Merge branch 'dyrs-spider'

py/tests/test_电影人生.py

@@ -0,0 +1,163 @@
+import unittest
+from importlib.machinery import SourceFileLoader
+from pathlib import Path
+from unittest.mock import patch
+
+
+ROOT = Path(__file__).resolve().parents[1]
+MODULE = SourceFileLoader("dyrs_spider", str(ROOT / "电影人生.py")).load_module()
+Spider = MODULE.Spider
+
+SAMPLE_LIST_HTML = """
+<a data-url="/dyrscom-foo.html" href="/dyrscom-foo.html" title="片名A">
+  <img data-src="/cover/a.jpg" />
+  <div class="text-[10px]">更新至10集</div>
+</a>
+<div class="items-center flex mt-1"><span>2025</span><span>剧情</span></div>
+<a data-url="/dyrscom-bar.html" href="/dyrscom-bar.html" title="片名B">
+  <img src="https://img.example/b.jpg" />
+</a>
+"""
+
+DETAIL_HTML = """
+<meta property="og:image" content="/poster.jpg" />
+<meta name="description" content="简介描述" />
+<h1>电影人生示例</h1>
+<div><span>年份</span><span>2025</span></div>
+<div><span>地区</span><span>大陆</span></div>
+<div><span>语言</span><span>国语</span></div>
+<h3>导演</h3><div><a><span>张三</span></a></div>
+<h3>主演</h3><div><a><span>李四</span></a><a><span>王五</span></a></div>
+<h3>标签</h3><div><a><span>#剧情</span></a><a><span>#悬疑</span></a></div>
+<h3>剧情简介</h3><div><div class="text-sm">这是一段剧情。</div></div>
+<div id="originTabs">
+  <a href="/dyrscom-foo.html?origin=line1"><button data-origin="线路一">线路一</button></a>
+  <a href="/dyrscom-foo.html?origin=line2"><button data-origin="线路二">线路二</button></a>
+</div>
+"""
+
+LINE1_HTML = """
+<div class="seqlist">
+  <a href="/dyrscom-foo.html?origin=line1&play=1" data-title="第1集" data-origin="线路一">第1集</a>
+  <a href="/dyrscom-foo.html?origin=line1&play=2" data-title="第2集" data-origin="线路一">第2集</a>
+</div>
+"""
+
+LINE2_HTML = """
+<div class="seqlist">
+  <a href="/dyrscom-foo.html?origin=line2&play=1" data-title="正片" data-origin="线路二">正片</a>
+</div>
+"""
+
+SEARCH_HTML = """
+<a data-url="/dyrscom-c.html" href="/dyrscom-c.html" title="繁花2023"></a>
+<a data-url="/dyrscom-a.html" href="/dyrscom-a.html" title="繁花"></a>
+<a data-url="/dyrscom-b.html" href="/dyrscom-b.html" title="阿凡达"></a>
+"""
+
+
+class TestDYRSSpider(unittest.TestCase):
+    def setUp(self):
+        Spider._instance = None
+        self.spider = Spider()
+        self.spider.init()
+
+    def test_home_content_exposes_classes_and_filters(self):
+        content = self.spider.homeContent(False)
+        self.assertEqual(
+            [item["type_id"] for item in content["class"]],
+            ["dianying", "dianshiju", "dongman", "zongyi"],
+        )
+        self.assertEqual(
+            [item["key"] for item in content["filters"]["dianying"]],
+            ["class", "sort_field"],
+        )
+
+    def test_parse_cards_extracts_short_id_title_pic_and_remarks(self):
+        cards = self.spider._parse_vod_cards(SAMPLE_LIST_HTML)
+        self.assertEqual(cards[0]["vod_id"], "dyrscom-foo.html")
+        self.assertEqual(cards[0]["vod_name"], "片名A")
+        self.assertEqual(cards[0]["vod_pic"], "https://dyrsok.com/cover/a.jpg")
+        self.assertEqual(cards[0]["vod_year"], "2025")
+        self.assertEqual(cards[0]["type_name"], "剧情")
+        self.assertEqual(cards[0]["vod_remarks"], "更新至10集")
+
+    @patch.object(Spider, "_request_html")
+    def test_category_content_builds_query_string(self, mock_html):
+        mock_html.return_value = SAMPLE_LIST_HTML
+        result = self.spider.categoryContent(
+            "dianying",
+            "2",
+            False,
+            {"class": "动作", "sort_field": "update_time"},
+        )
+        self.assertEqual(result["page"], 2)
+        self.assertEqual(result["list"][0]["vod_id"], "dyrscom-foo.html")
+        mock_html.assert_called_with(
+            "https://dyrsok.com/dianying.html?class=%E5%8A%A8%E4%BD%9C&sort_field=update_time&page=2"
+        )
+
+    @patch.object(Spider, "_request_html")
+    def test_home_video_content_reads_home_page(self, mock_html):
+        mock_html.return_value = SAMPLE_LIST_HTML
+        result = self.spider.homeVideoContent()
+        self.assertEqual(len(result["list"]), 2)
+        mock_html.assert_called_with("https://dyrsok.com/")
+
+    @patch.object(Spider, "_request_html")
+    def test_detail_content_extracts_meta_and_lines(self, mock_html):
+        mock_html.side_effect = [DETAIL_HTML, LINE1_HTML, LINE2_HTML]
+        result = self.spider.detailContent(["dyrscom-foo.html"])
+        vod = result["list"][0]
+        self.assertEqual(vod["vod_id"], "dyrscom-foo.html")
+        self.assertEqual(vod["vod_name"], "电影人生示例")
+        self.assertEqual(vod["vod_pic"], "https://dyrsok.com/poster.jpg")
+        self.assertEqual(vod["vod_year"], "2025")
+        self.assertEqual(vod["vod_area"], "大陆")
+        self.assertEqual(vod["vod_lang"], "国语")
+        self.assertEqual(vod["vod_director"], "张三")
+        self.assertEqual(vod["vod_actor"], "李四,王五")
+        self.assertEqual(vod["type_name"], "剧情 / 悬疑")
+        self.assertEqual(vod["vod_play_from"], "线路一$$$线路二")
+        self.assertIn("第1集$", vod["vod_play_url"])
+        self.assertIn("正片$", vod["vod_play_url"])
+
+    @patch.object(Spider, "_request_html")
+    def test_search_content_refines_exact_match_first(self, mock_html):
+        mock_html.return_value = SEARCH_HTML
+        result = self.spider.searchContent("繁花", False, "1")
+        self.assertEqual([item["vod_name"] for item in result["list"][:2]], ["繁花", "繁花2023"])
+        mock_html.assert_called_with("https://dyrsok.com/s.html?name=%E7%B9%81%E8%8A%B1")
+
+    @patch.object(Spider, "_request_html")
+    @patch.object(Spider, "_request_response")
+    def test_player_content_resolves_api_m3u8_and_raw_playlist(self, mock_response, mock_html):
+        mock_html.side_effect = [
+            '<script>fetch("/api/m3u8?origin=line1&url=abc123")</script>',
+            "#EXTM3U\n/api/m3u8?id=xyz&raw=1\n",
+        ]
+
+        class FakeResponse:
+            status_code = 302
+            headers = {"Location": "https://media.example/master.m3u8"}
+            text = ""
+
+        mock_response.return_value = FakeResponse()
+        play_id = (
+            '{"title":"第1集","origin":"线路一","page":"https://dyrsok.com/dyrscom-foo.html?play=1",'
+            '"vodName":"电影人生示例","pic":"https://dyrsok.com/poster.jpg"}'
+        )
+        result = self.spider.playerContent("线路一", play_id, {})
+        self.assertEqual(result["parse"], 0)
+        self.assertEqual(result["url"], "https://media.example/api/m3u8?id=xyz&raw=1")
+
+    @patch.object(Spider, "_request_html")
+    def test_player_content_falls_back_to_parse_when_no_api_link(self, mock_html):
+        mock_html.return_value = "<html><body>empty</body></html>"
+        result = self.spider.playerContent("线路一", '{"page":"https://dyrsok.com/dyrscom-foo.html?play=1"}', {})
+        self.assertEqual(result["parse"], 1)
+        self.assertEqual(result["url"], "https://dyrsok.com/dyrscom-foo.html?play=1")
+
+
+if __name__ == "__main__":
+    unittest.main()

py/电影人生.py

@@ -0,0 +1,383 @@
+# coding=utf-8
+import json
+import re
+import sys
+from urllib.parse import quote, urlencode, urljoin
+
+from base.spider import Spider as BaseSpider
+
+sys.path.append("..")
+
+
+class Spider(BaseSpider):
+    def __init__(self):
+        self.name = "电影人生"
+        self.host = "https://dyrsok.com"
+        self.headers = {
+            "User-Agent": (
+                "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+                "AppleWebKit/537.36 (KHTML, like Gecko) "
+                "Chrome/146.0.0.0 Safari/537.36"
+            ),
+            "Referer": self.host + "/",
+        }
+        self.classes = [
+            {"type_id": "dianying", "type_name": "电影"},
+            {"type_id": "dianshiju", "type_name": "电视剧"},
+            {"type_id": "dongman", "type_name": "动漫"},
+            {"type_id": "zongyi", "type_name": "综艺"},
+        ]
+        common_movie_tv = [
+            {
+                "key": "class",
+                "name": "类型",
+                "init": "",
+                "value": [
+                    {"n": "全部", "v": ""},
+                    {"n": "剧情", "v": "剧情"},
+                    {"n": "喜剧", "v": "喜剧"},
+                    {"n": "动作", "v": "动作"},
+                ],
+            },
+            {
+                "key": "sort_field",
+                "name": "排序",
+                "init": "",
+                "value": [
+                    {"n": "默认", "v": ""},
+                    {"n": "热度", "v": "play_hot"},
+                    {"n": "更新时间", "v": "update_time"},
+                ],
+            },
+        ]
+        common_dm = [
+            {
+                "key": "class",
+                "name": "类型",
+                "init": "",
+                "value": [
+                    {"n": "全部", "v": ""},
+                    {"n": "冒险", "v": "冒险"},
+                    {"n": "热血", "v": "热血"},
+                    {"n": "搞笑", "v": "搞笑"},
+                ],
+            },
+            {
+                "key": "sort_field",
+                "name": "排序",
+                "init": "",
+                "value": [
+                    {"n": "默认", "v": ""},
+                    {"n": "热度", "v": "play_hot"},
+                    {"n": "更新时间", "v": "update_time"},
+                ],
+            },
+        ]
+        common_zy = [
+            {
+                "key": "class",
+                "name": "类型",
+                "init": "",
+                "value": [
+                    {"n": "全部", "v": ""},
+                    {"n": "真人秀", "v": "真人秀"},
+                    {"n": "脱口秀", "v": "脱口秀"},
+                    {"n": "音乐", "v": "音乐"},
+                ],
+            },
+            {
+                "key": "sort_field",
+                "name": "排序",
+                "init": "",
+                "value": [
+                    {"n": "默认", "v": ""},
+                    {"n": "热度", "v": "play_hot"},
+                    {"n": "更新时间", "v": "update_time"},
+                ],
+            },
+        ]
+        self.filters = {
+            "dianying": common_movie_tv,
+            "dianshiju": common_movie_tv,
+            "dongman": common_dm,
+            "zongyi": common_zy,
+        }
+
+    def init(self, extend=""):
+        return None
+
+    def getName(self):
+        return self.name
+
+    def homeContent(self, filter):
+        return {"class": self.classes, "filters": self.filters}
+
+    def homeVideoContent(self):
+        return {"list": self._parse_vod_cards(self._request_html(self.host + "/"))[:24]}
+
+    def _abs_url(self, value):
+        raw = str(value or "").strip()
+        if not raw:
+            return ""
+        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, url, headers=None):
+        request_headers = dict(self.headers)
+        if headers:
+            request_headers.update(headers)
+        response = self.fetch(url, headers=request_headers, timeout=10, verify=False)
+        return response.text if response.status_code == 200 else ""
+
+    def _request_response(self, url, headers=None, allow_redirects=False):
+        request_headers = dict(self.headers)
+        if headers:
+            request_headers.update(headers)
+        return self.fetch(
+            url,
+            headers=request_headers,
+            timeout=10,
+            verify=False,
+            allow_redirects=allow_redirects,
+        )
+
+    def _parse_vod_cards(self, html):
+        root = self.html(html)
+        if root is None:
+            return []
+        cards = []
+        seen = set()
+        for node in root.xpath("//a[@data-url and @title]"):
+            href = ((node.xpath("./@href") or [""])[0]).strip()
+            title = ((node.xpath("./@title") or [""])[0]).strip()
+            if not href or not title or "/dyrscom-" not in href:
+                continue
+            vod_id = href.lstrip("/")
+            if vod_id in seen:
+                continue
+            seen.add(vod_id)
+            parent = node.getparent()
+            year = ""
+            type_name = ""
+            if parent is not None:
+                year = self._clean_text(
+                    "".join(parent.xpath(".//*[contains(@class,'items-center')][1]/span[1]//text()"))
+                )
+                type_name = self._clean_text(
+                    "".join(parent.xpath(".//*[contains(@class,'items-center')][1]/span[last()]//text()"))
+                )
+            remarks = self._clean_text("".join(node.xpath(".//*[contains(@class,'text-[10px]')][1]//text()")))
+            pic = ((node.xpath(".//img[1]/@data-src") or node.xpath(".//img[1]/@src") or [""])[0]).strip()
+            cards.append(
+                {
+                    "vod_id": vod_id,
+                    "vod_name": title,
+                    "vod_pic": self._abs_url(pic),
+                    "vod_url": self._abs_url(href),
+                    "vod_year": year,
+                    "type_name": type_name,
+                    "vod_remarks": remarks,
+                }
+            )
+        return cards
+
+    def categoryContent(self, tid, pg, filter, extend):
+        page = int(pg)
+        values = extend if isinstance(extend, dict) else {}
+        query = {}
+        if values.get("class"):
+            query["class"] = values["class"]
+        if values.get("sort_field"):
+            query["sort_field"] = values["sort_field"]
+        if page > 1:
+            query["page"] = page
+        url = self.host + f"/{tid}.html"
+        if query:
+            url += "?" + urlencode(query)
+        return {
+            "page": page,
+            "total": 0,
+            "list": self._parse_vod_cards(self._request_html(url)),
+        }
+
+    def _pick_meta_value(self, html, label):
+        patterns = [
+            rf"{label}\s*</span>\s*<span[^>]*>([^<]+)</span>",
+            rf">{label}\s*<[^>]*>\s*<span[^>]*>([^<]+)</span>",
+            rf"<span[^>]*>{label}</span>\s*<span[^>]*>([^<]+)</span>",
+        ]
+        for pattern in patterns:
+            matched = re.search(pattern, html)
+            if matched:
+                return self._clean_text(matched.group(1))
+        root = self.html(html)
+        if root is None:
+            return ""
+        nodes = root.xpath(f"//span[normalize-space(text())='{label}']/following-sibling::span[1]")
+        if nodes:
+            return self._clean_text("".join(nodes[0].xpath(".//text()")))
+        return ""
+
+    def _extract_link_texts(self, html, title):
+        root = self.html(html)
+        if root is None:
+            return []
+        values = []
+        for node in root.xpath(f"//h3[contains(normalize-space(.), '{title}')]/following-sibling::*[1]//a//span"):
+            text = self._clean_text("".join(node.xpath(".//text()"))).replace("#", "")
+            if text:
+                values.append(text)
+        return values
+
+    def detailContent(self, ids):
+        vod_id = str(ids[0] if isinstance(ids, list) and ids else ids).strip()
+        if not vod_id:
+            return {"list": []}
+        url = self._abs_url(vod_id)
+        html = self._request_html(url)
+        root = self.html(html)
+        if root is None:
+            return {"list": []}
+
+        vod_name = self._clean_text("".join(root.xpath("(//h1|//h2)[1]//text()")))
+        vod_pic = self._abs_url(((root.xpath("//meta[@property='og:image']/@content") or [""])[0]).strip())
+        vod_content = self._clean_text(
+            "".join(
+                root.xpath(
+                    "//h3[contains(normalize-space(.), '剧情简介')]/following-sibling::*[1]"
+                    "//*[contains(@class,'text-sm')][1]//text()"
+                )
+            )
+        ) or self._clean_text(((root.xpath("//meta[@name='description']/@content") or [""])[0]))
+        vod_year = self._pick_meta_value(html, "年份")
+        vod_area = self._pick_meta_value(html, "地区")
+        vod_lang = self._pick_meta_value(html, "语言")
+        vod_director = ",".join(self._extract_link_texts(html, "导演"))
+        vod_actor = ",".join(self._extract_link_texts(html, "主演"))
+        tags = self._extract_link_texts(html, "标签")
+
+        from_list = []
+        url_list = []
+        for line_node in root.xpath("//*[@id='originTabs']//a[@href]"):
+            href = ((line_node.xpath("./@href") or [""])[0]).strip()
+            name = self._clean_text(
+                ((line_node.xpath(".//button[@data-origin]/@data-origin") or [""])[0])
+                or "".join(line_node.xpath(".//text()"))
+            )
+            line_url = self._abs_url(href)
+            line_html = html if line_url == url else self._request_html(line_url)
+            line_root = self.html(line_html)
+            episodes = []
+            if line_root is not None:
+                for episode in line_root.xpath("//*[contains(@class,'seqlist')]//a[@href]"):
+                    ep_href = ((episode.xpath("./@href") or [""])[0]).strip()
+                    ep_title = self._clean_text(
+                        ((episode.xpath("./@data-title") or [""])[0]) or "".join(episode.xpath(".//text()"))
+                    ) or "播放"
+                    payload = json.dumps(
+                        {
+                            "title": ep_title,
+                            "origin": name,
+                            "page": self._abs_url(ep_href),
+                            "vodName": vod_name,
+                            "pic": vod_pic,
+                        },
+                        ensure_ascii=False,
+                    )
+                    episodes.append(f"{ep_title}${payload}")
+            if episodes:
+                from_list.append(name)
+                url_list.append("#".join(episodes))
+
+        return {
+            "list": [
+                {
+                    "vod_id": vod_id,
+                    "vod_name": vod_name,
+                    "vod_pic": vod_pic,
+                    "vod_content": vod_content,
+                    "vod_year": vod_year,
+                    "vod_area": vod_area,
+                    "vod_lang": vod_lang,
+                    "vod_director": vod_director,
+                    "vod_actor": vod_actor,
+                    "type_name": " / ".join(tags),
+                    "vod_play_from": "$$$".join(from_list),
+                    "vod_play_url": "$$$".join(url_list),
+                }
+            ]
+        }
+
+    def _normalize_keyword(self, value):
+        return re.sub(r"[\s\-_—–·•:：,，.。!?！？'\"“”‘’()（）\[\]【】{}]", "", str(value or "")).lower()
+
+    def _search_score(self, vod_name, keyword):
+        name = self._normalize_keyword(vod_name)
+        key = self._normalize_keyword(keyword)
+        if not name or not key:
+            return 0
+        if name == key:
+            return 1000
+        if name.startswith(key):
+            return 800
+        if key in name:
+            return 600
+        return 0
+
+    def _refine_search_results(self, items, keyword):
+        scored = [(self._search_score(item.get("vod_name"), keyword), item) for item in items]
+        matched = [
+            item
+            for score, item in sorted(scored, key=lambda pair: (-pair[0], pair[1].get("vod_name", "")))
+            if score > 0
+        ]
+        return matched or items
+
+    def searchContent(self, key, quick, pg="1"):
+        page = int(pg)
+        keyword = self._clean_text(key)
+        if not keyword:
+            return {"page": page, "total": 0, "list": []}
+        url = self.host + "/s.html?name=" + quote(keyword)
+        if page > 1:
+            url += "&page=" + str(page - 1)
+        items = self._parse_vod_cards(self._request_html(url))
+        return {"page": page, "total": len(items), "list": self._refine_search_results(items, keyword)}
+
+    def playerContent(self, flag, id, vipFlags):
+        raw = str(id or "").strip()
+        if not raw:
+            return {"parse": 1, "playUrl": "", "url": "", "header": {}, "jx": 1}
+        try:
+            meta = json.loads(raw)
+        except Exception:
+            meta = {"page": raw}
+        page_url = self._abs_url(meta.get("page", ""))
+        headers = {
+            "User-Agent": self.headers["User-Agent"],
+            "Referer": page_url or self.host + "/",
+            "Origin": self.host,
+        }
+        html = self._request_html(page_url, headers={"Referer": self.host + "/"}) if page_url else ""
+        matched = re.search(r"/api/m3u8\?origin=([^\"'\\\s&]+|[^\"'\\\s]+?)(&amp;|&)url=([a-zA-Z0-9]+)", html)
+        if not matched:
+            return {"parse": 1, "playUrl": "", "url": page_url, "header": headers, "jx": 1}
+
+        api_url = self.host + "/api/m3u8?origin=" + matched.group(1) + "&url=" + matched.group(3)
+        probe = self._request_response(api_url, headers=headers, allow_redirects=False)
+        final_url = api_url
+        location = ""
+        if hasattr(probe, "headers"):
+            location = probe.headers.get("Location") or probe.headers.get("location") or ""
+        if location:
+            final_url = self._abs_url(location)
+            playlist = self._request_html(final_url, headers={"Referer": self.host + "/"})
+            raw_line = next(
+                (line.strip() for line in playlist.splitlines() if "/api/m3u8?id=" in line and "raw=1" in line),
+                "",
+            )
+            if raw_line:
+                final_url = urljoin(final_url, raw_line)
+        return {"parse": 0, "playUrl": "", "url": final_url, "header": headers, "jx": 0}