feat: add dbku category and search flow

This commit is contained in:
Harold
2026-04-18 11:59:46 +08:00
parent 742de4d9e8
commit 197eec9a61
2 changed files with 128 additions and 0 deletions
+57
View File
@@ -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]
@@ -38,6 +39,62 @@ class TestDBKUSpider(unittest.TestCase):
],
)
@patch.object(Spider, "fetch")
def test_request_html_uses_dbku_headers(self, mock_fetch):
class FakeResponse:
def __init__(self, text):
self.text = text
self.status_code = 200
self.encoding = "utf-8"
mock_fetch.return_value = FakeResponse("<html><body>ok</body></html>")
html = self.spider._request_html("/vodtype/1--------1---.html", expect_xpath="//body")
self.assertIn("ok", html)
called_headers = mock_fetch.call_args.kwargs["headers"]
self.assertEqual(called_headers["Referer"], "https://www.dbku.tv")
self.assertEqual(called_headers["Origin"], "https://www.dbku.tv")
@patch.object(Spider, "_request_html")
def test_category_content_builds_page_result(self, mock_request_html):
mock_request_html.return_value = """
<div class="myui-vodlist__box">
<a href="/voddetail/456.html" title="分类影片" data-original="/cover.jpg"></a>
<span class="pic-text">HD</span>
</div>
"""
result = self.spider.categoryContent("movie", "2", False, {})
self.assertEqual(result["page"], 2)
self.assertEqual(result["list"][0]["vod_name"], "分类影片")
self.assertEqual(result["list"][0]["vod_pic"], "https://www.dbku.tv/cover.jpg")
def test_parse_search_cards_prefers_search_list_container(self):
html = """
<div id="searchList">
<div class="myui-vodlist__box">
<a href="/voddetail/789.html" title="搜索命中" data-original="/search.jpg"></a>
</div>
</div>
<div class="myui-vodlist__box">
<a href="/voddetail/999.html" title="回退结果" data-original="/fallback.jpg"></a>
</div>
"""
results = self.spider._parse_search_cards(html)
self.assertEqual(len(results), 1)
self.assertEqual(results[0]["vod_name"], "搜索命中")
@patch.object(Spider, "_request_html")
def test_search_content_reuses_search_parser(self, mock_request_html):
mock_request_html.return_value = """
<div id="searchList">
<div class="myui-vodlist__box">
<a href="/voddetail/321.html" title="搜索影片" data-original="/search.jpg"></a>
</div>
</div>
"""
result = self.spider.searchContent("繁花", False, "1")
self.assertEqual(result["list"][0]["vod_id"], "https://www.dbku.tv/voddetail/321.html")
self.assertEqual(result["list"][0]["vod_name"], "搜索影片")
if __name__ == "__main__":
unittest.main()
+71
View File
@@ -1,5 +1,8 @@
# coding=utf-8
import sys
from urllib.parse import quote
from lxml import etree
from base.spider import Spider as BaseSpider
@@ -25,6 +28,14 @@ class Spider(BaseSpider):
{"type_name": "港剧", "type_id": "hk"},
{"type_name": "陆剧", "type_id": "luju"},
]
self.category_paths = {
"index": "/vodtype/2--------{pg}---.html",
"movie": "/vodtype/1--------{pg}---.html",
"variety": "/vodtype/3--------{pg}---.html",
"anime": "/vodtype/4--------{pg}---.html",
"hk": "/vodtype/20--------{pg}---.html",
"luju": "/vodtype/13--------{pg}---.html",
}
def init(self, extend=""):
return None
@@ -89,3 +100,63 @@ class Spider(BaseSpider):
}
)
return results
def _request_html(self, path_or_url, expect_xpath=None, referer=None):
target = path_or_url if path_or_url.startswith("http") else self._build_url(path_or_url)
headers = dict(self.headers)
headers["Referer"] = referer or self.host
headers["Origin"] = self.host
response = self.fetch(target, headers=headers, timeout=10)
if response.status_code != 200:
return ""
html = response.text or ""
if expect_xpath:
root = self.html(html)
if root is None or not root.xpath(expect_xpath):
return ""
return html
def _parse_cards_from_nodes(self, nodes):
results = []
seen = set()
for card in nodes:
snippet = self._parse_list_cards(etree.tostring(card, encoding="unicode"))
for item in snippet:
if item["vod_id"] in seen:
continue
seen.add(item["vod_id"])
results.append(item)
return results
def _parse_search_cards(self, html):
root = self.html(html)
if root is None:
return []
search_list = root.xpath("//*[@id='searchList']")
if search_list:
cards = search_list[0].xpath(".//*[contains(@class,'myui-vodlist__box')]")
parsed = self._parse_cards_from_nodes(cards)
if parsed:
return parsed
return self._parse_list_cards(html)
def _page_result(self, items, pg):
page = int(pg)
pagecount = page + 1 if items else page
return {
"list": items,
"page": page,
"pagecount": pagecount,
"limit": len(items),
"total": pagecount * max(len(items), 1),
}
def categoryContent(self, tid, pg, filter, extend):
path = self.category_paths.get(tid, self.category_paths["index"]).format(pg=pg)
html = self._request_html(path, expect_xpath="//*[contains(@class,'myui-vodlist__box')]")
return self._page_result(self._parse_list_cards(html), pg)
def searchContent(self, key, quick, pg="1"):
path = "/vodsearch/-------------.html?wd={0}&submit=".format(quote(key))
html = self._request_html(path, expect_xpath="//*[@id='searchList']|//*[contains(@class,'myui-vodlist__box')]")
return self._page_result(self._parse_search_cards(html), pg)