feat: add feikuai category and search parsing

py/tests/test_飞快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]
@@ -28,3 +29,50 @@ class TestFeikuaiSpider(unittest.TestCase):
 
     def test_home_video_content_returns_empty_list(self):
         self.assertEqual(self.spider.homeVideoContent(), {"list": []})
+
+    @patch.object(Spider, "_request_html")
+    def test_category_content_parses_short_vod_id(self, mock_request_html):
+        mock_request_html.return_value = """
+        <a class="module-poster-item" href="/voddetail/12345.html" title="分类影片">
+          <img class="lazy" data-original="/cover.jpg" />
+          <div class="module-item-note">更新至10集</div>
+        </a>
+        """
+        result = self.spider.categoryContent("2", "3", False, {})
+        self.assertEqual(
+            mock_request_html.call_args.args[0],
+            "https://feikuai.tv/vodshow/2--------3---.html",
+        )
+        self.assertEqual(
+            result["list"],
+            [
+                {
+                    "vod_id": "/voddetail/12345.html",
+                    "vod_name": "分类影片",
+                    "vod_pic": "https://feikuai.tv/cover.jpg",
+                    "vod_remarks": "更新至10集",
+                }
+            ],
+        )
+        self.assertNotIn("pagecount", result)
+
+    @patch.object(Spider, "_request_html")
+    def test_search_content_parses_cards_and_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="module-card-item module-item">
+          <a class="module-card-item-poster" href="/voddetail/67890.html"></a>
+          <div class="module-item-pic"><img data-original="/search.jpg" /></div>
+          <div class="module-card-item-title"><strong>搜索命中</strong></div>
+          <div class="module-item-note">HD</div>
+        </div>
+        """
+        result = self.spider.searchContent("繁花", False, "2")
+        self.assertEqual(
+            mock_request_html.call_args.args[0],
+            "https://feikuai.tv/label/search_ajax.html?wd=%E7%B9%81%E8%8A%B1&by=time&order=desc&page=2",
+        )
+        self.assertEqual(result["list"][0]["vod_id"], "/voddetail/67890.html")

py/飞快TV.py

@@ -1,5 +1,7 @@
 # coding=utf-8
+import re
 import sys
+from urllib.parse import quote, urljoin
 
 from base.spider import Spider as BaseSpider
 
@@ -38,3 +40,96 @@ class Spider(BaseSpider):
 
     def homeVideoContent(self):
         return {"list": []}
+
+    def _build_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 _clean_text(self, text):
+        return re.sub(r"\s+", " ", str(text or "").replace("\xa0", " ")).strip()
+
+    def _request_html(self, path_or_url):
+        target = path_or_url if str(path_or_url).startswith("http") else self._build_url(path_or_url)
+        response = self.fetch(target, headers=self.headers, timeout=10)
+        if response.status_code != 200:
+            return ""
+        return str(response.text or "")
+
+    def _parse_category_cards(self, html):
+        root = self.html(html or "")
+        if root is None:
+            return []
+        items = []
+        for node in root.xpath("//a[contains(@class,'module-poster-item')]"):
+            vod_id = self._clean_text("".join(node.xpath("./@href")))
+            vod_name = self._clean_text("".join(node.xpath("./@title"))) or self._clean_text(
+                "".join(node.xpath(".//*[contains(@class,'module-poster-item-title')][1]//text()"))
+            )
+            vod_pic = self._clean_text(
+                "".join(node.xpath(".//img[contains(@class,'lazy')][1]/@data-original"))
+            )
+            vod_remarks = self._clean_text(
+                "".join(node.xpath(".//*[contains(@class,'module-item-note')][1]//text()"))
+            )
+            if vod_id and vod_name:
+                items.append(
+                    {
+                        "vod_id": vod_id,
+                        "vod_name": vod_name,
+                        "vod_pic": self._build_url(vod_pic),
+                        "vod_remarks": vod_remarks,
+                    }
+                )
+        return items
+
+    def _parse_search_cards(self, html):
+        root = self.html(html or "")
+        if root is None:
+            return []
+        items = []
+        for node in root.xpath(
+            "//*[contains(@class,'module-card-item') and contains(@class,'module-item')]"
+        ):
+            vod_id = self._clean_text(
+                "".join(node.xpath(".//a[contains(@class,'module-card-item-poster')][1]/@href"))
+            )
+            vod_name = self._clean_text(
+                "".join(node.xpath(".//*[contains(@class,'module-card-item-title')][1]//strong/text()"))
+            )
+            vod_pic = self._clean_text(
+                "".join(node.xpath(".//*[contains(@class,'module-item-pic')]//img[1]/@data-original"))
+            )
+            vod_remarks = self._clean_text(
+                "".join(node.xpath(".//*[contains(@class,'module-item-note')][1]//text()"))
+            )
+            if vod_id and vod_name:
+                items.append(
+                    {
+                        "vod_id": vod_id,
+                        "vod_name": vod_name,
+                        "vod_pic": self._build_url(vod_pic),
+                        "vod_remarks": vod_remarks,
+                    }
+                )
+        return items
+
+    def categoryContent(self, tid, pg, filter, extend):
+        page = max(1, int(pg))
+        url = self.host + f"/vodshow/{tid}--------{page}---.html"
+        items = self._parse_category_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 + "/label/search_ajax.html?wd=" + quote(keyword) + f"&by=time&order=desc&page={page}"
+        items = self._parse_search_cards(self._request_html(url))
+        return {"page": page, "limit": len(items), "total": len(items), "list": items}