feat: scaffold wanougege spider

py/tests/test_玩偶哥哥.py

@@ -0,0 +1,50 @@
+import unittest
+from importlib.machinery import SourceFileLoader
+from pathlib import Path
+
+
+ROOT = Path(__file__).resolve().parents[1]
+MODULE = SourceFileLoader("wanougege_spider", str(ROOT / "玩偶哥哥.py")).load_module()
+Spider = MODULE.Spider
+
+
+class TestWanOuGeGeSpider(unittest.TestCase):
+    def setUp(self):
+        Spider._instance = None
+        self.spider = Spider()
+        self.spider.init()
+
+    def test_home_content_exposes_all_eight_categories(self):
+        content = self.spider.homeContent(False)
+        self.assertEqual(
+            [(item["type_id"], item["type_name"]) for item in content["class"]],
+            [
+                ("1", "玩偶电影"),
+                ("2", "玩偶剧集"),
+                ("3", "玩偶动漫"),
+                ("4", "玩偶综艺"),
+                ("44", "臻彩视界"),
+                ("6", "玩偶短剧"),
+                ("5", "玩偶音乐"),
+                ("46", "玩偶纪录"),
+            ],
+        )
+
+    def test_home_video_content_returns_empty_list(self):
+        self.assertEqual(self.spider.homeVideoContent(), {"list": []})
+
+    def test_build_and_fix_urls(self):
+        self.assertEqual(self.spider._build_url("/voddetail/1.html"), "http://wogg.xxooo.cf/voddetail/1.html")
+        self.assertEqual(
+            self.spider._fix_img_url("/db.php?url=https://img.example/poster.jpg"),
+            "http://wogg.xxooo.cf/db.php?url=https://img.example/poster.jpg",
+        )
+        self.assertEqual(
+            self.spider._fix_img_url("https://gimg1.baidu.com/gimg/?src=data:image/png;base64,AAAA"),
+            "",
+        )
+
+    def test_detect_pan_type_returns_type_and_title(self):
+        self.assertEqual(self.spider._detect_pan_type("https://pan.baidu.com/s/demo"), ("baidu", "百度资源"))
+        self.assertEqual(self.spider._detect_pan_type("https://pan.quark.cn/s/demo"), ("quark", "夸克资源"))
+        self.assertEqual(self.spider._detect_pan_type("https://example.com/video"), ("", ""))

py/玩偶哥哥.py

@@ -0,0 +1,75 @@
+# coding=utf-8
+import re
+import sys
+from urllib.parse import urljoin
+
+from base.spider import Spider as BaseSpider
+
+sys.path.append("..")
+
+
+class Spider(BaseSpider):
+    def __init__(self):
+        self.name = "玩偶哥哥"
+        self.host = "http://wogg.xxooo.cf"
+        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"
+            ),
+            "Referer": self.host + "/",
+        }
+        self.categories = [
+            {"type_id": "1", "type_name": "玩偶电影"},
+            {"type_id": "2", "type_name": "玩偶剧集"},
+            {"type_id": "3", "type_name": "玩偶动漫"},
+            {"type_id": "4", "type_name": "玩偶综艺"},
+            {"type_id": "44", "type_name": "臻彩视界"},
+            {"type_id": "6", "type_name": "玩偶短剧"},
+            {"type_id": "5", "type_name": "玩偶音乐"},
+            {"type_id": "46", "type_name": "玩偶纪录"},
+        ]
+        self.pan_patterns = [
+            ("baidu", "百度资源", r"pan\.baidu\.com|yun\.baidu\.com"),
+            ("a139", "139资源", r"yun\.139\.com"),
+            ("a189", "天翼资源", r"cloud\.189\.cn"),
+            ("a123", "123资源", r"123684\.com|123865\.com|123912\.com|123pan\.com"),
+            ("a115", "115资源", r"115\.com"),
+            ("quark", "夸克资源", r"pan\.quark\.cn"),
+            ("xunlei", "迅雷资源", r"pan\.xunlei\.com"),
+            ("aliyun", "阿里资源", r"aliyundrive\.com|alipan\.com"),
+            ("uc", "UC资源", r"drive\.uc\.cn"),
+        ]
+
+    def init(self, extend=""):
+        return None
+
+    def getName(self):
+        return self.name
+
+    def homeContent(self, filter):
+        return {"class": self.categories}
+
+    def homeVideoContent(self):
+        return {"list": []}
+
+    def _build_url(self, path):
+        return urljoin(self.host + "/", str(path or "").strip())
+
+    def _fix_img_url(self, img_url):
+        raw = str(img_url or "").strip()
+        if not raw:
+            return ""
+        if raw.startswith("/db.php?url="):
+            return self._build_url(raw)
+        if re.search(r"^https?://[^/]*gimg\d*\.baidu\.com/gimg/", raw, re.I) and "src=data:image/" in raw:
+            return ""
+        return raw
+
+    def _detect_pan_type(self, url):
+        raw = str(url or "").strip()
+        for pan_type, title, pattern in self.pan_patterns:
+            if re.search(pattern, raw, re.I):
+                return pan_type, title
+        return "", ""