feat: scaffold rrdy spider

py/tests/test_人人电影.py

@@ -0,0 +1,49 @@
+import unittest
+from importlib.machinery import SourceFileLoader
+from pathlib import Path
+
+
+ROOT = Path(__file__).resolve().parents[1]
+MODULE = SourceFileLoader("rrdy_spider", str(ROOT / "人人电影.py")).load_module()
+Spider = MODULE.Spider
+
+
+class TestRenRenDianYingSpider(unittest.TestCase):
+    def setUp(self):
+        Spider._instance = None
+        self.spider = Spider()
+        self.spider.init()
+
+    def test_home_content_exposes_reference_categories(self):
+        content = self.spider.homeContent(False)
+        self.assertEqual(
+            [(item["type_id"], item["type_name"]) for item in content["class"]],
+            [
+                ("movie/list_2", "电影"),
+                ("dianshiju/list_6", "电视剧"),
+                ("dongman/list_13", "动漫"),
+                ("zongyi/list_10", "老电影"),
+            ],
+        )
+
+    def test_home_video_content_returns_empty_list(self):
+        self.assertEqual(self.spider.homeVideoContent(), {"list": []})
+
+    def test_build_url_and_pan_detection_helpers(self):
+        self.assertEqual(self.spider._build_url("/movie/1.html"), "https://www.rrdynb.com/movie/1.html")
+        self.assertEqual(
+            self.spider._build_url("https://pan.baidu.com/s/demo"),
+            "https://pan.baidu.com/s/demo",
+        )
+        self.assertTrue(self.spider._is_supported_pan_url("https://pan.baidu.com/s/demo"))
+        self.assertTrue(self.spider._is_supported_pan_url("https://pan.quark.cn/s/demo"))
+        self.assertFalse(self.spider._is_supported_pan_url("https://pan.xunlei.com/s/demo"))
+
+    def test_clean_search_title_and_normalize_title(self):
+        self.assertEqual(
+            self.spider._clean_search_title("<font color='red'>剑来</font> 第二季"),
+            "剑来 第二季",
+        )
+        self.assertEqual(self.spider._normalize_title("《繁花》"), "繁花")
+        self.assertEqual(self.spider._normalize_title("「诛仙」特别篇"), "诛仙")
+        self.assertEqual(self.spider._normalize_title("普通标题"), "普通标题")

py/人人电影.py

@@ -0,0 +1,80 @@
+# 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 = "人人电影"
+        self.host = "https://www.rrdynb.com"
+        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": "movie/list_2", "type_name": "电影"},
+            {"type_id": "dianshiju/list_6", "type_name": "电视剧"},
+            {"type_id": "dongman/list_13", "type_name": "动漫"},
+            {"type_id": "zongyi/list_10", "type_name": "老电影"},
+        ]
+        self.supported_pan_patterns = [
+            r"pan\.baidu\.com|yun\.baidu\.com",
+            r"pan\.quark\.cn",
+            r"drive\.uc\.cn",
+            r"115\.com",
+            r"123pan\.com|123684\.com|123865\.com|123912\.com",
+            r"cloud\.189\.cn",
+            r"yun\.139\.com",
+        ]
+        self.excluded_pan_patterns = [
+            r"pan\.xunlei\.com",
+            r"aliyundrive\.com",
+            r"alipan\.com",
+        ]
+
+    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):
+        raw = str(path or "").strip()
+        if not raw:
+            return ""
+        if raw.startswith(("http://", "https://")):
+            return raw
+        return urljoin(self.host + "/", raw)
+
+    def _clean_search_title(self, text):
+        return str(text or "").replace("<font color='red'>", "").replace("</font>", "").strip()
+
+    def _normalize_title(self, raw_title):
+        cleaned = self._clean_search_title(raw_title)
+        matched = re.search(r"《(.*?)》|「(.*?)」", cleaned)
+        if matched:
+            return (matched.group(1) or matched.group(2) or "").strip()
+        return cleaned.strip()
+
+    def _is_supported_pan_url(self, url):
+        raw = str(url or "").strip()
+        if not raw:
+            return False
+        if any(re.search(pattern, raw, re.I) for pattern in self.excluded_pan_patterns):
+            return False
+        return any(re.search(pattern, raw, re.I) for pattern in self.supported_pan_patterns)