feat: scaffold letu spider

py/tests/test_乐兔.py

@@ -0,0 +1,35 @@
+import unittest
+from importlib.machinery import SourceFileLoader
+from pathlib import Path
+
+
+ROOT = Path(__file__).resolve().parents[1]
+MODULE = SourceFileLoader("letu_spider", str(ROOT / "乐兔.py")).load_module()
+Spider = MODULE.Spider
+
+
+class TestLeTuSpider(unittest.TestCase):
+    def setUp(self):
+        Spider._instance = None
+        self.spider = Spider()
+        self.spider.init()
+
+    def test_home_content_exposes_expected_categories(self):
+        content = self.spider.homeContent(False)
+        self.assertEqual(
+            [item["type_id"] for item in content["class"]],
+            ["1", "2", "3", "4", "5"],
+        )
+
+    def test_home_video_content_returns_empty_list(self):
+        self.assertEqual(self.spider.homeVideoContent(), {"list": []})
+
+    def test_encode_and_decode_detail_and_play_ids(self):
+        self.assertEqual(self.spider._encode_vod_id("/detail/demo.html"), "detail/demo")
+        self.assertEqual(self.spider._decode_vod_id("detail/demo"), "https://www.letu.me/detail/demo.html")
+        self.assertEqual(self.spider._encode_play_id("/play/123-1-1.html"), "play/123-1-1")
+        self.assertEqual(self.spider._decode_play_id("play/123-1-1"), "https://www.letu.me/play/123-1-1.html")
+
+
+if __name__ == "__main__":
+    unittest.main()

py/乐兔.py

@@ -0,0 +1,60 @@
+# 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 = "乐兔"
+        self.host = "https://www.letu.me"
+        self.headers = {
+            "User-Agent": (
+                "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+                "AppleWebKit/537.36 (KHTML, like Gecko) "
+                "Chrome/144.0.0.0 Safari/537.36"
+            ),
+            "Referer": self.host + "/",
+        }
+        self.categories = [
+            {"type_id": "1", "type_name": "电影"},
+            {"type_id": "2", "type_name": "电视剧"},
+            {"type_id": "3", "type_name": "综艺"},
+            {"type_id": "4", "type_name": "动漫"},
+            {"type_id": "5", "type_name": "短剧"},
+        ]
+
+    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 _encode_vod_id(self, href):
+        matched = re.search(r"/detail/([^/?#]+)\.html", self._build_url(href))
+        return f"detail/{matched.group(1)}" if matched else ""
+
+    def _decode_vod_id(self, vod_id):
+        matched = re.search(r"^detail/([^/?#]+)$", str(vod_id or "").strip())
+        return self._build_url(f"/detail/{matched.group(1)}.html") if matched else ""
+
+    def _encode_play_id(self, href):
+        matched = re.search(r"/play/([^/?#]+)\.html", self._build_url(href))
+        return f"play/{matched.group(1)}" if matched else ""
+
+    def _decode_play_id(self, play_id):
+        matched = re.search(r"^play/([^/?#]+)$", str(play_id or "").strip())
+        return self._build_url(f"/play/{matched.group(1)}.html") if matched else ""