yeyinly/tvboxzt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feat: add ouge detail and player support

Browse Source
This commit is contained in:
Harold
2026-04-20 14:59:12 +08:00
parent 7b1449c7ab
commit 59e1524810
2 changed files with 168 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
py/tests/test_欧歌.py
+74
View File
@@ -135,6 +135,80 @@ class TestOuGeSpider(unittest.TestCase):
self.assertEqual(result, {"page": 1, "total": 0, "list": []})
mock_request_html.assert_not_called()
def test_parse_detail_page_extracts_metadata_and_deduplicated_pan_groups(self):
html = """
<div class="page-title">欧歌示例</div>
<div class="mobile-play">
<img class="lazyload" data-src="/poster-detail.jpg" />
</div>
<div class="module-item-caption"><span>2025</span></div>
<div class="video-info-itemtitle">导演</div>
<div><a>导演甲</a><a>导演乙</a></div>
<div class="video-info-itemtitle">主演</div>
<div><a>演员甲</a><a>演员乙</a></div>
<div class="video-info-itemtitle">剧情</div>
<div><p>这是一段剧情简介。</p></div>
<div class="module-row-info"><p>https://pan.quark.cn/s/q-demo</p></div>
<div class="module-row-info"><p>百度合集 https://pan.baidu.com/s/b-demo</p></div>
<div class="module-row-info"><p>https://pan.quark.cn/s/q-demo</p></div>
"""
vod = self.spider._parse_detail_page(html, "/index.php/vod/detail/id/999.html")
self.assertEqual(vod["vod_id"], "/index.php/vod/detail/id/999.html")
self.assertEqual(vod["vod_name"], "欧歌示例")
self.assertEqual(vod["vod_pic"], "https://woog.nxog.eu.org/poster-detail.jpg")
self.assertEqual(vod["vod_year"], "2025")
self.assertEqual(vod["vod_director"], "导演甲,导演乙")
self.assertEqual(vod["vod_actor"], "演员甲,演员乙")
self.assertEqual(vod["vod_content"], "这是一段剧情简介。")
self.assertEqual(vod["vod_play_from"], "baidu$$$quark")
self.assertEqual(
vod["vod_play_url"],
"百度资源$https://pan.baidu.com/s/b-demo$$$夸克资源$https://pan.quark.cn/s/q-demo",
)
@patch.object(Spider, "_request_html")
def test_detail_content_reads_detail_page_and_returns_single_vod(self, mock_request_html):
mock_request_html.return_value = """
<div class="page-title">详情标题</div>
<div class="module-row-info"><p>https://pan.quark.cn/s/detail-demo</p></div>
"""
result = self.spider.detailContent(["/index.php/vod/detail/id/1000.html"])
self.assertEqual(
mock_request_html.call_args.args[0],
"https://woog.nxog.eu.org/index.php/vod/detail/id/1000.html",
)
self.assertEqual(result["list"][0]["vod_id"], "/index.php/vod/detail/id/1000.html")
self.assertEqual(result["list"][0]["vod_name"], "详情标题")
self.assertEqual(result["list"][0]["vod_play_from"], "quark")
self.assertEqual(result["list"][0]["vod_play_url"], "夸克资源$https://pan.quark.cn/s/detail-demo")
def test_parse_detail_page_returns_empty_shell_for_blank_html(self):
self.assertEqual(
self.spider._parse_detail_page("", "/index.php/vod/detail/id/404.html"),
{
"vod_id": "/index.php/vod/detail/id/404.html",
"vod_name": "",
"vod_pic": "",
"vod_year": "",
"vod_director": "",
"vod_actor": "",
"vod_content": "",
"vod_play_from": "",
"vod_play_url": "",
},
)
def test_player_content_transparently_returns_supported_pan_link(self):
result = self.spider.playerContent("quark", "https://pan.quark.cn/s/demo", {})
self.assertEqual(result["parse"], 0)
self.assertEqual(result["jx"], 0)
self.assertEqual(result["url"], "https://pan.quark.cn/s/demo")
self.assertEqual(result["header"], {})
def test_player_content_returns_empty_url_for_unknown_link(self):
result = self.spider.playerContent("unknown", "/index.php/vod/play/id/1.html", {})
self.assertEqual(result, {"parse": 0, "jx": 0, "playUrl": "", "url": "", "header": {}})
if __name__ == "__main__":
unittest.main()
py/欧歌.py
+94
View File
@@ -179,3 +179,97 @@ class Spider(BaseSpider):
return {"page": page, "total": 0, "list": []}
items = self._parse_search_cards(self._request_html(self._build_search_url(keyword, pg)))
return {"page": page, "total": len(items), "list": items}
def _blank_detail(self, vod_id):
return {
"vod_id": vod_id,
"vod_name": "",
"vod_pic": "",
"vod_year": "",
"vod_director": "",
"vod_actor": "",
"vod_content": "",
"vod_play_from": "",
"vod_play_url": "",
}
def _extract_share_url(self, text):
matched = re.search(r"https?://[^\s'\"<>]+", self._stringify(text), re.I)
return matched.group(0).strip() if matched else ""
def _join_people(self, node):
values = [self._clean_text(text) for text in node.xpath(".//a//text()")]
if not any(values):
values = [self._clean_text(text) for text in node.xpath(".//text()")]
values = [value for value in values if value]
return ",".join(values)
def _extract_pan_groups(self, root):
groups = []
seen = set()
for node in root.xpath("//*[contains(@class,'module-row-info')]//p"):
text = self._clean_text("".join(node.xpath(".//text()")))
share_url = self._extract_share_url(text)
pan_type, title = self._detect_pan_type(share_url)
if not share_url or not pan_type or share_url in seen:
continue
seen.add(share_url)
groups.append((pan_type, f"{title}${share_url}"))
groups.sort(key=lambda item: self.pan_priority.get(item[0], 999))
return groups
def _parse_detail_page(self, html, vod_id):
if not self._stringify(html).strip():
return self._blank_detail(vod_id)
root = self.html(html)
if root is None:
return self._blank_detail(vod_id)
vod = self._blank_detail(vod_id)
vod["vod_name"] = self._clean_text("".join(root.xpath("(//*[contains(@class,'page-title')])[1]//text()")))
pic = (
((root.xpath("//*[contains(@class,'mobile-play')]//*[contains(@class,'lazyload')][1]/@data-src") or [""])[0]).strip()
or ((root.xpath("//*[contains(@class,'mobile-play')]//*[contains(@class,'lazyload')][1]/@src") or [""])[0]).strip()
)
vod["vod_pic"] = self._fix_img_url(pic)
vod["vod_year"] = self._clean_text(
((root.xpath("(//*[contains(@class,'module-item-caption')]//span[1]/text())") or [""])[0])
)
for label_node in root.xpath("//*[contains(@class,'video-info-itemtitle')]"):
label = self._clean_text("".join(label_node.xpath(".//text()")))
siblings = label_node.xpath("./following-sibling::*[1]")
if not siblings:
continue
block = siblings[0]
if "导演" in label:
vod["vod_director"] = self._join_people(block)
elif "主演" in label:
vod["vod_actor"] = self._join_people(block)
elif "剧情" in label:
texts = block.xpath(".//p//text()") or block.xpath(".//text()")
vod["vod_content"] = self._clean_text("".join(texts))
pan_groups = self._extract_pan_groups(root)
vod["vod_play_from"] = "$$$".join(item[0] for item in pan_groups)
vod["vod_play_url"] = "$$$".join(item[1] for item in pan_groups)
return vod
def detailContent(self, ids):
result = {"list": []}
for raw_id in ids:
vod_id = self._stringify(raw_id).strip()
if not vod_id:
continue
html = self._request_html(self._build_url(vod_id))
result["list"].append(self._parse_detail_page(html, vod_id))
return result
def _is_supported_pan_link(self, url):
return bool(self._detect_pan_type(url)[0])
def playerContent(self, flag, id, vipFlags):
target = self._stringify(id).strip()
if target and self._is_supported_pan_link(target):
return {"parse": 0, "jx": 0, "playUrl": "", "url": target, "header": {}}
return {"parse": 0, "jx": 0, "playUrl": "", "url": "", "header": {}}