feat: add ddys list and search flows

py/tests/test_低端影视.py

@@ -1,6 +1,8 @@
 import unittest
 from importlib.machinery import SourceFileLoader
 from pathlib import Path
+from urllib.parse import quote
+from unittest.mock import patch
 
 
 ROOT = Path(__file__).resolve().parents[1]
@@ -36,6 +38,108 @@ class TestDDYSSpider(unittest.TestCase):
         url = self.spider._build_category_url("series", "1", {})
         self.assertEqual(url, "https://ddys.io/series/page/1")
 
+    def test_parse_movie_cards_extracts_expected_fields(self):
+        html = """
+        <div class="movie-card">
+          <a href="/movie/test-title/">
+            <img src="/poster.jpg" />
+            <span class="poster-badge">HD</span>
+            <h3>测试电影</h3>
+          </a>
+        </div>
+        """
+        cards = self.spider._parse_movie_cards(html)
+        self.assertEqual(
+            cards,
+            [
+                {
+                    "vod_id": "https://ddys.io/movie/test-title/",
+                    "vod_name": "测试电影",
+                    "vod_pic": "https://ddys.io/poster.jpg",
+                    "vod_remarks": "HD",
+                }
+            ],
+        )
+
+    @patch.object(Spider, "_request_html")
+    def test_category_content_uses_built_url_and_returns_page_result(self, mock_request_html):
+        mock_request_html.return_value = """
+        <div class="movie-card">
+          <a href="/series/demo/">
+            <img src="/series.jpg" />
+            <span class="poster-badge">更新至3集</span>
+            <h3>示例剧</h3>
+          </a>
+        </div>
+        """
+        result = self.spider.categoryContent("series", "2", False, {"area": "/region/japan"})
+        self.assertEqual(mock_request_html.call_args.args[0], "https://ddys.io/series/region/japan/page/2")
+        self.assertEqual(result["page"], 2)
+        self.assertEqual(result["pagecount"], 3)
+        self.assertEqual(result["limit"], 24)
+        self.assertEqual(result["list"][0]["vod_name"], "示例剧")
+
+    def test_request_html_posts_form_data_for_search(self):
+        calls = {}
+
+        class FakeResponse:
+            def __init__(self):
+                self.status_code = 200
+                self.text = (
+                    '<div class="movie-card"><a href="/movie/hit/">'
+                    '<img src="/search.jpg" /><h3>命中结果</h3></a></div>'
+                )
+                self.encoding = "utf-8"
+
+        def fake_post(
+            url,
+            params=None,
+            data=None,
+            json=None,
+            cookies=None,
+            headers=None,
+            timeout=5,
+            verify=True,
+            stream=False,
+            allow_redirects=True,
+        ):
+            calls["url"] = url
+            calls["data"] = data
+            calls["headers"] = headers
+            return FakeResponse()
+
+        self.spider.post = fake_post
+        html = self.spider._request_html(
+            self.spider.host + "/search",
+            method="POST",
+            data=f"q={quote('繁花')}",
+            headers={"Content-Type": "application/x-www-form-urlencoded"},
+        )
+        self.assertIn("命中结果", html)
+        self.assertEqual(calls["url"], "https://ddys.io/search")
+        self.assertEqual(calls["data"], "q=%E7%B9%81%E8%8A%B1")
+        self.assertEqual(calls["headers"]["Content-Type"], "application/x-www-form-urlencoded")
+
+    @patch.object(Spider, "_request_html")
+    def test_search_content_posts_keyword_and_parses_cards(self, mock_request_html):
+        mock_request_html.return_value = """
+        <div class="mb-12">
+          <div class="movie-card">
+            <a href="/anime/result/">
+              <img src="/anime.jpg" alt="搜索动漫" />
+              <span class="poster-badge">全集</span>
+              <h3>搜索动漫</h3>
+            </a>
+          </div>
+        </div>
+        """
+        result = self.spider.searchContent("繁花", False, "1")
+        kwargs = mock_request_html.call_args.kwargs
+        self.assertEqual(kwargs["method"], "POST")
+        self.assertEqual(kwargs["data"], "q=%E7%B9%81%E8%8A%B1")
+        self.assertEqual(result["list"][0]["vod_id"], "https://ddys.io/anime/result/")
+        self.assertEqual(result["pagecount"], 2)
+
 
 if __name__ == "__main__":
     unittest.main()

py/低端影视.py

@@ -1,6 +1,8 @@
 # coding=utf-8
 import json
+import re
 import sys
+from urllib.parse import quote
 
 from base.spider import Spider as BaseSpider
 
@@ -99,3 +101,78 @@ class Spider(BaseSpider):
             f"/page/{int(pg)}"
         )
         return self._build_url(path)
+
+    def _request_html(self, path_or_url, method="GET", data=None, headers=None, referer=None):
+        target = path_or_url if str(path_or_url).startswith("http") else self._build_url(path_or_url)
+        merged_headers = dict(self.headers)
+        if headers:
+            merged_headers.update(headers)
+        merged_headers["Referer"] = referer or self.headers["Referer"]
+        if method == "POST":
+            response = self.post(target, data=data, headers=merged_headers, timeout=10)
+        else:
+            response = self.fetch(target, headers=merged_headers, timeout=10)
+        if response.status_code != 200:
+            return ""
+        return response.text or ""
+
+    def _clean_text(self, text):
+        return re.sub(r"\s+", " ", str(text or "").replace("\xa0", " ")).strip()
+
+    def _parse_movie_cards(self, html, root_xpath="//*[contains(@class,'movie-card')]"):
+        root = self.html(html)
+        if root is None:
+            return []
+        items = []
+        seen = set()
+        for node in root.xpath(root_xpath):
+            href = ((node.xpath(".//a[@href][1]/@href") or [""])[0]).strip()
+            title = self._clean_text("".join(node.xpath(".//h3[1]//text()")))
+            pic = (
+                ((node.xpath(".//img[1]/@src") or [""])[0]).strip()
+                or ((node.xpath(".//img[1]/@data-src") or [""])[0]).strip()
+            )
+            remarks = self._clean_text("".join(node.xpath(".//*[contains(@class,'poster-badge')][1]//text()")))
+            vod_id = self._build_url(href)
+            if not vod_id or not title or vod_id in seen:
+                continue
+            seen.add(vod_id)
+            items.append(
+                {
+                    "vod_id": vod_id,
+                    "vod_name": title,
+                    "vod_pic": self._build_url(pic),
+                    "vod_remarks": remarks,
+                }
+            )
+        return items
+
+    def categoryContent(self, tid, pg, filter, extend):
+        page = int(pg)
+        items = self._parse_movie_cards(self._request_html(self._build_category_url(tid, pg, extend)))
+        return {
+            "list": items,
+            "page": page,
+            "pagecount": page + 1 if items else page,
+            "limit": 24,
+            "total": page * 24 + len(items),
+        }
+
+    def searchContent(self, key, quick, pg="1"):
+        page = int(pg)
+        keyword = self._stringify(key).strip()
+        if not keyword:
+            return {"page": page, "pagecount": 0, "total": 0, "list": []}
+        html = self._request_html(
+            self.host + "/search",
+            method="POST",
+            data=f"q={quote(keyword)}",
+            headers={"Content-Type": "application/x-www-form-urlencoded"},
+        )
+        items = self._parse_movie_cards(
+            html,
+            root_xpath="(//*[contains(@class,'mb-12')])[1]//*[contains(@class,'movie-card')]",
+        )
+        if not items:
+            items = self._parse_movie_cards(html)
+        return {"page": page, "pagecount": page + 1 if items else page, "total": len(items), "list": items}