更新源 202607010650
This commit is contained in:
github-actions[bot]
+2
-3
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"spider": "./jar/spider.jar;md5;5a5c64f87f0b0066919fa9b499912e4e",
|
"spider": "./jar/spider.jar;md5;feb3dd35be7c31aa2a39bea423961279",
|
||||||
"lives": [
|
"lives": [
|
||||||
{"name": "live","boot": false,"type": 0,"url": "./tv.txt","playerType": 2,"ua": "okhttp/3.8.1","timeout": 20,"epg": "https://epg.cdn.loc.cc/?ch={name}&date={date}","logo": "https://logo.wyfc.qzz.io/{name}.png"}
|
{"name": "live","boot": false,"type": 0,"url": "./tv.txt","playerType": 2,"ua": "okhttp/3.8.1","timeout": 20,"epg": "https://epg.cdn.loc.cc/?ch={name}&date={date}","logo": "https://logo.wyfc.qzz.io/{name}.png"}
|
||||||
],
|
],
|
||||||
@@ -97,9 +97,8 @@
|
|||||||
{"key": "百度网盘","name": "百度 • 网盘","type": 3,"api": "csp_PanBaidu","searchable": 0,"filterable": 0,"changeable": 0,"style": {"type": "list","ratio": 1.433}},
|
{"key": "百度网盘","name": "百度 • 网盘","type": 3,"api": "csp_PanBaidu","searchable": 0,"filterable": 0,"changeable": 0,"style": {"type": "list","ratio": 1.433}},
|
||||||
{"key": "盘搜","name": "盘搜 • 搜索","type": 3,"api": "csp_PanSou","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
{"key": "盘搜","name": "盘搜 • 搜索","type": 3,"api": "csp_PanSou","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
||||||
{"key": "古哥","name": "古哥 • 搜索","type": 3,"api": "csp_GugeSo","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
{"key": "古哥","name": "古哥 • 搜索","type": 3,"api": "csp_GugeSo","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
||||||
{"key": "兄弟","name": "兄弟 • 搜索","type": 3,"api": "csp_XiongdiPan","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
|
||||||
{"key": "百酷","name": "百酷 • 搜索","type": 3,"api": "csp_Baiku","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
{"key": "百酷","name": "百酷 • 搜索","type": 3,"api": "csp_Baiku","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
||||||
{"key": "米搜","name": "米搜 • 搜索","type": 3,"api": "csp_MiSou","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
{"key": "米搜","name": "米搜 • 搜索","type": 3,"api": "csp_MiSou","searchable": 1,"quickSearch": 0,"filterable": 0,"ext": {"site": ["https://misoso.shop","http://www.misoso.shop"]},"timeout": 60},
|
||||||
{"key": "鬼鬼","name": "鬼鬼 • 搜索","type": 3,"api": "csp_GuiGui","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
{"key": "鬼鬼","name": "鬼鬼 • 搜索","type": 3,"api": "csp_GuiGui","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
||||||
{"key": "混合","name": "混合 • 搜索","type": 3,"api": "csp_HunHePan","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
{"key": "混合","name": "混合 • 搜索","type": 3,"api": "csp_HunHePan","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
||||||
{"key": "天翼","name": "天翼 • 搜索","type": 3,"api": "csp_TianYiSou","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
{"key": "天翼","name": "天翼 • 搜索","type": 3,"api": "csp_TianYiSou","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
||||||
|
|||||||
Binary file not shown.
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"spider": "./jar/spider.jar;md5;5a5c64f87f0b0066919fa9b499912e4e",
|
"spider": "./jar/spider.jar;md5;feb3dd35be7c31aa2a39bea423961279",
|
||||||
"lives": [
|
"lives": [
|
||||||
{"name": "migu","type": 0,"url": "https://develop202.github.io/migu_video/interface.txt","playerType": 1,"ua": "okhttp/3.8.1","timeout": 20,"epg": "https://epg.cdn.loc.cc/?ch={name}&date={date}","logo": "https://logo.wyfc.qzz.io/{name}.png"},
|
{"name": "migu","type": 0,"url": "https://develop202.github.io/migu_video/interface.txt","playerType": 1,"ua": "okhttp/3.8.1","timeout": 20,"epg": "https://epg.cdn.loc.cc/?ch={name}&date={date}","logo": "https://logo.wyfc.qzz.io/{name}.png"},
|
||||||
{"name": "live","type": 0,"url": "https://epg.pw/test_channels.m3u","playerType": 1,"ua": "okhttp/3.8.1","timeout": 20,"epg": "https://epg.cdn.loc.cc/?ch={name}&date={date}","logo": "https://logo.wyfc.qzz.io/{name}.png"},
|
{"name": "live","type": 0,"url": "https://epg.pw/test_channels.m3u","playerType": 1,"ua": "okhttp/3.8.1","timeout": 20,"epg": "https://epg.cdn.loc.cc/?ch={name}&date={date}","logo": "https://logo.wyfc.qzz.io/{name}.png"},
|
||||||
@@ -98,9 +98,8 @@
|
|||||||
{"key": "百度网盘","name": "百度 • 网盘","type": 3,"api": "csp_PanBaidu","searchable": 0,"filterable": 0,"changeable": 0,"style": {"type": "list","ratio": 1.433}},
|
{"key": "百度网盘","name": "百度 • 网盘","type": 3,"api": "csp_PanBaidu","searchable": 0,"filterable": 0,"changeable": 0,"style": {"type": "list","ratio": 1.433}},
|
||||||
{"key": "盘搜","name": "盘搜 • 搜索","type": 3,"api": "csp_PanSou","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
{"key": "盘搜","name": "盘搜 • 搜索","type": 3,"api": "csp_PanSou","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
||||||
{"key": "古哥","name": "古哥 • 搜索","type": 3,"api": "csp_GugeSo","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
{"key": "古哥","name": "古哥 • 搜索","type": 3,"api": "csp_GugeSo","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
||||||
{"key": "兄弟","name": "兄弟 • 搜索","type": 3,"api": "csp_XiongdiPan","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
|
||||||
{"key": "百酷","name": "百酷 • 搜索","type": 3,"api": "csp_Baiku","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
{"key": "百酷","name": "百酷 • 搜索","type": 3,"api": "csp_Baiku","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
||||||
{"key": "米搜","name": "米搜 • 搜索","type": 3,"api": "csp_MiSou","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
{"key": "米搜","name": "米搜 • 搜索","type": 3,"api": "csp_MiSou","searchable": 1,"quickSearch": 0,"filterable": 0,"ext": {"site": ["https://misoso.shop","http://www.misoso.shop"]},"timeout": 60},
|
||||||
{"key": "鬼鬼","name": "鬼鬼 • 搜索","type": 3,"api": "csp_GuiGui","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
{"key": "鬼鬼","name": "鬼鬼 • 搜索","type": 3,"api": "csp_GuiGui","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
||||||
{"key": "混合","name": "混合 • 搜索","type": 3,"api": "csp_HunHePan","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
{"key": "混合","name": "混合 • 搜索","type": 3,"api": "csp_HunHePan","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
||||||
{"key": "天翼","name": "天翼 • 搜索","type": 3,"api": "csp_TianYiSou","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
{"key": "天翼","name": "天翼 • 搜索","type": 3,"api": "csp_TianYiSou","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
||||||
|
|||||||
+502
-240
@@ -1,240 +1,502 @@
|
|||||||
import re
|
# -*- coding: utf-8 -*-
|
||||||
import sys
|
# 修复：歌手不显示歌手图片
|
||||||
from base64 import b64encode, b64decode
|
# by：垃圾星河
|
||||||
from urllib.parse import quote, unquote
|
# 代码指导：嗷呜呜呜呜
|
||||||
from pyquery import PyQuery as pq
|
# 增加：自动人机验证绕过
|
||||||
from requests import Session, adapters
|
|
||||||
from urllib3.util.retry import Retry
|
import re
|
||||||
from concurrent.futures import ThreadPoolExecutor, as_completed
|
import sys
|
||||||
sys.path.append('..')
|
import time
|
||||||
from base.spider import Spider
|
from base64 import b64encode, b64decode
|
||||||
|
from urllib.parse import quote, unquote
|
||||||
class Spider(Spider):
|
from pyquery import PyQuery as pq
|
||||||
def init(self, extend=""):
|
from requests import Session, adapters
|
||||||
self.host = "https://www.22a5.com"
|
from urllib3.util.retry import Retry
|
||||||
self.session = Session()
|
from concurrent.futures import ThreadPoolExecutor, as_completed
|
||||||
adapter = adapters.HTTPAdapter(max_retries=Retry(total=3, backoff_factor=0.5, status_forcelist=[429, 500, 502, 503, 504]), pool_connections=20, pool_maxsize=50)
|
|
||||||
self.session.mount("http://", adapter)
|
sys.path.append('..')
|
||||||
self.session.mount("https://", adapter)
|
from base.spider import Spider
|
||||||
self.headers = {"User-Agent": "Mozilla/5.0 (Linux; Android 10; K) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Mobile Safari/537.36"}
|
|
||||||
self.session.headers.update(self.headers)
|
|
||||||
|
class Spider(Spider):
|
||||||
def getName(self): return "爱听音乐"
|
def init(self, extend=""):
|
||||||
def isVideoFormat(self, url): return bool(re.search(r'\.(m3u8|mp4|mp3|m4a|flv)(\?|$)', url or "", re.I))
|
self.host = "https://www.22a5.com"
|
||||||
def manualVideoCheck(self): return False
|
self.session = Session()
|
||||||
def destroy(self): self.session.close()
|
adapter = adapters.HTTPAdapter(
|
||||||
|
max_retries=Retry(total=3, backoff_factor=0.5, status_forcelist=[429, 500, 502, 503, 504]),
|
||||||
def homeContent(self, filter):
|
pool_connections=20,
|
||||||
classes = [{"type_name": n, "type_id": i} for n, i in [("歌手","/singerlist/index/index/index/index.html"), ("TOP榜单","/list/top.html"), ("新歌榜","/list/new.html"), ("电台","/radiolist/index.html"), ("高清MV","/mvlist/oumei.html"), ("专辑","/albumlist/index.html"), ("歌单","/playtype/index.html")]]
|
pool_maxsize=50
|
||||||
filters = {p: d for p in [c["type_id"] for c in classes if "singer" not in c["type_id"]] if (d := self._fetch_filters(p))}
|
)
|
||||||
|
self.session.mount("http://", adapter)
|
||||||
if "/radiolist/index.html" not in filters:
|
self.session.mount("https://", adapter)
|
||||||
filters["/radiolist/index.html"] = [{"key": "id", "name": "分类", "value": [{"n": n, "v": v} for n,v in zip(["最新","最热","有声小说","相声","音乐","情感","国漫","影视","脱口秀","历史","儿童","教育","八卦","推理","头条"], ["index","hot","novel","xiangyi","music","emotion","game","yingshi","talkshow","history","children","education","gossip","tuili","headline"])]}]
|
self.headers = {
|
||||||
|
"User-Agent": "Mozilla/5.0 (Linux; Android 10; K) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Mobile Safari/537.36"
|
||||||
filters["/singerlist/index/index/index/index.html"] = [
|
}
|
||||||
{"key": "area", "name": "地区", "value": [{"n": n, "v": v} for n,v in [("全部","index"),("华语","huayu"),("欧美","oumei"),("韩国","hanguo"),("日本","ribrn")]]},
|
self.session.headers.update(self.headers)
|
||||||
{"key": "sex", "name": "性别", "value": [{"n": n, "v": v} for n,v in [("全部","index"),("男","male"),("女","girl"),("组合","band")]]},
|
|
||||||
{"key": "genre", "name": "流派", "value": [{"n": n, "v": v} for n,v in [("全部","index"),("流行","liuxing"),("电子","dianzi"),("摇滚","yaogun"),("嘻哈","xiha"),("R&B","rb"),("民谣","minyao"),("爵士","jueshi"),("古典","gudian")]]},
|
def getName(self):
|
||||||
{"key": "char", "name": "字母", "value": [{"n": n, "v": v} for n,v in [("全部","index")] + [{"n": chr(i), "v": chr(i).lower()} for i in range(65, 91)]]}
|
return "爱听音乐"
|
||||||
]
|
|
||||||
return {"class": classes, "filters": filters, "list": []}
|
def isVideoFormat(self, url):
|
||||||
|
return bool(re.search(r'\.(m3u8|mp4|mp3|m4a|flv)(\?|$)', url or "", re.I))
|
||||||
def homeVideoContent(self): return {"list": []}
|
|
||||||
|
def manualVideoCheck(self):
|
||||||
def categoryContent(self, tid, pg, filter, extend):
|
return False
|
||||||
pg = int(pg or 1)
|
|
||||||
url = tid
|
def destroy(self):
|
||||||
if "/singerlist/" in tid:
|
self.session.close()
|
||||||
p = tid.split('/')
|
|
||||||
if len(p) >= 6:
|
# ==================== 新增人机验证绕过 ====================
|
||||||
url = "/".join(p[:2] + [extend.get(k, p[i]) for i, k in enumerate(["area", "sex", "genre"], 2)] + [f"{extend.get('char', 'index')}.html"])
|
|
||||||
elif "id" in extend and extend["id"] not in ["index", "top"]:
|
def _bypass_verification(self, url, response_text):
|
||||||
url = tid.replace("index.html", f"{extend['id']}.html").replace("top.html", f"{extend['id']}.html")
|
"""若当前页面是人机验证，自动提交勾选"""
|
||||||
if url == tid: url = f"{tid.rsplit('/', 1)[0]}/{extend['id']}.html"
|
if '安全人机验证' not in response_text and 'human_check' not in response_text:
|
||||||
|
return None
|
||||||
if pg > 1:
|
|
||||||
sep = "/" if any(x in url for x in ["/singerlist/", "/radiolist/", "/mvlist/", "/playtype/", "/list/"]) else "_"
|
# 提取 csrf_token（支持多种格式）
|
||||||
url = re.sub(r'(_\d+|/\d+)?\.html$', f'{sep}{pg}.html', url)
|
token_match = re.search(r'name="csrf_token"\s+value="([^"]+)"', response_text)
|
||||||
|
if not token_match:
|
||||||
doc = self.getpq(url)
|
print("[爱听音乐] 未找到 csrf_token，跳过绕过")
|
||||||
return {"list": self._parse_list(doc(".play_list li, .video_list li, .pic_list li, .singer_list li, .ali li, .layui-row li, .base_l li"), tid), "page": pg, "pagecount": 9999, "limit": 90, "total": 999999}
|
return None
|
||||||
|
token = token_match.group(1)
|
||||||
def searchContent(self, key, quick, pg="1"):
|
|
||||||
return {"list": self._parse_list(self.getpq(f"/so/{quote(key)}/{pg}.html")(".base_l li, .play_list li"), "search"), "page": int(pg)}
|
# 构造提交数据
|
||||||
|
data = {
|
||||||
def detailContent(self, ids):
|
'csrf_token': token,
|
||||||
url = self._abs(ids[0])
|
'human_check': 'on'
|
||||||
doc = self.getpq(url)
|
}
|
||||||
vod = {"vod_id": url, "vod_name": self._clean(doc("h1").text() or doc("title").text()), "vod_pic": self._abs(doc(".djpg img, .pic img, .djpic img").attr("src")), "vod_play_from": "爱听音乐", "vod_content": ""}
|
|
||||||
|
try:
|
||||||
if any(x in url for x in ["/playlist/", "/album/", "/list/", "/singer/", "/special/", "/radio/", "/radiolist/"]):
|
# 发送 POST 请求，自动跟随重定向
|
||||||
eps = self._get_eps(doc)
|
post_resp = self.session.post(url, data=data, allow_redirects=True, timeout=10)
|
||||||
page_urls = {self._abs(a.attr("href")) for a in doc(".page a, .dede_pages a, .pagelist a").items() if a.attr("href") and "javascript" not in a.attr("href")} - {url}
|
print("[爱听音乐] 人机验证已绕过")
|
||||||
if page_urls:
|
return post_resp
|
||||||
with ThreadPoolExecutor(max_workers=5) as ex:
|
except Exception as e:
|
||||||
for r in as_completed([ex.submit(lambda u: self._get_eps(self.getpq(u)), u) for u in sorted(page_urls, key=lambda x: int(re.search(r'[_\/](\d+)\.html', x).group(1)) if re.search(r'[_\/](\d+)\.html', x) else 0)]):
|
print(f"[爱听音乐] 人机验证提交失败: {e}")
|
||||||
eps.extend(r.result() or [])
|
return None
|
||||||
if eps:
|
|
||||||
vod.update({"vod_play_from": "播放列表", "vod_play_url": "#".join(eps)})
|
def getpq(self, url):
|
||||||
return {"list": [vod]}
|
"""获取页面并自动处理人机验证（重试3次）"""
|
||||||
|
full_url = self._abs(url)
|
||||||
play_list = []
|
|
||||||
if mid := re.search(r'/(song|mp3|radio|radiolist|radioplay)/([^/]+)\.html', url):
|
for attempt in range(3):
|
||||||
lrc_url = f"{self.host}/plug/down.php?ac=music&lk=lrc&id={mid.group(2)}"
|
try:
|
||||||
play_list = [f"播放${self.e64('0@@@@' + url + '|||' + lrc_url)}"]
|
resp = self.session.get(full_url, timeout=5)
|
||||||
|
|
||||||
elif vid := re.search(r'/(video|mp4)/([^/]+)\.html', url):
|
# 若遇到验证页，尝试绕过
|
||||||
with ThreadPoolExecutor(max_workers=3) as ex:
|
if '安全人机验证' in resp.text or 'human_check' in resp.text:
|
||||||
fs = {ex.submit(self._api, "/plug/down.php", {"ac": "vplay", "id": vid.group(2), "q": q}): n for n, q in [("蓝光", 1080), ("超清", 720), ("高清", 480)]}
|
print("[爱听音乐] 检测到人机验证，尝试自动绕过...")
|
||||||
play_list = [f"{fs[f]}${self.e64('0@@@@'+u)}" for f in as_completed(fs) if (u := f.result())]
|
bypass_resp = self._bypass_verification(full_url, resp.text)
|
||||||
play_list.sort(key=lambda x: {"蓝":0, "超":1, "高":2}.get(x[0], 3))
|
if bypass_resp:
|
||||||
|
# 验证成功后，返回最终页面（可能是重定向后的目标）
|
||||||
vod["vod_play_url"] = "#".join(play_list) if play_list else f"解析失败${self.e64('1@@@@'+url)}"
|
return pq(bypass_resp.text)
|
||||||
return {"list": [vod]}
|
else:
|
||||||
|
# 绕过失败，等待后重试
|
||||||
def playerContent(self, flag, id, vipFlags):
|
time.sleep(1)
|
||||||
raw = self.d64(id).split("@@@@")[-1]
|
continue
|
||||||
url, subt = raw.split("|||") if "|||" in raw else (raw, "")
|
else:
|
||||||
url = url.replace(r"\/", "/")
|
# 正常页面直接返回
|
||||||
|
return pq(resp.text)
|
||||||
if ".html" in url and not self.isVideoFormat(url):
|
|
||||||
if mid := re.search(r'/(song|mp3|radio|radiolist|radioplay)/([^/]+)\.html', url):
|
except Exception as e:
|
||||||
if r_url := self._api("/js/play.php", method="POST", data={"id": mid.group(2), "type": "music"}, headers={"Referer": url.replace("http://","https://"), "X-Requested-With": "XMLHttpRequest"}):
|
print(f"[爱听音乐] 请求失败 (尝试 {attempt+1}/3): {e}")
|
||||||
url = r_url if ".php" not in r_url else url
|
time.sleep(0.5 * (attempt + 1))
|
||||||
elif vid := re.search(r'/(video|mp4)/([^/]+)\.html', url):
|
|
||||||
with ThreadPoolExecutor(max_workers=3) as ex:
|
# 全部失败，返回空文档
|
||||||
for f in as_completed([ex.submit(self._api, "/plug/down.php", {"ac": "vplay", "id": vid.group(2), "q": q}) for q in [1080, 720, 480]]):
|
return pq("<html></html>")
|
||||||
if v_url := f.result():
|
|
||||||
url = v_url; break
|
# ==================== 原有功能（保持不变） ====================
|
||||||
|
|
||||||
result = {"parse": 0, "url": url, "header": {"User-Agent": self.headers["User-Agent"]}}
|
def homeContent(self, filter):
|
||||||
if "22a5.com" in url: result["header"]["Referer"] = self.host + "/"
|
classes = [
|
||||||
|
{"type_name": n, "type_id": i}
|
||||||
# OK影视3.6.5+支持LRC格式滚动歌词
|
for n, i in [
|
||||||
if subt:
|
("歌手", "/singerlist/index/index/index/index.html"),
|
||||||
try:
|
("TOP榜单", "/list/top.html"),
|
||||||
r = self.session.get(subt, headers={"Referer": self.host + "/"}, timeout=5)
|
("新歌榜", "/list/new.html"),
|
||||||
lrc_content = r.text
|
("电台", "/radiolist/index.html"),
|
||||||
if lrc_content:
|
("高清MV", "/mvlist/oumei.html"),
|
||||||
# 过滤广告内容
|
("专辑", "/albumlist/index.html"),
|
||||||
lrc_content = self._filter_lrc_ads(lrc_content)
|
("歌单", "/playtype/index.html")
|
||||||
result["lrc"] = lrc_content
|
]
|
||||||
except:
|
]
|
||||||
pass
|
filters = {}
|
||||||
|
for p in [c["type_id"] for c in classes if "singer" not in c["type_id"]]:
|
||||||
return result
|
d = self._fetch_filters(p)
|
||||||
|
if d:
|
||||||
def _filter_lrc_ads(self, lrc_text):
|
filters[p] = d
|
||||||
"""过滤LRC歌词中的广告内容"""
|
|
||||||
lines = lrc_text.splitlines()
|
if "/radiolist/index.html" not in filters:
|
||||||
filtered_lines = []
|
filters["/radiolist/index.html"] = [{
|
||||||
|
"key": "id",
|
||||||
# 广告关键词模式
|
"name": "分类",
|
||||||
ad_patterns = [
|
"value": [
|
||||||
r'欢迎来访.*',
|
{"n": n, "v": v}
|
||||||
r'本站.*',
|
for n, v in zip(
|
||||||
r'.*广告.*',
|
["最新", "最热", "有声小说", "相声", "音乐", "情感", "国漫", "影视", "脱口秀", "历史", "儿童", "教育", "八卦", "推理", "头条"],
|
||||||
r'QQ群.*',
|
["index", "hot", "novel", "xiangyi", "music", "emotion", "game", "yingshi", "talkshow", "history",
|
||||||
r'.*www\..*',
|
"children", "education", "gossip", "tuili", "headline"]
|
||||||
r'.*http.*',
|
)
|
||||||
r'.*\.com.*',
|
]
|
||||||
r'.*\.cn.*',
|
}]
|
||||||
r'.*\.net.*',
|
|
||||||
r'.*音乐网.*',
|
filters["/singerlist/index/index/index/index.html"] = [
|
||||||
r'.*提供.*',
|
{
|
||||||
r'.*下载.*',
|
"key": "area",
|
||||||
]
|
"name": "地区",
|
||||||
|
"value": [
|
||||||
for line in lines:
|
{"n": "全部", "v": "index"},
|
||||||
# 保留时间标签行，但过滤掉广告文本
|
{"n": "华语", "v": "huayu"},
|
||||||
if re.match(r'\[\d{2}:\d{2}', line):
|
{"n": "欧美", "v": "oumei"},
|
||||||
# 检查是否包含广告
|
{"n": "韩国", "v": "hanguo"},
|
||||||
is_ad = False
|
{"n": "日本", "v": "ribrn"}
|
||||||
for pattern in ad_patterns:
|
]
|
||||||
if re.search(pattern, line, re.IGNORECASE):
|
},
|
||||||
is_ad = True
|
{
|
||||||
break
|
"key": "sex",
|
||||||
|
"name": "性别",
|
||||||
if not is_ad:
|
"value": [
|
||||||
filtered_lines.append(line)
|
{"n": "全部", "v": "index"},
|
||||||
else:
|
{"n": "男", "v": "male"},
|
||||||
# 非时间标签行（可能是元数据），保留
|
{"n": "女", "v": "girl"},
|
||||||
filtered_lines.append(line)
|
{"n": "组合", "v": "band"}
|
||||||
|
]
|
||||||
return '\n'.join(filtered_lines)
|
},
|
||||||
|
{
|
||||||
def localProxy(self, param):
|
"key": "genre",
|
||||||
url = unquote(param.get("url", ""))
|
"name": "流派",
|
||||||
type_ = param.get("type")
|
"value": [
|
||||||
|
{"n": "全部", "v": "index"},
|
||||||
if type_ == "img":
|
{"n": "流行", "v": "liuxing"},
|
||||||
return [200, "image/jpeg", self.session.get(url, headers={"Referer": self.host + "/"}, timeout=5).content, {}]
|
{"n": "电子", "v": "dianzi"},
|
||||||
|
{"n": "摇滚", "v": "yaogun"},
|
||||||
elif type_ == "lrc":
|
{"n": "嘻哈", "v": "xiha"},
|
||||||
try:
|
{"n": "R&B", "v": "rb"},
|
||||||
r = self.session.get(url, headers={"Referer": self.host + "/"}, timeout=5)
|
{"n": "民谣", "v": "minyao"},
|
||||||
# 同时过滤代理中的广告
|
{"n": "爵士", "v": "jueshi"},
|
||||||
lrc_content = r.text
|
{"n": "古典", "v": "gudian"}
|
||||||
lrc_content = self._filter_lrc_ads(lrc_content)
|
]
|
||||||
return [200, "application/octet-stream", lrc_content.encode('utf-8'), {}]
|
}
|
||||||
except:
|
]
|
||||||
return [404, "text/plain", "Error", {}]
|
return {"class": classes, "filters": filters, "list": []}
|
||||||
|
|
||||||
return None
|
def homeVideoContent(self):
|
||||||
|
return {"list": []}
|
||||||
def _parse_list(self, items, tid=""):
|
|
||||||
res = []
|
def categoryContent(self, tid, pg, filter, extend):
|
||||||
for li in items.items():
|
pg = int(pg or 1)
|
||||||
a = li("a").eq(0)
|
url = tid
|
||||||
if not (href := a.attr("href")) or href == "/" or any(x in href for x in ["/user/", "/login/", "javascript"]): continue
|
if "/singerlist/" in tid:
|
||||||
if not (name := self._clean(li(".name").text() or a.attr("title") or a.text())): continue
|
parts = tid.split('/')
|
||||||
pic = self._abs((li("img").attr("src") or "").replace('120', '500'))
|
if len(parts) >= 6:
|
||||||
res.append({"vod_id": self._abs(href), "vod_name": name, "vod_pic": f"{self.getProxyUrl()}&url={pic}&type=img" if pic else "", "style": {"type": "oval" if "/singer/" in href else ("list" if any(x in tid for x in ["/list/", "/playtype/", "/albumlist/"]) else "rect"), "ratio": 1 if "/singer/" in href else 1.33}})
|
url = "/".join(parts[:2] + [extend.get(k, parts[i]) for i, k in enumerate(["area", "sex", "genre"], 2)] +
|
||||||
return res
|
[f"{extend.get('char', 'index')}.html"])
|
||||||
|
elif "id" in extend and extend["id"] not in ["index", "top"]:
|
||||||
def _get_eps(self, doc):
|
url = tid.replace("index.html", f"{extend['id']}.html").replace("top.html", f"{extend['id']}.html")
|
||||||
eps = []
|
if url == tid:
|
||||||
for li in doc(".play_list li, .song_list li, .music_list li").items():
|
url = f"{tid.rsplit('/', 1)[0]}/{extend['id']}.html"
|
||||||
if not (a := li("a").eq(0)).attr("href") or not re.search(r'/(song|mp3|radio|radiolist|radioplay)/([^/]+)\.html', a.attr("href")): continue
|
|
||||||
full_url = self._abs(a.attr("href"))
|
if pg > 1:
|
||||||
|
sep = "/" if any(x in url for x in ["/singerlist/", "/radiolist/", "/mvlist/", "/playtype/", "/list/"]) else "_"
|
||||||
lrc_part = ""
|
url = re.sub(r'(_\d+|/\d+)?\.html$', f'{sep}{pg}.html', url)
|
||||||
mid = re.search(r'/(song|mp3|radio|radiolist|radioplay)/([^/]+)\.html', full_url)
|
|
||||||
if mid:
|
doc = self.getpq(url)
|
||||||
lrc_url = f"{self.host}/plug/down.php?ac=music&lk=lrc&id={mid.group(2)}"
|
items = doc(".play_list li, .video_list li, .pic_list li, .singer_list li, .ali li, .layui-row li, .base_l li")
|
||||||
lrc_part = f"|||{lrc_url}"
|
return {
|
||||||
|
"list": self._parse_list(items, tid),
|
||||||
eps.append(f"{self._clean(a.text() or li('.name').text())}${self.e64('0@@@@' + full_url + lrc_part)}")
|
"page": pg,
|
||||||
return eps
|
"pagecount": 9999,
|
||||||
|
"limit": 90,
|
||||||
def _clean(self, text): return re.sub(r'(爱玩音乐网|视频下载说明|视频下载地址|www\.2t58\.com|MP3免费下载|LRC歌词下载|全部歌曲|\[第\d+页\]|刷新|每日推荐|最新|热门|推荐|MV|高清|无损)', '', text or "", flags=re.I).strip()
|
"total": 999999
|
||||||
|
}
|
||||||
def _fetch_filters(self, url):
|
|
||||||
doc, filters = self.getpq(url), []
|
def searchContent(self, key, quick, pg="1"):
|
||||||
for i, group in enumerate([doc(s) for s in [".ilingku_fl", ".class_list", ".screen_list", ".box_list", ".nav_list"] if doc(s)]):
|
doc = self.getpq(f"/so/{quote(key)}/{pg}.html")
|
||||||
opts, seen = [{"n": "全部", "v": "top" if "top" in url else "index"}], set()
|
items = doc(".base_l li, .play_list li")
|
||||||
for a in group("a").items():
|
return {
|
||||||
if (v := (a.attr("href") or "").split("?")[0].rstrip('/').split('/')[-1].replace('.html','')) and v not in seen:
|
"list": self._parse_list(items, "search"),
|
||||||
opts.append({"n": a.text().strip(), "v": v}); seen.add(v)
|
"page": int(pg)
|
||||||
if len(opts) > 1: filters.append({"key": f"id{i}" if i else "id", "name": "分类", "value": opts})
|
}
|
||||||
return filters
|
|
||||||
|
def detailContent(self, ids):
|
||||||
def _api(self, path, params=None, method="GET", headers=None, data=None):
|
url = self._abs(ids[0])
|
||||||
try:
|
doc = self.getpq(url)
|
||||||
h = self.headers.copy()
|
vod = {
|
||||||
if headers: h.update(headers)
|
"vod_id": url,
|
||||||
r = (self.session.post if method == "POST" else self.session.get)(f"{self.host}{path}", params=params, data=data, headers=h, timeout=10, allow_redirects=False)
|
"vod_name": self._clean(doc("h1").text() or doc("title").text()),
|
||||||
if loc := r.headers.get("Location"): return self._abs(loc.strip())
|
"vod_pic": self._abs(doc(".djpg img, .pic img, .djpic img").attr("src")),
|
||||||
return self._abs(r.json().get("url", "").replace(r"\/", "/")) or (r.text.strip() if r.text.strip().startswith("http") else "")
|
"vod_play_from": "爱听音乐",
|
||||||
except: return ""
|
"vod_content": ""
|
||||||
|
}
|
||||||
def getpq(self, url):
|
|
||||||
import time
|
if any(x in url for x in ["/playlist/", "/album/", "/list/", "/singer/", "/special/", "/radio/", "/radiolist/"]):
|
||||||
for _ in range(2):
|
eps = self._get_eps(doc)
|
||||||
try: return pq(self.session.get(self._abs(url), timeout=5).text)
|
page_urls = {
|
||||||
except: time.sleep(0.1)
|
self._abs(a.attr("href"))
|
||||||
return pq("<html></html>")
|
for a in doc(".page a, .dede_pages a, .pagelist a").items()
|
||||||
|
if a.attr("href") and "javascript" not in a.attr("href")
|
||||||
def _abs(self, url): return url if url.startswith("http") else (f"{self.host}{'/' if not url.startswith('/') else ''}{url}" if url else "")
|
} - {url}
|
||||||
def e64(self, text): return b64encode(text.encode("utf-8")).decode("utf-8")
|
if page_urls:
|
||||||
def d64(self, text): return b64decode(text.encode("utf-8")).decode("utf-8")
|
with ThreadPoolExecutor(max_workers=5) as ex:
|
||||||
|
futures = []
|
||||||
|
for u in sorted(page_urls, key=lambda x: int(re.search(r'[_/](\d+)\.html', x).group(1)) if re.search(
|
||||||
|
r'[_/](\d+)\.html', x) else 0):
|
||||||
|
futures.append(ex.submit(lambda uu: self._get_eps(self.getpq(uu)), u))
|
||||||
|
for f in as_completed(futures):
|
||||||
|
eps.extend(f.result() or [])
|
||||||
|
if eps:
|
||||||
|
vod.update({
|
||||||
|
"vod_play_from": "播放列表",
|
||||||
|
"vod_play_url": "#".join(eps)
|
||||||
|
})
|
||||||
|
return {"list": [vod]}
|
||||||
|
|
||||||
|
play_list = []
|
||||||
|
if mid := re.search(r'/(song|mp3|radio|radiolist|radioplay)/([^/]+)\.html', url):
|
||||||
|
lrc_url = f"{self.host}/plug/down.php?ac=music&lk=lrc&id={mid.group(2)}"
|
||||||
|
play_list = [f"播放${self.e64('0@@@@' + url + '|||' + lrc_url)}"]
|
||||||
|
|
||||||
|
elif vid := re.search(r'/(video|mp4)/([^/]+)\.html', url):
|
||||||
|
with ThreadPoolExecutor(max_workers=3) as ex:
|
||||||
|
fs = {
|
||||||
|
ex.submit(self._api, "/plug/down.php", {"ac": "vplay", "id": vid.group(2), "q": q}): n
|
||||||
|
for n, q in [("蓝光", 1080), ("超清", 720), ("高清", 480)]
|
||||||
|
}
|
||||||
|
play_list = [f"{fs[f]}${self.e64('0@@@@'+u)}" for f in as_completed(fs) if (u := f.result())]
|
||||||
|
play_list.sort(key=lambda x: {"蓝": 0, "超": 1, "高": 2}.get(x[0], 3))
|
||||||
|
|
||||||
|
vod["vod_play_url"] = "#".join(play_list) if play_list else f"解析失败${self.e64('1@@@@'+url)}"
|
||||||
|
return {"list": [vod]}
|
||||||
|
|
||||||
|
def playerContent(self, flag, id, vipFlags):
|
||||||
|
raw = self.d64(id).split("@@@@")[-1]
|
||||||
|
url, subt = raw.split("|||") if "|||" in raw else (raw, "")
|
||||||
|
url = url.replace(r"\/", "/")
|
||||||
|
|
||||||
|
if ".html" in url and not self.isVideoFormat(url):
|
||||||
|
if mid := re.search(r'/(song|mp3|radio|radiolist|radioplay)/([^/]+)\.html', url):
|
||||||
|
if r_url := self._api("/js/play.php", method="POST", data={"id": mid.group(2), "type": "music"},
|
||||||
|
headers={"Referer": url.replace("http://", "https://"),
|
||||||
|
"X-Requested-With": "XMLHttpRequest"}):
|
||||||
|
url = r_url if ".php" not in r_url else url
|
||||||
|
elif vid := re.search(r'/(video|mp4)/([^/]+)\.html', url):
|
||||||
|
with ThreadPoolExecutor(max_workers=3) as ex:
|
||||||
|
for f in as_completed(
|
||||||
|
[ex.submit(self._api, "/plug/down.php", {"ac": "vplay", "id": vid.group(2), "q": q}) for q in
|
||||||
|
[1080, 720, 480]]):
|
||||||
|
if v_url := f.result():
|
||||||
|
url = v_url
|
||||||
|
break
|
||||||
|
|
||||||
|
result = {"parse": 0, "url": url, "header": {"User-Agent": self.headers["User-Agent"]}}
|
||||||
|
if "22a5.com" in url:
|
||||||
|
result["header"]["Referer"] = self.host + "/"
|
||||||
|
|
||||||
|
# OK影视3.6.5+支持LRC格式滚动歌词
|
||||||
|
if subt:
|
||||||
|
try:
|
||||||
|
r = self.session.get(subt, headers={"Referer": self.host + "/"}, timeout=5)
|
||||||
|
lrc_content = r.text
|
||||||
|
if lrc_content:
|
||||||
|
lrc_content = self._filter_lrc_ads(lrc_content)
|
||||||
|
result["lrc"] = lrc_content
|
||||||
|
except:
|
||||||
|
pass
|
||||||
|
|
||||||
|
return result
|
||||||
|
|
||||||
|
def _filter_lrc_ads(self, lrc_text):
|
||||||
|
"""过滤LRC歌词中的广告内容"""
|
||||||
|
lines = lrc_text.splitlines()
|
||||||
|
filtered_lines = []
|
||||||
|
|
||||||
|
# 广告关键词模式
|
||||||
|
ad_patterns = [
|
||||||
|
r'欢迎来访.*',
|
||||||
|
r'本站.*',
|
||||||
|
r'.*广告.*',
|
||||||
|
r'QQ群.*',
|
||||||
|
r'.*www\..*',
|
||||||
|
r'.*http.*',
|
||||||
|
r'.*\.com.*',
|
||||||
|
r'.*\.cn.*',
|
||||||
|
r'.*\.net.*',
|
||||||
|
r'.*音乐网.*',
|
||||||
|
r'.*提供.*',
|
||||||
|
r'.*下载.*',
|
||||||
|
]
|
||||||
|
|
||||||
|
for line in lines:
|
||||||
|
if re.match(r'\[\d{2}:\d{2}', line):
|
||||||
|
is_ad = False
|
||||||
|
for pattern in ad_patterns:
|
||||||
|
if re.search(pattern, line, re.IGNORECASE):
|
||||||
|
is_ad = True
|
||||||
|
break
|
||||||
|
if not is_ad:
|
||||||
|
filtered_lines.append(line)
|
||||||
|
else:
|
||||||
|
filtered_lines.append(line)
|
||||||
|
|
||||||
|
return '\n'.join(filtered_lines)
|
||||||
|
|
||||||
|
def localProxy(self, param):
|
||||||
|
url = unquote(param.get("url", ""))
|
||||||
|
type_ = param.get("type")
|
||||||
|
|
||||||
|
if type_ == "img":
|
||||||
|
try:
|
||||||
|
headers = {
|
||||||
|
"Referer": "https://www.baidu.com/",
|
||||||
|
"User-Agent": self.headers["User-Agent"],
|
||||||
|
"Accept": "image/webp,image/apng,image/*,*/*;q=0.8",
|
||||||
|
"Accept-Language": "zh-CN,zh;q=0.9"
|
||||||
|
}
|
||||||
|
resp = self.session.get(url, headers=headers, timeout=10)
|
||||||
|
return [200, "image/jpeg", resp.content, {}]
|
||||||
|
except Exception as e:
|
||||||
|
print(f"图片代理失败: {e}")
|
||||||
|
return [404, "text/plain", b"", {}]
|
||||||
|
|
||||||
|
elif type_ == "lrc":
|
||||||
|
try:
|
||||||
|
r = self.session.get(url, headers={"Referer": self.host + "/"}, timeout=5)
|
||||||
|
lrc_content = r.text
|
||||||
|
lrc_content = self._filter_lrc_ads(lrc_content)
|
||||||
|
return [200, "application/octet-stream", lrc_content.encode('utf-8'), {}]
|
||||||
|
except:
|
||||||
|
return [404, "text/plain", "Error", {}]
|
||||||
|
|
||||||
|
return None
|
||||||
|
|
||||||
|
# ==================== 辅助方法 ====================
|
||||||
|
|
||||||
|
def _parse_list(self, items, tid=""):
|
||||||
|
"""解析列表项，修复歌手头像 - 直接返回原始图片URL"""
|
||||||
|
res = []
|
||||||
|
for li in items.items():
|
||||||
|
a = li("a").eq(0)
|
||||||
|
if not (href := a.attr("href")) or href == "/" or any(x in href for x in ["/user/", "/login/", "javascript"]):
|
||||||
|
continue
|
||||||
|
if not (name := self._clean(li(".name").text() or a.attr("title") or a.text())):
|
||||||
|
continue
|
||||||
|
|
||||||
|
is_singer = "/singer/" in href or "/singerlist" in tid
|
||||||
|
|
||||||
|
pic = ""
|
||||||
|
src = ""
|
||||||
|
|
||||||
|
if is_singer:
|
||||||
|
img = li(".pic img").eq(0)
|
||||||
|
src = img.attr("src") or ""
|
||||||
|
if not src:
|
||||||
|
img = li("img").eq(0)
|
||||||
|
src = img.attr("src") or ""
|
||||||
|
else:
|
||||||
|
img = li("img").eq(0)
|
||||||
|
src = img.attr("src") or ""
|
||||||
|
if not src:
|
||||||
|
img = li(".pic img").eq(0)
|
||||||
|
src = img.attr("src") or ""
|
||||||
|
|
||||||
|
if src:
|
||||||
|
if src.startswith('//'):
|
||||||
|
src = 'https:' + src
|
||||||
|
elif src.startswith('/'):
|
||||||
|
src = self.host + src
|
||||||
|
pic = src
|
||||||
|
|
||||||
|
res.append({
|
||||||
|
"vod_id": self._abs(href),
|
||||||
|
"vod_name": name,
|
||||||
|
"vod_pic": pic,
|
||||||
|
"style": {
|
||||||
|
"type": "oval" if is_singer else ("list" if any(
|
||||||
|
x in tid for x in ["/list/", "/playtype/", "/albumlist/"]) else "rect"),
|
||||||
|
"ratio": 1 if is_singer else 1.33
|
||||||
|
}
|
||||||
|
})
|
||||||
|
return res
|
||||||
|
|
||||||
|
def _get_eps(self, doc):
|
||||||
|
eps = []
|
||||||
|
for li in doc(".play_list li, .song_list li, .music_list li").items():
|
||||||
|
a = li("a").eq(0)
|
||||||
|
href = a.attr("href")
|
||||||
|
if not href or not re.search(r'/(song|mp3|radio|radiolist|radioplay)/([^/]+)\.html', href):
|
||||||
|
continue
|
||||||
|
full_url = self._abs(href)
|
||||||
|
|
||||||
|
lrc_part = ""
|
||||||
|
mid = re.search(r'/(song|mp3|radio|radiolist|radioplay)/([^/]+)\.html', full_url)
|
||||||
|
if mid:
|
||||||
|
lrc_url = f"{self.host}/plug/down.php?ac=music&lk=lrc&id={mid.group(2)}"
|
||||||
|
lrc_part = f"|||{lrc_url}"
|
||||||
|
|
||||||
|
eps.append(f"{self._clean(a.text() or li('.name').text())}${self.e64('0@@@@' + full_url + lrc_part)}")
|
||||||
|
return eps
|
||||||
|
|
||||||
|
def _clean(self, text):
|
||||||
|
return re.sub(
|
||||||
|
r'(爱玩音乐网|视频下载说明|视频下载地址|www\.2t58\.com|MP3免费下载|LRC歌词下载|全部歌曲|\[第\d+页\]|刷新|每日推荐|最新|热门|推荐|MV|高清|无损)',
|
||||||
|
'',
|
||||||
|
text or '',
|
||||||
|
flags=re.I
|
||||||
|
).strip()
|
||||||
|
|
||||||
|
def _fetch_filters(self, url):
|
||||||
|
doc = self.getpq(url)
|
||||||
|
filters = []
|
||||||
|
for i, group in enumerate([
|
||||||
|
doc(".ilingku_fl"),
|
||||||
|
doc(".class_list"),
|
||||||
|
doc(".screen_list"),
|
||||||
|
doc(".box_list"),
|
||||||
|
doc(".nav_list")
|
||||||
|
]):
|
||||||
|
if group:
|
||||||
|
opts = [{"n": "全部", "v": "top" if "top" in url else "index"}]
|
||||||
|
seen = set()
|
||||||
|
for a in group("a").items():
|
||||||
|
v = (a.attr("href") or "").split("?")[0].rstrip('/').split('/')[-1].replace('.html', '')
|
||||||
|
if v and v not in seen:
|
||||||
|
opts.append({"n": a.text().strip(), "v": v})
|
||||||
|
seen.add(v)
|
||||||
|
if len(opts) > 1:
|
||||||
|
filters.append({"key": f"id{i}" if i else "id", "name": "分类", "value": opts})
|
||||||
|
return filters
|
||||||
|
|
||||||
|
def _api(self, path, params=None, method="GET", headers=None, data=None):
|
||||||
|
try:
|
||||||
|
h = self.headers.copy()
|
||||||
|
if headers:
|
||||||
|
h.update(headers)
|
||||||
|
r = (self.session.post if method == "POST" else self.session.get)(
|
||||||
|
f"{self.host}{path}",
|
||||||
|
params=params,
|
||||||
|
data=data,
|
||||||
|
headers=h,
|
||||||
|
timeout=10,
|
||||||
|
allow_redirects=False
|
||||||
|
)
|
||||||
|
if loc := r.headers.get("Location"):
|
||||||
|
return self._abs(loc.strip())
|
||||||
|
return self._abs(r.json().get("url", "").replace(r"\/", "/")) or (r.text.strip() if r.text.strip().startswith(
|
||||||
|
"http") else "")
|
||||||
|
except:
|
||||||
|
return ""
|
||||||
|
|
||||||
|
def _abs(self, url):
|
||||||
|
if not url:
|
||||||
|
return ""
|
||||||
|
if url.startswith("http"):
|
||||||
|
return url
|
||||||
|
if url.startswith("//"):
|
||||||
|
return "https:" + url
|
||||||
|
return f"{self.host}{'/' if not url.startswith('/') else ''}{url}"
|
||||||
|
|
||||||
|
def e64(self, text):
|
||||||
|
return b64encode(text.encode("utf-8")).decode("utf-8")
|
||||||
|
|
||||||
|
def d64(self, text):
|
||||||
|
return b64decode(text.encode("utf-8")).decode("utf-8")
|
||||||
+2
-3
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"spider": "./spider.jar;md5;5a5c64f87f0b0066919fa9b499912e4e",
|
"spider": "./spider.jar;md5;feb3dd35be7c31aa2a39bea423961279",
|
||||||
"wallpaper": "http://127.0.0.1:9978/proxy?do=wallpaper",
|
"wallpaper": "http://127.0.0.1:9978/proxy?do=wallpaper",
|
||||||
"sites": [
|
"sites": [
|
||||||
{"key": "豆瓣","name": "豆瓣 • 首页","type": 3,"api": "csp_Douban","searchable": 0},
|
{"key": "豆瓣","name": "豆瓣 • 首页","type": 3,"api": "csp_Douban","searchable": 0},
|
||||||
@@ -88,9 +88,8 @@
|
|||||||
{"key": "百度网盘","name": "百度 • 网盘","type": 3,"api": "csp_PanBaidu","searchable": 0,"filterable": 0,"changeable": 0,"style": {"type": "list","ratio": 1.433}},
|
{"key": "百度网盘","name": "百度 • 网盘","type": 3,"api": "csp_PanBaidu","searchable": 0,"filterable": 0,"changeable": 0,"style": {"type": "list","ratio": 1.433}},
|
||||||
{"key": "盘搜","name": "盘搜 • 搜索","type": 3,"api": "csp_PanSou","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
{"key": "盘搜","name": "盘搜 • 搜索","type": 3,"api": "csp_PanSou","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
||||||
{"key": "古哥","name": "古哥 • 搜索","type": 3,"api": "csp_GugeSo","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
{"key": "古哥","name": "古哥 • 搜索","type": 3,"api": "csp_GugeSo","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
||||||
{"key": "兄弟","name": "兄弟 • 搜索","type": 3,"api": "csp_XiongdiPan","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
|
||||||
{"key": "百酷","name": "百酷 • 搜索","type": 3,"api": "csp_Baiku","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
{"key": "百酷","name": "百酷 • 搜索","type": 3,"api": "csp_Baiku","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
||||||
{"key": "米搜","name": "米搜 • 搜索","type": 3,"api": "csp_MiSou","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
{"key": "米搜","name": "米搜 • 搜索","type": 3,"api": "csp_MiSou","searchable": 1,"quickSearch": 0,"filterable": 0,"ext": {"site": ["https://misoso.shop","http://www.misoso.shop"]},"timeout": 60},
|
||||||
{"key": "鬼鬼","name": "鬼鬼 • 搜索","type": 3,"api": "csp_GuiGui","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
{"key": "鬼鬼","name": "鬼鬼 • 搜索","type": 3,"api": "csp_GuiGui","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
||||||
{"key": "混合","name": "混合 • 搜索","type": 3,"api": "csp_HunHePan","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
{"key": "混合","name": "混合 • 搜索","type": 3,"api": "csp_HunHePan","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
||||||
{"key": "天翼","name": "天翼 • 搜索","type": 3,"api": "csp_TianYiSou","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
{"key": "天翼","name": "天翼 • 搜索","type": 3,"api": "csp_TianYiSou","searchable": 1,"quickSearch": 0,"filterable": 0,"timeout": 60},
|
||||||
|
|||||||
+502
-240
@@ -1,240 +1,502 @@
|
|||||||
import re
|
# -*- coding: utf-8 -*-
|
||||||
import sys
|
# 修复：歌手不显示歌手图片
|
||||||
from base64 import b64encode, b64decode
|
# by：垃圾星河
|
||||||
from urllib.parse import quote, unquote
|
# 代码指导：嗷呜呜呜呜
|
||||||
from pyquery import PyQuery as pq
|
# 增加：自动人机验证绕过
|
||||||
from requests import Session, adapters
|
|
||||||
from urllib3.util.retry import Retry
|
import re
|
||||||
from concurrent.futures import ThreadPoolExecutor, as_completed
|
import sys
|
||||||
sys.path.append('..')
|
import time
|
||||||
from base.spider import Spider
|
from base64 import b64encode, b64decode
|
||||||
|
from urllib.parse import quote, unquote
|
||||||
class Spider(Spider):
|
from pyquery import PyQuery as pq
|
||||||
def init(self, extend=""):
|
from requests import Session, adapters
|
||||||
self.host = "https://www.22a5.com"
|
from urllib3.util.retry import Retry
|
||||||
self.session = Session()
|
from concurrent.futures import ThreadPoolExecutor, as_completed
|
||||||
adapter = adapters.HTTPAdapter(max_retries=Retry(total=3, backoff_factor=0.5, status_forcelist=[429, 500, 502, 503, 504]), pool_connections=20, pool_maxsize=50)
|
|
||||||
self.session.mount("http://", adapter)
|
sys.path.append('..')
|
||||||
self.session.mount("https://", adapter)
|
from base.spider import Spider
|
||||||
self.headers = {"User-Agent": "Mozilla/5.0 (Linux; Android 10; K) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Mobile Safari/537.36"}
|
|
||||||
self.session.headers.update(self.headers)
|
|
||||||
|
class Spider(Spider):
|
||||||
def getName(self): return "爱听音乐"
|
def init(self, extend=""):
|
||||||
def isVideoFormat(self, url): return bool(re.search(r'\.(m3u8|mp4|mp3|m4a|flv)(\?|$)', url or "", re.I))
|
self.host = "https://www.22a5.com"
|
||||||
def manualVideoCheck(self): return False
|
self.session = Session()
|
||||||
def destroy(self): self.session.close()
|
adapter = adapters.HTTPAdapter(
|
||||||
|
max_retries=Retry(total=3, backoff_factor=0.5, status_forcelist=[429, 500, 502, 503, 504]),
|
||||||
def homeContent(self, filter):
|
pool_connections=20,
|
||||||
classes = [{"type_name": n, "type_id": i} for n, i in [("歌手","/singerlist/index/index/index/index.html"), ("TOP榜单","/list/top.html"), ("新歌榜","/list/new.html"), ("电台","/radiolist/index.html"), ("高清MV","/mvlist/oumei.html"), ("专辑","/albumlist/index.html"), ("歌单","/playtype/index.html")]]
|
pool_maxsize=50
|
||||||
filters = {p: d for p in [c["type_id"] for c in classes if "singer" not in c["type_id"]] if (d := self._fetch_filters(p))}
|
)
|
||||||
|
self.session.mount("http://", adapter)
|
||||||
if "/radiolist/index.html" not in filters:
|
self.session.mount("https://", adapter)
|
||||||
filters["/radiolist/index.html"] = [{"key": "id", "name": "分类", "value": [{"n": n, "v": v} for n,v in zip(["最新","最热","有声小说","相声","音乐","情感","国漫","影视","脱口秀","历史","儿童","教育","八卦","推理","头条"], ["index","hot","novel","xiangyi","music","emotion","game","yingshi","talkshow","history","children","education","gossip","tuili","headline"])]}]
|
self.headers = {
|
||||||
|
"User-Agent": "Mozilla/5.0 (Linux; Android 10; K) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Mobile Safari/537.36"
|
||||||
filters["/singerlist/index/index/index/index.html"] = [
|
}
|
||||||
{"key": "area", "name": "地区", "value": [{"n": n, "v": v} for n,v in [("全部","index"),("华语","huayu"),("欧美","oumei"),("韩国","hanguo"),("日本","ribrn")]]},
|
self.session.headers.update(self.headers)
|
||||||
{"key": "sex", "name": "性别", "value": [{"n": n, "v": v} for n,v in [("全部","index"),("男","male"),("女","girl"),("组合","band")]]},
|
|
||||||
{"key": "genre", "name": "流派", "value": [{"n": n, "v": v} for n,v in [("全部","index"),("流行","liuxing"),("电子","dianzi"),("摇滚","yaogun"),("嘻哈","xiha"),("R&B","rb"),("民谣","minyao"),("爵士","jueshi"),("古典","gudian")]]},
|
def getName(self):
|
||||||
{"key": "char", "name": "字母", "value": [{"n": n, "v": v} for n,v in [("全部","index")] + [{"n": chr(i), "v": chr(i).lower()} for i in range(65, 91)]]}
|
return "爱听音乐"
|
||||||
]
|
|
||||||
return {"class": classes, "filters": filters, "list": []}
|
def isVideoFormat(self, url):
|
||||||
|
return bool(re.search(r'\.(m3u8|mp4|mp3|m4a|flv)(\?|$)', url or "", re.I))
|
||||||
def homeVideoContent(self): return {"list": []}
|
|
||||||
|
def manualVideoCheck(self):
|
||||||
def categoryContent(self, tid, pg, filter, extend):
|
return False
|
||||||
pg = int(pg or 1)
|
|
||||||
url = tid
|
def destroy(self):
|
||||||
if "/singerlist/" in tid:
|
self.session.close()
|
||||||
p = tid.split('/')
|
|
||||||
if len(p) >= 6:
|
# ==================== 新增人机验证绕过 ====================
|
||||||
url = "/".join(p[:2] + [extend.get(k, p[i]) for i, k in enumerate(["area", "sex", "genre"], 2)] + [f"{extend.get('char', 'index')}.html"])
|
|
||||||
elif "id" in extend and extend["id"] not in ["index", "top"]:
|
def _bypass_verification(self, url, response_text):
|
||||||
url = tid.replace("index.html", f"{extend['id']}.html").replace("top.html", f"{extend['id']}.html")
|
"""若当前页面是人机验证，自动提交勾选"""
|
||||||
if url == tid: url = f"{tid.rsplit('/', 1)[0]}/{extend['id']}.html"
|
if '安全人机验证' not in response_text and 'human_check' not in response_text:
|
||||||
|
return None
|
||||||
if pg > 1:
|
|
||||||
sep = "/" if any(x in url for x in ["/singerlist/", "/radiolist/", "/mvlist/", "/playtype/", "/list/"]) else "_"
|
# 提取 csrf_token（支持多种格式）
|
||||||
url = re.sub(r'(_\d+|/\d+)?\.html$', f'{sep}{pg}.html', url)
|
token_match = re.search(r'name="csrf_token"\s+value="([^"]+)"', response_text)
|
||||||
|
if not token_match:
|
||||||
doc = self.getpq(url)
|
print("[爱听音乐] 未找到 csrf_token，跳过绕过")
|
||||||
return {"list": self._parse_list(doc(".play_list li, .video_list li, .pic_list li, .singer_list li, .ali li, .layui-row li, .base_l li"), tid), "page": pg, "pagecount": 9999, "limit": 90, "total": 999999}
|
return None
|
||||||
|
token = token_match.group(1)
|
||||||
def searchContent(self, key, quick, pg="1"):
|
|
||||||
return {"list": self._parse_list(self.getpq(f"/so/{quote(key)}/{pg}.html")(".base_l li, .play_list li"), "search"), "page": int(pg)}
|
# 构造提交数据
|
||||||
|
data = {
|
||||||
def detailContent(self, ids):
|
'csrf_token': token,
|
||||||
url = self._abs(ids[0])
|
'human_check': 'on'
|
||||||
doc = self.getpq(url)
|
}
|
||||||
vod = {"vod_id": url, "vod_name": self._clean(doc("h1").text() or doc("title").text()), "vod_pic": self._abs(doc(".djpg img, .pic img, .djpic img").attr("src")), "vod_play_from": "爱听音乐", "vod_content": ""}
|
|
||||||
|
try:
|
||||||
if any(x in url for x in ["/playlist/", "/album/", "/list/", "/singer/", "/special/", "/radio/", "/radiolist/"]):
|
# 发送 POST 请求，自动跟随重定向
|
||||||
eps = self._get_eps(doc)
|
post_resp = self.session.post(url, data=data, allow_redirects=True, timeout=10)
|
||||||
page_urls = {self._abs(a.attr("href")) for a in doc(".page a, .dede_pages a, .pagelist a").items() if a.attr("href") and "javascript" not in a.attr("href")} - {url}
|
print("[爱听音乐] 人机验证已绕过")
|
||||||
if page_urls:
|
return post_resp
|
||||||
with ThreadPoolExecutor(max_workers=5) as ex:
|
except Exception as e:
|
||||||
for r in as_completed([ex.submit(lambda u: self._get_eps(self.getpq(u)), u) for u in sorted(page_urls, key=lambda x: int(re.search(r'[_\/](\d+)\.html', x).group(1)) if re.search(r'[_\/](\d+)\.html', x) else 0)]):
|
print(f"[爱听音乐] 人机验证提交失败: {e}")
|
||||||
eps.extend(r.result() or [])
|
return None
|
||||||
if eps:
|
|
||||||
vod.update({"vod_play_from": "播放列表", "vod_play_url": "#".join(eps)})
|
def getpq(self, url):
|
||||||
return {"list": [vod]}
|
"""获取页面并自动处理人机验证（重试3次）"""
|
||||||
|
full_url = self._abs(url)
|
||||||
play_list = []
|
|
||||||
if mid := re.search(r'/(song|mp3|radio|radiolist|radioplay)/([^/]+)\.html', url):
|
for attempt in range(3):
|
||||||
lrc_url = f"{self.host}/plug/down.php?ac=music&lk=lrc&id={mid.group(2)}"
|
try:
|
||||||
play_list = [f"播放${self.e64('0@@@@' + url + '|||' + lrc_url)}"]
|
resp = self.session.get(full_url, timeout=5)
|
||||||
|
|
||||||
elif vid := re.search(r'/(video|mp4)/([^/]+)\.html', url):
|
# 若遇到验证页，尝试绕过
|
||||||
with ThreadPoolExecutor(max_workers=3) as ex:
|
if '安全人机验证' in resp.text or 'human_check' in resp.text:
|
||||||
fs = {ex.submit(self._api, "/plug/down.php", {"ac": "vplay", "id": vid.group(2), "q": q}): n for n, q in [("蓝光", 1080), ("超清", 720), ("高清", 480)]}
|
print("[爱听音乐] 检测到人机验证，尝试自动绕过...")
|
||||||
play_list = [f"{fs[f]}${self.e64('0@@@@'+u)}" for f in as_completed(fs) if (u := f.result())]
|
bypass_resp = self._bypass_verification(full_url, resp.text)
|
||||||
play_list.sort(key=lambda x: {"蓝":0, "超":1, "高":2}.get(x[0], 3))
|
if bypass_resp:
|
||||||
|
# 验证成功后，返回最终页面（可能是重定向后的目标）
|
||||||
vod["vod_play_url"] = "#".join(play_list) if play_list else f"解析失败${self.e64('1@@@@'+url)}"
|
return pq(bypass_resp.text)
|
||||||
return {"list": [vod]}
|
else:
|
||||||
|
# 绕过失败，等待后重试
|
||||||
def playerContent(self, flag, id, vipFlags):
|
time.sleep(1)
|
||||||
raw = self.d64(id).split("@@@@")[-1]
|
continue
|
||||||
url, subt = raw.split("|||") if "|||" in raw else (raw, "")
|
else:
|
||||||
url = url.replace(r"\/", "/")
|
# 正常页面直接返回
|
||||||
|
return pq(resp.text)
|
||||||
if ".html" in url and not self.isVideoFormat(url):
|
|
||||||
if mid := re.search(r'/(song|mp3|radio|radiolist|radioplay)/([^/]+)\.html', url):
|
except Exception as e:
|
||||||
if r_url := self._api("/js/play.php", method="POST", data={"id": mid.group(2), "type": "music"}, headers={"Referer": url.replace("http://","https://"), "X-Requested-With": "XMLHttpRequest"}):
|
print(f"[爱听音乐] 请求失败 (尝试 {attempt+1}/3): {e}")
|
||||||
url = r_url if ".php" not in r_url else url
|
time.sleep(0.5 * (attempt + 1))
|
||||||
elif vid := re.search(r'/(video|mp4)/([^/]+)\.html', url):
|
|
||||||
with ThreadPoolExecutor(max_workers=3) as ex:
|
# 全部失败，返回空文档
|
||||||
for f in as_completed([ex.submit(self._api, "/plug/down.php", {"ac": "vplay", "id": vid.group(2), "q": q}) for q in [1080, 720, 480]]):
|
return pq("<html></html>")
|
||||||
if v_url := f.result():
|
|
||||||
url = v_url; break
|
# ==================== 原有功能（保持不变） ====================
|
||||||
|
|
||||||
result = {"parse": 0, "url": url, "header": {"User-Agent": self.headers["User-Agent"]}}
|
def homeContent(self, filter):
|
||||||
if "22a5.com" in url: result["header"]["Referer"] = self.host + "/"
|
classes = [
|
||||||
|
{"type_name": n, "type_id": i}
|
||||||
# OK影视3.6.5+支持LRC格式滚动歌词
|
for n, i in [
|
||||||
if subt:
|
("歌手", "/singerlist/index/index/index/index.html"),
|
||||||
try:
|
("TOP榜单", "/list/top.html"),
|
||||||
r = self.session.get(subt, headers={"Referer": self.host + "/"}, timeout=5)
|
("新歌榜", "/list/new.html"),
|
||||||
lrc_content = r.text
|
("电台", "/radiolist/index.html"),
|
||||||
if lrc_content:
|
("高清MV", "/mvlist/oumei.html"),
|
||||||
# 过滤广告内容
|
("专辑", "/albumlist/index.html"),
|
||||||
lrc_content = self._filter_lrc_ads(lrc_content)
|
("歌单", "/playtype/index.html")
|
||||||
result["lrc"] = lrc_content
|
]
|
||||||
except:
|
]
|
||||||
pass
|
filters = {}
|
||||||
|
for p in [c["type_id"] for c in classes if "singer" not in c["type_id"]]:
|
||||||
return result
|
d = self._fetch_filters(p)
|
||||||
|
if d:
|
||||||
def _filter_lrc_ads(self, lrc_text):
|
filters[p] = d
|
||||||
"""过滤LRC歌词中的广告内容"""
|
|
||||||
lines = lrc_text.splitlines()
|
if "/radiolist/index.html" not in filters:
|
||||||
filtered_lines = []
|
filters["/radiolist/index.html"] = [{
|
||||||
|
"key": "id",
|
||||||
# 广告关键词模式
|
"name": "分类",
|
||||||
ad_patterns = [
|
"value": [
|
||||||
r'欢迎来访.*',
|
{"n": n, "v": v}
|
||||||
r'本站.*',
|
for n, v in zip(
|
||||||
r'.*广告.*',
|
["最新", "最热", "有声小说", "相声", "音乐", "情感", "国漫", "影视", "脱口秀", "历史", "儿童", "教育", "八卦", "推理", "头条"],
|
||||||
r'QQ群.*',
|
["index", "hot", "novel", "xiangyi", "music", "emotion", "game", "yingshi", "talkshow", "history",
|
||||||
r'.*www\..*',
|
"children", "education", "gossip", "tuili", "headline"]
|
||||||
r'.*http.*',
|
)
|
||||||
r'.*\.com.*',
|
]
|
||||||
r'.*\.cn.*',
|
}]
|
||||||
r'.*\.net.*',
|
|
||||||
r'.*音乐网.*',
|
filters["/singerlist/index/index/index/index.html"] = [
|
||||||
r'.*提供.*',
|
{
|
||||||
r'.*下载.*',
|
"key": "area",
|
||||||
]
|
"name": "地区",
|
||||||
|
"value": [
|
||||||
for line in lines:
|
{"n": "全部", "v": "index"},
|
||||||
# 保留时间标签行，但过滤掉广告文本
|
{"n": "华语", "v": "huayu"},
|
||||||
if re.match(r'\[\d{2}:\d{2}', line):
|
{"n": "欧美", "v": "oumei"},
|
||||||
# 检查是否包含广告
|
{"n": "韩国", "v": "hanguo"},
|
||||||
is_ad = False
|
{"n": "日本", "v": "ribrn"}
|
||||||
for pattern in ad_patterns:
|
]
|
||||||
if re.search(pattern, line, re.IGNORECASE):
|
},
|
||||||
is_ad = True
|
{
|
||||||
break
|
"key": "sex",
|
||||||
|
"name": "性别",
|
||||||
if not is_ad:
|
"value": [
|
||||||
filtered_lines.append(line)
|
{"n": "全部", "v": "index"},
|
||||||
else:
|
{"n": "男", "v": "male"},
|
||||||
# 非时间标签行（可能是元数据），保留
|
{"n": "女", "v": "girl"},
|
||||||
filtered_lines.append(line)
|
{"n": "组合", "v": "band"}
|
||||||
|
]
|
||||||
return '\n'.join(filtered_lines)
|
},
|
||||||
|
{
|
||||||
def localProxy(self, param):
|
"key": "genre",
|
||||||
url = unquote(param.get("url", ""))
|
"name": "流派",
|
||||||
type_ = param.get("type")
|
"value": [
|
||||||
|
{"n": "全部", "v": "index"},
|
||||||
if type_ == "img":
|
{"n": "流行", "v": "liuxing"},
|
||||||
return [200, "image/jpeg", self.session.get(url, headers={"Referer": self.host + "/"}, timeout=5).content, {}]
|
{"n": "电子", "v": "dianzi"},
|
||||||
|
{"n": "摇滚", "v": "yaogun"},
|
||||||
elif type_ == "lrc":
|
{"n": "嘻哈", "v": "xiha"},
|
||||||
try:
|
{"n": "R&B", "v": "rb"},
|
||||||
r = self.session.get(url, headers={"Referer": self.host + "/"}, timeout=5)
|
{"n": "民谣", "v": "minyao"},
|
||||||
# 同时过滤代理中的广告
|
{"n": "爵士", "v": "jueshi"},
|
||||||
lrc_content = r.text
|
{"n": "古典", "v": "gudian"}
|
||||||
lrc_content = self._filter_lrc_ads(lrc_content)
|
]
|
||||||
return [200, "application/octet-stream", lrc_content.encode('utf-8'), {}]
|
}
|
||||||
except:
|
]
|
||||||
return [404, "text/plain", "Error", {}]
|
return {"class": classes, "filters": filters, "list": []}
|
||||||
|
|
||||||
return None
|
def homeVideoContent(self):
|
||||||
|
return {"list": []}
|
||||||
def _parse_list(self, items, tid=""):
|
|
||||||
res = []
|
def categoryContent(self, tid, pg, filter, extend):
|
||||||
for li in items.items():
|
pg = int(pg or 1)
|
||||||
a = li("a").eq(0)
|
url = tid
|
||||||
if not (href := a.attr("href")) or href == "/" or any(x in href for x in ["/user/", "/login/", "javascript"]): continue
|
if "/singerlist/" in tid:
|
||||||
if not (name := self._clean(li(".name").text() or a.attr("title") or a.text())): continue
|
parts = tid.split('/')
|
||||||
pic = self._abs((li("img").attr("src") or "").replace('120', '500'))
|
if len(parts) >= 6:
|
||||||
res.append({"vod_id": self._abs(href), "vod_name": name, "vod_pic": f"{self.getProxyUrl()}&url={pic}&type=img" if pic else "", "style": {"type": "oval" if "/singer/" in href else ("list" if any(x in tid for x in ["/list/", "/playtype/", "/albumlist/"]) else "rect"), "ratio": 1 if "/singer/" in href else 1.33}})
|
url = "/".join(parts[:2] + [extend.get(k, parts[i]) for i, k in enumerate(["area", "sex", "genre"], 2)] +
|
||||||
return res
|
[f"{extend.get('char', 'index')}.html"])
|
||||||
|
elif "id" in extend and extend["id"] not in ["index", "top"]:
|
||||||
def _get_eps(self, doc):
|
url = tid.replace("index.html", f"{extend['id']}.html").replace("top.html", f"{extend['id']}.html")
|
||||||
eps = []
|
if url == tid:
|
||||||
for li in doc(".play_list li, .song_list li, .music_list li").items():
|
url = f"{tid.rsplit('/', 1)[0]}/{extend['id']}.html"
|
||||||
if not (a := li("a").eq(0)).attr("href") or not re.search(r'/(song|mp3|radio|radiolist|radioplay)/([^/]+)\.html', a.attr("href")): continue
|
|
||||||
full_url = self._abs(a.attr("href"))
|
if pg > 1:
|
||||||
|
sep = "/" if any(x in url for x in ["/singerlist/", "/radiolist/", "/mvlist/", "/playtype/", "/list/"]) else "_"
|
||||||
lrc_part = ""
|
url = re.sub(r'(_\d+|/\d+)?\.html$', f'{sep}{pg}.html', url)
|
||||||
mid = re.search(r'/(song|mp3|radio|radiolist|radioplay)/([^/]+)\.html', full_url)
|
|
||||||
if mid:
|
doc = self.getpq(url)
|
||||||
lrc_url = f"{self.host}/plug/down.php?ac=music&lk=lrc&id={mid.group(2)}"
|
items = doc(".play_list li, .video_list li, .pic_list li, .singer_list li, .ali li, .layui-row li, .base_l li")
|
||||||
lrc_part = f"|||{lrc_url}"
|
return {
|
||||||
|
"list": self._parse_list(items, tid),
|
||||||
eps.append(f"{self._clean(a.text() or li('.name').text())}${self.e64('0@@@@' + full_url + lrc_part)}")
|
"page": pg,
|
||||||
return eps
|
"pagecount": 9999,
|
||||||
|
"limit": 90,
|
||||||
def _clean(self, text): return re.sub(r'(爱玩音乐网|视频下载说明|视频下载地址|www\.2t58\.com|MP3免费下载|LRC歌词下载|全部歌曲|\[第\d+页\]|刷新|每日推荐|最新|热门|推荐|MV|高清|无损)', '', text or "", flags=re.I).strip()
|
"total": 999999
|
||||||
|
}
|
||||||
def _fetch_filters(self, url):
|
|
||||||
doc, filters = self.getpq(url), []
|
def searchContent(self, key, quick, pg="1"):
|
||||||
for i, group in enumerate([doc(s) for s in [".ilingku_fl", ".class_list", ".screen_list", ".box_list", ".nav_list"] if doc(s)]):
|
doc = self.getpq(f"/so/{quote(key)}/{pg}.html")
|
||||||
opts, seen = [{"n": "全部", "v": "top" if "top" in url else "index"}], set()
|
items = doc(".base_l li, .play_list li")
|
||||||
for a in group("a").items():
|
return {
|
||||||
if (v := (a.attr("href") or "").split("?")[0].rstrip('/').split('/')[-1].replace('.html','')) and v not in seen:
|
"list": self._parse_list(items, "search"),
|
||||||
opts.append({"n": a.text().strip(), "v": v}); seen.add(v)
|
"page": int(pg)
|
||||||
if len(opts) > 1: filters.append({"key": f"id{i}" if i else "id", "name": "分类", "value": opts})
|
}
|
||||||
return filters
|
|
||||||
|
def detailContent(self, ids):
|
||||||
def _api(self, path, params=None, method="GET", headers=None, data=None):
|
url = self._abs(ids[0])
|
||||||
try:
|
doc = self.getpq(url)
|
||||||
h = self.headers.copy()
|
vod = {
|
||||||
if headers: h.update(headers)
|
"vod_id": url,
|
||||||
r = (self.session.post if method == "POST" else self.session.get)(f"{self.host}{path}", params=params, data=data, headers=h, timeout=10, allow_redirects=False)
|
"vod_name": self._clean(doc("h1").text() or doc("title").text()),
|
||||||
if loc := r.headers.get("Location"): return self._abs(loc.strip())
|
"vod_pic": self._abs(doc(".djpg img, .pic img, .djpic img").attr("src")),
|
||||||
return self._abs(r.json().get("url", "").replace(r"\/", "/")) or (r.text.strip() if r.text.strip().startswith("http") else "")
|
"vod_play_from": "爱听音乐",
|
||||||
except: return ""
|
"vod_content": ""
|
||||||
|
}
|
||||||
def getpq(self, url):
|
|
||||||
import time
|
if any(x in url for x in ["/playlist/", "/album/", "/list/", "/singer/", "/special/", "/radio/", "/radiolist/"]):
|
||||||
for _ in range(2):
|
eps = self._get_eps(doc)
|
||||||
try: return pq(self.session.get(self._abs(url), timeout=5).text)
|
page_urls = {
|
||||||
except: time.sleep(0.1)
|
self._abs(a.attr("href"))
|
||||||
return pq("<html></html>")
|
for a in doc(".page a, .dede_pages a, .pagelist a").items()
|
||||||
|
if a.attr("href") and "javascript" not in a.attr("href")
|
||||||
def _abs(self, url): return url if url.startswith("http") else (f"{self.host}{'/' if not url.startswith('/') else ''}{url}" if url else "")
|
} - {url}
|
||||||
def e64(self, text): return b64encode(text.encode("utf-8")).decode("utf-8")
|
if page_urls:
|
||||||
def d64(self, text): return b64decode(text.encode("utf-8")).decode("utf-8")
|
with ThreadPoolExecutor(max_workers=5) as ex:
|
||||||
|
futures = []
|
||||||
|
for u in sorted(page_urls, key=lambda x: int(re.search(r'[_/](\d+)\.html', x).group(1)) if re.search(
|
||||||
|
r'[_/](\d+)\.html', x) else 0):
|
||||||
|
futures.append(ex.submit(lambda uu: self._get_eps(self.getpq(uu)), u))
|
||||||
|
for f in as_completed(futures):
|
||||||
|
eps.extend(f.result() or [])
|
||||||
|
if eps:
|
||||||
|
vod.update({
|
||||||
|
"vod_play_from": "播放列表",
|
||||||
|
"vod_play_url": "#".join(eps)
|
||||||
|
})
|
||||||
|
return {"list": [vod]}
|
||||||
|
|
||||||
|
play_list = []
|
||||||
|
if mid := re.search(r'/(song|mp3|radio|radiolist|radioplay)/([^/]+)\.html', url):
|
||||||
|
lrc_url = f"{self.host}/plug/down.php?ac=music&lk=lrc&id={mid.group(2)}"
|
||||||
|
play_list = [f"播放${self.e64('0@@@@' + url + '|||' + lrc_url)}"]
|
||||||
|
|
||||||
|
elif vid := re.search(r'/(video|mp4)/([^/]+)\.html', url):
|
||||||
|
with ThreadPoolExecutor(max_workers=3) as ex:
|
||||||
|
fs = {
|
||||||
|
ex.submit(self._api, "/plug/down.php", {"ac": "vplay", "id": vid.group(2), "q": q}): n
|
||||||
|
for n, q in [("蓝光", 1080), ("超清", 720), ("高清", 480)]
|
||||||
|
}
|
||||||
|
play_list = [f"{fs[f]}${self.e64('0@@@@'+u)}" for f in as_completed(fs) if (u := f.result())]
|
||||||
|
play_list.sort(key=lambda x: {"蓝": 0, "超": 1, "高": 2}.get(x[0], 3))
|
||||||
|
|
||||||
|
vod["vod_play_url"] = "#".join(play_list) if play_list else f"解析失败${self.e64('1@@@@'+url)}"
|
||||||
|
return {"list": [vod]}
|
||||||
|
|
||||||
|
def playerContent(self, flag, id, vipFlags):
|
||||||
|
raw = self.d64(id).split("@@@@")[-1]
|
||||||
|
url, subt = raw.split("|||") if "|||" in raw else (raw, "")
|
||||||
|
url = url.replace(r"\/", "/")
|
||||||
|
|
||||||
|
if ".html" in url and not self.isVideoFormat(url):
|
||||||
|
if mid := re.search(r'/(song|mp3|radio|radiolist|radioplay)/([^/]+)\.html', url):
|
||||||
|
if r_url := self._api("/js/play.php", method="POST", data={"id": mid.group(2), "type": "music"},
|
||||||
|
headers={"Referer": url.replace("http://", "https://"),
|
||||||
|
"X-Requested-With": "XMLHttpRequest"}):
|
||||||
|
url = r_url if ".php" not in r_url else url
|
||||||
|
elif vid := re.search(r'/(video|mp4)/([^/]+)\.html', url):
|
||||||
|
with ThreadPoolExecutor(max_workers=3) as ex:
|
||||||
|
for f in as_completed(
|
||||||
|
[ex.submit(self._api, "/plug/down.php", {"ac": "vplay", "id": vid.group(2), "q": q}) for q in
|
||||||
|
[1080, 720, 480]]):
|
||||||
|
if v_url := f.result():
|
||||||
|
url = v_url
|
||||||
|
break
|
||||||
|
|
||||||
|
result = {"parse": 0, "url": url, "header": {"User-Agent": self.headers["User-Agent"]}}
|
||||||
|
if "22a5.com" in url:
|
||||||
|
result["header"]["Referer"] = self.host + "/"
|
||||||
|
|
||||||
|
# OK影视3.6.5+支持LRC格式滚动歌词
|
||||||
|
if subt:
|
||||||
|
try:
|
||||||
|
r = self.session.get(subt, headers={"Referer": self.host + "/"}, timeout=5)
|
||||||
|
lrc_content = r.text
|
||||||
|
if lrc_content:
|
||||||
|
lrc_content = self._filter_lrc_ads(lrc_content)
|
||||||
|
result["lrc"] = lrc_content
|
||||||
|
except:
|
||||||
|
pass
|
||||||
|
|
||||||
|
return result
|
||||||
|
|
||||||
|
def _filter_lrc_ads(self, lrc_text):
|
||||||
|
"""过滤LRC歌词中的广告内容"""
|
||||||
|
lines = lrc_text.splitlines()
|
||||||
|
filtered_lines = []
|
||||||
|
|
||||||
|
# 广告关键词模式
|
||||||
|
ad_patterns = [
|
||||||
|
r'欢迎来访.*',
|
||||||
|
r'本站.*',
|
||||||
|
r'.*广告.*',
|
||||||
|
r'QQ群.*',
|
||||||
|
r'.*www\..*',
|
||||||
|
r'.*http.*',
|
||||||
|
r'.*\.com.*',
|
||||||
|
r'.*\.cn.*',
|
||||||
|
r'.*\.net.*',
|
||||||
|
r'.*音乐网.*',
|
||||||
|
r'.*提供.*',
|
||||||
|
r'.*下载.*',
|
||||||
|
]
|
||||||
|
|
||||||
|
for line in lines:
|
||||||
|
if re.match(r'\[\d{2}:\d{2}', line):
|
||||||
|
is_ad = False
|
||||||
|
for pattern in ad_patterns:
|
||||||
|
if re.search(pattern, line, re.IGNORECASE):
|
||||||
|
is_ad = True
|
||||||
|
break
|
||||||
|
if not is_ad:
|
||||||
|
filtered_lines.append(line)
|
||||||
|
else:
|
||||||
|
filtered_lines.append(line)
|
||||||
|
|
||||||
|
return '\n'.join(filtered_lines)
|
||||||
|
|
||||||
|
def localProxy(self, param):
|
||||||
|
url = unquote(param.get("url", ""))
|
||||||
|
type_ = param.get("type")
|
||||||
|
|
||||||
|
if type_ == "img":
|
||||||
|
try:
|
||||||
|
headers = {
|
||||||
|
"Referer": "https://www.baidu.com/",
|
||||||
|
"User-Agent": self.headers["User-Agent"],
|
||||||
|
"Accept": "image/webp,image/apng,image/*,*/*;q=0.8",
|
||||||
|
"Accept-Language": "zh-CN,zh;q=0.9"
|
||||||
|
}
|
||||||
|
resp = self.session.get(url, headers=headers, timeout=10)
|
||||||
|
return [200, "image/jpeg", resp.content, {}]
|
||||||
|
except Exception as e:
|
||||||
|
print(f"图片代理失败: {e}")
|
||||||
|
return [404, "text/plain", b"", {}]
|
||||||
|
|
||||||
|
elif type_ == "lrc":
|
||||||
|
try:
|
||||||
|
r = self.session.get(url, headers={"Referer": self.host + "/"}, timeout=5)
|
||||||
|
lrc_content = r.text
|
||||||
|
lrc_content = self._filter_lrc_ads(lrc_content)
|
||||||
|
return [200, "application/octet-stream", lrc_content.encode('utf-8'), {}]
|
||||||
|
except:
|
||||||
|
return [404, "text/plain", "Error", {}]
|
||||||
|
|
||||||
|
return None
|
||||||
|
|
||||||
|
# ==================== 辅助方法 ====================
|
||||||
|
|
||||||
|
def _parse_list(self, items, tid=""):
|
||||||
|
"""解析列表项，修复歌手头像 - 直接返回原始图片URL"""
|
||||||
|
res = []
|
||||||
|
for li in items.items():
|
||||||
|
a = li("a").eq(0)
|
||||||
|
if not (href := a.attr("href")) or href == "/" or any(x in href for x in ["/user/", "/login/", "javascript"]):
|
||||||
|
continue
|
||||||
|
if not (name := self._clean(li(".name").text() or a.attr("title") or a.text())):
|
||||||
|
continue
|
||||||
|
|
||||||
|
is_singer = "/singer/" in href or "/singerlist" in tid
|
||||||
|
|
||||||
|
pic = ""
|
||||||
|
src = ""
|
||||||
|
|
||||||
|
if is_singer:
|
||||||
|
img = li(".pic img").eq(0)
|
||||||
|
src = img.attr("src") or ""
|
||||||
|
if not src:
|
||||||
|
img = li("img").eq(0)
|
||||||
|
src = img.attr("src") or ""
|
||||||
|
else:
|
||||||
|
img = li("img").eq(0)
|
||||||
|
src = img.attr("src") or ""
|
||||||
|
if not src:
|
||||||
|
img = li(".pic img").eq(0)
|
||||||
|
src = img.attr("src") or ""
|
||||||
|
|
||||||
|
if src:
|
||||||
|
if src.startswith('//'):
|
||||||
|
src = 'https:' + src
|
||||||
|
elif src.startswith('/'):
|
||||||
|
src = self.host + src
|
||||||
|
pic = src
|
||||||
|
|
||||||
|
res.append({
|
||||||
|
"vod_id": self._abs(href),
|
||||||
|
"vod_name": name,
|
||||||
|
"vod_pic": pic,
|
||||||
|
"style": {
|
||||||
|
"type": "oval" if is_singer else ("list" if any(
|
||||||
|
x in tid for x in ["/list/", "/playtype/", "/albumlist/"]) else "rect"),
|
||||||
|
"ratio": 1 if is_singer else 1.33
|
||||||
|
}
|
||||||
|
})
|
||||||
|
return res
|
||||||
|
|
||||||
|
def _get_eps(self, doc):
|
||||||
|
eps = []
|
||||||
|
for li in doc(".play_list li, .song_list li, .music_list li").items():
|
||||||
|
a = li("a").eq(0)
|
||||||
|
href = a.attr("href")
|
||||||
|
if not href or not re.search(r'/(song|mp3|radio|radiolist|radioplay)/([^/]+)\.html', href):
|
||||||
|
continue
|
||||||
|
full_url = self._abs(href)
|
||||||
|
|
||||||
|
lrc_part = ""
|
||||||
|
mid = re.search(r'/(song|mp3|radio|radiolist|radioplay)/([^/]+)\.html', full_url)
|
||||||
|
if mid:
|
||||||
|
lrc_url = f"{self.host}/plug/down.php?ac=music&lk=lrc&id={mid.group(2)}"
|
||||||
|
lrc_part = f"|||{lrc_url}"
|
||||||
|
|
||||||
|
eps.append(f"{self._clean(a.text() or li('.name').text())}${self.e64('0@@@@' + full_url + lrc_part)}")
|
||||||
|
return eps
|
||||||
|
|
||||||
|
def _clean(self, text):
|
||||||
|
return re.sub(
|
||||||
|
r'(爱玩音乐网|视频下载说明|视频下载地址|www\.2t58\.com|MP3免费下载|LRC歌词下载|全部歌曲|\[第\d+页\]|刷新|每日推荐|最新|热门|推荐|MV|高清|无损)',
|
||||||
|
'',
|
||||||
|
text or '',
|
||||||
|
flags=re.I
|
||||||
|
).strip()
|
||||||
|
|
||||||
|
def _fetch_filters(self, url):
|
||||||
|
doc = self.getpq(url)
|
||||||
|
filters = []
|
||||||
|
for i, group in enumerate([
|
||||||
|
doc(".ilingku_fl"),
|
||||||
|
doc(".class_list"),
|
||||||
|
doc(".screen_list"),
|
||||||
|
doc(".box_list"),
|
||||||
|
doc(".nav_list")
|
||||||
|
]):
|
||||||
|
if group:
|
||||||
|
opts = [{"n": "全部", "v": "top" if "top" in url else "index"}]
|
||||||
|
seen = set()
|
||||||
|
for a in group("a").items():
|
||||||
|
v = (a.attr("href") or "").split("?")[0].rstrip('/').split('/')[-1].replace('.html', '')
|
||||||
|
if v and v not in seen:
|
||||||
|
opts.append({"n": a.text().strip(), "v": v})
|
||||||
|
seen.add(v)
|
||||||
|
if len(opts) > 1:
|
||||||
|
filters.append({"key": f"id{i}" if i else "id", "name": "分类", "value": opts})
|
||||||
|
return filters
|
||||||
|
|
||||||
|
def _api(self, path, params=None, method="GET", headers=None, data=None):
|
||||||
|
try:
|
||||||
|
h = self.headers.copy()
|
||||||
|
if headers:
|
||||||
|
h.update(headers)
|
||||||
|
r = (self.session.post if method == "POST" else self.session.get)(
|
||||||
|
f"{self.host}{path}",
|
||||||
|
params=params,
|
||||||
|
data=data,
|
||||||
|
headers=h,
|
||||||
|
timeout=10,
|
||||||
|
allow_redirects=False
|
||||||
|
)
|
||||||
|
if loc := r.headers.get("Location"):
|
||||||
|
return self._abs(loc.strip())
|
||||||
|
return self._abs(r.json().get("url", "").replace(r"\/", "/")) or (r.text.strip() if r.text.strip().startswith(
|
||||||
|
"http") else "")
|
||||||
|
except:
|
||||||
|
return ""
|
||||||
|
|
||||||
|
def _abs(self, url):
|
||||||
|
if not url:
|
||||||
|
return ""
|
||||||
|
if url.startswith("http"):
|
||||||
|
return url
|
||||||
|
if url.startswith("//"):
|
||||||
|
return "https:" + url
|
||||||
|
return f"{self.host}{'/' if not url.startswith('/') else ''}{url}"
|
||||||
|
|
||||||
|
def e64(self, text):
|
||||||
|
return b64encode(text.encode("utf-8")).decode("utf-8")
|
||||||
|
|
||||||
|
def d64(self, text):
|
||||||
|
return b64decode(text.encode("utf-8")).decode("utf-8")
|
||||||
Binary file not shown.
Reference in New Issue
Block a user