From f6c847e8716960c8f91dca829686fe41094f1be7 Mon Sep 17 00:00:00 2001 From: Harold <8866033@gmail.com> Date: Sun, 19 Apr 2026 19:01:11 +0800 Subject: [PATCH] feat: add juquanquan list and search flows --- py/tests/test_剧圈圈.py | 55 ++++++++++++++++++++++++++++++++ py/剧圈圈.py | 69 ++++++++++++++++++++++++++++++++++++++++- 2 files changed, 123 insertions(+), 1 deletion(-) diff --git a/py/tests/test_剧圈圈.py b/py/tests/test_剧圈圈.py index ed3d9c9..2c2f4f4 100644 --- a/py/tests/test_剧圈圈.py +++ b/py/tests/test_剧圈圈.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] @@ -41,6 +42,60 @@ class TestJuQuanQuanSpider(unittest.TestCase): ], ) + def test_parse_cards_extracts_compact_vod_ids(self): + html = """ + + +
示例影片
+
更新至1集
+ + """ + self.assertEqual( + self.spider._parse_cards(html), + [ + { + "vod_id": "vod/123", + "vod_name": "示例影片", + "vod_pic": "https://www.jqqzx.cc/cover.jpg", + "vod_remarks": "更新至1集", + } + ], + ) + + @patch.object(Spider, "_request_html") + def test_home_video_content_limits_recommendations(self, mock_request_html): + mock_request_html.return_value = "".join( + f'
影片{index}
' + for index in range(1, 45) + ) + result = self.spider.homeVideoContent() + self.assertEqual(len(result["list"]), 40) + self.assertEqual(result["list"][0]["vod_id"], "vod/1") + + @patch.object(Spider, "_request_html") + def test_category_content_builds_page_result(self, mock_request_html): + mock_request_html.return_value = """ + +
分类影片
+ + """ + result = self.spider.categoryContent("juji", "2", False, {}) + self.assertEqual(mock_request_html.call_args.args[0], "https://www.jqqzx.cc/type/juji/page/2.html") + self.assertEqual(result["page"], 2) + self.assertEqual(result["pagecount"], 3) + self.assertEqual(result["list"][0]["vod_id"], "vod/456") + + @patch.object(Spider, "_request_html") + def test_search_content_uses_suggest_api(self, mock_request_html): + mock_request_html.return_value = '{"list":[{"id":"777","name":"搜索结果","pic":"/pic.jpg"}]}' + result = self.spider.searchContent("繁花", False, "1") + self.assertEqual( + mock_request_html.call_args.args[0], + "https://www.jqqzx.cc/index.php/ajax/suggest?mid=1&wd=%E7%B9%81%E8%8A%B1", + ) + self.assertEqual(result["list"][0]["vod_id"], "vod/777") + self.assertEqual(result["pagecount"], 1) + if __name__ == "__main__": unittest.main() diff --git a/py/剧圈圈.py b/py/剧圈圈.py index ebbaa58..b1beacb 100644 --- a/py/剧圈圈.py +++ b/py/剧圈圈.py @@ -2,7 +2,7 @@ import json import re import sys -from urllib.parse import urljoin +from urllib.parse import quote, urljoin from base.spider import Spider as BaseSpider @@ -77,3 +77,70 @@ class Spider(BaseSpider): } ) return items + + def _request_html(self, path_or_url, headers=None): + target = path_or_url if str(path_or_url).startswith("http") else self._build_url(path_or_url) + request_headers = dict(self.headers) + if headers: + request_headers.update(headers) + response = self.fetch(target, headers=request_headers, timeout=10) + if response.status_code != 200: + return "" + return response.text or "" + + def _parse_cards(self, html): + root = self.html(html) + if root is None: + return [] + items = [] + seen = set() + for anchor in root.xpath("//a[contains(@class,'module-poster-item') and contains(@class,'module-item')]"): + vod_id = self._encode_vod_id((anchor.xpath("./@href") or [""])[0]) + if not vod_id or vod_id in seen: + continue + title = self._clean_text( + "".join(anchor.xpath(".//*[contains(@class,'module-poster-item-title')][1]//text()")) + or (anchor.xpath("./@title") or [""])[0] + or (anchor.xpath(".//img[1]/@alt") or [""])[0] + ) + if not title: + continue + seen.add(vod_id) + pic = ( + anchor.xpath(".//img[1]/@data-original") + or anchor.xpath(".//img[1]/@src") + or [""] + )[0] + note = self._clean_text("".join(anchor.xpath(".//*[contains(@class,'module-item-note')][1]//text()"))) + items.append( + { + "vod_id": vod_id, + "vod_name": title, + "vod_pic": self._build_url(pic), + "vod_remarks": note, + } + ) + return items + + def homeVideoContent(self): + return {"list": self._parse_cards(self._request_html(self.host))[:40]} + + def categoryContent(self, tid, pg, filter, extend): + page = int(pg) + items = self._parse_cards(self._request_html(self._build_url(f"/type/{tid}/page/{page}.html"))) + return { + "page": page, + "pagecount": page + 1 if items else page, + "total": page * len(items) + (1 if items else 0), + "list": items, + } + + def searchContent(self, key, quick, pg="1"): + page = int(pg) + keyword = self._clean_text(key) + if not keyword: + return {"page": page, "pagecount": 1, "total": 0, "list": []} + items = self._parse_search_list( + self._request_html(self._build_url(f"/index.php/ajax/suggest?mid=1&wd={quote(keyword)}")) + ) + return {"page": page, "pagecount": 1, "total": len(items), "list": items}