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

feat: add letu list and search parsing

Browse Source
This commit is contained in:
Harold
2026-04-20 09:32:49 +08:00
parent 1f8dd65363
commit 8eb9cc6f23
2 changed files with 137 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
py/tests/test_乐兔.py
+60
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]
@@ -30,6 +31,65 @@ class TestLeTuSpider(unittest.TestCase):
self.assertEqual(self.spider._encode_play_id("/play/123-1-1.html"), "play/123-1-1")
self.assertEqual(self.spider._decode_play_id("play/123-1-1"), "https://www.letu.me/play/123-1-1.html")
def test_parse_cards_extracts_compact_vod_ids(self):
html = """
<div class="grid container_list">
<div class="s6">
<a href="/detail/demo.html" title="示例影片"></a>
<img class="large" data-src="/cover.jpg" />
<div class="small-text">更新至1集</div>
</div>
</div>
"""
self.assertEqual(
self.spider._parse_cards(html),
[
{
"vod_id": "detail/demo",
"vod_name": "示例影片",
"vod_pic": "https://www.letu.me/cover.jpg",
"vod_remarks": "更新至1集",
}
],
)
@patch.object(Spider, "_request_html")
def test_category_content_uses_type_page_url(self, mock_request_html):
mock_request_html.return_value = """
<div class="grid container_list">
<div class="s6">
<a href="/detail/cat-demo.html" title="分类片"></a>
<img class="large" data-src="/cat.jpg" />
<div class="small-text">HD</div>
</div>
</div>
"""
result = self.spider.categoryContent("2", "3", False, {})
self.assertEqual(mock_request_html.call_args.args[0], "https://www.letu.me/type/2-3.html")
self.assertEqual(result["page"], 3)
self.assertEqual(result["limit"], 1)
self.assertNotIn("pagecount", result)
self.assertEqual(result["list"][0]["vod_id"], "detail/cat-demo")
@patch.object(Spider, "_request_html")
def test_search_content_uses_search_url_and_parses_cards(self, mock_request_html):
mock_request_html.return_value = """
<div class="result-list">
<div class="result-item">
<a href="/detail/search-demo.html">搜索影片</a>
<img class="large" data-src="/search.jpg" />
<div class="small-text">全集</div>
</div>
</div>
"""
result = self.spider.searchContent("繁花", False, "1")
self.assertEqual(
mock_request_html.call_args.args[0],
"https://www.letu.me/vodsearch/-------------.html?wd=%E7%B9%81%E8%8A%B1",
)
self.assertEqual(result["list"][0]["vod_id"], "detail/search-demo")
self.assertNotIn("pagecount", result)
if __name__ == "__main__":
unittest.main()
py/乐兔.py
+77 -1
View File
@@ -1,7 +1,7 @@
# coding=utf-8
import re
import sys
from urllib.parse import urljoin
from urllib.parse import quote, urljoin
from base.spider import Spider as BaseSpider
@@ -58,3 +58,79 @@ class Spider(BaseSpider):
def _decode_play_id(self, play_id):
matched = re.search(r"^play/([^/?#]+)$", str(play_id or "").strip())
return self._build_url(f"/play/{matched.group(1)}.html") if matched else ""
def _clean_text(self, text):
return re.sub(r"\s+", " ", str(text or "")).strip()
def _request_html(self, path_or_url):
target = path_or_url if str(path_or_url).startswith("http") else self._build_url(path_or_url)
response = self.fetch(target, headers=dict(self.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 node in root.xpath("//*[contains(@class,'grid') and contains(@class,'container_list')]//*[contains(@class,'s6')]"):
href = "".join(node.xpath(".//a[1]/@href")).strip()
vod_id = self._encode_vod_id(href)
if not vod_id or vod_id in seen:
continue
name = self._clean_text("".join(node.xpath(".//a[1]/@title")) or "".join(node.xpath(".//a[1]//text()")))
if not name:
continue
pic = self._clean_text(
"".join(node.xpath(".//*[contains(@class,'large')][1]/@data-src | .//*[contains(@class,'large')][1]/@src"))
)
remark = self._clean_text("".join(node.xpath(".//*[contains(@class,'small-text')][1]//text()")))
seen.add(vod_id)
items.append(
{
"vod_id": vod_id,
"vod_name": name,
"vod_pic": self._build_url(pic),
"vod_remarks": remark,
}
)
return items
def _page_result(self, items, pg):
page = int(pg)
return {"page": page, "limit": len(items), "total": len(items), "list": items}
def categoryContent(self, tid, pg, filter, extend):
html = self._request_html(self._build_url(f"/type/{tid}-{int(pg)}.html"))
return self._page_result(self._parse_cards(html), pg)
def searchContent(self, key, quick, pg="1"):
keyword = self._clean_text(key)
if not keyword:
return self._page_result([], pg)
html = self._request_html(self._build_url(f"/vodsearch/-------------.html?wd={quote(keyword)}"))
root = self.html(html)
if root is None:
return self._page_result([], pg)
items = []
for node in root.xpath("//*[contains(@class,'result-list')]//*[contains(@class,'result-item')]"):
href = "".join(node.xpath(".//a[1]/@href")).strip()
vod_id = self._encode_vod_id(href)
name = self._clean_text("".join(node.xpath(".//a[1]//text()")))
if not vod_id or not name:
continue
pic = self._clean_text(
"".join(node.xpath(".//*[contains(@class,'large')][1]/@data-src | .//*[contains(@class,'large')][1]/@src"))
)
remark = self._clean_text("".join(node.xpath(".//*[contains(@class,'small-text')][1]//text()")))
items.append(
{
"vod_id": vod_id,
"vod_name": name,
"vod_pic": self._build_url(pic),
"vod_remarks": remark,
}
)
return self._page_result(items, pg)