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

Merge branch 'wanougege-spider'

Browse Source
This commit is contained in:
Harold
2026-04-20 14:42:04 +08:00
parent 4e40575aba f83d3ea7cc
commit 4e9e958261
2 changed files with 465 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
py/tests/test_玩偶哥哥.py
+200
View File
@@ -0,0 +1,200 @@
import unittest
from importlib.machinery import SourceFileLoader
from pathlib import Path
from unittest.mock import patch
ROOT = Path(__file__).resolve().parents[1]
MODULE = SourceFileLoader("wanougege_spider", str(ROOT / "玩偶哥哥.py")).load_module()
Spider = MODULE.Spider
class TestWanOuGeGeSpider(unittest.TestCase):
def setUp(self):
Spider._instance = None
self.spider = Spider()
self.spider.init()
def test_home_content_exposes_all_eight_categories(self):
content = self.spider.homeContent(False)
self.assertEqual(
[(item["type_id"], item["type_name"]) for item in content["class"]],
[
("1", "玩偶电影"),
("2", "玩偶剧集"),
("3", "玩偶动漫"),
("4", "玩偶综艺"),
("44", "臻彩视界"),
("6", "玩偶短剧"),
("5", "玩偶音乐"),
("46", "玩偶纪录"),
],
)
def test_home_video_content_returns_empty_list(self):
self.assertEqual(self.spider.homeVideoContent(), {"list": []})
def test_build_and_fix_urls(self):
self.assertEqual(self.spider._build_url("/voddetail/1.html"), "http://wogg.xxooo.cf/voddetail/1.html")
self.assertEqual(
self.spider._fix_img_url("/db.php?url=https://img.example/poster.jpg"),
"http://wogg.xxooo.cf/db.php?url=https://img.example/poster.jpg",
)
self.assertEqual(
self.spider._fix_img_url("https://gimg1.baidu.com/gimg/?src=data:image/png;base64,AAAA"),
"",
)
def test_detect_pan_type_returns_type_and_title(self):
self.assertEqual(self.spider._detect_pan_type("https://pan.baidu.com/s/demo"), ("baidu", "百度资源"))
self.assertEqual(self.spider._detect_pan_type("https://pan.quark.cn/s/demo"), ("quark", "夸克资源"))
self.assertEqual(self.spider._detect_pan_type("https://example.com/video"), ("", ""))
def test_parse_cards_extracts_short_path_ids(self):
html = """
<div id="main">
<div class="module-item">
<div class="module-item-pic">
<a href="/voddetail/123.html"></a>
<img data-src="/poster.jpg" alt="示例影片" />
</div>
<div class="module-item-text">HD</div>
</div>
</div>
"""
self.assertEqual(
self.spider._parse_cards(html),
[
{
"vod_id": "/voddetail/123.html",
"vod_name": "示例影片",
"vod_pic": "http://wogg.xxooo.cf/poster.jpg",
"vod_remarks": "HD",
}
],
)
@patch.object(Spider, "_request_html")
def test_category_content_builds_reference_url_and_returns_page_payload(self, mock_request_html):
mock_request_html.return_value = """
<div id="main">
<div class="module-item">
<div class="module-item-pic">
<a href="/voddetail/456.html"></a>
<img data-src="/cate.jpg" alt="分类影片" />
</div>
<div class="module-item-text">更新至10集</div>
</div>
</div>
"""
result = self.spider.categoryContent("2", "3", False, {})
self.assertEqual(
mock_request_html.call_args.args[0],
"http://wogg.xxooo.cf/vodshow/2--------3---.html",
)
self.assertEqual(result["page"], 3)
self.assertEqual(result["limit"], 1)
self.assertEqual(result["list"][0]["vod_name"], "分类影片")
self.assertNotIn("pagecount", result)
@patch.object(Spider, "_request_html")
def test_search_content_builds_reference_search_url_and_parses_results(self, mock_request_html):
mock_request_html.return_value = """
<div class="module-search-item">
<a class="video-serial" href="/voddetail/789.html" title="搜索影片">抢先版</a>
<div class="module-item-pic">
<img data-src="/search.jpg" alt="搜索影片" />
</div>
</div>
"""
result = self.spider.searchContent("繁花", False, "2")
self.assertEqual(
mock_request_html.call_args.args[0],
"http://wogg.xxooo.cf/vodsearch/-------------.html?wd=%E7%B9%81%E8%8A%B1&page=2",
)
self.assertEqual(
result["list"][0],
{
"vod_id": "/voddetail/789.html",
"vod_name": "搜索影片",
"vod_pic": "http://wogg.xxooo.cf/search.jpg",
"vod_remarks": "抢先版",
},
)
def test_search_content_returns_empty_list_for_blank_keyword(self):
self.assertEqual(self.spider.searchContent("", False, "1"), {"page": 1, "total": 0, "list": []})
def test_build_pan_lines_deduplicates_and_sorts_supported_links(self):
detail = {
"pan_urls": [
"https://pan.quark.cn/s/q1",
"https://pan.baidu.com/s/b1",
"https://pan.baidu.com/s/b1",
"https://example.com/ignored",
]
}
self.assertEqual(
self.spider._build_pan_lines(detail),
[
("baidu#玩偶哥哥", "百度资源$https://pan.baidu.com/s/b1"),
("quark#玩偶哥哥", "夸克资源$https://pan.quark.cn/s/q1"),
],
)
def test_parse_detail_page_extracts_meta_content_and_pan_urls(self):
html = """
<div class="page-title">示例剧</div>
<div class="mobile-play"><img class="lazyload" data-src="/poster.jpg" /></div>
<div class="video-info-itemtitle">年代</div><div><a>2024</a></div>
<div class="video-info-itemtitle">导演</div><div><a>导演甲</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>一段剧情简介</p></div>
<div class="module-row-info">
<p>https://pan.quark.cn/s/q1</p>
<p>https://pan.baidu.com/s/b1</p>
</div>
"""
detail = self.spider._parse_detail_page("/voddetail/123.html", html)
self.assertEqual(detail["vod_name"], "示例剧")
self.assertEqual(detail["vod_pic"], "http://wogg.xxooo.cf/poster.jpg")
self.assertEqual(detail["vod_year"], "2024")
self.assertEqual(detail["vod_director"], "导演甲")
self.assertEqual(detail["vod_actor"], "演员甲,演员乙")
self.assertEqual(detail["vod_content"], "一段剧情简介")
self.assertEqual(detail["pan_urls"], ["https://pan.quark.cn/s/q1", "https://pan.baidu.com/s/b1"])
@patch.object(Spider, "_request_html")
def test_detail_content_builds_pan_play_fields(self, mock_request_html):
mock_request_html.return_value = """
<div class="page-title">示例剧</div>
<div class="mobile-play"><img class="lazyload" data-src="/poster.jpg" /></div>
<div class="video-info-itemtitle">年代</div><div><a>2024</a></div>
<div class="video-info-itemtitle">导演</div><div><a>导演甲</a></div>
<div class="video-info-itemtitle">主演</div><div><a>演员甲</a></div>
<div class="video-info-itemtitle">剧情</div><div><p>一段剧情简介</p></div>
<div class="module-row-info">
<p>https://pan.quark.cn/s/q1</p>
<p>https://pan.baidu.com/s/b1</p>
</div>
"""
result = self.spider.detailContent(["/voddetail/123.html"])
vod = result["list"][0]
self.assertEqual(vod["vod_name"], "示例剧")
self.assertEqual(vod["vod_play_from"], "baidu#玩偶哥哥$$$quark#玩偶哥哥")
self.assertEqual(
vod["vod_play_url"],
"百度资源$https://pan.baidu.com/s/b1$$$夸克资源$https://pan.quark.cn/s/q1",
)
def test_player_content_passthroughs_supported_pan_urls(self):
self.assertEqual(
self.spider.playerContent("baidu#玩偶哥哥", "https://pan.baidu.com/s/demo", {}),
{"parse": 0, "playUrl": "", "url": "https://pan.baidu.com/s/demo"},
)
def test_player_content_rejects_non_pan_url(self):
self.assertEqual(
self.spider.playerContent("site", "/vodplay/1-1-1.html", {}),
{"parse": 0, "playUrl": "", "url": ""},
)
py/玩偶哥哥.py
+265
View File
@@ -0,0 +1,265 @@
# coding=utf-8
import re
import sys
from urllib.parse import quote, urljoin
from base.spider import Spider as BaseSpider
sys.path.append("..")
class Spider(BaseSpider):
def __init__(self):
self.name = "玩偶哥哥"
self.host = "http://wogg.xxooo.cf"
self.headers = {
"User-Agent": (
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
"AppleWebKit/537.36 (KHTML, like Gecko) "
"Chrome/136.0.0.0 Safari/537.36"
),
"Referer": self.host + "/",
}
self.categories = [
{"type_id": "1", "type_name": "玩偶电影"},
{"type_id": "2", "type_name": "玩偶剧集"},
{"type_id": "3", "type_name": "玩偶动漫"},
{"type_id": "4", "type_name": "玩偶综艺"},
{"type_id": "44", "type_name": "臻彩视界"},
{"type_id": "6", "type_name": "玩偶短剧"},
{"type_id": "5", "type_name": "玩偶音乐"},
{"type_id": "46", "type_name": "玩偶纪录"},
]
self.pan_patterns = [
("baidu", "百度资源", r"pan\.baidu\.com|yun\.baidu\.com"),
("a139", "139资源", r"yun\.139\.com"),
("a189", "天翼资源", r"cloud\.189\.cn"),
("a123", "123资源", r"123684\.com|123865\.com|123912\.com|123pan\.com"),
("a115", "115资源", r"115\.com"),
("quark", "夸克资源", r"pan\.quark\.cn"),
("xunlei", "迅雷资源", r"pan\.xunlei\.com"),
("aliyun", "阿里资源", r"aliyundrive\.com|alipan\.com"),
("uc", "UC资源", r"drive\.uc\.cn"),
]
self.pan_priority = {
"baidu": 1,
"a139": 2,
"a189": 3,
"a123": 4,
"a115": 5,
"quark": 6,
"xunlei": 7,
"aliyun": 8,
"uc": 9,
}
def init(self, extend=""):
return None
def getName(self):
return self.name
def homeContent(self, filter):
return {"class": self.categories}
def homeVideoContent(self):
return {"list": []}
def _build_url(self, path):
return urljoin(self.host + "/", str(path or "").strip())
def _fix_img_url(self, img_url):
raw = str(img_url or "").strip()
if not raw:
return ""
if raw.startswith("/db.php?url="):
return self._build_url(raw)
if re.search(r"^https?://[^/]*gimg\d*\.baidu\.com/gimg/", raw, re.I) and "src=data:image/" in raw:
return ""
return raw
def _detect_pan_type(self, url):
raw = str(url or "").strip()
for pan_type, title, pattern in self.pan_patterns:
if re.search(pattern, raw, re.I):
return pan_type, title
return "", ""
def _clean_text(self, text):
return re.sub(r"\s+", " ", str(text or "").replace("\xa0", " ")).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 _page_result(self, items, pg):
page = int(pg)
return {"page": page, "limit": len(items), "total": page * 20 + len(items), "list": items}
def _parse_cards(self, html):
root = self.html(html)
if root is None:
return []
items = []
seen = set()
for node in root.xpath("//*[@id='main']//*[contains(@class,'module-item')]"):
href = "".join(node.xpath(".//*[contains(@class,'module-item-pic')]//a[1]/@href")).strip()
title = "".join(node.xpath(".//*[contains(@class,'module-item-pic')]//img[1]/@alt")).strip()
pic = (
"".join(node.xpath(".//*[contains(@class,'module-item-pic')]//img[1]/@data-src")).strip()
or "".join(node.xpath(".//*[contains(@class,'module-item-pic')]//img[1]/@src")).strip()
)
remarks = self._clean_text("".join(node.xpath(".//*[contains(@class,'module-item-text')][1]//text()")))
if not href or not title or href in seen:
continue
seen.add(href)
items.append(
{
"vod_id": href,
"vod_name": title,
"vod_pic": self._build_url(self._fix_img_url(pic)),
"vod_remarks": remarks,
}
)
return items
def categoryContent(self, tid, pg, filter, extend):
url = self._build_url(f"/vodshow/{tid}--------{int(pg)}---.html")
return self._page_result(self._parse_cards(self._request_html(url)), pg)
def searchContent(self, key, quick, pg="1"):
keyword = self._clean_text(key)
page = int(pg)
if not keyword:
return {"page": page, "total": 0, "list": []}
url = self._build_url(f"/vodsearch/-------------.html?wd={quote(keyword)}&page={page}")
root = self.html(self._request_html(url))
if root is None:
return {"page": page, "total": 0, "list": []}
items = []
for node in root.xpath("//*[contains(@class,'module-search-item')]"):
href = "".join(node.xpath(".//*[contains(@class,'video-serial')][1]/@href")).strip()
title = "".join(node.xpath(".//*[contains(@class,'video-serial')][1]/@title")).strip()
pic = (
"".join(node.xpath(".//*[contains(@class,'module-item-pic')]//img[1]/@data-src")).strip()
or "".join(node.xpath(".//*[contains(@class,'module-item-pic')]//img[1]/@src")).strip()
)
remarks = self._clean_text(
"".join(node.xpath(".//*[contains(@class,'video-serial')][1]//text()"))
or "".join(node.xpath(".//*[contains(@class,'module-item-text')][1]//text()"))
)
if not href or not title:
continue
items.append(
{
"vod_id": href,
"vod_name": title,
"vod_pic": self._build_url(self._fix_img_url(pic)),
"vod_remarks": remarks,
}
)
return {"page": page, "total": len(items), "list": items}
def _parse_detail_page(self, vod_id, html):
root = self.html(html)
if root is None:
return {
"vod_id": vod_id,
"vod_name": "",
"vod_pic": "",
"vod_year": "",
"vod_director": "",
"vod_actor": "",
"vod_content": "",
"pan_urls": [],
}
detail = {
"vod_id": vod_id,
"vod_name": self._clean_text("".join(root.xpath("//*[contains(@class,'page-title')][1]//text()"))),
"vod_pic": self._build_url(
self._fix_img_url(
"".join(
root.xpath(
"//*[contains(@class,'mobile-play')]//*[contains(@class,'lazyload')][1]/@data-src | "
"//*[contains(@class,'mobile-play')]//*[contains(@class,'lazyload')][1]/@src"
)
).strip()
)
),
"vod_year": "",
"vod_director": "",
"vod_actor": "",
"vod_content": "",
"pan_urls": [],
}
for label_node in root.xpath("//*[contains(@class,'video-info-itemtitle')]"):
key = self._clean_text("".join(label_node.xpath(".//text()")))
sibling = label_node.getnext()
if sibling is None:
continue
values = [self._clean_text(text) for text in sibling.xpath(".//a//text()")]
joined = ",".join([value for value in values if value])
text_value = self._clean_text("".join(sibling.xpath(".//text()")))
if "年代" in key:
detail["vod_year"] = joined or text_value
elif "导演" in key:
detail["vod_director"] = joined or text_value
elif "主演" in key:
detail["vod_actor"] = joined or text_value
elif "剧情" in key:
detail["vod_content"] = text_value
pan_urls = []
for node in root.xpath("//*[contains(@class,'module-row-info')]//p"):
text = self._clean_text("".join(node.xpath(".//text()")))
if text:
pan_urls.append(text)
detail["pan_urls"] = pan_urls
return detail
def _build_pan_lines(self, detail):
lines = []
seen = set()
for url in detail.get("pan_urls", []):
pan_type, title = self._detect_pan_type(url)
if not pan_type or url in seen:
continue
seen.add(url)
lines.append((self.pan_priority.get(pan_type, 999), f"{pan_type}#玩偶哥哥", f"{title}${url}"))
lines.sort(key=lambda item: item[0])
return [(item[1], item[2]) for item in lines]
def detailContent(self, ids):
result = {"list": []}
for raw_id in ids:
vod_id = str(raw_id or "").strip()
detail = self._parse_detail_page(vod_id, self._request_html(self._build_url(vod_id)))
lines = self._build_pan_lines(detail)
result["list"].append(
{
"vod_id": vod_id,
"vod_name": detail["vod_name"],
"vod_pic": detail["vod_pic"],
"vod_year": detail["vod_year"],
"vod_director": detail["vod_director"],
"vod_actor": detail["vod_actor"],
"vod_content": detail["vod_content"],
"vod_play_from": "$$$".join([item[0] for item in lines]),
"vod_play_url": "$$$".join([item[1] for item in lines]),
}
)
return result
def playerContent(self, flag, id, vipFlags):
pan_type, _ = self._detect_pan_type(id)
if pan_type:
return {"parse": 0, "playUrl": "", "url": id}
return {"parse": 0, "playUrl": "", "url": ""}