from __future__ import annotations
import unittest
from unittest.mock import Mock, patch
import requests
from sakura_cloud.services.online_search_engine import (
OnlineSearchEngine,
RuleConfig,
RuleManager,
build_search_request,
build_search_url,
parse_comic,
parse_novel,
resolve_resource_url,
title_match_score,
)
class OnlineSearchEngineTest(unittest.TestCase):
def test_resolve_resource_url_handles_relative_and_scheme_relative(self) -> None:
self.assertEqual(
resolve_resource_url("https://example.com/books/index.html", "../read/1.html"),
"https://example.com/read/1.html",
)
self.assertEqual(
resolve_resource_url("https://example.com", "//cdn.example.com/a.webp"),
"https://cdn.example.com/a.webp",
)
def test_build_search_url_replaces_common_legado_placeholders(self) -> None:
keyword = "十宗罪"
template = "/search?q={{key}}&k={keyword}&s=%s&x=searchKey"
result = build_search_url(template, keyword)
self.assertNotIn("{{key}}", result)
self.assertNotIn("{keyword}", result)
self.assertNotIn("%s", result)
self.assertNotIn("searchKey", result)
self.assertIn("%E5%8D%81%E5%AE%97%E7%BD%AA", result)
def test_build_search_request_supports_post_body(self) -> None:
url, data = build_search_request("POST /search@keyword={{key}}&page=1", "魔法", "https://novel.example.com")
self.assertEqual(url, "https://novel.example.com/search")
self.assertEqual(data, {"keyword": "%E9%AD%94%E6%B3%95", "page": "1"})
def test_title_match_score_uses_noise_words_and_fuzzy_match(self) -> None:
self.assertGreater(title_match_score("十宗罪 最新章节 免费阅读", "十宗罪"), 0.75)
self.assertGreater(title_match_score("千分之一的魔法", "千分之一魔法"), 0.55)
def test_rule_manager_can_disable_rules(self) -> None:
manager = RuleManager([RuleConfig(rule_id="a", name="A", base_url="https://a.example", search_url="/s?q={{key}}")])
self.assertEqual(len(manager.get_rules("all")), 1)
manager.disable_rule("a")
self.assertEqual(manager.get_rules("all"), [])
def test_search_rule_parses_json_payload_without_network(self) -> None:
response = requests.Response()
response.status_code = 200
response._content = (
b'{"data":[{"bookName":"Sakura Magic","bookUrl":"/book/1","author":"Nana","cover":"/c.jpg"}]}'
)
response.headers["content-type"] = "application/json; charset=utf-8"
session = Mock()
session.request.return_value = response
manager = RuleManager(
[
RuleConfig(
rule_id="json",
name="JSON Source",
base_url="https://novel.example.com",
resource_type="novel",
search_url="/search?q={{key}}",
rule_search={
"bookList": "$.data[*]",
"name": "$.bookName",
"bookUrl": "$.bookUrl",
"author": "$.author",
"cover": "$.cover",
},
)
]
)
engine = OnlineSearchEngine(manager, session=session)
with patch("sakura_cloud.services.online_search_engine.assert_public_url"):
rows = engine.search_resource("Sakura", "novel")
self.assertEqual(len(rows), 1)
self.assertEqual(rows[0].url, "https://novel.example.com/book/1")
self.assertEqual(rows[0].cover, "https://novel.example.com/c.jpg")
def test_parse_novel_public_page_without_cookie(self) -> None:
html = """
神秘复苏
第一章\n论坛里的故事。\n这里是正文。
"""
response = requests.Response()
response.status_code = 200
response._content = html.encode("utf-8")
response.headers["content-type"] = "text/html; charset=utf-8"
session = Mock()
session.request.return_value = response
engine = OnlineSearchEngine(session=session)
with patch("sakura_cloud.services.online_search_engine.assert_public_url"):
parsed = engine.parse_novel("https://novel.example.com/read/1.html")
self.assertEqual(parsed.title, "神秘复苏")
self.assertIn("论坛里的故事", parsed.chapters[0].content or "")
self.assertEqual(parsed.cover, "https://novel.example.com/cover.jpg")
def test_parse_comic_reads_lazy_loaded_images(self) -> None:
html = """
魔法漫画
"""
response = requests.Response()
response.status_code = 200
response._content = html.encode("utf-8")
response.headers["content-type"] = "text/html; charset=utf-8"
session = Mock()
session.request.return_value = response
engine = OnlineSearchEngine(session=session)
with patch("sakura_cloud.services.online_search_engine.assert_public_url"):
parsed = engine.parse_comic("https://manga.example.com/c/1")
self.assertEqual(parsed.title, "魔法漫画")
self.assertEqual(parsed.chapters[0].images, ("https://manga.example.com/manga/001.webp",))
def test_http_444_is_reported_as_site_rejected(self) -> None:
response = requests.Response()
response.status_code = 444
response._content = b""
session = Mock()
session.request.return_value = response
engine = OnlineSearchEngine(session=session)
with patch("sakura_cloud.services.online_search_engine.assert_public_url"):
with self.assertRaisesRegex(Exception, "拒绝访问"):
engine.parse_comic("https://manga.example.com/c/1")
def test_popular_manga_titles_can_be_found_from_html_cards(self) -> None:
html = """
"""
response = requests.Response()
response.status_code = 200
response._content = html.encode("utf-8")
response.headers["content-type"] = "text/html; charset=utf-8"
session = Mock()
session.request.return_value = response
manager = RuleManager(
[RuleConfig(rule_id="manga-html", name="漫画源", base_url="https://manga.example.com", resource_type="manga", search_url="/search?q={{key}}")]
)
engine = OnlineSearchEngine(manager, session=session)
with patch("sakura_cloud.services.online_search_engine.assert_public_url"):
one = engine.search_resource("一人之下", "manga")
naruto = engine.search_resource("火影忍者", "manga")
fox = engine.search_resource("狐妖小红娘", "manga")
self.assertEqual(one[0].url, "https://manga.example.com/comic/yirenzhixia")
self.assertEqual(naruto[0].cover, "https://manga.example.com/cover/naruto.jpg")
self.assertEqual(fox[0].title, "狐妖小红娘在线阅读")
def test_popular_novel_titles_can_be_found_from_json(self) -> None:
response = requests.Response()
response.status_code = 200
response._content = (
'{"data":[{"bookName":"龙族","id":"dragon-raja","author":"江南"},'
'{"bookName":"乐可","bookUrl":"/book/leke","author":"匿名"}]}'
).encode("utf-8")
response.headers["content-type"] = "application/json; charset=utf-8"
session = Mock()
session.request.return_value = response
manager = RuleManager(
[RuleConfig(rule_id="novel-json", name="小说源", base_url="https://novel.example.com", resource_type="novel", search_url="/api/search?key={{keyword}}")]
)
engine = OnlineSearchEngine(manager, session=session)
with patch("sakura_cloud.services.online_search_engine.assert_public_url"):
dragon = engine.search_resource("龙族", "novel")
leke = engine.search_resource("乐可", "novel")
self.assertEqual(dragon[0].url, "https://novel.example.com/book/dragon-raja/")
self.assertEqual(leke[0].url, "https://novel.example.com/book/leke")
def test_manga_script_images_can_be_viewed(self) -> None:
html = """
一人之下 第1话
"""
response = requests.Response()
response.status_code = 200
response._content = html.encode("utf-8")
response.headers["content-type"] = "text/html; charset=utf-8"
session = Mock()
session.request.return_value = response
engine = OnlineSearchEngine(session=session)
with patch("sakura_cloud.services.online_search_engine.assert_public_url"):
parsed = engine.parse_comic("https://manga.example.com/comic/yirenzhixia/1")
self.assertEqual(parsed.chapters[0].images[0], "https://manga.example.com/pages/001.webp")
self.assertEqual(parsed.chapters[0].images[1], "https://cdn.example.com/pages/002.avif")
def test_novel_body_can_be_read_for_dragon_and_leke_like_pages(self) -> None:
html = """
龙族
第一章 卡塞尔之门。
路明非站在雨里,故事从这里开始。
下一章
"""
response = requests.Response()
response.status_code = 200
response._content = html.encode("utf-8")
response.headers["content-type"] = "text/html; charset=utf-8"
session = Mock()
session.request.return_value = response
engine = OnlineSearchEngine(session=session)
with patch("sakura_cloud.services.online_search_engine.assert_public_url"):
parsed = engine.parse_novel("https://novel.example.com/read/1.html")
self.assertEqual(parsed.title, "龙族")
self.assertIn("路明非", parsed.chapters[0].content or "")
self.assertEqual(parsed.chapters[1].url, "https://novel.example.com/read/2.html")
class TopLevelFunctionTest(unittest.TestCase):
def test_top_level_parse_functions_are_available(self) -> None:
self.assertTrue(callable(parse_novel))
self.assertTrue(callable(parse_comic))
if __name__ == "__main__":
unittest.main()