + for group in groups: + if self._is_same_title(group[0], item): + matched_group = group + break + if matched_group is None: + groups.append([item]) + else: + matched_group.append(item) + + result = [] + for group in groups: + group.sort(key=lambda item: self._site_rank(item["_site"])) + primary = group[0] + payload = [ + { + "site": item["_site"], + "path": item["_detail_path"], + "name": item.get("vod_name", ""), + "year": item.get("vod_year", ""), + } + for item in group + ] + result.append( + { + "vod_id": self._encode_aggregate_vod_id(payload), + "vod_name": primary["vod_name"], + "vod_pic": primary.get("vod_pic", ""), + "vod_remarks": primary.get("vod_remarks", ""), + "vod_year": primary.get("vod_year", ""), + } + ) + return result + + def searchContent(self, key, quick, pg="1"): + page = int(pg) + keyword = str(key or "").strip() + if not keyword: + return {"page": page, "total": 0, "list": []} + + all_items = [] + for site in self.sites: + try: + all_items.extend(self._fetch_site_search(site, keyword, page)) + except Exception: + continue + + merged = self._aggregate_search_results(all_items) + return {"page": page, "total": len(merged), "list": merged} + + def _detect_pan_type(self, url): + value = str(url or "").lower() + if "pan.baidu.com" in value: + return "baidu", "百度资源" + if "pan.quark.cn" in value: + return "quark", "夸克资源" + if "drive.uc.cn" in value: + return "uc", "UC资源" + if "alipan.com" in value or "aliyundrive.com" in value: + return "aliyun", "阿里资源" + if "pan.xunlei.com" in value: + return "xunlei", "迅雷资源" + if "123pan.com" in value: + return "a123", "123资源" + if "115.com" in value: + return "a115", "115资源" + if "189.cn" in value: + return "a189", "天翼资源" + if "139.com" in value: + return "a139", "移动云资源" + return "", "" + + def _join_next_sibling_links(self, root, label): + values = [] + labels = root.xpath(f"//*[contains(@class,'video-info-itemtitle') and contains(normalize-space(.), '{label}')]") + for node in labels: + sibling = node.getnext() + if sibling is None: + continue + for text in sibling.xpath(".//a/text()"): + clean = str(text).strip() + if clean: + values.append(clean) + unique = [] + for value in values: + if value not in unique: + unique.append(value) + return ",".join(unique) + + def _join_next_sibling_text(self, root, label): + labels = root.xpath(f"//*[contains(@class,'video-info-itemtitle') and contains(normalize-space(.), '{label}')]") + for node in labels: + sibling = node.getnext() + if sibling is None: + continue + text = "".join(sibling.xpath(".//text()")).strip() + if text: + return text + return "" + + def _parse_detail_page(self, site, detail_path, html): + root = self.html(html) + if root is None: + return { + "vod_name": "", + "vod_pic": "", + "vod_year": "", + "vod_director": "", + "vod_actor": "", + "vod_content": "", + "pan_urls": [], + "_site_name": site["name"], + } + + title = "".join(root.xpath("//*[contains(@class,'page-title')][1]//text()")).strip() + pic = ((root.xpath("//*[contains(@class,'mobile-play')]//img[1]/@data-src") or [""])[0]).strip() + pan_urls = [] + for node in root.xpath(site["detail_pan_xpath"]): + text = "".join(node.xpath(".//text()")).strip() + if text.startswith("http"): + pan_urls.append(text) + + return { + "vod_name": title, + "vod_pic": self._build_absolute_url(site["domains"][0], pic), + "vod_year": "", + "vod_director": self._join_next_sibling_links(root, "导演"), + "vod_actor": self._join_next_sibling_links(root, "主演"), + "vod_content": self._join_next_sibling_text(root, "剧情"), + "pan_urls": pan_urls, + "_site_name": site["name"], + } + + def _fetch_site_detail(self, site, detail_path): + html = self._request_with_failover(site, detail_path) + return self._parse_detail_page(site, detail_path, html) + + def _build_pan_lines(self, detail): + lines = [] + seen = set() + for url in detail.get("pan_urls", []): + pan_type, title = self._detect_pan_type(url) + if not pan_type or url in seen: + continue + seen.add(url) + lines.append( + ( + self.pan_priority.get(pan_type, 999), + f"{pan_type}#{detail['_site_name']}", + f"{title}${url}", + ) + ) + lines.sort(key=lambda item: item[0]) + return lines + + def detailContent(self, ids): + vod_id = ids[0] + if str(vod_id).startswith("agg:"): + payload = self._decode_aggregate_vod_id(vod_id) + details = [] + for item in payload: + site = self._get_site(item["site"]) + try: + details.append(self._fetch_site_detail(site, item["path"])) + except Exception: + continue + + primary = details[0] + all_lines = [] + seen_urls = set() + for detail in details: + for _, line_from, line_url in self._build_pan_lines(detail): + share_url = line_url.split("$", 1)[1] + if share_url in seen_urls: + continue + seen_urls.add(share_url) + all_lines.append((line_from, line_url)) + + return { + "list": [ + { + "vod_id": vod_id, + "vod_name": primary["vod_name"], + "vod_pic": primary["vod_pic"], + "vod_year": primary["vod_year"], + "vod_director": primary["vod_director"], + "vod_actor": primary["vod_actor"], + "vod_content": primary["vod_content"], + "vod_play_from": "$$$".join([item[0] for item in all_lines]), + "vod_play_url": "$$$".join([item[1] for item in all_lines]), + } + ] + } + + info = self._decode_site_vod_id(vod_id) + site = self._get_site(info["site"]) + detail = self._fetch_site_detail(site, info["path"]) + lines = self._build_pan_lines(detail) + return { + "list": [ + { + "vod_id": vod_id, + "vod_name": detail["vod_name"], + "vod_pic": detail["vod_pic"], + "vod_year": detail["vod_year"], + "vod_director": detail["vod_director"], + "vod_actor": detail["vod_actor"], + "vod_content": detail["vod_content"], + "vod_play_from": "$$$".join([item[1] for item in lines]), + "vod_play_url": "$$$".join([item[2] for item in lines]), + } + ] + } + + def playerContent(self, flag, id, vipFlags): + pan_type, _ = self._detect_pan_type(id) + if pan_type: + return {"parse": 0, "playUrl": "", "url": id} + return {"parse": 0, "playUrl": "", "url": ""}