- 
- 
- 年份：2025
-地区：大陆
-导演：张三
-主演：李四
-
- 
- 一段剧情简介
https://pan.quark.cn/s/q1
-https://pan.baidu.com/s/b1
-一段剧情简介
https://pan.quark.cn/s/q1
-https://pan.baidu.com/s/b1
-一段剧情简介
https://pan.quark.cn/s/q1
-https://pan.baidu.com/s/b1
-一段剧情简介
https://pan.quark.cn/s/q1
-https://pan.baidu.com/s/b1
-
-
-"""
-
-
-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/")
-```
-
-- [ ] **Step 2: Run test to verify it fails**
-
-Run: `cd py && python -m unittest tests.test_电影人生.TestDYRSSpider.test_home_content_exposes_classes_and_filters -v`
-Expected: FAIL with `FileNotFoundError` for `py/电影人生.py`
-
-- [ ] **Step 3: Write minimal implementation**
-
-```python
-# coding=utf-8
-import json
-import re
-import sys
-from urllib.parse import 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"}]},
- {"key": "sort_field", "name": "排序", "init": "", "value": [{"n": "默认", "v": ""}, {"n": "更新时间", "v": "update_time"}]},
- ]
- self.filters = {
- "dianying": common_movie_tv,
- "dianshiju": common_movie_tv,
- "dongman": common_movie_tv,
- "zongyi": common_movie_tv,
- }
-
- 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 "")).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 _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 = self._clean_text("".join(parent.xpath(".//*[contains(@class,'items-center')][1]/span[1]//text()"))) if parent is not None else ""
- type_name = self._clean_text("".join(parent.xpath(".//*[contains(@class,'items-center')][1]/span[last()]//text()"))) if parent is not None else ""
- 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 {}
- qs = {}
- if values.get("class"):
- qs["class"] = values["class"]
- if values.get("sort_field"):
- qs["sort_field"] = values["sort_field"]
- if page > 1:
- qs["page"] = page
- url = self.host + f"/{tid}.html"
- if qs:
- url += "?" + urlencode(qs)
- return {"page": page, "total": 0, "list": self._parse_vod_cards(self._request_html(url))}
-```
-
-- [ ] **Step 4: Run test to verify it passes**
-
-Run: `cd py && python -m unittest tests.test_电影人生.TestDYRSSpider.test_home_content_exposes_classes_and_filters -v`
-Expected: PASS
-
-- [ ] **Step 5: Commit**
-
-```bash
-git add py/电影人生.py py/tests/test_电影人生.py
-git commit -m "feat: add dyrs spider scaffold"
-```
-
-### Task 2: Add Detail Parsing And Play List Assembly
-
-**Files:**
-- Modify: `py/tests/test_电影人生.py`
-- Modify: `py/电影人生.py`
-
-- [ ] **Step 1: Write the failing test**
-
-```python
-DETAIL_HTML = """
-
-
-
- 
-
-
- 
https://pan.quark.cn/s/demo1
-https://pan.baidu.com/s/demo2
-
- 
- 
- 
- 