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

玩偶聚合

Browse Source
This commit is contained in:
Harold
2026-04-20 16:05:34 +08:00
parent b2d57ae549
commit 7ae814b49b
3 changed files with 46 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
py/tests/test_人人电影.py
+41
View File
@@ -102,6 +102,31 @@ class TestRenRenDianYingSpider(unittest.TestCase):
],
)
def test_parse_cards_uses_first_intro_link_instead_of_concatenating_multiple_detail_urls(self):
html = """
<ul id="movielist">
<li>
<div class="intro">
<h2><a href="/movie/2025/0814/51262.html" title="第一部">第一部</a></h2>
<h2><a href="/movie/2026/0217/57139.html" title="第二部">第二部</a></h2>
</div>
<img class="pure-img" data-original="/poster.jpg" />
<div class="dou"><b>HD</b></div>
</li>
</ul>
"""
self.assertEqual(
self.spider._parse_cards(html),
[
{
"vod_id": "/movie/2025/0814/51262.html",
"vod_name": "第一部",
"vod_pic": "https://www.rrdynb.com/poster.jpg",
"vod_remarks": "HD",
}
],
)
@patch.object(Spider, "_request_html")
def test_category_content_builds_reference_url_and_page_payload(self, mock_request_html):
mock_request_html.return_value = """
@@ -123,6 +148,22 @@ class TestRenRenDianYingSpider(unittest.TestCase):
self.assertEqual(result["list"][0]["vod_name"], "分类影片")
self.assertNotIn("pagecount", result)
@patch.object(Spider, "_request_html")
def test_category_content_uses_plain_path_for_first_page(self, mock_request_html):
mock_request_html.return_value = """
<ul id="movielist">
<li>
<img class="pure-img" data-original="/page1.jpg" />
<div class="intro"><h2><a href="/movie/111.html" title="第一页影片">第一页影片</a></h2></div>
<div class="dou"><b>HD</b></div>
</li>
</ul>
"""
result = self.spider.categoryContent("movie/list_2", "1", False, {})
self.assertEqual(mock_request_html.call_args.args[0], "https://www.rrdynb.com/movie/list_2.html")
self.assertEqual(result["page"], 1)
self.assertEqual(result["list"][0]["vod_id"], "/movie/111.html")
@patch.object(Spider, "_request_html")
def test_search_content_builds_reference_url_and_cleans_highlight_title(self, mock_request_html):
mock_request_html.return_value = """
py/人人电影.py
+4 -4
View File
@@ -129,10 +129,10 @@ class Spider(BaseSpider):
items = []
seen = set()
for node in root.xpath("//*[@id='movielist']//li"):
href = "".join(node.xpath(".//*[contains(@class,'intro')]//h2//a[1]/@href")).strip()
href = self._first_xpath_result(node, ".//*[contains(@class,'intro')]//h2//a/@href")
title = (
"".join(node.xpath(".//*[contains(@class,'intro')]//h2//a[1]/@title")).strip()
or "".join(node.xpath(".//*[contains(@class,'intro')]//h2//a[1]//text()")).strip()
self._first_xpath_result(node, ".//*[contains(@class,'intro')]//h2//a/@title")
or self._first_xpath_result(node, ".//*[contains(@class,'intro')]//h2//a//text()")
)
pic = (
self._first_xpath_result(node, ".//*[contains(@class,'pure-img')][1]/@data-original")
@@ -161,7 +161,7 @@ class Spider(BaseSpider):
class_path = str(tid or "").lstrip("/")
url = self._build_url(f"{class_path}_{page}.html")
items = self._parse_cards(self._request_html(url))
return {"page": page, "limit": len(items), "total": page * 20 + len(items), "list": items}
return {"page": page, "limit": len(items), "total": page * 30 + len(items), "list": items}
def searchContent(self, key, quick, pg="1"):
page = int(pg)
py/奕搜.py
+1 -1
View File
@@ -105,7 +105,7 @@ class Spider(BaseSpider):
def categoryContent(self, tid, pg, filter, extend):
page = int(pg)
items = self._parse_list_boxes(self._request_html(self._build_url(f"/{tid}.html?page={page}")))
return {"page": page, "limit": len(items) or 20, "total": page * (len(items) or 20), "list": items}
return {"page": page, "limit": len(items) or 20, "total": page * 30 + (len(items) or 20), "list": items}
def searchContent(self, key, quick, pg="1"):
page = int(pg)