feat: add FKTV list and search parsing

py/tests/test_凡客TV.py

@@ -1,6 +1,7 @@
 import unittest
 from importlib.machinery import SourceFileLoader
 from pathlib import Path
+from unittest.mock import patch
 
 
 ROOT = Path(__file__).resolve().parents[1]
@@ -49,6 +50,58 @@ class TestFKTVSpider(unittest.TestCase):
         self.assertEqual(payload["episode_name"], "第1集")
         self.assertEqual(payload["page"], "https://fktv.me/movie/detail/9001")
 
+    @patch.object(Spider, "_request_html")
+    def test_category_content_builds_url_and_parses_cards(self, mock_request_html):
+        mock_request_html.return_value = """
+        <div class="card-wrap">
+          <div class="meta-wrap">
+            <a class="normal-title" href="/movie/detail/abc123" title="示例电影">示例电影</a>
+            <img class="lazy-load" data-src="/poster.jpg" />
+            <span class="tag">电影</span>
+            <span class="tag">更新中</span>
+          </div>
+        </div>
+        """
+        result = self.spider.categoryContent("1", "2", False, {})
+        self.assertEqual(
+            mock_request_html.call_args.args[0],
+            "https://fktv.me/channel?page=2&cat_id=1&page_size=32&order=new",
+        )
+        self.assertEqual(
+            result["list"],
+            [
+                {
+                    "vod_id": "abc123",
+                    "vod_name": "示例电影",
+                    "vod_pic": "https://fktv.me/poster.jpg",
+                    "vod_remarks": "电影 | 更新中",
+                    "type_name": "电影",
+                }
+            ],
+        )
+        self.assertNotIn("pagecount", result)
+
+    @patch.object(Spider, "_request_html")
+    def test_search_content_builds_url_and_handles_blank_keyword(self, mock_request_html):
+        blank = self.spider.searchContent("", False, "1")
+        self.assertEqual(blank, {"page": 1, "limit": 0, "total": 0, "list": []})
+        mock_request_html.assert_not_called()
+
+        mock_request_html.return_value = """
+        <div class="hover-wrap">
+          <a class="hover-title" href="/movie/detail/xyz789" title="搜索影片">搜索影片</a>
+          <img class="lazy-load" data-src="https://img.example/search.jpg" />
+          <span class="tag">剧集</span>
+        </div>
+        """
+        result = self.spider.searchContent("繁花", False, "3")
+        self.assertEqual(
+            mock_request_html.call_args.args[0],
+            "https://fktv.me/search?keyword=%E7%B9%81%E8%8A%B1",
+        )
+        self.assertEqual(result["page"], 3)
+        self.assertEqual(result["list"][0]["vod_id"], "xyz789")
+
 
 if __name__ == "__main__":
     unittest.main()

py/凡客TV.py

@@ -1,6 +1,8 @@
 # coding=utf-8
 import json
+import re
 import sys
+from urllib.parse import quote, urljoin
 
 from base.spider import Spider as BaseSpider
 
@@ -37,6 +39,103 @@ class Spider(BaseSpider):
     def homeContent(self, filter):
         return {"class": self.classes}
 
+    def homeVideoContent(self):
+        return {"list": []}
+
+    def _clean_text(self, value):
+        return re.sub(r"\s+", " ", str(value or "").replace("\xa0", " ")).strip()
+
+    def _abs_url(self, value):
+        raw = str(value or "").strip()
+        if not raw:
+            return ""
+        if raw.startswith(("http://", "https://")):
+            return raw
+        if raw.startswith("//"):
+            return "https:" + raw
+        return urljoin(self.host + "/", raw)
+
+    def _page_headers(self, referer=""):
+        headers = {"User-Agent": self.user_agent, "Referer": referer or self.host + "/"}
+        if self.cookie:
+            headers["Cookie"] = self.cookie
+        return headers
+
+    def _request_html(self, url, headers=None):
+        response = self.fetch(url, headers=headers or self._page_headers(), timeout=10, verify=False)
+        if response.status_code != 200:
+            return ""
+        return str(response.text or "")
+
+    def _extract_cards(self, html):
+        root = self.html(html or "")
+        if root is None:
+            return []
+        items = []
+        seen = set()
+        nodes = root.xpath("//*[contains(@class,'meta-wrap')]/.. | //*[contains(@class,'hover-wrap')]")
+        for node in nodes:
+            href = self._clean_text(
+                "".join(
+                    node.xpath(
+                        ".//a[contains(@class,'normal-title') or contains(@class,'hover-title')][1]/@href"
+                    )
+                )
+            )
+            matched = re.search(r"/movie/detail/([0-9A-Za-z]+)", href)
+            if not matched:
+                continue
+            vod_id = matched.group(1)
+            if vod_id in seen:
+                continue
+            seen.add(vod_id)
+            title = self._clean_text(
+                "".join(
+                    node.xpath(
+                        ".//a[contains(@class,'normal-title') or contains(@class,'hover-title')][1]/@title"
+                    )
+                )
+            ) or self._clean_text(
+                "".join(
+                    node.xpath(
+                        ".//a[contains(@class,'normal-title') or contains(@class,'hover-title')][1]//text()"
+                    )
+                )
+            )
+            pic = self._clean_text("".join(node.xpath(".//*[contains(@class,'lazy-load')][1]/@data-src")))
+            tags = [
+                self._clean_text("".join(tag.xpath(".//text()")))
+                for tag in node.xpath(".//*[contains(@class,'tag')]")
+            ]
+            tags = [tag for tag in tags if tag]
+            if not title:
+                continue
+            items.append(
+                {
+                    "vod_id": vod_id,
+                    "vod_name": title,
+                    "vod_pic": self._abs_url(pic),
+                    "vod_remarks": " | ".join(tags),
+                    "type_name": tags[0] if tags else "",
+                }
+            )
+        return items
+
+    def categoryContent(self, tid, pg, filter, extend):
+        page = max(1, int(pg))
+        url = self.host + f"/channel?page={page}&cat_id={tid}&page_size=32&order=new"
+        items = self._extract_cards(self._request_html(url))
+        return {"page": page, "limit": len(items), "total": len(items), "list": items}
+
+    def searchContent(self, key, quick, pg="1"):
+        page = max(1, int(pg))
+        keyword = self._clean_text(key)
+        if not keyword:
+            return {"page": page, "limit": 0, "total": 0, "list": []}
+        url = self.host + "/search?keyword=" + quote(keyword)
+        items = self._extract_cards(self._request_html(url))
+        return {"page": page, "limit": len(items), "total": len(items), "list": items}
+
     def _encode_play_id(self, payload):
         return json.dumps(payload, ensure_ascii=False, separators=(",", ":"))