Sync all projects
This commit is contained in:
github-actions[bot]
@@ -0,0 +1,163 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
# 8x8x官网: https://www.7xb38c.com/
|
||||
|
||||
import sys,re,json,base64
|
||||
from urllib.parse import quote
|
||||
sys.path.append('..')
|
||||
try:
|
||||
from base.spider import Spider as _Base
|
||||
except ImportError:
|
||||
class _Base:
|
||||
def fetch(self,url,headers=None,**kw):
|
||||
import requests as rq
|
||||
kw.pop('timeout',None);r=rq.get(url,headers=headers,timeout=15,**kw)
|
||||
r.encoding='utf-8';return r
|
||||
|
||||
try:
|
||||
import curl_cffi.requests as cr
|
||||
_HAS_CFFI=True
|
||||
except ImportError:
|
||||
_HAS_CFFI=False
|
||||
import requests as cr
|
||||
|
||||
_H=[104,116,116,112,115,58,47,47,119,119,119,46,51,97,98,102,117,103,57,50,100,46,99,111,109]
|
||||
H=bytes(_H).decode()
|
||||
U="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
|
||||
CATS={1:"大陆",2:"日韩",3:"欧美",4:"动漫",5:"三级"}
|
||||
TC=None
|
||||
|
||||
# ── 动态发现 body path ──
|
||||
def _discover_body(session):
|
||||
"""从 SPA 壳中提取 body 路径前缀, 失败返回默认值"""
|
||||
try:
|
||||
kw={"timeout":10}
|
||||
if _HAS_CFFI:kw["impersonate"]="chrome120"
|
||||
r=session.get(H+"/",**kw)
|
||||
r.raise_for_status()
|
||||
js_name=re.search(r'src=/assets/(app\.[a-f0-9]+\.js)',r.text)
|
||||
if not js_name:return"/cou345w"
|
||||
r2=session.get(H+"/assets/"+js_name.group(1),**kw)
|
||||
r2.raise_for_status()
|
||||
seg=re.search(r'atob\("([^"]+)"\)',r2.text)
|
||||
if not seg:return"/cou345w"
|
||||
return"/"+base64.b64decode(seg.group(1)).decode()
|
||||
except Exception as e:
|
||||
print(f"[8x8x] body discover failed: {e}, using default")
|
||||
return"/cou345w"
|
||||
|
||||
|
||||
class Spider(_Base):
|
||||
def init(self,extend=""):
|
||||
self._s=cr.Session()
|
||||
self._s.headers.update({"User-Agent":U,"Accept-Language":"zh-CN,zh;q=0.9"})
|
||||
self._s.verify=False
|
||||
# ★ 动态发现 body path
|
||||
self._bd=_discover_body(self._s)
|
||||
print(f"[8x8x] body path: {self._bd}")
|
||||
|
||||
def getName(self):return"8x8x"
|
||||
def isVideoFormat(self,u):return".m3u8"in u or".mp4"in u
|
||||
def manualVideoCheck(self):return False
|
||||
|
||||
def _get(self,url,timeout=15):
|
||||
if not url.startswith("http"):url=H+self._bd+url
|
||||
try:
|
||||
kw={"timeout":timeout}
|
||||
if _HAS_CFFI:kw["impersonate"]="chrome120"
|
||||
r=self._s.get(url,**kw);r.raise_for_status()
|
||||
if hasattr(r,'encoding'):r.encoding='utf-8'
|
||||
return r.text
|
||||
except Exception as e:
|
||||
print(f"[8x8x]GET {url[:60]} -> {e}")
|
||||
return""
|
||||
|
||||
def _tags(self):
|
||||
global TC
|
||||
if TC is not None:return TC
|
||||
h=self._get("/");g={}
|
||||
if not h:TC=g;return g
|
||||
for gm in re.finditer(r'<div class=tag-group data-group-id=\d+><span class=tag-group-label>([^<]+)</span>(.*?)</div>',h,re.DOTALL):
|
||||
gn=gm.group(1);inner=gm.group(2)
|
||||
ts=re.findall(r'<a href=(/tags/[^/]+/)\s[^>]*>([^<]+)</a>',inner)
|
||||
if ts:g[gn]=ts
|
||||
TC=g;return g
|
||||
|
||||
def _cards(self,h):
|
||||
v=[]
|
||||
for m in re.finditer(r'<a href=(/vd/(\d+)/)\s[^>]*>(.*?)</a>',h,re.DOTALL):
|
||||
inner=m.group(3)
|
||||
tm=re.search(r'<div class=card-title>(.*?)</div>',inner)
|
||||
im=re.search(r'data-src=([^\s>]+)',inner)
|
||||
v.append({"vod_id":m.group(1),"vod_name":tm.group(1)if tm else"N/A","vod_pic":im.group(1)if im else"","vod_remarks":""})
|
||||
return v
|
||||
|
||||
def homeContent(self,filter=False):
|
||||
t=self._tags();cs=[]
|
||||
for cid,cn in sorted(CATS.items()):cs.append({"type_id":str(cid),"type_name":cn})
|
||||
for gn in sorted(t.keys()):
|
||||
for url,name in t[gn]:cs.append({"type_id":url,"type_name":f"[{gn}] {name}"})
|
||||
return{"class":cs}
|
||||
|
||||
def homeVideoContent(self):
|
||||
h=self._get("/")
|
||||
return{"list":self._cards(h)[:30]if h else[]}
|
||||
|
||||
def categoryContent(self,tid,pg=1,filter=False,extend=None):
|
||||
try:
|
||||
pn=max(int(str(pg)),1)
|
||||
base=tid.rstrip("/")if tid.startswith("/tags/")else f"/category/{int(tid)}"
|
||||
h=self._get(f"{base}/page/{pn}/")
|
||||
if not h:return{"list":[],"page":pg,"pagecount":1}
|
||||
mp=re.search(r'data-max=(\d+)',h);pc=int(mp.group(1))if mp else pn
|
||||
v=self._cards(h)
|
||||
return{"list":v,"page":pn,"pagecount":pc,"limit":len(v),"total":pc*len(v)if v else 0}
|
||||
except Exception as e:print(f"[8x8x]cat:{e}");return{"list":[],"page":pg,"pagecount":1}
|
||||
|
||||
def detailContent(self,ids):
|
||||
vid=ids[0]
|
||||
if not vid.startswith("/vd/"):vid=f"/vd/{vid.strip('/')}/"
|
||||
h=self._get(vid)
|
||||
if not h:return{"list":[]}
|
||||
tm=re.search(r'<title>(.*?)</title>',h);title=tm.group(1).replace(" - 8x8x","")if tm else""
|
||||
pm=re.search(r'data-poster=([^\s>]+)',h);pic=pm.group(1).strip('"').strip("'")if pm else""
|
||||
mm=re.search(r'data-m3u8=([^\s>]+)',h)
|
||||
if not mm:return{"list":[{"vod_id":ids[0],"vod_name":title,"vod_pic":pic}]}
|
||||
m3u8_path=mm.group(1).strip('"').strip("'")
|
||||
pf=[];pu=[]
|
||||
for i,rn in enumerate(["data-route1","data-route2","data-route3"],1):
|
||||
rm=re.search(rf'{rn}=([^\s>]+)',h)
|
||||
if rm:
|
||||
rt=rm.group(1).strip('"').strip("'")
|
||||
full_m3u8=rt.rstrip("/")+"/"+m3u8_path.lstrip("/")
|
||||
pf.append(f"线路{i}")
|
||||
pu.append(f"线路{i}${full_m3u8}")
|
||||
return{"list":[{"vod_id":ids[0],"vod_name":title,"vod_pic":pic,"type_name":"","vod_year":"","vod_area":"","vod_remarks":"","vod_actor":"","vod_director":"","vod_content":"","vod_play_from":"$$$".join(pf),"vod_play_url":"$$$".join(pu)}]}
|
||||
|
||||
def playerContent(self,flag,id,vipFlags=None):
|
||||
if id and".m3u8"in id:return{"url":id,"header":json.dumps({"User-Agent":U,"Referer":H+"/"})}
|
||||
d=self.detailContent([id])
|
||||
if d and d.get("list"):
|
||||
urls=d["list"][0].get("vod_play_url","").split("$$$")
|
||||
if urls:
|
||||
first=urls[0]
|
||||
if"$"in first:first=first.split("$",1)[1]
|
||||
return{"url":first,"header":json.dumps({"User-Agent":U,"Referer":H+"/"})}
|
||||
return{"url":""}
|
||||
|
||||
def searchContent(self,key,quick=False,pg=1):
|
||||
try:
|
||||
pn=max(int(str(pg)),1)
|
||||
url=f"{H}/api/search/video?keyword={quote(key)}&page={pn}"
|
||||
kw={"timeout":15}
|
||||
if _HAS_CFFI:kw["impersonate"]="chrome120"
|
||||
r=self._s.get(url,**kw);r.raise_for_status()
|
||||
data=r.json()
|
||||
if data.get("code")!=0:return{"list":[]}
|
||||
dl=data.get("data",{})
|
||||
videos=[]
|
||||
for item in dl.get("list",[]):
|
||||
videos.append({"vod_id":f"/vd/{item['id']}/","vod_name":item.get("title",""),"vod_pic":item.get("litpic",""),"vod_remarks":item.get("typename","")})
|
||||
return{"list":videos,"page":pn,"pagecount":dl.get("total_pages",pn),"limit":len(videos),"total":dl.get("total",0)}
|
||||
except Exception as e:print(f"[8x8x]search:{e}");return{"list":[],"page":pg,"pagecount":1}
|
||||
|
||||
def localProxy(self,param):pass
|
||||
@@ -0,0 +1,192 @@
|
||||
#coding=utf-8
|
||||
#!/usr/bin/python
|
||||
import sys
|
||||
sys.path.append('..')
|
||||
import json
|
||||
import re
|
||||
|
||||
from base.spider import Spider
|
||||
|
||||
class Spider(Spider):
|
||||
def getName(self):
|
||||
return "91Porn"
|
||||
|
||||
def init(self, extend):
|
||||
self.baseUrl = "https://91porn.com"
|
||||
self.header = {
|
||||
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
|
||||
"Accept-Language": "zh-CN,zh;q=0.9",
|
||||
"Referer": self.baseUrl + "/index.php"
|
||||
}
|
||||
self.cookies = {}
|
||||
|
||||
# ✨ 核心改造：动态从 config.json 的 ext 参数中读取配置
|
||||
self.username = ""
|
||||
self.password = ""
|
||||
self.email = ""
|
||||
|
||||
try:
|
||||
if extend:
|
||||
extendDict = json.loads(extend) if isinstance(extend, str) else extend
|
||||
self.username = str(extendDict.get('username', '')).strip()
|
||||
self.password = str(extendDict.get('password', '')).strip()
|
||||
self.email = str(extendDict.get('email', '')).strip()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
self.is_ready = False
|
||||
|
||||
def safe_bypass_and_verify(self):
|
||||
if self.is_ready:
|
||||
return True
|
||||
try:
|
||||
rsp = self.fetch(self.baseUrl + "/email_verify.php", headers=self.header, timeout=5)
|
||||
self.cookies.update(rsp.cookies.get_dict())
|
||||
self.cookies['language'] = 'cn_CN'
|
||||
self.cookies['CNAM'] = '1'
|
||||
|
||||
# 如果外部没有配置邮箱，则直接作为普通游客会话放行
|
||||
if not self.email:
|
||||
self.is_ready = True
|
||||
return True
|
||||
|
||||
post_data = {"email": self.email, "recover": "Submit", "submit": "true"}
|
||||
v_hd = self.header.copy()
|
||||
v_hd["Content-Type"] = "application/x-www-form-urlencoded"
|
||||
v_hd["Referer"] = self.baseUrl + "/email_verify.php"
|
||||
|
||||
rsp_v = self.post(self.baseUrl + "/email_verify.php", data=post_data, headers=v_hd, cookies=self.cookies, timeout=5)
|
||||
self.cookies.update(rsp_v.cookies.get_dict())
|
||||
self.is_ready = True
|
||||
return True
|
||||
except Exception:
|
||||
self.is_ready = True
|
||||
return False
|
||||
|
||||
def homeContent(self, filter):
|
||||
result = {}
|
||||
classList = [
|
||||
{"type_name": "今日排行", "type_id": "hot"},
|
||||
{"type_name": "最近更新", "type_id": "rp"},
|
||||
{"type_name": "本月最热", "type_id": "md"}
|
||||
]
|
||||
result['class'] = classList
|
||||
return result
|
||||
|
||||
def homeVideoContent(self):
|
||||
return {'list': []}
|
||||
|
||||
def categoryContent(self, cid, page, filter, ext):
|
||||
self.safe_bypass_and_verify()
|
||||
result = {'page': int(page), 'pagecount': 1, 'limit': 0, 'total': 0, 'list': []}
|
||||
page = int(page)
|
||||
|
||||
url = self.baseUrl + "/v.php?category=" + cid + "&page=" + str(page)
|
||||
if cid == "hot":
|
||||
url = self.baseUrl + "/index.php"
|
||||
elif cid == "rp":
|
||||
url = self.baseUrl + "/v.php?next=watch&page=" + str(page)
|
||||
|
||||
try:
|
||||
rsp = self.fetch(url, headers=self.header, cookies=self.cookies, timeout=5)
|
||||
html = self.html(rsp.text)
|
||||
items = html.xpath("//div[contains(@class, 'well')]")
|
||||
videos = []
|
||||
for item in items:
|
||||
try:
|
||||
a_tag = item.xpath(".//a[contains(@href, 'view_video.php')]")
|
||||
if not a_tag:
|
||||
continue
|
||||
href = a_tag[0].get('href', '')
|
||||
v_match = re.search(r'viewkey=([a-zA-Z0-9]+)', href)
|
||||
if not v_match:
|
||||
continue
|
||||
vod_id = v_match.group(1)
|
||||
|
||||
name_nodes = item.xpath(".//span[contains(@class, 'video-title')]/text()")
|
||||
vod_name = name_nodes[0].strip() if name_nodes else "精彩视频"
|
||||
|
||||
img_nodes = item.xpath(".//img[contains(@class, 'img-responsive')]/@src")
|
||||
vod_pic = img_nodes[0].strip() if img_nodes else ""
|
||||
if vod_pic.startswith('//'):
|
||||
vod_pic = "https:" + vod_pic
|
||||
|
||||
remark_nodes = item.xpath(".//span[@class='duration']/text()")
|
||||
vod_remarks = remark_nodes[0].strip() if remark_nodes else "完整版"
|
||||
|
||||
videos.append({"vod_id": vod_id, "vod_name": self.cleanText(self.removeHtmlTags(vod_name)), "vod_pic": vod_pic, "vod_remarks": vod_remarks})
|
||||
except:
|
||||
continue
|
||||
result['list'] = videos
|
||||
result['limit'] = len(videos)
|
||||
result['pagecount'] = page + 1 if len(videos) >= 10 else page
|
||||
except Exception:
|
||||
pass
|
||||
return result
|
||||
|
||||
def detailContent(self, did):
|
||||
self.safe_bypass_and_verify()
|
||||
tid = did[0]
|
||||
url = self.baseUrl + "/view_video.php?viewkey=" + tid
|
||||
try:
|
||||
rsp = self.fetch(url, headers=self.header, cookies=self.cookies, timeout=5)
|
||||
html_text = rsp.text.replace('&', '&')
|
||||
root = self.html(html_text)
|
||||
|
||||
title_nodes = root.xpath("//h4[contains(@class, 'login_register_header')]/text() | //title/text()")
|
||||
title = title_nodes[0].strip().replace(" - 91porn", "").strip() if title_nodes else "精彩视频"
|
||||
|
||||
cover_nodes = root.xpath("//video/@poster")
|
||||
cover_pic = cover_nodes[0] if cover_nodes else ""
|
||||
|
||||
real_video_url = ""
|
||||
strencode_match = re.search(r'strencode2\([\"\']([^\"\'\)]+)[\"\']\)', html_text)
|
||||
if strencode_match:
|
||||
ciphertext = strencode_match.group(1)
|
||||
|
||||
try:
|
||||
from urllib.parse import unquote
|
||||
decrypted_html = unquote(ciphertext)
|
||||
except:
|
||||
import urllib
|
||||
decrypted_html = urllib.unquote(ciphertext)
|
||||
|
||||
src_match = re.search(r"src=['\"]([^'\"]+)['\"]", decrypted_html)
|
||||
if src_match:
|
||||
real_video_url = src_match.group(1)
|
||||
|
||||
if not real_video_url:
|
||||
src_nodes = root.xpath("//video/source/@src | //video/@src")
|
||||
if src_nodes:
|
||||
real_video_url = src_nodes[0]
|
||||
|
||||
if not real_video_url:
|
||||
real_video_url = url
|
||||
|
||||
vod = {"vod_id": tid, "vod_name": self.cleanText(self.removeHtmlTags(title)), "vod_pic": cover_pic, "type_name": "在线视频", "vod_content": "资源解析就绪", "vod_play_from": "91Porn秒解流", "vod_play_url": "直连资源源$" + real_video_url}
|
||||
return {'list': [vod]}
|
||||
except Exception:
|
||||
pass
|
||||
return {'list': []}
|
||||
|
||||
def playerContent(self, flag, pid, vipFlags):
|
||||
need_parse = 1 if "view_video.php" in pid else 0
|
||||
return {"url": pid, "header": self.header, "parse": need_parse}
|
||||
|
||||
def searchContent(self, key, quick):
|
||||
return {'list': []}
|
||||
|
||||
def searchContentPage(self, key, quick, page):
|
||||
return {'list': []}
|
||||
|
||||
def isVideoFormat(self, url):
|
||||
pass
|
||||
|
||||
def manualVideoCheck(self):
|
||||
pass
|
||||
|
||||
def localProxy(self, params):
|
||||
return None
|
||||
|
||||
def destroy(self):
|
||||
pass
|
||||
@@ -0,0 +1,255 @@
|
||||
#author Kyle
|
||||
import sys
|
||||
import time
|
||||
import json
|
||||
import re
|
||||
import urllib.parse
|
||||
from base64 import b64decode, b64encode
|
||||
sys.path.append('..')
|
||||
from base.spider import Spider
|
||||
|
||||
class Spider(Spider):
|
||||
def init(self, extend=""):
|
||||
self.host = "https://www.eporner.com"
|
||||
self.headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
|
||||
'Referer': self.host + '/',
|
||||
'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8'
|
||||
}
|
||||
self.timeout = 10
|
||||
self.retries = 2
|
||||
self.cookies = {"EPRNS": "1"}
|
||||
|
||||
def getName(self):
|
||||
return "EP涩"
|
||||
|
||||
def isVideoFormat(self, url):
|
||||
return True
|
||||
|
||||
def manualVideoCheck(self):
|
||||
return False
|
||||
|
||||
def destroy(self):
|
||||
pass
|
||||
|
||||
def homeContent(self, filter):
|
||||
result = {}
|
||||
result['class'] = [
|
||||
{"type_id": "/cat/all/", "type_name": "最新"},
|
||||
{"type_id": "/best-videos/", "type_name": "最佳视频"},
|
||||
{"type_id": "/top-rated/", "type_name": "最高评分"},
|
||||
{"type_id": "/cat/4k-porn/", "type_name": "4K"},
|
||||
]
|
||||
return result
|
||||
|
||||
def homeVideoContent(self):
|
||||
result = {}
|
||||
videos = self._api_search(query="all", page=1, order="latest", gay="0", per_page=20)
|
||||
result['list'] = videos
|
||||
return result
|
||||
|
||||
def categoryContent(self, tid, pg, filter, extend):
|
||||
result = {}
|
||||
params = self._map_tid_to_api(tid)
|
||||
videos = self._api_search(page=int(pg), **params)
|
||||
result['list'] = videos
|
||||
result['page'] = pg
|
||||
result['pagecount'] = 9999
|
||||
result['limit'] = len(videos) or 20
|
||||
result['total'] = 999999
|
||||
return result
|
||||
|
||||
def searchContent(self, key, quick, pg="1"):
|
||||
result = {}
|
||||
videos = self._api_search(query=key or "all", page=int(pg), order="latest", gay="0")
|
||||
result['list'] = videos
|
||||
result['page'] = pg
|
||||
result['pagecount'] = 9999
|
||||
result['limit'] = len(videos) or 20
|
||||
result['total'] = 999999
|
||||
return result
|
||||
|
||||
def detailContent(self, ids):
|
||||
result = {}
|
||||
url = ids[0]
|
||||
if not url.startswith('http'):
|
||||
url = self.host + url
|
||||
r = self.fetch(url, headers=self.headers)
|
||||
root = self.html(r.text)
|
||||
og_title = root.xpath('//meta[@property="og:title"]/@content')
|
||||
if og_title:
|
||||
title = og_title[0].replace(' - EPORNER', '').strip()
|
||||
else:
|
||||
h1 = "".join(root.xpath('//h1//text()'))
|
||||
title = re.sub(r"\s*(\d+\s*min.*)$", "", h1).strip() or "爱看AV"
|
||||
img_elem = root.xpath('//meta[@property="og:image"]/@content') or root.xpath('//img[@id="mainvideoimg"]/@src')
|
||||
thumbnail = img_elem[0] if img_elem else ""
|
||||
meta_desc = (root.xpath('//meta[@name="description"]/@content') or root.xpath('//meta[@property="og:description"]/@content'))
|
||||
desc_text = meta_desc[0] if meta_desc else ""
|
||||
dur_match = re.search(r"Duration:\s*([0-9:]+)", desc_text)
|
||||
duration = dur_match.group(1) if dur_match else ""
|
||||
encoded_url = self.e64(url)
|
||||
play_url = f"播放${encoded_url}"
|
||||
vod = {
|
||||
"vod_id": url,
|
||||
"vod_name": title,
|
||||
"vod_pic": thumbnail,
|
||||
"vod_remarks": duration,
|
||||
"vod_content": desc_text.strip(),
|
||||
"vod_play_from": "🍑Play",
|
||||
"vod_play_url": play_url
|
||||
}
|
||||
result['list'] = [vod]
|
||||
return result
|
||||
|
||||
def playerContent(self, flag, id, vipFlags):
|
||||
result = {}
|
||||
url = self.d64(id)
|
||||
if not url.startswith('http'):
|
||||
url = self.host + url
|
||||
r = self.fetch(url, headers=self.headers)
|
||||
html_content = r.text
|
||||
pattern = r"vid\s*=\s*'([^']+)';\s*[\w*\.]+hash\s*=\s*['\"]([\da-f]{32})"
|
||||
match = re.search(pattern, html_content)
|
||||
if match:
|
||||
vid, hash_val = match.groups()
|
||||
hash_code = ''.join((self.encode_base_n(int(hash_val[i:i + 8], 16), 36) for i in range(0, 32, 8)))
|
||||
xhr_url = f"{self.host}/xhr/video/{vid}?hash={hash_code}&device=generic&domain=www.eporner.com&fallback=false&embed=false&supportedFormats=mp4"
|
||||
xhr_headers = {
|
||||
**self.headers,
|
||||
'X-Requested-With': 'XMLHttpRequest',
|
||||
'Accept': 'application/json, text/javascript, */*; q=0.01'
|
||||
}
|
||||
resp = self.fetch(xhr_url, headers=xhr_headers)
|
||||
data = json.loads(resp.text)
|
||||
if data.get("available", True):
|
||||
sources_block = data.get("sources", {})
|
||||
sources = sources_block.get("mp4", {})
|
||||
final_url = None
|
||||
if sources:
|
||||
quality_sorted = sorted(sources.keys(), key=lambda q: int(re.sub(r"\D", "", q) or 0), reverse=True)
|
||||
best_quality = quality_sorted[0]
|
||||
final_url = sources[best_quality].get("src")
|
||||
else:
|
||||
hls = sources_block.get("hls")
|
||||
if isinstance(hls, dict):
|
||||
final_url = hls.get("src")
|
||||
elif isinstance(hls, list) and hls:
|
||||
final_url = hls[0].get("src")
|
||||
best_quality = "hls"
|
||||
if final_url:
|
||||
result["parse"] = 0
|
||||
result["url"] = final_url
|
||||
result["header"] = {
|
||||
'User-Agent': self.headers['User-Agent'],
|
||||
'Referer': url,
|
||||
'Origin': self.host,
|
||||
'Accept': '*/*'
|
||||
}
|
||||
return result
|
||||
|
||||
def encode_base_n(self, num, n, table=None):
|
||||
FULL_TABLE = '0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ'
|
||||
if not table:
|
||||
table = FULL_TABLE[:n]
|
||||
if n > len(table):
|
||||
raise ValueError('base %d exceeds table length %d' % (n, len(table)))
|
||||
if num == 0:
|
||||
return table[0]
|
||||
ret = ''
|
||||
while num:
|
||||
ret = table[num % n] + ret
|
||||
num = num // n
|
||||
return ret
|
||||
|
||||
def e64(self, text):
|
||||
return b64encode(text.encode()).decode()
|
||||
|
||||
def d64(self, encoded_text):
|
||||
return b64decode(encoded_text.encode()).decode()
|
||||
|
||||
def html(self, content):
|
||||
from lxml import etree
|
||||
return etree.HTML(content)
|
||||
|
||||
def fetch(self, url, headers=None, timeout=None):
|
||||
import requests, ssl
|
||||
ssl._create_default_https_context = ssl._create_unverified_context
|
||||
if headers is None:
|
||||
headers = self.headers
|
||||
if timeout is None:
|
||||
timeout = self.timeout
|
||||
for _ in range(self.retries + 1):
|
||||
resp = requests.get(url, headers=headers, timeout=timeout, verify=False, cookies=getattr(self, 'cookies', None))
|
||||
resp.encoding = 'utf-8'
|
||||
return resp
|
||||
time.sleep(1)
|
||||
raise Exception("Fetch failed")
|
||||
|
||||
def _parse_video_list(self, root):
|
||||
videos = []
|
||||
items = root.xpath('//div[contains(@class, "mb") and @data-id]')
|
||||
for item in items:
|
||||
link = item.xpath('.//a[contains(@href, "/video-")]/@href')
|
||||
if not link:
|
||||
continue
|
||||
vod_id = self.host + link[0]
|
||||
title = "".join(item.xpath('.//p[contains(@class, "mbtit")]//text()')).strip()
|
||||
img = item.xpath('.//img/@src')
|
||||
thumbnail = img[0] if img else ""
|
||||
duration = "".join(item.xpath('.//span[contains(@class,"mbtim")]/text()')).strip()
|
||||
videos.append({
|
||||
"vod_id": vod_id,
|
||||
"vod_name": title or "爱看AV",
|
||||
"vod_pic": thumbnail,
|
||||
"vod_remarks": duration
|
||||
})
|
||||
return videos
|
||||
|
||||
def _map_tid_to_api(self, tid: str):
|
||||
params = {"query": "all", "order": "latest", "gay": "0", "per_page": 30}
|
||||
t = (tid or '').strip('/').lower()
|
||||
if t.startswith('best-videos'):
|
||||
params["order"] = "most-popular"
|
||||
elif t.startswith('top-rated'):
|
||||
params["order"] = "top-rated"
|
||||
elif t.startswith('cat/4k-porn'):
|
||||
params["query"] = "4k"
|
||||
elif t.startswith('cat/gay'):
|
||||
params["gay"] = "2"
|
||||
params["order"] = "latest"
|
||||
else:
|
||||
params["gay"] = "0"
|
||||
return params
|
||||
|
||||
def _api_search(self, query="all", page=1, order="latest", gay="0", per_page=30, thumbsize="medium"):
|
||||
base = f"{self.host}/api/v2/video/search/"
|
||||
q = {
|
||||
"query": query,
|
||||
"per_page": per_page,
|
||||
"page": page,
|
||||
"thumbsize": thumbsize,
|
||||
"order": order,
|
||||
"format": "json"
|
||||
}
|
||||
if gay is not None:
|
||||
q["gay"] = gay
|
||||
url = base + "?" + urllib.parse.urlencode(q)
|
||||
r = self.fetch(url, headers={**self.headers, 'X-Requested-With': 'XMLHttpRequest'})
|
||||
data = json.loads(r.text)
|
||||
return self._parse_api_list(data)
|
||||
|
||||
def _parse_api_list(self, data: dict):
|
||||
videos = []
|
||||
for v in (data or {}).get('videos', []):
|
||||
vurl = v.get('url') or ''
|
||||
title = v.get('title') or ''
|
||||
thumb = (v.get('default_thumb') or {}).get('src') or ''
|
||||
remarks = v.get('length_min') or ''
|
||||
videos.append({
|
||||
"vod_id": vurl if vurl.startswith('http') else (self.host + vurl),
|
||||
"vod_name": title or "爱看AV",
|
||||
"vod_pic": thumb,
|
||||
"vod_remarks": remarks
|
||||
})
|
||||
return videos
|
||||
@@ -0,0 +1,335 @@
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
import re
|
||||
from base.spider import Spider
|
||||
import sys
|
||||
import json
|
||||
import base64
|
||||
import urllib.parse
|
||||
from Crypto.Cipher import ARC4
|
||||
from Crypto.Util.Padding import unpad
|
||||
import binascii
|
||||
|
||||
sys.path.append('..')
|
||||
|
||||
xurl = "https://www.fullhd.xxx/zh/"
|
||||
|
||||
headerx = {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.87 Safari/537.36'
|
||||
}
|
||||
|
||||
pm = ''
|
||||
|
||||
class Spider(Spider):
|
||||
global xurl
|
||||
global headerx
|
||||
|
||||
def getName(self):
|
||||
return "首页"
|
||||
|
||||
def init(self, extend):
|
||||
pass
|
||||
|
||||
def isVideoFormat(self, url):
|
||||
pass
|
||||
|
||||
def manualVideoCheck(self):
|
||||
pass
|
||||
|
||||
def extract_middle_text(self, text, start_str, end_str, pl, start_index1: str = '', end_index2: str = ''):
|
||||
if pl == 3:
|
||||
plx = []
|
||||
while True:
|
||||
start_index = text.find(start_str)
|
||||
if start_index == -1:
|
||||
break
|
||||
end_index = text.find(end_str, start_index + len(start_str))
|
||||
if end_index == -1:
|
||||
break
|
||||
middle_text = text[start_index + len(start_str):end_index]
|
||||
plx.append(middle_text)
|
||||
text = text.replace(start_str + middle_text + end_str, '')
|
||||
if len(plx) > 0:
|
||||
purl = ''
|
||||
for i in range(len(plx)):
|
||||
matches = re.findall(start_index1, plx[i])
|
||||
output = ""
|
||||
for match in matches:
|
||||
match3 = re.search(r'(?:^|[^0-9])(\d+)(?:[^0-9]|$)', match[1])
|
||||
if match3:
|
||||
number = match3.group(1)
|
||||
else:
|
||||
number = 0
|
||||
if 'http' not in match[0]:
|
||||
output += f"#{'📽️' + match[1]}${number}{xurl}{match[0]}"
|
||||
else:
|
||||
output += f"#{'📽️' + match[1]}${number}{match[0]}"
|
||||
output = output[1:]
|
||||
purl = purl + output + "$$$"
|
||||
purl = purl[:-3]
|
||||
return purl
|
||||
else:
|
||||
return ""
|
||||
else:
|
||||
start_index = text.find(start_str)
|
||||
if start_index == -1:
|
||||
return ""
|
||||
end_index = text.find(end_str, start_index + len(start_str))
|
||||
if end_index == -1:
|
||||
return ""
|
||||
|
||||
if pl == 0:
|
||||
middle_text = text[start_index + len(start_str):end_index]
|
||||
return middle_text.replace("\\", "")
|
||||
|
||||
if pl == 1:
|
||||
middle_text = text[start_index + len(start_str):end_index]
|
||||
matches = re.findall(start_index1, middle_text)
|
||||
if matches:
|
||||
jg = ' '.join(matches)
|
||||
return jg
|
||||
|
||||
if pl == 2:
|
||||
middle_text = text[start_index + len(start_str):end_index]
|
||||
matches = re.findall(start_index1, middle_text)
|
||||
if matches:
|
||||
new_list = [f'✨{item}' for item in matches]
|
||||
jg = '$$$'.join(new_list)
|
||||
return jg
|
||||
|
||||
def homeContent(self, filter):
|
||||
result = {}
|
||||
result = {"class": [{"type_id": "latest-updates", "type_name": "最新视频🌠"},
|
||||
{"type_id": "top-rated", "type_name": "最佳视频🌠"},
|
||||
{"type_id": "most-popular", "type_name": "热门影片🌠"}],
|
||||
}
|
||||
return result
|
||||
|
||||
def homeVideoContent(self):
|
||||
videos = []
|
||||
try:
|
||||
detail = requests.get(url=xurl, headers=headerx)
|
||||
detail.encoding = "utf-8"
|
||||
res = detail.text
|
||||
doc = BeautifulSoup(res, "lxml")
|
||||
|
||||
# Get videos from different sections
|
||||
sections = {
|
||||
"latest-updates": "最新视频",
|
||||
"top-rated": "最佳视频",
|
||||
"most-popular": "热门影片"
|
||||
}
|
||||
|
||||
for section_id, section_name in sections.items():
|
||||
section = doc.find('div', id=f"list_videos_videos_watched_right_now_items")
|
||||
if not section:
|
||||
continue
|
||||
|
||||
vods = section.find_all('div', class_="item")
|
||||
for vod in vods:
|
||||
names = vod.find_all('a')
|
||||
name = names[0]['title'] if names and 'title' in names[0].attrs else section_name
|
||||
|
||||
ids = vod.find_all('a')
|
||||
id = ids[0]['href'] if ids else ""
|
||||
|
||||
pics = vod.find('img', class_="lazyload")
|
||||
pic = pics['data-src'] if pics and 'data-src' in pics.attrs else ""
|
||||
|
||||
if pic and 'http' not in pic:
|
||||
pic = xurl + pic
|
||||
|
||||
remarks = vod.find('span', class_="duration")
|
||||
remark = remarks.text.strip() if remarks else ""
|
||||
|
||||
video = {
|
||||
"vod_id": id,
|
||||
"vod_name": name,
|
||||
"vod_pic": pic,
|
||||
"vod_remarks": remark
|
||||
}
|
||||
videos.append(video)
|
||||
|
||||
result = {'list': videos}
|
||||
return result
|
||||
except Exception as e:
|
||||
print(f"Error in homeVideoContent: {str(e)}")
|
||||
return {'list': []}
|
||||
|
||||
def categoryContent(self, cid, pg, filter, ext):
|
||||
result = {}
|
||||
videos = []
|
||||
try:
|
||||
if pg and int(pg) > 1:
|
||||
url = f'{xurl}/{cid}/{pg}/'
|
||||
else:
|
||||
url = f'{xurl}/{cid}/'
|
||||
|
||||
detail = requests.get(url=url, headers=headerx)
|
||||
detail.encoding = "utf-8"
|
||||
res = detail.text
|
||||
doc = BeautifulSoup(res, "lxml")
|
||||
|
||||
section = doc.find('div', class_="list-videos")
|
||||
if section:
|
||||
vods = section.find_all('div', class_="item")
|
||||
for vod in vods:
|
||||
names = vod.find_all('a')
|
||||
name = names[0]['title'] if names and 'title' in names[0].attrs else ""
|
||||
|
||||
ids = vod.find_all('a')
|
||||
id = ids[0]['href'] if ids else ""
|
||||
|
||||
pics = vod.find('img', class_="lazyload")
|
||||
pic = pics['data-src'] if pics and 'data-src' in pics.attrs else ""
|
||||
|
||||
if pic and 'http' not in pic:
|
||||
pic = xurl + pic
|
||||
|
||||
remarks = vod.find('span', class_="duration")
|
||||
remark = remarks.text.strip() if remarks else ""
|
||||
|
||||
video = {
|
||||
"vod_id": id,
|
||||
"vod_name": name,
|
||||
"vod_pic": pic,
|
||||
"vod_remarks": remark
|
||||
}
|
||||
videos.append(video)
|
||||
|
||||
except Exception as e:
|
||||
print(f"Error in categoryContent: {str(e)}")
|
||||
|
||||
result = {
|
||||
'list': videos,
|
||||
'page': pg,
|
||||
'pagecount': 9999,
|
||||
'limit': 90,
|
||||
'total': 999999
|
||||
}
|
||||
return result
|
||||
|
||||
def detailContent(self, ids):
|
||||
global pm
|
||||
did = ids[0]
|
||||
result = {}
|
||||
videos = []
|
||||
playurl = ''
|
||||
if 'http' not in did:
|
||||
did = xurl + did
|
||||
res1 = requests.get(url=did, headers=headerx)
|
||||
res1.encoding = "utf-8"
|
||||
res = res1.text
|
||||
|
||||
content = '👉' + self.extract_middle_text(res,'<h1>','</h1>', 0)
|
||||
|
||||
yanuan = self.extract_middle_text(res, '<span>Pornstars:</span>','</div>',1, 'href=".*?">(.*?)</a>')
|
||||
|
||||
bofang = did
|
||||
|
||||
videos.append({
|
||||
"vod_id": did,
|
||||
"vod_actor": yanuan,
|
||||
"vod_director": '',
|
||||
"vod_content": content,
|
||||
"vod_play_from": '💗4K💗',
|
||||
"vod_play_url": bofang
|
||||
})
|
||||
|
||||
result['list'] = videos
|
||||
return result
|
||||
|
||||
def playerContent(self, flag, id, vipFlags):
|
||||
parts = id.split("http")
|
||||
xiutan = 0
|
||||
if xiutan == 0:
|
||||
if len(parts) > 1:
|
||||
before_https, after_https = parts[0], 'http' + parts[1]
|
||||
res = requests.get(url=after_https, headers=headerx)
|
||||
res = res.text
|
||||
|
||||
url2 = self.extract_middle_text(res, '<video', '</video>', 0).replace('\\', '')
|
||||
soup = BeautifulSoup(url2, 'html.parser')
|
||||
first_source = soup.find('source')
|
||||
src_value = first_source.get('src')
|
||||
|
||||
response = requests.head(src_value, allow_redirects=False)
|
||||
if response.status_code == 302:
|
||||
redirect_url = response.headers['Location']
|
||||
|
||||
response = requests.head(redirect_url, allow_redirects=False)
|
||||
if response.status_code == 302:
|
||||
redirect_url = response.headers['Location']
|
||||
|
||||
result = {}
|
||||
result["parse"] = xiutan
|
||||
result["playUrl"] = ''
|
||||
result["url"] = redirect_url
|
||||
result["header"] = headerx
|
||||
return result
|
||||
|
||||
def searchContentPage(self, key, quick, page):
|
||||
result = {}
|
||||
videos = []
|
||||
if not page:
|
||||
page = '1'
|
||||
if page == '1':
|
||||
url = f'{xurl}/search/{key}/'
|
||||
else:
|
||||
url = f'{xurl}/search/{key}/{str(page)}/'
|
||||
|
||||
try:
|
||||
detail = requests.get(url=url, headers=headerx)
|
||||
detail.encoding = "utf-8"
|
||||
res = detail.text
|
||||
doc = BeautifulSoup(res, "lxml")
|
||||
|
||||
section = doc.find('div', class_="list-videos")
|
||||
if section:
|
||||
vods = section.find_all('div', class_="item")
|
||||
for vod in vods:
|
||||
names = vod.find_all('a')
|
||||
name = names[0]['title'] if names and 'title' in names[0].attrs else ""
|
||||
|
||||
ids = vod.find_all('a')
|
||||
id = ids[0]['href'] if ids else ""
|
||||
|
||||
pics = vod.find('img', class_="lazyload")
|
||||
pic = pics['data-src'] if pics and 'data-src' in pics.attrs else ""
|
||||
|
||||
if pic and 'http' not in pic:
|
||||
pic = xurl + pic
|
||||
|
||||
remarks = vod.find('span', class_="duration")
|
||||
remark = remarks.text.strip() if remarks else ""
|
||||
|
||||
video = {
|
||||
"vod_id": id,
|
||||
"vod_name": name,
|
||||
"vod_pic": pic,
|
||||
"vod_remarks": remark
|
||||
}
|
||||
videos.append(video)
|
||||
except Exception as e:
|
||||
print(f"Error in searchContentPage: {str(e)}")
|
||||
|
||||
result = {
|
||||
'list': videos,
|
||||
'page': page,
|
||||
'pagecount': 9999,
|
||||
'limit': 90,
|
||||
'total': 999999
|
||||
}
|
||||
return result
|
||||
|
||||
def searchContent(self, key, quick):
|
||||
return self.searchContentPage(key, quick, '1')
|
||||
|
||||
def localProxy(self, params):
|
||||
if params['type'] == "m3u8":
|
||||
return self.proxyM3u8(params)
|
||||
elif params['type'] == "media":
|
||||
return self.proxyMedia(params)
|
||||
elif params['type'] == "ts":
|
||||
return self.proxyTs(params)
|
||||
return None
|
||||
@@ -0,0 +1,71 @@
|
||||
|
||||
import re
|
||||
import requests
|
||||
|
||||
class Spider():
|
||||
def getName(self):
|
||||
return 'JAV36'
|
||||
|
||||
def init(self, extend=''):
|
||||
pass
|
||||
|
||||
def getDependence(self):
|
||||
return []
|
||||
|
||||
def homeContent(self, filter):
|
||||
return {
|
||||
'class': [
|
||||
{'type_name': '最新更新', 'type_id': 'latest-updates/'},
|
||||
{'type_name': '4K高清', 'type_id': 'tags/4k/'}
|
||||
],
|
||||
'list': []
|
||||
}
|
||||
|
||||
def homeVideoContent(self):
|
||||
return self.categoryContent('latest-updates/', 1, False, {})
|
||||
|
||||
def categoryContent(self, tid, pg, filter, extend):
|
||||
url = f'https://jav36.com/{tid}'
|
||||
if int(pg) > 1:
|
||||
url = f'https://jav36.com/{tid}{pg}/'
|
||||
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36'}
|
||||
try:
|
||||
res = requests.get(url, headers=headers, timeout=15)
|
||||
return {'list': self.parse_list(res.text)}
|
||||
except: return {'list': []}
|
||||
|
||||
def searchContent(self, keyword, quick, pg=1):
|
||||
url = f'https://jav36.com/search/{keyword}/'
|
||||
if int(pg) > 1:
|
||||
url = f'https://jav36.com/search/{keyword}/{pg}/'
|
||||
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36'}
|
||||
try:
|
||||
res = requests.get(url, headers=headers, timeout=15)
|
||||
return {'list': self.parse_list(res.text)}
|
||||
except: return {'list': []}
|
||||
|
||||
def parse_list(self, html):
|
||||
vod_list = []
|
||||
pattern = r'href=\"https://jav36\.com/videos/(?P<id_path>\d+/(?P<id>[^/]+)/)\" title=\"(?P<name>[^\"]+)\".*?data-original=\"(?P<pic>[^\"]+)\"'
|
||||
for m in re.finditer(pattern, html, re.S):
|
||||
vod_list.append({
|
||||
'vod_id': m.group('id_path'),
|
||||
'vod_name': m.group('name').strip(),
|
||||
'vod_pic': m.group('pic'),
|
||||
'vod_remarks': 'Full HD'
|
||||
})
|
||||
return vod_list
|
||||
|
||||
def detailContent(self, ids):
|
||||
return {'list': [{'vod_id': ids[0], 'vod_name': 'Video', 'vod_play_from': 'Direct', 'vod_play_url': 'Play$'+ids[0]}]}
|
||||
|
||||
def playerContent(self, flag, id, vipFlags):
|
||||
url = f'https://jav36.com/videos/{id}'
|
||||
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36'}
|
||||
try:
|
||||
res = requests.get(url, headers=headers, timeout=10)
|
||||
match = re.search(r'\"contentUrl\"\s*:\s*\"([^\"]+)\"', res.text)
|
||||
if match:
|
||||
return {'parse': 0, 'url': match.group(1), 'header': {'User-Agent': headers['User-Agent'], 'Referer': 'https://jav36.com/'}}
|
||||
except: pass
|
||||
return {'parse': 0, 'url': url}
|
||||
@@ -0,0 +1,161 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
import re
|
||||
import urllib.parse
|
||||
import requests
|
||||
|
||||
try:
|
||||
from base.spider import Spider as BaseSpider
|
||||
except ImportError:
|
||||
class BaseSpider:
|
||||
pass
|
||||
|
||||
class Spider(BaseSpider):
|
||||
BASE_URL = "https://jable.sbs"
|
||||
FALLBACK_URLS = ["https://jable.sbs", "https://jable.tv"]
|
||||
HEADERS = {
|
||||
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
|
||||
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
|
||||
"Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
|
||||
"Referer": BASE_URL + "/",
|
||||
}
|
||||
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.name = "JableTV"
|
||||
self.session = requests.Session()
|
||||
self.session.headers.update(self.HEADERS)
|
||||
self._class_cache = None
|
||||
|
||||
def init(self, extend="{}"):
|
||||
return None
|
||||
|
||||
def getName(self):
|
||||
return self.name
|
||||
|
||||
def homeContent(self, filter):
|
||||
html = self._get(self.BASE_URL + "/latest-updates/")
|
||||
return {"class": self._classes(), "filters": {}, "list": self._parse_list(html), "parse": 0, "jx": 0}
|
||||
|
||||
def homeVideoContent(self):
|
||||
return {"list": self._parse_list(self._get(self.BASE_URL + "/latest-updates/"))}
|
||||
|
||||
def categoryContent(self, tid, pg, filter, extend):
|
||||
page = self._to_int(pg, 1)
|
||||
path = str(tid or "latest-updates").strip("/")
|
||||
url = self.BASE_URL + "/" + path + "/" if page <= 1 else self.BASE_URL + "/" + path + "/" + str(page) + "/"
|
||||
data = self._parse_list(self._get(url))
|
||||
return {"page": page, "pagecount": page if len(data) < 10 else page + 1, "limit": 24, "total": 99999, "list": data, "parse": 0, "jx": 0}
|
||||
|
||||
def detailContent(self, ids):
|
||||
result = {"list": [], "parse": 0, "jx": 0}
|
||||
if not ids:
|
||||
return result
|
||||
url = self._fix_url(ids[0] if str(ids[0]).startswith("http") else self.BASE_URL + "/videos/" + str(ids[0]).strip("/") + "/")
|
||||
html = self._get(url)
|
||||
name = self._clean(self._match(html, r'<h4[^>]*>(.*?)</h4>') or self._match(html, r'<meta[^>]+property=["\']og:title["\'][^>]+content=["\']([^"\']+)') or self._match(html, r'<title>(.*?)</title>').split("-")[0])
|
||||
pic = self._match(html, r'<meta[^>]+property=["\']og:image["\'][^>]+content=["\']([^"\']+)') or self._match(html, r'<video[^>]+poster=["\']([^"\']+)') or self._match(html, r'<img[^>]+(?:data-src|src)=["\']([^"\']+)')
|
||||
tags = ",".join([self._clean(x) for x in re.findall(r'<a[^>]+href=["\'][^"\']*/tags/[^"\']+["\'][^>]*>(.*?)</a>', html, re.S)])
|
||||
remarks = self._clean(" ".join(re.findall(r'<h6[^>]*>(.*?)</h6>', html, re.S)[:3]))
|
||||
content = self._clean(self._match(html, r'<div[^>]+class=["\'][^"\']*(?:description|info|text)[^"\']*["\'][^>]*>(.*?)</div>') or remarks or name)
|
||||
m3u8 = self._m3u8(html)
|
||||
result["list"].append({"vod_id": url, "vod_name": name, "vod_pic": urllib.parse.urljoin(self.BASE_URL, pic), "type_name": tags, "vod_year": "", "vod_area": "", "vod_remarks": remarks, "vod_actor": tags, "vod_director": "", "vod_content": content, "vod_play_from": "Jable", "vod_play_url": "正片$" + (m3u8 or url)})
|
||||
return result
|
||||
|
||||
def searchContent(self, key, quick, pg="1"):
|
||||
page = self._to_int(pg, 1)
|
||||
q = urllib.parse.quote(str(key))
|
||||
url = self.BASE_URL + "/search/" + q + "/" if page <= 1 else self.BASE_URL + "/search/" + q + "/" + str(page) + "/"
|
||||
data = self._parse_list(self._get(url))
|
||||
return {"page": page, "pagecount": page if len(data) < 10 else page + 1, "limit": 24, "total": 99999, "list": data, "parse": 0, "jx": 0}
|
||||
|
||||
def playerContent(self, flag, id, vipFlags):
|
||||
result = {"parse": 0, "playUrl": "", "url": id or "", "jx": 0, "header": {"User-Agent": self.HEADERS["User-Agent"], "Referer": self.BASE_URL + "/"}}
|
||||
if not id:
|
||||
return result
|
||||
if ".m3u8" in id or ".mp4" in id:
|
||||
return result
|
||||
play_page = self._fix_url(id if str(id).startswith("http") else self.BASE_URL + "/videos/" + str(id).strip("/") + "/")
|
||||
html = self._get(play_page)
|
||||
m3u8 = self._m3u8(html)
|
||||
if m3u8:
|
||||
result["url"] = m3u8
|
||||
result["header"] = {"User-Agent": self.HEADERS["User-Agent"], "Referer": play_page, "Origin": self.BASE_URL}
|
||||
else:
|
||||
result["url"] = play_page
|
||||
result["parse"] = 1
|
||||
return result
|
||||
|
||||
def _classes(self, html=None):
|
||||
if self._class_cache:
|
||||
return self._class_cache
|
||||
self._class_cache = [
|
||||
{"type_id": "latest-updates", "type_name": "最近更新"},
|
||||
{"type_id": "hot", "type_name": "热门影片"},
|
||||
{"type_id": "new-release", "type_name": "全新上市"},
|
||||
{"type_id": "tags/chinese-subtitle", "type_name": "中文字幕"},
|
||||
{"type_id": "tags/drama", "type_name": "剧情"},
|
||||
{"type_id": "tags/cosplay", "type_name": "角色扮演"},
|
||||
]
|
||||
return self._class_cache
|
||||
|
||||
def _parse_list(self, html):
|
||||
data, seen = [], set()
|
||||
cards = re.findall(r'(<div[^>]+class=["\'][^"\']*video-img-box[^"\']*["\'][\s\S]*?</h6>[\s\S]*?</div>\s*</div>)', html or "", re.S | re.I)
|
||||
if not cards:
|
||||
cards = re.findall(r'(<a[^>]+href=["\'][^"\']*/videos/[^"\']+["\'][\s\S]*?</a>)', html or "", re.S | re.I)
|
||||
for item in cards:
|
||||
href = self._match(item, r'href=["\']([^"\']*/videos/[^"\']+)["\']')
|
||||
if not href:
|
||||
continue
|
||||
name = self._clean(self._match(item, r'<h6[^>]*class=["\'][^"\']*title[^"\']*["\'][^>]*>\s*<a[^>]*>(.*?)</a>') or self._match(item, r'title=["\']([^"\']+)') or self._match(item, r'alt=["\']([^"\']+)'))
|
||||
pic = self._match(item, r'(?:data-src|data-original|data-lazy-src|data-lazyload)=["\']([^"\']+)') or self._match(item, r'<img[^>]+src=["\']([^"\']+)')
|
||||
remarks = self._clean(self._match(item, r'<span[^>]+class=["\'][^"\']*(?:duration|label|badge)[^"\']*["\'][^>]*>(.*?)</span>') or self._match(item, r'(\d{1,2}:\d{2}(?::\d{2})?)'))
|
||||
full = self._fix_url(urllib.parse.urljoin(self.BASE_URL, href))
|
||||
if full not in seen and name and not re.fullmatch(r'\d{1,2}:\d{2}(?::\d{2})?', name):
|
||||
seen.add(full)
|
||||
data.append({"vod_id": full, "vod_name": name, "vod_pic": urllib.parse.urljoin(self.BASE_URL, pic), "vod_remarks": remarks})
|
||||
return data
|
||||
|
||||
def _get(self, url, headers=None):
|
||||
for real in self._candidate_urls(self._fix_url(url)):
|
||||
h = dict(self.HEADERS)
|
||||
h["Referer"] = self.BASE_URL + "/"
|
||||
if headers:
|
||||
h.update(headers)
|
||||
try:
|
||||
r = self.session.get(real, headers=h, timeout=15, verify=False)
|
||||
r.encoding = "utf-8"
|
||||
if r.status_code < 400 and "Just a moment" not in r.text and "cf-browser-verification" not in r.text:
|
||||
return r.text
|
||||
except Exception:
|
||||
continue
|
||||
return ""
|
||||
|
||||
def _candidate_urls(self, url):
|
||||
urls = [url]
|
||||
for host in self.FALLBACK_URLS:
|
||||
p = urllib.parse.urlparse(url)
|
||||
if p.netloc and host not in url:
|
||||
urls.append(host + p.path + ("?" + p.query if p.query else ""))
|
||||
return list(dict.fromkeys(urls))
|
||||
|
||||
def _fix_url(self, url):
|
||||
return str(url or "").replace("https://jable.tv", self.BASE_URL).replace("http://jable.tv", self.BASE_URL).replace("https://www.jable.tv", self.BASE_URL)
|
||||
|
||||
def _m3u8(self, html):
|
||||
return self._match(html, r'var\s+hlsUrl\s*=\s*["\']([^"\']+\.m3u8[^"\']*)') or self._match(html, r'["\'](https?://[^"\']+\.m3u8[^"\']*)["\']')
|
||||
|
||||
def _match(self, text, pattern):
|
||||
m = re.search(pattern, text or "", re.S | re.I)
|
||||
return m.group(1).strip() if m else ""
|
||||
|
||||
def _clean(self, text):
|
||||
text = re.sub(r'<.*?>', '', text or '')
|
||||
text = text.replace(' ', ' ').replace('&', '&').replace('&', '&').replace('"', '"')
|
||||
return re.sub(r'\s+', ' ', text).strip()
|
||||
|
||||
def _to_int(self, value, default=0):
|
||||
try:
|
||||
return int(value)
|
||||
except Exception:
|
||||
return default
|
||||
@@ -0,0 +1,301 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import json
|
||||
import re
|
||||
import sys
|
||||
from base64 import b64decode, b64encode
|
||||
from urllib.parse import urlparse
|
||||
|
||||
import requests
|
||||
from pyquery import PyQuery as pq
|
||||
from requests import Session
|
||||
sys.path.append('..')
|
||||
from base.spider import Spider
|
||||
|
||||
class Spider(Spider):
|
||||
|
||||
def init(self, extend=""):
|
||||
'''
|
||||
内置代理配置：真心jar为例
|
||||
{
|
||||
"key": "Phb",
|
||||
"name": "Phb",
|
||||
"type": 3,
|
||||
"searchable": 1,
|
||||
"quickSearch": 1,
|
||||
"filterable": 1,
|
||||
"api": "./py/Phb.py",
|
||||
"ext": {
|
||||
"http": "http://127.0.0.1:1072",
|
||||
"https": "http://127.0.0.1:1072"
|
||||
}
|
||||
},
|
||||
注：http(s)代理都是http
|
||||
'''
|
||||
try:self.proxies = json.loads(extend)
|
||||
except:self.proxies = {}
|
||||
self.headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.5410.0 Safari/537.36',
|
||||
'pragma': 'no-cache',
|
||||
'cache-control': 'no-cache',
|
||||
'sec-ch-ua-platform': '"Windows"',
|
||||
'sec-ch-ua': '"Not(A:Brand";v="99", "Google Chrome";v="133", "Chromium";v="133"',
|
||||
'dnt': '1',
|
||||
'sec-ch-ua-mobile': '?0',
|
||||
'sec-fetch-site': 'cross-site',
|
||||
'sec-fetch-mode': 'cors',
|
||||
'sec-fetch-dest': 'empty',
|
||||
'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8',
|
||||
'priority': 'u=1, i',
|
||||
}
|
||||
self.host = self.gethost()
|
||||
self.headers.update({'referer': f'{self.host}/', 'origin': self.host})
|
||||
self.session = Session()
|
||||
self.session.proxies.update(self.proxies)
|
||||
self.session.headers.update(self.headers)
|
||||
pass
|
||||
|
||||
def getName(self):
|
||||
pass
|
||||
|
||||
def isVideoFormat(self, url):
|
||||
pass
|
||||
|
||||
def manualVideoCheck(self):
|
||||
pass
|
||||
|
||||
def destroy(self):
|
||||
pass
|
||||
|
||||
def homeContent(self, filter):
|
||||
result = {}
|
||||
cateManual = {
|
||||
"视频": "/video",
|
||||
"片单": "/playlists",
|
||||
"频道": "/channels",
|
||||
"分类": "/categories",
|
||||
"明星": "/pornstars"
|
||||
}
|
||||
classes = []
|
||||
filters = {}
|
||||
for k in cateManual:
|
||||
classes.append({
|
||||
'type_name': k,
|
||||
'type_id': cateManual[k]
|
||||
})
|
||||
result['class'] = classes
|
||||
result['filters'] = filters
|
||||
return result
|
||||
|
||||
def homeVideoContent(self):
|
||||
data = self.getpq('/recommended')
|
||||
vhtml = data("#recommendedListings .pcVideoListItem .phimage")
|
||||
return {'list': self.getlist(vhtml)}
|
||||
|
||||
def categoryContent(self, tid, pg, filter, extend):
|
||||
vdata = []
|
||||
result = {}
|
||||
result['page'] = pg
|
||||
result['pagecount'] = 9999
|
||||
result['limit'] = 90
|
||||
result['total'] = 999999
|
||||
if tid == '/video' or '_this_video' in tid:
|
||||
pagestr = f'&' if '?' in tid else f'?'
|
||||
tid = tid.split('_this_video')[0]
|
||||
data = self.getpq(f'{tid}{pagestr}page={pg}')
|
||||
vdata = self.getlist(data('#videoCategory .pcVideoListItem'))
|
||||
elif tid == '/playlists':
|
||||
data = self.getpq(f'{tid}?page={pg}')
|
||||
vhtml = data('#playListSection li')
|
||||
vdata = []
|
||||
for i in vhtml.items():
|
||||
vdata.append({
|
||||
'vod_id': 'playlists_click_' + i('.thumbnail-info-wrapper .display-block a').attr('href'),
|
||||
'vod_name': i('.thumbnail-info-wrapper .display-block a').attr('title'),
|
||||
'vod_pic': self.proxy(i('.largeThumb').attr('src')),
|
||||
'vod_tag': 'folder',
|
||||
'vod_remarks': i('.playlist-videos .number').text(),
|
||||
'style': {"type": "rect", "ratio": 1.33}
|
||||
})
|
||||
elif tid == '/channels':
|
||||
data = self.getpq(f'{tid}?o=rk&page={pg}')
|
||||
vhtml = data('#filterChannelsSection li .description')
|
||||
vdata = []
|
||||
for i in vhtml.items():
|
||||
vdata.append({
|
||||
'vod_id': 'director_click_' + i('.avatar a').attr('href'),
|
||||
'vod_name': i('.avatar img').attr('alt'),
|
||||
'vod_pic': self.proxy(i('.avatar img').attr('src')),
|
||||
'vod_tag': 'folder',
|
||||
'vod_remarks': i('.descriptionContainer ul li').eq(-1).text(),
|
||||
'style': {"type": "rect", "ratio": 1.33}
|
||||
})
|
||||
elif tid == '/categories' and pg == '1':
|
||||
result['pagecount'] = 1
|
||||
data = self.getpq(f'{tid}')
|
||||
vhtml = data('.categoriesListSection li .relativeWrapper')
|
||||
vdata = []
|
||||
for i in vhtml.items():
|
||||
vdata.append({
|
||||
'vod_id': i('a').attr('href') + '_this_video',
|
||||
'vod_name': i('a').attr('alt'),
|
||||
'vod_pic': self.proxy(i('a img').attr('src')),
|
||||
'vod_tag': 'folder',
|
||||
'style': {"type": "rect", "ratio": 1.33}
|
||||
})
|
||||
elif tid == '/pornstars':
|
||||
data = self.getpq(f'{tid}?o=t&page={pg}')
|
||||
vhtml = data('#popularPornstars .performerCard .wrap')
|
||||
vdata = []
|
||||
for i in vhtml.items():
|
||||
vdata.append({
|
||||
'vod_id': 'pornstars_click_' + i('a').attr('href'),
|
||||
'vod_name': i('.performerCardName').text(),
|
||||
'vod_pic': self.proxy(i('a img').attr('src')),
|
||||
'vod_tag': 'folder',
|
||||
'vod_year': i('.performerVideosViewsCount span').eq(0).text(),
|
||||
'vod_remarks': i('.performerVideosViewsCount span').eq(-1).text(),
|
||||
'style': {"type": "rect", "ratio": 1.33}
|
||||
})
|
||||
elif 'playlists_click' in tid:
|
||||
tid = tid.split('click_')[-1]
|
||||
if pg == '1':
|
||||
hdata = self.getpq(tid)
|
||||
self.token = hdata('#searchInput').attr('data-token')
|
||||
vdata = self.getlist(hdata('#videoPlaylist .pcVideoListItem .phimage'))
|
||||
else:
|
||||
tid = tid.split('playlist/')[-1]
|
||||
data = self.getpq(f'/playlist/viewChunked?id={tid}&token={self.token}&page={pg}')
|
||||
vdata = self.getlist(data('.pcVideoListItem .phimage'))
|
||||
elif 'director_click' in tid:
|
||||
tid = tid.split('click_')[-1]
|
||||
data = self.getpq(f'{tid}/videos?page={pg}')
|
||||
vdata = self.getlist(data('#showAllChanelVideos .pcVideoListItem .phimage'))
|
||||
elif 'pornstars_click' in tid:
|
||||
tid = tid.split('click_')[-1]
|
||||
data = self.getpq(f'{tid}/videos?page={pg}')
|
||||
vdata = self.getlist(data('#mostRecentVideosSection .pcVideoListItem .phimage'))
|
||||
result['list'] = vdata
|
||||
return result
|
||||
|
||||
def detailContent(self, ids):
|
||||
url = f"{self.host}{ids[0]}"
|
||||
data = self.getpq(ids[0])
|
||||
vn = data('meta[property="og:title"]').attr('content')
|
||||
dtext = data('.userInfo .usernameWrap a')
|
||||
pdtitle = '[a=cr:' + json.dumps(
|
||||
{'id': 'director_click_' + dtext.attr('href'), 'name': dtext.text()}) + '/]' + dtext.text() + '[/a]'
|
||||
vod = {
|
||||
'vod_name': vn,
|
||||
'vod_director': pdtitle,
|
||||
'vod_remarks': (data('.userInfo').text() + ' / ' + data('.ratingInfo').text()).replace('\n', ' / '),
|
||||
'vod_play_from': '老僧酿酒',
|
||||
'vod_play_url': ''
|
||||
}
|
||||
js_content = data("#player script").eq(0).text()
|
||||
plist = [f"{vn}${self.e64(f'{1}@@@@{url}')}"]
|
||||
try:
|
||||
pattern = r'"mediaDefinitions":\s*(\[.*?\]),\s*"isVertical"'
|
||||
match = re.search(pattern, js_content, re.DOTALL)
|
||||
if match:
|
||||
json_str = match.group(1)
|
||||
udata = json.loads(json_str)
|
||||
plist = [
|
||||
f"{media['height']}${self.e64(f'{0}@@@@{url}')}"
|
||||
for media in udata[:-1]
|
||||
if (url := media.get('videoUrl'))
|
||||
]
|
||||
except Exception as e:
|
||||
print(f"提取mediaDefinitions失败: {str(e)}")
|
||||
vod['vod_play_url'] = '#'.join(plist)
|
||||
return {'list': [vod]}
|
||||
|
||||
def searchContent(self, key, quick, pg="1"):
|
||||
data = self.getpq(f'/video/search?search={key}&page={pg}')
|
||||
return {'list': self.getlist(data('#videoSearchResult .pcVideoListItem .phimage'))}
|
||||
|
||||
def playerContent(self, flag, id, vipFlags):
|
||||
ids = self.d64(id).split('@@@@')
|
||||
if '.m3u8' in ids[1]: ids[1] = self.proxy(ids[1], 'm3u8')
|
||||
return {'parse': int(ids[0]), 'url': ids[1], 'header': self.headers}
|
||||
|
||||
def localProxy(self, param):
|
||||
url = self.d64(param.get('url'))
|
||||
if param.get('type') == 'm3u8':
|
||||
return self.m3Proxy(url)
|
||||
else:
|
||||
return self.tsProxy(url)
|
||||
|
||||
def m3Proxy(self, url):
|
||||
ydata = requests.get(url, headers=self.headers, proxies=self.proxies, allow_redirects=False)
|
||||
data = ydata.content.decode('utf-8')
|
||||
if ydata.headers.get('Location'):
|
||||
url = ydata.headers['Location']
|
||||
data = requests.get(url, headers=self.headers, proxies=self.proxies).content.decode('utf-8')
|
||||
lines = data.strip().split('\n')
|
||||
last_r = url[:url.rfind('/')]
|
||||
parsed_url = urlparse(url)
|
||||
durl = parsed_url.scheme + "://" + parsed_url.netloc
|
||||
for index, string in enumerate(lines):
|
||||
if '#EXT' not in string:
|
||||
if 'http' not in string:
|
||||
domain = last_r if string.count('/') < 2 else durl
|
||||
string = domain + ('' if string.startswith('/') else '/') + string
|
||||
lines[index] = self.proxy(string, string.split('.')[-1].split('?')[0])
|
||||
data = '\n'.join(lines)
|
||||
return [200, "application/vnd.apple.mpegur", data]
|
||||
|
||||
def tsProxy(self, url):
|
||||
data = requests.get(url, headers=self.headers, proxies=self.proxies, stream=True)
|
||||
return [200, data.headers['Content-Type'], data.content]
|
||||
|
||||
def gethost(self):
|
||||
try:
|
||||
response = requests.get('https://www.pornhub.com', headers=self.headers, proxies=self.proxies,
|
||||
allow_redirects=False)
|
||||
return response.headers['Location'][:-1]
|
||||
except Exception as e:
|
||||
print(f"获取主页失败: {str(e)}")
|
||||
return "https://www.pornhub.com"
|
||||
|
||||
def e64(self, text):
|
||||
try:
|
||||
text_bytes = text.encode('utf-8')
|
||||
encoded_bytes = b64encode(text_bytes)
|
||||
return encoded_bytes.decode('utf-8')
|
||||
except Exception as e:
|
||||
print(f"Base64编码错误: {str(e)}")
|
||||
return ""
|
||||
|
||||
def d64(self, encoded_text):
|
||||
try:
|
||||
encoded_bytes = encoded_text.encode('utf-8')
|
||||
decoded_bytes = b64decode(encoded_bytes)
|
||||
return decoded_bytes.decode('utf-8')
|
||||
except Exception as e:
|
||||
print(f"Base64解码错误: {str(e)}")
|
||||
return ""
|
||||
|
||||
def getlist(self, data):
|
||||
vlist = []
|
||||
for i in data.items():
|
||||
vlist.append({
|
||||
'vod_id': i('a').attr('href'),
|
||||
'vod_name': i('a').attr('title'),
|
||||
'vod_pic': self.proxy(i('img').attr('src')),
|
||||
'vod_remarks': i('.bgShadeEffect').text() or i('.duration').text(),
|
||||
'style': {'ratio': 1.33, 'type': 'rect'}
|
||||
})
|
||||
return vlist
|
||||
|
||||
def getpq(self, path):
|
||||
try:
|
||||
response = self.session.get(f'{self.host}{path}').text
|
||||
return pq(response.encode('utf-8'))
|
||||
except Exception as e:
|
||||
print(f"请求失败: , {str(e)}")
|
||||
return None
|
||||
|
||||
def proxy(self, data, type='img'):
|
||||
if data and len(self.proxies):return f"{self.getProxyUrl()}&url={self.e64(data)}&type={type}"
|
||||
else:return data
|
||||
@@ -0,0 +1,124 @@
|
||||
import sys
|
||||
import re
|
||||
import json
|
||||
import requests
|
||||
from requests.adapters import HTTPAdapter
|
||||
from requests.packages.urllib3.util.retry import Retry
|
||||
from base.spider import Spider
|
||||
|
||||
class Spider(Spider):
|
||||
def getName(self):
|
||||
return "TOPTV"
|
||||
|
||||
def init(self, extend=""):
|
||||
super().init(extend)
|
||||
self.site_url = "https://toptv15.cyou"
|
||||
self.headers = {
|
||||
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
|
||||
"Referer": self.site_url
|
||||
}
|
||||
self.sess = requests.Session()
|
||||
self.sess.mount("https://", HTTPAdapter(max_retries=Retry(total=3, backoff_factor=1)))
|
||||
|
||||
def fetch(self, url, timeout=10):
|
||||
try:
|
||||
res = self.sess.get(url, headers=self.headers, timeout=timeout, verify=False)
|
||||
res.encoding = "utf-8"
|
||||
return res
|
||||
except:
|
||||
return None
|
||||
|
||||
def homeContent(self, filter):
|
||||
cate_list = [
|
||||
{"type_name": "国产自拍", "type_id": "1"},
|
||||
{"type_name": "国产传媒", "type_id": "2"},
|
||||
{"type_name": "探花系列", "type_id": "3"},
|
||||
{"type_name": "人妻熟女", "type_id": "4"},
|
||||
{"type_name": "日本无码", "type_id": "5"},
|
||||
{"type_name": "美乳巨乳", "type_id": "6"},
|
||||
{"type_name": "强制侵犯", "type_id": "7"},
|
||||
{"type_name": "制服诱惑", "type_id": "8"},
|
||||
{"type_name": "绝色佳人", "type_id": "9"},
|
||||
{"type_name": "家庭乱伦", "type_id": "10"},
|
||||
{"type_name": "绝顶潮吹", "type_id": "11"},
|
||||
{"type_name": "网红主播", "type_id": "12"}
|
||||
]
|
||||
return {"class": cate_list}
|
||||
|
||||
def categoryContent(self, tid, pg, filter, extend):
|
||||
if not hasattr(self, 'site_url'): self.init()
|
||||
pg = int(pg) if str(pg).isdigit() else 1
|
||||
list_url = f"{self.site_url}/index.php/vod/type/id/{tid}/page/{pg}.html"
|
||||
res = self.fetch(list_url)
|
||||
video_list = []
|
||||
if res:
|
||||
pattern = r'href="(/index.php/vod/detail/id/(\d+).html)".*?data-original="(.*?)".*?vod-name.*?>(.*?)<'
|
||||
matches = re.findall(pattern, res.text, re.S)
|
||||
for href, v_id, pic, name in matches:
|
||||
video_list.append({
|
||||
"vod_id": v_id,
|
||||
"vod_name": name.strip(),
|
||||
"vod_pic": pic if pic.startswith("http") else self.site_url + pic,
|
||||
"vod_remarks": ""
|
||||
})
|
||||
return {'list': video_list, 'page': pg, 'pagecount': 999, 'limit': 20, 'total': 9999}
|
||||
|
||||
def detailContent(self, ids):
|
||||
if not hasattr(self, 'site_url'): self.init()
|
||||
vod_id = ids[0]
|
||||
res = self.fetch(f"{self.site_url}/index.php/vod/detail/id/{vod_id}.html")
|
||||
if not res: return {}
|
||||
html = res.text
|
||||
name_match = re.search(r'vod-name.*?>(.*?)<', html) or re.search(r'title-box.*?>(.*?)<', html)
|
||||
pic_match = re.search(r'detail-pic.*?src="(.*?)"', html) or re.search(r'data-original="(.*?)"', html)
|
||||
|
||||
play_matches = re.findall(r'href="(/index.php/vod/play/id/(\d+)/sid/(\d+)/nid/(\d+).html)">(.*?)<', html)
|
||||
play_urls = []
|
||||
for m in play_matches:
|
||||
play_urls.append(f"{m[4]}${m[1]}-{m[2]}-{m[3]}")
|
||||
|
||||
if not play_urls:
|
||||
play_urls.append(f"立即播放${vod_id}-1-1")
|
||||
|
||||
vod = {
|
||||
"vod_id": vod_id,
|
||||
"vod_name": name_match.group(1).strip() if name_match else "视频详情",
|
||||
"vod_pic": pic_match.group(1) if pic_match else "",
|
||||
"vod_play_from": "TOP-TV",
|
||||
"vod_play_url": "#".join(play_urls)
|
||||
}
|
||||
return {"list": [vod]}
|
||||
|
||||
def playerContent(self, flag, id, vipFlags):
|
||||
if not hasattr(self, 'site_url'): self.init()
|
||||
parts = id.split('-')
|
||||
if len(parts) == 3:
|
||||
v_id, s_id, n_id = parts
|
||||
play_url = f"{self.site_url}/index.php/vod/play/id/{v_id}/sid/{s_id}/nid/{n_id}.html"
|
||||
else:
|
||||
play_url = f"{self.site_url}/index.php/vod/play/id/{id}.html"
|
||||
res = self.fetch(play_url)
|
||||
if res:
|
||||
data_json = re.search(r'var player_aaaa=(.*?)</script>', res.text)
|
||||
if data_json:
|
||||
try:
|
||||
url = json.loads(data_json.group(1)).get("url", "")
|
||||
return {"parse": 0, "url": url, "header": self.headers}
|
||||
except:
|
||||
pass
|
||||
return {"parse": 1, "url": play_url}
|
||||
|
||||
def searchContent(self, key, quick, pg=1):
|
||||
if not hasattr(self, 'site_url'): self.init()
|
||||
res = self.fetch(f"{self.site_url}/index.php/vod/search/page/{pg}/wd/{key}.html")
|
||||
video_list = []
|
||||
if res:
|
||||
pattern = r'href="(/index.php/vod/detail/id/(\d+).html)".*?data-original="(.*?)".*?vod-name.*?>(.*?)<'
|
||||
matches = re.findall(pattern, res.text, re.S)
|
||||
for href, v_id, pic, name in matches:
|
||||
video_list.append({
|
||||
"vod_id": v_id,
|
||||
"vod_name": name.strip(),
|
||||
"vod_pic": pic if pic.startswith("http") else self.site_url + pic
|
||||
})
|
||||
return {"list": video_list}
|
||||
@@ -0,0 +1,303 @@
|
||||
# coding: utf-8
|
||||
import json
|
||||
import sys
|
||||
import re
|
||||
import urllib.request
|
||||
import urllib.parse
|
||||
import ssl
|
||||
|
||||
sys.path.append('..')
|
||||
from base.spider import Spider
|
||||
|
||||
VERSION = '2.0.0'
|
||||
|
||||
SITE_URL = 'https://newxvideos.pages.dev'
|
||||
API_URL = 'https://newxvideos.pages.dev/api'
|
||||
|
||||
CATEGORIES = [
|
||||
{"type_id": "Arab-159", "type_name": "阿拉伯"},
|
||||
{"type_id": "Mature-38", "type_name": "成熟"},
|
||||
{"type_id": "Cuckold-237", "type_name": "出轨背叛"},
|
||||
{"type_id": "Femdom-235", "type_name": "调教"},
|
||||
{"type_id": "Anal-12", "type_name": "肛交"},
|
||||
{"type_id": "Brunette-25", "type_name": "褐发"},
|
||||
{"type_id": "Black_Woman-30", "type_name": "黑人"},
|
||||
{"type_id": "Redhead-31", "type_name": "红发"},
|
||||
{"type_id": "Fucked_Up_Family-81", "type_name": "家庭乱搞"},
|
||||
{"type_id": "Blonde-20", "type_name": "金发"},
|
||||
{"type_id": "Big_Cock-34", "type_name": "巨屌"},
|
||||
{"type_id": "Big_Tits-23", "type_name": "巨乳"},
|
||||
{"type_id": "Big_Ass-24", "type_name": "巨臀"},
|
||||
{"type_id": "Blowjob-15", "type_name": "口交"},
|
||||
{"type_id": "Latina-16", "type_name": "拉丁裔"},
|
||||
{"type_id": "Milf-19", "type_name": "辣妈"},
|
||||
{"type_id": "Gapes-167", "type_name": "裂开"},
|
||||
{"type_id": "Ass-14", "type_name": "美臀"},
|
||||
{"type_id": "Lesbian-26", "type_name": "女同"},
|
||||
{"type_id": "bbw-51", "type_name": "胖女"},
|
||||
{"type_id": "Squirting-56", "type_name": "喷出"},
|
||||
{"type_id": "Fisting-165", "type_name": "拳交"},
|
||||
{"type_id": "Gangbang-69", "type_name": "群交"},
|
||||
{"type_id": "Teen-13", "type_name": "少女"},
|
||||
{"type_id": "Cumshot-18", "type_name": "射颜"},
|
||||
{"type_id": "Cam_Porn-58", "type_name": "摄像头"},
|
||||
{"type_id": "Bi_Sexual-62", "type_name": "双性恋"},
|
||||
{"type_id": "Stockings-28", "type_name": "丝袜"},
|
||||
{"type_id": "Oiled-22", "type_name": "涂油"},
|
||||
{"type_id": "Lingerie-83", "type_name": "性感内衣"},
|
||||
{"type_id": "Asian_Woman-32", "type_name": "亚洲"},
|
||||
{"type_id": "Amateur-65", "type_name": "业余"},
|
||||
{"type_id": "Interracial-27", "type_name": "异族"},
|
||||
{"type_id": "Indian-89", "type_name": "印度"},
|
||||
{"type_id": "Creampie-40", "type_name": "中出"},
|
||||
{"type_id": "Solo_and_Masturbation-33", "type_name": "自慰"},
|
||||
{"type_id": "AI-239", "type_name": "AI"},
|
||||
{"type_id": "ASMR-229", "type_name": "ASMR"},
|
||||
]
|
||||
|
||||
|
||||
class Spider(Spider):
|
||||
def getName(self):
|
||||
return "V-HUB[成人]"
|
||||
|
||||
def init(self, extend):
|
||||
if extend:
|
||||
self.host = extend.get('host', SITE_URL)
|
||||
else:
|
||||
self.host = SITE_URL
|
||||
self.api_url = self.host.rstrip('/') + '/api'
|
||||
self.headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
|
||||
'Referer': self.host + '/',
|
||||
'Origin': self.host
|
||||
}
|
||||
self._ssl_context = ssl.create_default_context()
|
||||
self._ssl_context.check_hostname = False
|
||||
self._ssl_context.verify_mode = ssl.CERT_NONE
|
||||
|
||||
def _xhttp(self, params):
|
||||
"""使用标准库urllib发起HTTP GET请求"""
|
||||
try:
|
||||
qs = urllib.parse.urlencode(params)
|
||||
full_url = self.api_url + '?' + qs
|
||||
req = urllib.request.Request(full_url, headers=self.headers, method='GET')
|
||||
resp = urllib.request.urlopen(req, context=self._ssl_context, timeout=15)
|
||||
data = json.loads(resp.read().decode('utf-8'))
|
||||
if isinstance(data, list):
|
||||
return data
|
||||
elif isinstance(data, dict) and 'data' in data:
|
||||
return data['data']
|
||||
return []
|
||||
except Exception as e:
|
||||
print('_xhttp error: %s' % str(e), file=sys.stderr)
|
||||
return []
|
||||
|
||||
def _format_time_cn(self, time_str):
|
||||
"""将英文时间格式转为中文，如 '11 min' -> '11分钟'"""
|
||||
if not time_str:
|
||||
return ''
|
||||
m = re.match(r'^(\d+)\s*min\s*$', time_str.strip(), re.IGNORECASE)
|
||||
if m:
|
||||
return m.group(1) + '分钟'
|
||||
m = re.match(r'^(\d+)\s*h(?:our)?s?\s*(\d+)?\s*min\s*$', time_str.strip(), re.IGNORECASE)
|
||||
if m:
|
||||
h = m.group(1)
|
||||
mi = m.group(2)
|
||||
if mi:
|
||||
return h + '小时' + mi + '分钟'
|
||||
return h + '小时'
|
||||
return time_str
|
||||
|
||||
def _extract_xvid(self, url):
|
||||
"""从视频URL的查询参数中提取xvid值"""
|
||||
if not url:
|
||||
return ''
|
||||
parsed = urllib.parse.urlparse(url)
|
||||
qs = urllib.parse.parse_qs(parsed.query)
|
||||
if 'xvid' in qs:
|
||||
return qs['xvid'][0]
|
||||
return ''
|
||||
|
||||
def _build_vod_list(self, raw_data):
|
||||
"""将API返回的原始数据构造为vod列表"""
|
||||
videos = []
|
||||
for item in raw_data:
|
||||
title = item.get('title', '')
|
||||
clean_title = re.sub(r'^AVOTC资源网[—-]+\s*', '', title).strip()
|
||||
if not clean_title:
|
||||
clean_title = title
|
||||
|
||||
url = item.get('url', '')
|
||||
vod_id = self._extract_xvid(url)
|
||||
if not vod_id:
|
||||
vod_id = str(item.get('videoid', ''))
|
||||
|
||||
videos.append({
|
||||
'vod_id': vod_id,
|
||||
'vod_name': clean_title,
|
||||
'vod_pic': item.get('img', ''),
|
||||
'vod_remarks': self._format_time_cn(item.get('time', '')),
|
||||
'vod_url': url
|
||||
})
|
||||
return videos
|
||||
|
||||
def homeContent(self, filter):
|
||||
"""首页：返回分类列表 + 首页视频"""
|
||||
classes = []
|
||||
for cat in CATEGORIES:
|
||||
classes.append({'type_id': cat['type_id'], 'type_name': cat['type_name']})
|
||||
|
||||
raw_data = self._xhttp({'play': 'list', 'page': 1})
|
||||
videos = self._build_vod_list(raw_data)
|
||||
|
||||
return {'class': classes, 'list': videos}
|
||||
|
||||
def homeVideoContent(self):
|
||||
return {'list': []}
|
||||
|
||||
def categoryContent(self, tid, pg, filter, extend):
|
||||
"""分类内容"""
|
||||
raw_data = self._xhttp({'play': 'class', 'c': tid, 'page': pg})
|
||||
videos = self._build_vod_list(raw_data)
|
||||
|
||||
type_name = tid
|
||||
for cat in CATEGORIES:
|
||||
if cat['type_id'] == tid:
|
||||
type_name = cat['type_name']
|
||||
break
|
||||
|
||||
return {
|
||||
'page': int(pg),
|
||||
'pagecount': 9999,
|
||||
'limit': 90,
|
||||
'total': 9999,
|
||||
'type_name': type_name,
|
||||
'list': videos
|
||||
}
|
||||
|
||||
def detailContent(self, array):
|
||||
"""详情：通过xvid获取视频播放地址"""
|
||||
result = {}
|
||||
if not array or not array[0]:
|
||||
return result
|
||||
|
||||
xvid = array[0]
|
||||
vod = {
|
||||
'vod_id': xvid,
|
||||
'vod_name': '视频详情',
|
||||
'vod_pic': '',
|
||||
'vod_remarks': '',
|
||||
'vod_play_from': 'newxvideos',
|
||||
'vod_play_url': ''
|
||||
}
|
||||
|
||||
try:
|
||||
qs = urllib.parse.urlencode({'xvid': xvid})
|
||||
full_url = self.api_url + '?' + qs
|
||||
req = urllib.request.Request(full_url, headers=self.headers, method='GET')
|
||||
resp = urllib.request.urlopen(req, context=self._ssl_context, timeout=15)
|
||||
data = json.loads(resp.read().decode('utf-8'))
|
||||
except Exception as e:
|
||||
print('detailContent error: %s' % str(e), file=sys.stderr)
|
||||
result['list'] = [vod]
|
||||
return result
|
||||
|
||||
play_urls = []
|
||||
|
||||
if isinstance(data, dict):
|
||||
item = data
|
||||
if 'data' in data and isinstance(data['data'], dict):
|
||||
item = data['data']
|
||||
|
||||
hls_url = item.get('hls') or item.get('m3u8') or ''
|
||||
hight_url = item.get('hight') or item.get('high') or item.get('hd') or ''
|
||||
low_url = item.get('low') or item.get('sd') or ''
|
||||
|
||||
if hls_url:
|
||||
play_urls.append('高清HLS$' + hls_url)
|
||||
if hight_url:
|
||||
play_urls.append('高清MP4$' + hight_url)
|
||||
if low_url:
|
||||
play_urls.append('低清MP4$' + low_url)
|
||||
|
||||
title = item.get('title', '')
|
||||
if title:
|
||||
clean_title = re.sub(r'^AVOTC资源网[—-]+\s*', '', title).strip()
|
||||
if clean_title:
|
||||
vod['vod_name'] = clean_title
|
||||
|
||||
img = item.get('img', '')
|
||||
if img:
|
||||
vod['vod_pic'] = img
|
||||
|
||||
time_str = item.get('time', '')
|
||||
if time_str:
|
||||
vod['vod_remarks'] = self._format_time_cn(time_str)
|
||||
|
||||
elif isinstance(data, list):
|
||||
for item in data:
|
||||
hls_url = item.get('hls') or item.get('m3u8') or ''
|
||||
hight_url = item.get('hight') or item.get('high') or item.get('hd') or ''
|
||||
low_url = item.get('low') or item.get('sd') or ''
|
||||
|
||||
if hls_url:
|
||||
play_urls.append('高清HLS$' + hls_url)
|
||||
if hight_url:
|
||||
play_urls.append('高清MP4$' + hight_url)
|
||||
if low_url:
|
||||
play_urls.append('低清MP4$' + low_url)
|
||||
|
||||
if vod['vod_name'] == '视频详情':
|
||||
title = item.get('title', '')
|
||||
if title:
|
||||
clean_title = re.sub(r'^AVOTC资源网[—-]+\s*', '', title).strip()
|
||||
if clean_title:
|
||||
vod['vod_name'] = clean_title
|
||||
img = item.get('img', '')
|
||||
if img:
|
||||
vod['vod_pic'] = img
|
||||
time_str = item.get('time', '')
|
||||
if time_str:
|
||||
vod['vod_remarks'] = self._format_time_cn(time_str)
|
||||
|
||||
if play_urls:
|
||||
vod['vod_play_url'] = '#'.join(play_urls)
|
||||
|
||||
result['list'] = [vod]
|
||||
return result
|
||||
|
||||
def searchContent(self, key, quick, pg='1'):
|
||||
"""搜索"""
|
||||
raw_data = self._xhttp({'play': 'k', 'k': key, 'page': pg})
|
||||
videos = self._build_vod_list(raw_data)
|
||||
|
||||
return {
|
||||
'page': int(pg),
|
||||
'pagecount': 9999,
|
||||
'limit': 90,
|
||||
'total': 9999,
|
||||
'list': videos
|
||||
}
|
||||
|
||||
def playerContent(self, flag, id, vipFlags):
|
||||
"""播放地址解析 - 直接返回用户选择的清晰度地址"""
|
||||
if id and (id.startswith('http://') or id.startswith('https://')):
|
||||
return {
|
||||
'parse': 0,
|
||||
'playUrl': '',
|
||||
'url': id,
|
||||
'header': {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
|
||||
'Referer': self.host + '/'
|
||||
}
|
||||
}
|
||||
return {'parse': 0, 'playUrl': '', 'url': '', 'header': {}}
|
||||
|
||||
def isVideoFormat(self, url):
|
||||
return False
|
||||
|
||||
def manualVideoCheck(self):
|
||||
return False
|
||||
|
||||
def localProxy(self, param):
|
||||
return {}
|
||||
@@ -1,5 +1,5 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
# by @嗷呜
|
||||
# by @6666
|
||||
import json
|
||||
import re
|
||||
import sys
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
# by @嗷呜
|
||||
|
||||
import json
|
||||
import sys
|
||||
from base64 import b64decode, b64encode
|
||||
@@ -172,11 +172,11 @@ class Spider(Spider):
|
||||
|
||||
def gethost(self):
|
||||
try:
|
||||
response = self.fetch('https://xhamster.com', headers=self.headers, allow_redirects=False)
|
||||
response = self.fetch('https://zh.xhamster1.desi/', headers=self.headers, allow_redirects=False)
|
||||
return response.headers['Location']
|
||||
except Exception as e:
|
||||
print(f"获取主页失败: {str(e)}")
|
||||
return "https://zn.xhamster.com"
|
||||
return "https://zh.xhamster1.desi/"
|
||||
|
||||
def e64(self, text):
|
||||
try:
|
||||
|
||||
@@ -0,0 +1,360 @@
|
||||
# coding=utf-8
|
||||
import sys
|
||||
import os
|
||||
import re
|
||||
import json
|
||||
import urllib.parse
|
||||
from base.spider import Spider
|
||||
from bs4 import BeautifulSoup
|
||||
|
||||
class Spider(Spider):
|
||||
def getName(self):
|
||||
return "\u4e45\u4e45\u7f51"
|
||||
|
||||
def init(self, extend=""):
|
||||
self.host = "https://ww.jiujiu.one"
|
||||
print(f"Initialized with host: {self.host}")
|
||||
|
||||
def header(self):
|
||||
return {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
|
||||
'Referer': self.host,
|
||||
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
|
||||
'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
|
||||
}
|
||||
|
||||
def homeContent(self, filter):
|
||||
"""\u8fd4\u56de\u5206\u7c7b\u5217\u8868"""
|
||||
result = {}
|
||||
classes = [
|
||||
{"type_name": "亞洲無碼", "type_id": "68"},
|
||||
{"type_name": "日本女優", "type_id": "67"},
|
||||
{"type_name": "日本無碼", "type_id": "23"},
|
||||
{"type_name": "中文字幕", "type_id": "9"},
|
||||
{"type_name": "日本有碼", "type_id": "24"},
|
||||
{"type_name": "日韓無碼", "type_id": "82"},
|
||||
{"type_name": "無碼專區", "type_id": "113"},
|
||||
{"type_name": "AV明星", "type_id": "78"},
|
||||
{"type_name": "倫理影片", "type_id": "269"},
|
||||
{"type_name": "日本片商", "type_id": "90"},
|
||||
{"type_name": "國產自拍", "type_id": "80"},
|
||||
{"type_name": "傳媒原創", "type_id": "231"},
|
||||
{"type_name": "國產精品", "type_id": "63"},
|
||||
{"type_name": "國產情色", "type_id": "77"},
|
||||
{"type_name": "美女主播", "type_id": "105"},
|
||||
{"type_name": "強姦亂倫", "type_id": "33"},
|
||||
{"type_name": "國產主播", "type_id": "36"},
|
||||
{"type_name": "亞洲有碼", "type_id": "66"},
|
||||
{"type_name": "偷拍自拍", "type_id": "3"},
|
||||
{"type_name": "抖陰視頻", "type_id": "91"},
|
||||
{"type_name": "制服誘惑", "type_id": "31"},
|
||||
{"type_name": "黑料不打烊", "type_id": "10"},
|
||||
{"type_name": "歐美精品", "type_id": "25"},
|
||||
]
|
||||
result["class"] = classes
|
||||
result["list"] = []
|
||||
return result
|
||||
|
||||
def homeVideoContent(self):
|
||||
"""\u9996\u9875\u63a8\u8350\u89c6\u9891"""
|
||||
try:
|
||||
print("Fetching home page...")
|
||||
rsp = self.fetch(self.host, headers=self.header())
|
||||
print(f"Response status: {rsp.status}")
|
||||
|
||||
# \u4f7f\u7528\u6b63\u5219\u8865\u6551\u65b9\u6848\uff0c\u76f4\u63a5\u4eceHTML\u4e2d\u63d0\u53d6\u89c6\u9891\u4fe1\u606f
|
||||
html = rsp.text
|
||||
|
||||
# \u5339\u914d\u89c6\u9891\u9879\u6a21\u5f0f
|
||||
# \u67e5\u627e\u6240\u6709 div.item
|
||||
videos = []
|
||||
|
||||
# \u4f7f\u7528BeautifulSoup
|
||||
soup = BeautifulSoup(html, 'html.parser')
|
||||
|
||||
# \u76f4\u63a5\u67e5\u627e\u6240\u6709\u5e26\u6709\u89c6\u9891\u7684\u5361\u7247
|
||||
items = soup.find_all('div', class_=lambda c: c and 'item' in c.split())
|
||||
print(f"Found {len(items)} items with class containing 'item'")
|
||||
|
||||
for item in items:
|
||||
try:
|
||||
# \u627e\u5230\u94fe\u63a5
|
||||
links = item.find_all('a', href=True)
|
||||
if len(links) < 2:
|
||||
continue
|
||||
|
||||
# \u6807\u9898\u94fe\u63a5\u901a\u5e38\u662f\u7b2c\u4e8c\u4e2a
|
||||
title_link = links[1] if len(links) > 1 else links[0]
|
||||
href = title_link.get('href', '')
|
||||
|
||||
if not href:
|
||||
continue
|
||||
|
||||
# \u6784\u5efa\u5b8c\u6574\u7684URL
|
||||
if href.startswith('/'):
|
||||
vod_id = self.host + href
|
||||
else:
|
||||
vod_id = href
|
||||
|
||||
# \u6807\u9898
|
||||
vod_name = title_link.get_text(strip=True)
|
||||
|
||||
# \u5c01\u9762\u56fe
|
||||
vod_pic = ''
|
||||
img = item.find('img')
|
||||
if img:
|
||||
vod_pic = img.get('src') or img.get('data-src') or ''
|
||||
if vod_pic and not vod_pic.startswith('http'):
|
||||
if vod_pic.startswith('/'):
|
||||
vod_pic = self.host + vod_pic
|
||||
else:
|
||||
vod_pic = 'https:' + vod_pic if vod_pic.startswith('//') else vod_pic
|
||||
|
||||
# \u5907\u6ce8
|
||||
vod_remarks = ''
|
||||
badge = item.find('span', class_='badge')
|
||||
if badge:
|
||||
vod_remarks = badge.get_text(strip=True)
|
||||
|
||||
if vod_name and vod_id:
|
||||
videos.append({
|
||||
'vod_id': vod_id,
|
||||
'vod_name': vod_name,
|
||||
'vod_pic': vod_pic,
|
||||
'vod_remarks': vod_remarks
|
||||
})
|
||||
print(f"Added video: {vod_name}")
|
||||
except Exception as e:
|
||||
print(f"Error processing item: {e}")
|
||||
continue
|
||||
|
||||
print(f"Total videos extracted: {len(videos)}")
|
||||
return {'list': videos}
|
||||
except Exception as e:
|
||||
print(f"Error in homeVideoContent: {e}")
|
||||
return {'list': []}
|
||||
|
||||
def categoryContent(self, tid, pg, filter, extend):
|
||||
"""\u5206\u7c7b\u9875\u5185\u5bb9"""
|
||||
try:
|
||||
# \u6784\u5efa\u5206\u7c7b\u9875URL\uff0c\u652f\u6301\u5206\u9875
|
||||
if pg == "1":
|
||||
url = f"{self.host}/c/{tid}"
|
||||
else:
|
||||
url = f"{self.host}/c/{tid}?page={pg}"
|
||||
|
||||
print(f"Fetching category URL: {url}")
|
||||
rsp = self.fetch(url, headers=self.header())
|
||||
soup = BeautifulSoup(rsp.text, 'html.parser')
|
||||
videos = []
|
||||
|
||||
items = soup.find_all('div', class_=lambda c: c and 'item' in c.split())
|
||||
|
||||
for item in items:
|
||||
try:
|
||||
links = item.find_all('a', href=True)
|
||||
if len(links) < 2:
|
||||
continue
|
||||
|
||||
title_link = links[1] if len(links) > 1 else links[0]
|
||||
href = title_link.get('href', '')
|
||||
|
||||
if not href:
|
||||
continue
|
||||
|
||||
if href.startswith('/'):
|
||||
vod_id = self.host + href
|
||||
else:
|
||||
vod_id = href
|
||||
|
||||
vod_name = title_link.get_text(strip=True)
|
||||
|
||||
vod_pic = ''
|
||||
img = item.find('img')
|
||||
if img:
|
||||
vod_pic = img.get('src') or img.get('data-src') or ''
|
||||
if vod_pic and not vod_pic.startswith('http'):
|
||||
if vod_pic.startswith('/'):
|
||||
vod_pic = self.host + vod_pic
|
||||
else:
|
||||
vod_pic = 'https:' + vod_pic if vod_pic.startswith('//') else vod_pic
|
||||
|
||||
vod_remarks = ''
|
||||
badge = item.find('span', class_='badge')
|
||||
if badge:
|
||||
vod_remarks = badge.get_text(strip=True)
|
||||
|
||||
if vod_name and vod_id:
|
||||
videos.append({
|
||||
'vod_id': vod_id,
|
||||
'vod_name': vod_name,
|
||||
'vod_pic': vod_pic,
|
||||
'vod_remarks': vod_remarks
|
||||
})
|
||||
except Exception as e:
|
||||
print(f"Error processing item: {e}")
|
||||
continue
|
||||
|
||||
# \u83b7\u53d6\u603b\u9875\u6570
|
||||
total_pages = 1
|
||||
pagination = soup.find('ul', class_='pagination')
|
||||
if pagination:
|
||||
page_links = pagination.find_all('a')
|
||||
for link in page_links:
|
||||
text = link.get_text(strip=True)
|
||||
if text.isdigit():
|
||||
page_num = int(text)
|
||||
if page_num > total_pages:
|
||||
total_pages = page_num
|
||||
|
||||
return {
|
||||
'list': videos,
|
||||
'page': int(pg),
|
||||
'pagecount': total_pages,
|
||||
'limit': len(videos),
|
||||
'total': total_pages * len(videos) if total_pages > 0 else len(videos)
|
||||
}
|
||||
except Exception as e:
|
||||
print(f"Error in categoryContent: {e}")
|
||||
return {'list': [], 'page': int(pg), 'pagecount': 1, 'limit': 0, 'total': 0}
|
||||
|
||||
def detailContent(self, ids):
|
||||
"""\u8be6\u60c5\u9875\u5185\u5bb9"""
|
||||
try:
|
||||
vod_id = ids[0]
|
||||
if not vod_id.startswith('http'):
|
||||
vod_id = self.host + vod_id
|
||||
|
||||
print(f"Fetching detail page: {vod_id}")
|
||||
rsp = self.fetch(vod_id, headers=self.header())
|
||||
soup = BeautifulSoup(rsp.text, 'html.parser')
|
||||
|
||||
vod = {
|
||||
'vod_id': vod_id,
|
||||
'vod_name': '',
|
||||
'vod_pic': '',
|
||||
'vod_actor': '',
|
||||
'vod_director': '',
|
||||
'vod_content': '',
|
||||
'vod_play_from': '\u4e45\u4e45\u7f51',
|
||||
'vod_play_url': ''
|
||||
}
|
||||
|
||||
# \u6807\u9898
|
||||
title = soup.find('h1')
|
||||
if title:
|
||||
vod['vod_name'] = title.get_text(strip=True)
|
||||
|
||||
# \u5c01\u9762
|
||||
img = soup.find('meta', property='og:image')
|
||||
if img and img.get('content'):
|
||||
vod['vod_pic'] = img.get('content')
|
||||
else:
|
||||
img = soup.find('img', class_='card-img-top')
|
||||
if img:
|
||||
vod['vod_pic'] = img.get('src') or ''
|
||||
|
||||
# \u64ad\u653e\u5730\u5740 - \u67e5\u627evideo\u6807\u7b64\u6216iframe
|
||||
play_url = ''
|
||||
video = soup.find('video')
|
||||
if video:
|
||||
source = video.find('source')
|
||||
if source and source.get('src'):
|
||||
play_url = source.get('src')
|
||||
|
||||
if not play_url:
|
||||
iframe = soup.find('iframe')
|
||||
if iframe and iframe.get('src'):
|
||||
play_url = iframe.get('src')
|
||||
|
||||
if play_url:
|
||||
vod['vod_play_url'] = f'\u6b63\u7247${play_url}'
|
||||
|
||||
return {'list': [vod]}
|
||||
except Exception as e:
|
||||
print(f"Error in detailContent: {e}")
|
||||
return {'list': []}
|
||||
|
||||
def searchContent(self, key, quick, pg=1):
|
||||
"""\u641c\u7d22\u529f\u80fd"""
|
||||
try:
|
||||
search_url = f"{self.host}/node/search?q={urllib.parse.quote(keyword)}"
|
||||
print(f"Search URL: {search_url}")
|
||||
rsp = self.fetch(search_url, headers=self.header())
|
||||
soup = BeautifulSoup(rsp.text, 'html.parser')
|
||||
videos = []
|
||||
|
||||
items = soup.find_all('div', class_=lambda c: c and 'item' in c.split())
|
||||
|
||||
for item in items:
|
||||
try:
|
||||
links = item.find_all('a', href=True)
|
||||
if len(links) < 2:
|
||||
continue
|
||||
|
||||
title_link = links[1] if len(links) > 1 else links[0]
|
||||
href = title_link.get('href', '')
|
||||
|
||||
if not href:
|
||||
continue
|
||||
|
||||
if href.startswith('/'):
|
||||
vod_id = self.host + href
|
||||
else:
|
||||
vod_id = href
|
||||
|
||||
vod_name = title_link.get_text(strip=True)
|
||||
|
||||
vod_pic = ''
|
||||
img = item.find('img')
|
||||
if img:
|
||||
vod_pic = img.get('src') or img.get('data-src') or ''
|
||||
if vod_pic and not vod_pic.startswith('http'):
|
||||
if vod_pic.startswith('/'):
|
||||
vod_pic = self.host + vod_pic
|
||||
else:
|
||||
vod_pic = 'https:' + vod_pic if vod_pic.startswith('//') else vod_pic
|
||||
|
||||
vod_remarks = ''
|
||||
badge = item.find('span', class_='badge')
|
||||
if badge:
|
||||
vod_remarks = badge.get_text(strip=True)
|
||||
|
||||
if vod_name and vod_id:
|
||||
videos.append({
|
||||
'vod_id': vod_id,
|
||||
'vod_name': vod_name,
|
||||
'vod_pic': vod_pic,
|
||||
'vod_remarks': vod_remarks
|
||||
})
|
||||
except Exception as e:
|
||||
print(f"Error processing search item: {e}")
|
||||
continue
|
||||
|
||||
return {'list': videos}
|
||||
except Exception as e:
|
||||
print(f"Error in searchContent: {e}")
|
||||
return {'list': []}
|
||||
|
||||
def playerContent(self, flag, id, vipFlags):
|
||||
"""\u8fd4\u56de\u64ad\u653e\u5730\u5740"""
|
||||
return {
|
||||
'parse': 0,
|
||||
'playUrl': '',
|
||||
'url': id
|
||||
}
|
||||
|
||||
def isVideoFormat(self, url):
|
||||
"""\u5224\u65ad\u662f\u5426\u4e3a\u89c6\u9891\u683c\u5f0f"""
|
||||
video_extensions = ['.mp4', '.m3u8', '.flv', '.avi', '.mkv', '.wmv', '.mov']
|
||||
lower_url = url.lower()
|
||||
for ext in video_extensions:
|
||||
if ext in lower_url:
|
||||
return True
|
||||
return False
|
||||
|
||||
def localProxy(self, param):
|
||||
return None
|
||||
|
||||
def destroy(self):
|
||||
pass
|
||||
@@ -0,0 +1,276 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
# 爬虫源: 怦然心动 (prshinezenx.blog)
|
||||
# 站点类型: SPA + 服务端渲染，数据通过 Base64 编码嵌入 HTML
|
||||
# 开发者: AI Assistant
|
||||
# 日期: 2026-07-22
|
||||
|
||||
import re
|
||||
import json
|
||||
import base64
|
||||
from urllib.parse import urljoin, quote
|
||||
|
||||
from base.spider import Spider as BaseSpider
|
||||
|
||||
|
||||
class Spider(BaseSpider):
|
||||
def __init__(self):
|
||||
self.host = "https://prshinezenx.blog"
|
||||
self.headers = {
|
||||
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
|
||||
"Referer": self.host + "/",
|
||||
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
|
||||
"Accept-Language": "zh-CN,zh;q=0.9"
|
||||
}
|
||||
# 分类列表（从首页提取，本地硬编码保证首页秒出）
|
||||
self.classes = [
|
||||
{"type_id": "43", "type_name": "国产精选"},
|
||||
{"type_id": "31", "type_name": "束缚玩法"},
|
||||
{"type_id": "35", "type_name": "中字专区"},
|
||||
{"type_id": "33", "type_name": "女优精选"},
|
||||
{"type_id": "53", "type_name": "传媒拍摄"},
|
||||
{"type_id": "29", "type_name": "变性纪实"},
|
||||
{"type_id": "21", "type_name": "同志日常"},
|
||||
{"type_id": "23", "type_name": "百合情境"},
|
||||
{"type_id": "39", "type_name": "欧美精选"},
|
||||
{"type_id": "45", "type_name": "虚拟换脸"},
|
||||
{"type_id": "47", "type_name": "少女幻想"},
|
||||
{"type_id": "49", "type_name": "主播日记"},
|
||||
{"type_id": "51", "type_name": "约会实录"},
|
||||
{"type_id": "55", "type_name": "伦理剧场"},
|
||||
{"type_id": "57", "type_name": "黑料档案"},
|
||||
{"type_id": "63", "type_name": "自拍实录"},
|
||||
]
|
||||
# 无筛选功能
|
||||
self.filters = {}
|
||||
|
||||
def getName(self):
|
||||
return "怦然心动"
|
||||
|
||||
def getDependence(self):
|
||||
return []
|
||||
|
||||
def init(self, extend=""):
|
||||
"""初始化，零网络"""
|
||||
pass
|
||||
|
||||
def _fetch(self, url):
|
||||
"""请求页面，返回 HTML 文本"""
|
||||
try:
|
||||
rsp = self.fetch(url, headers=self.headers, timeout=15000)
|
||||
if rsp and hasattr(rsp, 'text'):
|
||||
return rsp.text
|
||||
return None
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
def _extract_vod_data(self, html):
|
||||
"""从 HTML 中提取 window.__vod_data__ 的 Base64 数据并解码"""
|
||||
if not html:
|
||||
return None
|
||||
pattern = r"const binaryStr = atob\('([^']+)'\)"
|
||||
match = re.search(pattern, html)
|
||||
if not match:
|
||||
return None
|
||||
base64_str = match.group(1)
|
||||
try:
|
||||
json_str = base64.b64decode(base64_str).decode('utf-8')
|
||||
return json.loads(json_str)
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
def _parse_list(self, items):
|
||||
"""解析视频列表项，打包数据到 vod_id 以便详情页快速展示"""
|
||||
if not items:
|
||||
return []
|
||||
result = []
|
||||
for item in items:
|
||||
vod_id = str(item.get("vod_id", ""))
|
||||
if not vod_id:
|
||||
continue
|
||||
vod_name = item.get("vod_name", "未知标题")
|
||||
vod_pic = item.get("vod_pic", "")
|
||||
if vod_pic and not vod_pic.startswith("http"):
|
||||
vod_pic = urljoin(self.host, vod_pic)
|
||||
vod_remark = item.get("vod_duration", "")
|
||||
type_id = str(item.get("type_id", ""))
|
||||
# 打包数据到 vod_id，方便详情页快速返回
|
||||
packed_id = f"{vod_id}|$|{vod_name}|$|{vod_pic}|$|{vod_remark}|$|{type_id}"
|
||||
result.append({
|
||||
"vod_id": packed_id,
|
||||
"vod_name": vod_name,
|
||||
"vod_pic": vod_pic,
|
||||
"vod_remarks": vod_remark,
|
||||
})
|
||||
return result
|
||||
|
||||
def homeContent(self, filter=False):
|
||||
"""首页：返回分类列表，零网络"""
|
||||
return {
|
||||
"class": self.classes,
|
||||
"filters": self.filters if filter else {}
|
||||
}
|
||||
|
||||
def getHomeContent(self, filter=False):
|
||||
return self.homeContent(filter)
|
||||
|
||||
def homeVideoContent(self):
|
||||
"""首页推荐视频"""
|
||||
html = self._fetch(self.host + "/")
|
||||
if not html:
|
||||
return {"list": []}
|
||||
data = self._extract_vod_data(html)
|
||||
if not data:
|
||||
return {"list": []}
|
||||
items = data.get("other_request_data", {}).get("random_list", [])
|
||||
if not items:
|
||||
items = data.get("request_data", {}).get("list", [])
|
||||
return {"list": self._parse_list(items[:20])}
|
||||
|
||||
def categoryContent(self, tid, pg=1, filter=False, extend=None):
|
||||
"""分类列表页"""
|
||||
page = pg or 1
|
||||
url = f"{self.host}/vodlist/type/{tid}/keyword/all/orderby/default/page/{page}.html"
|
||||
html = self._fetch(url)
|
||||
if not html:
|
||||
return {"list": [], "page": page, "pagecount": 1, "limit": 20, "total": 0}
|
||||
|
||||
data = self._extract_vod_data(html)
|
||||
if not data:
|
||||
return {"list": [], "page": page, "pagecount": 1, "limit": 20, "total": 0}
|
||||
|
||||
items = data.get("request_data", {}).get("list", [])
|
||||
total = data.get("request_data", {}).get("total", 0)
|
||||
limit = data.get("limit", 20)
|
||||
total_pages = (total + limit - 1) // limit if total > 0 else 1
|
||||
|
||||
return {
|
||||
"list": self._parse_list(items),
|
||||
"page": page,
|
||||
"pagecount": total_pages,
|
||||
"limit": limit,
|
||||
"total": total
|
||||
}
|
||||
|
||||
def detailContent(self, ids):
|
||||
"""视频详情 - 从打包的 vod_id 中解析数据，快速返回"""
|
||||
if not ids:
|
||||
return {"list": []}
|
||||
raw = str(ids[0])
|
||||
|
||||
# 解析打包的数据: vod_id|$|vod_name|$|vod_pic|$|vod_remark|$|type_id
|
||||
parts = raw.split("|$|")
|
||||
if len(parts) >= 5:
|
||||
vod_id = parts[0]
|
||||
vod_name = parts[1] if len(parts) > 1 else "未知标题"
|
||||
vod_pic = parts[2] if len(parts) > 2 else ""
|
||||
vod_remark = parts[3] if len(parts) > 3 else ""
|
||||
type_id = parts[4] if len(parts) > 4 else ""
|
||||
else:
|
||||
# 兼容旧格式：直接传数字ID
|
||||
vod_id = raw
|
||||
vod_name = ""
|
||||
vod_pic = ""
|
||||
vod_remark = ""
|
||||
type_id = ""
|
||||
|
||||
# 获取播放地址：请求详情页提取 vod_play_url
|
||||
if type_id:
|
||||
detail_url = f"{self.host}/voddetail/type/{type_id}/id/{vod_id}.html"
|
||||
else:
|
||||
detail_url = f"{self.host}/voddetail/type/all/id/{vod_id}.html"
|
||||
|
||||
html = self._fetch(detail_url)
|
||||
play_page = ""
|
||||
if html:
|
||||
data = self._extract_vod_data(html)
|
||||
if data:
|
||||
vod_info = data.get("vod_info", {})
|
||||
play_page = vod_info.get("vod_play_url", "")
|
||||
if not vod_name:
|
||||
vod_name = vod_info.get("vod_name", "未知标题")
|
||||
if not vod_pic:
|
||||
vod_pic = vod_info.get("vod_pic", "")
|
||||
if not vod_remark:
|
||||
vod_remark = vod_info.get("vod_duration", "")
|
||||
|
||||
if not play_page:
|
||||
return {
|
||||
"list": [{
|
||||
"vod_id": vod_id,
|
||||
"vod_name": vod_name or "未知标题",
|
||||
"vod_pic": vod_pic,
|
||||
"vod_remarks": vod_remark,
|
||||
"vod_content": "",
|
||||
"vod_play_from": "播放",
|
||||
"vod_play_url": ""
|
||||
}]
|
||||
}
|
||||
|
||||
# 如果是 ao jie xi 包装，提取真实 m3u8
|
||||
if "aojiexi.com" in play_page:
|
||||
match = re.search(r'url=([^&]+)', play_page)
|
||||
if match:
|
||||
real_url = match.group(1)
|
||||
real_url = re.sub(r'%([0-9A-Fa-f]{2})', lambda m: chr(int(m.group(1), 16)), real_url)
|
||||
play_page = real_url
|
||||
|
||||
# 构造播放数据：单线路单集
|
||||
# 格式参考 tmcrownxlift 成功案例
|
||||
return {
|
||||
"list": [{
|
||||
"vod_id": vod_id,
|
||||
"vod_name": vod_name or "未知标题",
|
||||
"vod_pic": vod_pic,
|
||||
"vod_remarks": vod_remark,
|
||||
"vod_content": "",
|
||||
"vod_play_from": "播放",
|
||||
"vod_play_url": "播放$" + play_page
|
||||
}]
|
||||
}
|
||||
|
||||
def searchContent(self, key, quick=False, pg="1"):
|
||||
"""搜索"""
|
||||
if not key:
|
||||
return {"list": []}
|
||||
page = pg or 1
|
||||
url = f"{self.host}/vodlist/type/all/keyword/{quote(key)}/orderby/default/page/{page}.html"
|
||||
html = self._fetch(url)
|
||||
if not html:
|
||||
return {"list": []}
|
||||
data = self._extract_vod_data(html)
|
||||
if not data:
|
||||
return {"list": []}
|
||||
items = data.get("request_data", {}).get("list", [])
|
||||
return {"list": self._parse_list(items)}
|
||||
|
||||
def playerContent(self, flag, vid, vipFlags=None):
|
||||
"""播放地址解析"""
|
||||
if not vid:
|
||||
return {"parse": 0, "url": ""}
|
||||
|
||||
if vid.endswith((".m3u8", ".mp4")):
|
||||
return {"parse": 0, "url": vid, "header": self.headers}
|
||||
|
||||
if "aojiexi.com" in vid:
|
||||
match = re.search(r'url=([^&]+)', vid)
|
||||
if match:
|
||||
real_url = match.group(1)
|
||||
real_url = re.sub(r'%([0-9A-Fa-f]{2})', lambda m: chr(int(m.group(1), 16)), real_url)
|
||||
return {"parse": 0, "url": real_url, "header": self.headers}
|
||||
|
||||
if vid.startswith("http"):
|
||||
html = self._fetch(vid)
|
||||
if html:
|
||||
match = re.search(r'https?://[^\s"\']+\.m3u8[^\s"\']*', html)
|
||||
if match:
|
||||
return {"parse": 0, "url": match.group(0), "header": self.headers}
|
||||
|
||||
return {"parse": 1, "url": vid}
|
||||
|
||||
def isVideoFormat(self, url):
|
||||
if not url:
|
||||
return False
|
||||
return url.endswith((".m3u8", ".mp4", ".m3u8?"))
|
||||
|
||||
def destroy(self):
|
||||
pass
|
||||
@@ -0,0 +1,461 @@
|
||||
# coding=utf-8
|
||||
import sys
|
||||
import json
|
||||
import re
|
||||
import requests
|
||||
import base64
|
||||
from bs4 import BeautifulSoup
|
||||
from urllib.parse import unquote, urljoin
|
||||
|
||||
try:
|
||||
from base.spider import Spider as BaseSpider
|
||||
except ImportError:
|
||||
class BaseSpider():
|
||||
def fetch(self, url, headers=None, timeout=10):
|
||||
try:
|
||||
res = requests.get(url, headers=headers, timeout=timeout, allow_redirects=True)
|
||||
res.encoding = 'utf-8'
|
||||
return res
|
||||
except Exception as e:
|
||||
print(f"fetch error: {e}")
|
||||
return None
|
||||
|
||||
class Spider(BaseSpider):
|
||||
def getName(self):
|
||||
return "撸一天"
|
||||
|
||||
def init(self, extend=""):
|
||||
self.host = "https://luyitian.com"
|
||||
self.session = requests.Session()
|
||||
self.session.headers.update({
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
|
||||
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
|
||||
'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
|
||||
'Connection': 'keep-alive'
|
||||
})
|
||||
|
||||
def homeVideoContent(self):
|
||||
return {"list": []}
|
||||
|
||||
def localProxy(self, params):
|
||||
return [200, "video/MP2T", ""]
|
||||
|
||||
def isVideoFormat(self, url):
|
||||
return False
|
||||
|
||||
def manualVideoCheck(self):
|
||||
return False
|
||||
|
||||
def fetch(self, url, headers=None, timeout=5):
|
||||
try:
|
||||
req_headers = headers or self.session.headers
|
||||
res = self.session.get(url, headers=req_headers, timeout=timeout, allow_redirects=True)
|
||||
res.encoding = 'utf-8'
|
||||
return res
|
||||
except Exception as e:
|
||||
print(f"fetch error: {e}")
|
||||
return None
|
||||
|
||||
def _get_topic_filters(self):
|
||||
"""
|
||||
从 /topic/ 页面提取所有专题入口，生成子分类列表。
|
||||
适配真实 URL：/topicdetail-7/
|
||||
"""
|
||||
url = f"{self.host}/topic/"
|
||||
res = self.fetch(url, timeout=5)
|
||||
if not res:
|
||||
return []
|
||||
soup = BeautifulSoup(res.text, 'html.parser')
|
||||
|
||||
# 专门匹配 /topicdetail- 链接
|
||||
topic_links = soup.select('a[href*="/topicdetail-"]')
|
||||
if not topic_links:
|
||||
# 兜底：可能写成 /topicdetail/ 格式
|
||||
topic_links = soup.select('a[href*="/topicdetail"]')
|
||||
|
||||
filters = []
|
||||
seen = set()
|
||||
for a in topic_links:
|
||||
href = a.get('href', '')
|
||||
# 提取数字 ID（例如 /topicdetail-7/）
|
||||
match = re.search(r'/topicdetail-(\d+)', href)
|
||||
if not match:
|
||||
match = re.search(r'/topicdetail/(\d+)', href)
|
||||
if not match:
|
||||
continue
|
||||
tid = match.group(1)
|
||||
name = a.get_text(strip=True) or a.get('title', '') or f"专题{tid}"
|
||||
if len(name) < 2:
|
||||
continue
|
||||
if tid not in seen:
|
||||
seen.add(tid)
|
||||
filters.append({"n": name, "v": tid})
|
||||
return filters
|
||||
|
||||
def homeContent(self, filter):
|
||||
classes = [
|
||||
{"type_name": "最近更新", "type_id": "new"},
|
||||
{"type_name": "热门影片", "type_id": "hot"},
|
||||
{"type_name": "影片专题", "type_id": "topic"},
|
||||
{"type_name": "中文字幕", "type_id": "28"},
|
||||
{"type_name": "国产", "type_id": "20"},
|
||||
{"type_name": "日本有码", "type_id": "21"},
|
||||
{"type_name": "日本无码", "type_id": "22"},
|
||||
{"type_name": "欧美", "type_id": "23"},
|
||||
{"type_name": "动漫", "type_id": "24"},
|
||||
{"type_name": "伦理", "type_id": "25"},
|
||||
{"type_name": "韩国", "type_id": "36"},
|
||||
{"type_name": "另类", "type_id": "41"}
|
||||
]
|
||||
|
||||
filters = {
|
||||
"28": [{"key": "tid", "name": "子分类", "value": [
|
||||
{"n": "全部", "v": "28"},
|
||||
{"n": "日本中字", "v": "51"}
|
||||
]}],
|
||||
"20": [{"key": "tid", "name": "子分类", "value": [
|
||||
{"n": "全部", "v": "20"},
|
||||
{"n": "国产精品", "v": "26"},
|
||||
{"n": "国产剧情", "v": "27"},
|
||||
{"n": "国产自拍", "v": "29"},
|
||||
{"n": "国产主播", "v": "35"},
|
||||
{"n": "国模私拍", "v": "85"},
|
||||
{"n": "网红明星", "v": "91"},
|
||||
{"n": "国产SM", "v": "105"},
|
||||
{"n": "台湾辣妹", "v": "107"},
|
||||
{"n": "香港正妹", "v": "108"}
|
||||
]}],
|
||||
"21": [{"key": "tid", "name": "子分类", "value": [
|
||||
{"n": "全部", "v": "21"},
|
||||
{"n": "人妻", "v": "31"},
|
||||
{"n": "素人", "v": "44"},
|
||||
{"n": "口爆颜射", "v": "46"},
|
||||
{"n": "萝莉少女", "v": "47"},
|
||||
{"n": "美乳巨乳", "v": "48"},
|
||||
{"n": "制服诱惑", "v": "52"},
|
||||
{"n": "调教", "v": "57"},
|
||||
{"n": "出轨", "v": "58"},
|
||||
{"n": "有码精品", "v": "101"}
|
||||
]}],
|
||||
"22": [{"key": "tid", "name": "子分类", "value": [
|
||||
{"n": "全部", "v": "22"},
|
||||
{"n": "无码精品", "v": "102"}
|
||||
]}],
|
||||
"23": [{"key": "tid", "name": "子分类", "value": [
|
||||
{"n": "全部", "v": "23"},
|
||||
{"n": "欧美精品", "v": "104"}
|
||||
]}],
|
||||
"24": [{"key": "tid", "name": "子分类", "value": [
|
||||
{"n": "全部", "v": "24"},
|
||||
{"n": "动漫精品", "v": "103"}
|
||||
]}],
|
||||
"25": [{"key": "tid", "name": "子分类", "value": [
|
||||
{"n": "全部", "v": "25"},
|
||||
{"n": "综合三级", "v": "39"}
|
||||
]}],
|
||||
"36": [{"key": "tid", "name": "子分类", "value": [
|
||||
{"n": "全部", "v": "36"},
|
||||
{"n": "韩国主播", "v": "37"}
|
||||
]}],
|
||||
"41": [{"key": "tid", "name": "子分类", "value": [
|
||||
{"n": "全部", "v": "41"},
|
||||
{"n": "Cosplay", "v": "106"}
|
||||
]}]
|
||||
}
|
||||
|
||||
# 动态注入专题子分类（例如：2018必看、2019必看...）
|
||||
topic_values = self._get_topic_filters()
|
||||
if topic_values:
|
||||
filters["topic"] = [{
|
||||
"key": "tid",
|
||||
"name": "专题",
|
||||
"value": topic_values
|
||||
}]
|
||||
|
||||
return {'class': classes, 'filters': filters}
|
||||
|
||||
def categoryContent(self, tid, pg, filter, extend):
|
||||
pg = int(pg)
|
||||
result = {"list": [], "page": pg, "pagecount": 999, "limit": 20, "total": 9999}
|
||||
|
||||
real_tid = extend.get('tid', tid)
|
||||
soup = None
|
||||
|
||||
# ---------- 影片专题下的具体专题（/topicdetail-7/） ----------
|
||||
if real_tid.isdigit() and tid == "topic":
|
||||
urls_to_try = [
|
||||
f"{self.host}/topicdetail-{real_tid}/",
|
||||
f"{self.host}/topicdetail-{real_tid}.html",
|
||||
f"{self.host}/topicdetail/{real_tid}/",
|
||||
f"{self.host}/topicdetail/{real_tid}.html",
|
||||
f"{self.host}/topicdetail-{real_tid}-{pg}/",
|
||||
f"{self.host}/topicdetail/{real_tid}-{pg}/"
|
||||
]
|
||||
for url in urls_to_try:
|
||||
res = self.fetch(url, headers={'Referer': self.host})
|
||||
if res and res.status_code == 200 and ('video-img-box' in res.text or 'vodlist' in res.text or 'vodplay' in res.text):
|
||||
soup = BeautifulSoup(res.text, 'html.parser')
|
||||
break
|
||||
if not soup:
|
||||
return result
|
||||
|
||||
# ---------- new / hot / topic 总入口 ----------
|
||||
elif real_tid in ["new", "hot", "topic"]:
|
||||
if real_tid == "topic":
|
||||
return result
|
||||
if pg > 1:
|
||||
url = f"{self.host}/label/{real_tid}/page/{pg}/"
|
||||
else:
|
||||
url = f"{self.host}/label/{real_tid}/"
|
||||
res = self.fetch(url, headers={'Referer': self.host})
|
||||
if not res:
|
||||
url = f"{self.host}/label/{real_tid}/"
|
||||
res = self.fetch(url, headers={'Referer': self.host})
|
||||
if not res:
|
||||
return result
|
||||
soup = BeautifulSoup(res.text, 'html.parser')
|
||||
|
||||
# ---------- 普通分类 ----------
|
||||
else:
|
||||
urls_to_try = [
|
||||
f"{self.host}/vodtype/{real_tid}-{pg}.html",
|
||||
f"{self.host}/vodtype/{real_tid}-{pg}/",
|
||||
f"{self.host}/type/{real_tid}-{pg}.html",
|
||||
f"{self.host}/type/{real_tid}-{pg}/",
|
||||
f"{self.host}/vodtype/{real_tid}/",
|
||||
f"{self.host}/vodtype/{real_tid}.html"
|
||||
]
|
||||
res = None
|
||||
for url in urls_to_try:
|
||||
res = self.fetch(url, headers={'Referer': self.host})
|
||||
if res and res.status_code == 200:
|
||||
if 'video-img-box' in res.text or 'vodlist' in res.text or 'item' in res.text:
|
||||
break
|
||||
res = None
|
||||
if not res:
|
||||
return result
|
||||
soup = BeautifulSoup(res.text, 'html.parser')
|
||||
|
||||
# ---------- 统一解析视频列表 ----------
|
||||
vod_list = []
|
||||
items = soup.select('.video-img-box') or soup.select('.video-film-list .video-item') or soup.select('.vodlist_item') or soup.select('.item')
|
||||
|
||||
for item in items:
|
||||
a = item.select_one('a')
|
||||
if not a:
|
||||
continue
|
||||
href = a.get('href', '')
|
||||
vid_match = re.search(r'/vodplay/(\d+)', href) or \
|
||||
re.search(r'/voddetail/(\d+)', href) or \
|
||||
re.search(r'/vod/(\d+)', href) or \
|
||||
re.search(r'/play/(\d+)', href)
|
||||
vid = vid_match.group(1) if vid_match else href
|
||||
|
||||
name = ""
|
||||
img = item.select_one('img')
|
||||
if img and img.get('alt'):
|
||||
name = img['alt']
|
||||
if not name and a.get('title'):
|
||||
name = a['title']
|
||||
if not name:
|
||||
title_elem = item.select_one('.title a') or item.select_one('.detail .title a')
|
||||
if title_elem:
|
||||
name = title_elem.get_text(strip=True)
|
||||
if not name:
|
||||
name = a.get_text(strip=True)
|
||||
if not name:
|
||||
name = "未知标题"
|
||||
|
||||
pic = ""
|
||||
if img:
|
||||
pic = img.get('data-src') or img.get('src', '')
|
||||
if pic and not pic.startswith('http'):
|
||||
pic = urljoin(self.host, pic)
|
||||
|
||||
remark = ""
|
||||
remark_elem = item.select_one('.sub-title') or item.select_one('.remarks') or item.select_one('.video-remarks')
|
||||
if remark_elem:
|
||||
remark = remark_elem.get_text(strip=True)
|
||||
if len(remark) > 20:
|
||||
remark = remark[:20]
|
||||
else:
|
||||
text = item.get_text(strip=True)
|
||||
parts = [p.strip() for p in text.split('\n') if p.strip()]
|
||||
if parts:
|
||||
remark = parts[-1][:20]
|
||||
|
||||
vod_list.append({
|
||||
"vod_id": vid,
|
||||
"vod_name": name.strip(),
|
||||
"vod_pic": pic,
|
||||
"vod_remarks": remark
|
||||
})
|
||||
|
||||
result['list'] = vod_list
|
||||
|
||||
# ---------- 分页信息 ----------
|
||||
page_elem = soup.select_one('.pagination a:last-child') or soup.select_one('.page a:last-child')
|
||||
if page_elem and page_elem.get('href'):
|
||||
try:
|
||||
nums = re.findall(r'(\d+)', page_elem['href'])
|
||||
if nums:
|
||||
result['pagecount'] = max(int(nums[-1]), 1)
|
||||
except:
|
||||
pass
|
||||
|
||||
return result
|
||||
|
||||
def detailContent(self, ids):
|
||||
vid = ids[0]
|
||||
url = f"{self.host}/vodplay/{vid}-1-1/"
|
||||
res = self.fetch(url, headers={'Referer': self.host})
|
||||
if not res:
|
||||
return {"list": []}
|
||||
|
||||
soup = BeautifulSoup(res.text, 'html.parser')
|
||||
raw_title = soup.title.text.split('|')[0].replace('在线播放在线观看','').replace('《','').replace('》','').strip()
|
||||
|
||||
vod = {
|
||||
"vod_id": vid,
|
||||
"vod_name": raw_title,
|
||||
"vod_type": "视频",
|
||||
"vod_content": "资源来自于网络",
|
||||
"vod_play_from": "Luyitian",
|
||||
"vod_play_url": f"播放${vid}-1-1"
|
||||
}
|
||||
return {"list": [vod]}
|
||||
|
||||
def searchContent(self, key, quick, pg=1):
|
||||
url = f"{self.host}/vodsearch/{key}----------{pg}---/"
|
||||
res = self.fetch(url, headers={'Referer': self.host})
|
||||
if not res:
|
||||
return {"list": []}
|
||||
|
||||
soup = BeautifulSoup(res.text, 'html.parser')
|
||||
vod_list = []
|
||||
items = soup.select('.video-img-box') or soup.select('.video-film-list .video-item')
|
||||
|
||||
for item in items:
|
||||
a = item.select_one('a')
|
||||
if not a:
|
||||
continue
|
||||
href = a.get('href', '')
|
||||
vid_match = re.search(r'/vodplay/(\d+)', href) or re.search(r'/voddetail/(\d+)', href)
|
||||
vid = vid_match.group(1) if vid_match else href
|
||||
|
||||
name = ""
|
||||
img = item.select_one('img')
|
||||
if img and img.get('alt'):
|
||||
name = img['alt']
|
||||
if not name and a.get('title'):
|
||||
name = a['title']
|
||||
if not name:
|
||||
title_elem = item.select_one('.title a')
|
||||
if title_elem:
|
||||
name = title_elem.get_text(strip=True)
|
||||
if not name:
|
||||
name = a.get_text(strip=True)
|
||||
if not name:
|
||||
name = "搜索结果"
|
||||
|
||||
pic = ""
|
||||
if img:
|
||||
pic = img.get('data-src') or img.get('src', '')
|
||||
|
||||
vod_list.append({
|
||||
"vod_id": vid,
|
||||
"vod_name": name.strip(),
|
||||
"vod_pic": pic,
|
||||
"vod_remarks": ""
|
||||
})
|
||||
return {"list": vod_list}
|
||||
|
||||
def _js_decode(self, js_str):
|
||||
b64_match = re.search(r'atob\s*\(\s*["\']([^"\']+)["\']\s*\)', js_str)
|
||||
if b64_match:
|
||||
try:
|
||||
decoded = base64.b64decode(b64_match.group(1)).decode('utf-8')
|
||||
return decoded
|
||||
except:
|
||||
pass
|
||||
unescape_match = re.search(r'unescape\s*\(\s*["\']([^"\']+)["\']\s*\)', js_str)
|
||||
if unescape_match:
|
||||
try:
|
||||
decoded = unquote(unescape_match.group(1))
|
||||
return decoded
|
||||
except:
|
||||
pass
|
||||
url_match = re.search(r'(https?://[^\s"\']+\.m3u8[^\s"\']*)', js_str, re.I)
|
||||
if url_match:
|
||||
return url_match.group(1)
|
||||
return None
|
||||
|
||||
def _sniff_xhr(self, html, page_url):
|
||||
patterns = [
|
||||
r'fetch\s*\(\s*["\']([^"\']+\.m3u8[^"\']*)["\']',
|
||||
r'XMLHttpRequest.*?\.open\s*\(\s*["\']GET["\']\s*,\s*["\']([^"\']+\.m3u8[^"\']*)["\']',
|
||||
r'\.get\s*\(\s*["\']([^"\']+\.m3u8[^"\']*)["\']',
|
||||
r'url\s*:\s*["\']([^"\']+\.m3u8[^"\']*)["\']',
|
||||
r'src\s*=\s*["\']([^"\']+\.m3u8[^"\']*)["\']',
|
||||
]
|
||||
for pat in patterns:
|
||||
match = re.search(pat, html, re.I)
|
||||
if match:
|
||||
url = match.group(1)
|
||||
if not url.startswith('http'):
|
||||
url = urljoin(page_url, url)
|
||||
return url
|
||||
|
||||
scripts = re.findall(r'<script[^>]*>(.*?)</script>', html, re.I | re.S)
|
||||
for script_content in scripts:
|
||||
if script_content.strip():
|
||||
found = self._js_decode(script_content)
|
||||
if found and '.m3u8' in found:
|
||||
return found
|
||||
return None
|
||||
|
||||
def playerContent(self, flag, id, vipFlags=None):
|
||||
play_url = f"{self.host}/vodplay/{id}/"
|
||||
res = self.fetch(play_url, headers={'Referer': self.host}, timeout=5)
|
||||
if not res:
|
||||
return {"parse": 1, "url": play_url}
|
||||
|
||||
html = res.text
|
||||
m3u8_url = None
|
||||
|
||||
match = re.search(r'var\s+player_aaaa\s*=\s*(\{.*?\});', html, re.DOTALL)
|
||||
if match:
|
||||
try:
|
||||
json_str = match.group(1).strip()
|
||||
if json_str.endswith(','):
|
||||
json_str = json_str[:-1]
|
||||
config = json.loads(json_str)
|
||||
m3u8_url = config.get('url', '')
|
||||
except:
|
||||
pass
|
||||
|
||||
if not m3u8_url:
|
||||
m3u8_url = self._js_decode(html)
|
||||
|
||||
if not m3u8_url:
|
||||
m3u8_url = self._sniff_xhr(html, play_url)
|
||||
|
||||
if not m3u8_url:
|
||||
return {"parse": 1, "url": play_url}
|
||||
|
||||
m3u8_url = unquote(m3u8_url)
|
||||
if m3u8_url.startswith('//'):
|
||||
m3u8_url = 'https:' + m3u8_url
|
||||
elif not m3u8_url.startswith('http'):
|
||||
m3u8_url = urljoin(self.host, m3u8_url)
|
||||
|
||||
return {
|
||||
"parse": 0,
|
||||
"playUrl": "",
|
||||
"url": m3u8_url,
|
||||
"header": {
|
||||
"User-Agent": self.session.headers['User-Agent'],
|
||||
"Referer": play_url,
|
||||
"Origin": self.host
|
||||
}
|
||||
}
|
||||
+10
-1
@@ -19,7 +19,7 @@ YOUTUBE_CLASSES = [
|
||||
{'type_id': '最新新聞', 'type_name': '新聞'},
|
||||
{'type_id': '新聞直播', 'type_name': '新聞直播'},
|
||||
{'type_id': '歌曲', 'type_name': '歌曲'},
|
||||
{'type_id': '動畫片', 'type_name': '動畫片'},
|
||||
{'type_id': '動畫', 'type_name': '動畫'},
|
||||
{'type_id': '短劇', 'type_name': '短劇'},
|
||||
{'type_id': '劇集', 'type_name': '劇集'},
|
||||
{'type_id': '電影', 'type_name': '電影'},
|
||||
@@ -28,6 +28,15 @@ YOUTUBE_CLASSES = [
|
||||
{'type_id': '16K HDR', 'type_name': '16K HDR'},
|
||||
{'type_id': '科技', 'type_name': '科技'},
|
||||
{'type_id': '解說', 'type_name': '解說'},
|
||||
{'type_id': '台劇', 'type_name': '台劇'},
|
||||
{'type_id': '陸劇', 'type_name': '陸劇'},
|
||||
{'type_id': '綜藝', 'type_name': '綜藝'},
|
||||
{'type_id': '網紅', 'type_name': '網紅'},
|
||||
{'type_id': '靈異', 'type_name': '靈異'},
|
||||
{'type_id': '探險', 'type_name': '探險'},
|
||||
{'type_id': '旅遊', 'type_name': '旅遊'},
|
||||
{'type_id': '美食', 'type_name': '美食'},
|
||||
|
||||
]
|
||||
|
||||
CATEGORY_QUERY = {
|
||||
|
||||
@@ -0,0 +1,162 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
import re
|
||||
import urllib.parse
|
||||
import requests
|
||||
try:
|
||||
from base.spider import Spider as BaseSpider
|
||||
except ImportError:
|
||||
class BaseSpider:
|
||||
def __init__(self):
|
||||
return None
|
||||
class Spider(BaseSpider):
|
||||
BASE_URL = "https://maomi66.cc"
|
||||
HEADERS = {
|
||||
"User-Agent": "Mozilla/5.0 (Linux; Android 12; Mobile) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Mobile Safari/537.36",
|
||||
"Referer": "https://maomi66.cc/",
|
||||
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
|
||||
"Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8"
|
||||
}
|
||||
def __init__(self):
|
||||
self.session = requests.Session()
|
||||
self.session.headers.update(self.HEADERS)
|
||||
self._class_cache = []
|
||||
def getName(self):
|
||||
return "猫咪AV"
|
||||
def init(self, extend=""):
|
||||
return None
|
||||
def isVideoFormat(self, url):
|
||||
return bool(re.search(r'\.(m3u8|mp4|flv|avi|mkv|mov)(\?|$)', url or '', re.I))
|
||||
def manualVideoCheck(self):
|
||||
return True
|
||||
def homeContent(self, filter):
|
||||
html = self._get(self.BASE_URL)
|
||||
classes = self._classes(html)
|
||||
return {"class": classes, "list": self._parse_list(html), "filters": {}, "parse": 0, "jx": 0}
|
||||
def homeVideoContent(self):
|
||||
return {"list": self._parse_list(self._get(self.BASE_URL))}
|
||||
def categoryContent(self, tid, pg, filter, extend):
|
||||
page = self._to_int(pg, 1)
|
||||
html = self._get(self.BASE_URL + "/list/%s-%s.html" % (tid, page))
|
||||
data = self._parse_list(html)
|
||||
return {"list": data, "page": page, "pagecount": page + 1 if data else page, "limit": len(data) or 20, "total": (page + 1) * (len(data) or 20)}
|
||||
def detailContent(self, ids):
|
||||
vid = ids[0] if isinstance(ids, list) and ids else str(ids)
|
||||
url = vid if str(vid).startswith("http") else self.BASE_URL + "/video/%s.html" % vid
|
||||
html = self._get(url)
|
||||
title = self._clean(self._match(html, r'<h1[^>]*>(.*?)</h1>') or self._match(html, r'<h2[^>]*>(.*?)</h2>') or self._match(html, r'<title[^>]*>(.*?)</title>'))
|
||||
if not title:
|
||||
title = "视频%s" % re.sub(r'\D+', '', str(vid))
|
||||
pic = self._fix(self._match(html, r'<meta[^>]+property=["\']og:image["\'][^>]+content=["\']([^"\']+)') or self._match(html, r'<video[^>]+poster=["\']([^"\']+)') or self._match(html, r'(?:data-original|data-src|src)=["\']([^"\']+\.(?:jpg|jpeg|png|webp|gif)[^"\']*)'))
|
||||
play = self._extract_play(html)
|
||||
tags = []
|
||||
for x in re.findall(r'<a[^>]+href=["\']/list/\d+-1\.html["\'][^>]*>(.*?)</a>', html, re.S):
|
||||
t = self._clean(x)
|
||||
if t and t not in tags:
|
||||
tags.append(t)
|
||||
content = self._clean(self._match(html, r'<div[^>]+class=["\'][^"\']*(?:des|intro|content|info)[^"\']*["\'][^>]*>(.*?)</div>')) or title
|
||||
vod = {
|
||||
"vod_id": str(vid).split("/")[-1].replace(".html", ""),
|
||||
"vod_name": title,
|
||||
"vod_pic": pic,
|
||||
"type_name": "/".join(tags[:3]),
|
||||
"vod_year": "",
|
||||
"vod_area": "",
|
||||
"vod_remarks": "",
|
||||
"vod_actor": "",
|
||||
"vod_director": "",
|
||||
"vod_content": content,
|
||||
"vod_play_from": "默认",
|
||||
"vod_play_url": "播放$%s" % (play or url)
|
||||
}
|
||||
return {"list": [vod]}
|
||||
def searchContent(self, key, quick, pg="1"):
|
||||
q = urllib.parse.quote(str(key or ""))
|
||||
page = self._to_int(pg, 1)
|
||||
html = self._get(self.BASE_URL + "/search.php?content=%s&type=1&page=%s" % (q, page))
|
||||
data = self._parse_list(html)
|
||||
if not data:
|
||||
html = self._get(self.BASE_URL + "/search.php?content=%s&type=1" % q)
|
||||
data = self._parse_list(html)
|
||||
return {"list": data, "page": page, "pagecount": page + 1 if data else page, "limit": len(data) or 20, "total": (page + 1) * (len(data) or 20)}
|
||||
def playerContent(self, flag, id, vipFlags):
|
||||
url = urllib.parse.unquote(str(id or ""))
|
||||
if "/video/" in url or re.fullmatch(r'\d+', url):
|
||||
page = url if url.startswith("http") else self.BASE_URL + "/video/%s.html" % url
|
||||
play = self._extract_play(self._get(page))
|
||||
url = play or page
|
||||
return {"parse": 0, "playUrl": "", "url": self._fix(url), "header": self.HEADERS}
|
||||
def _classes(self, html):
|
||||
arr = []
|
||||
for tid, name in re.findall(r'href=["\']/list/(\d+)-1\.html["\'][^>]*>(.*?)</a>', html or "", re.S):
|
||||
name = self._clean(name)
|
||||
if tid and name and not any(x["type_id"] == tid for x in arr):
|
||||
arr.append({"type_id": tid, "type_name": name})
|
||||
if not arr:
|
||||
arr = [
|
||||
{"type_id": "69829818", "type_name": "国产精品"},
|
||||
{"type_id": "71188148", "type_name": "国产自拍"},
|
||||
{"type_id": "43659662", "type_name": "日本精品"},
|
||||
{"type_id": "37440125", "type_name": "欧美极品"},
|
||||
{"type_id": "19211697", "type_name": "中文字幕"},
|
||||
{"type_id": "77777777", "type_name": "动漫精品"}
|
||||
]
|
||||
self._class_cache = arr
|
||||
return arr
|
||||
def _parse_list(self, html):
|
||||
out = []
|
||||
blocks = re.findall(r'<li[\s\S]*?</li>', html or "", re.I)
|
||||
if not blocks:
|
||||
blocks = re.findall(r'<a[^>]+href=["\']/video/\d+\.html["\'][\s\S]*?</a>', html or "", re.I)
|
||||
for item in blocks:
|
||||
vid = self._match(item, r'href=["\'][^"\']*/video/(\d+)\.html["\']')
|
||||
if not vid:
|
||||
continue
|
||||
name = self._clean(self._match(item, r'<h5[^>]*>\s*<a[^>]*>(.*?)</a>') or self._match(item, r'title=["\']([^"\']+)') or self._match(item, r'alt=["\']([^"\']+)'))
|
||||
pic = self._fix(self._match(item, r'data-original=["\']([^"\']+)') or self._match(item, r'data-src=["\']([^"\']+)') or self._match(item, r'<img[^>]+src=["\']([^"\']+)'))
|
||||
remark = self._clean(self._match(item, r'<span[^>]*>(.*?)</span>') or self._match(item, r'<em[^>]*>(.*?)</em>'))
|
||||
if not name:
|
||||
name = "视频%s" % vid
|
||||
vod = {"vod_id": vid, "vod_name": name, "vod_pic": pic, "vod_remarks": remark}
|
||||
if not any(x["vod_id"] == vid for x in out):
|
||||
out.append(vod)
|
||||
return out
|
||||
def _extract_play(self, html):
|
||||
play = self._match(html, r'hls\.loadSource\(["\']([^"\']+)["\']\)') or self._match(html, r'video\.src\s*=\s*["\']([^"\']+)["\']') or self._match(html, r'<source[^>]+src=["\']([^"\']+)["\']') or self._match(html, r'["\'](https?://[^"\']+play\.php\?[^"\']+)["\']') or self._match(html, r'["\'](/play\.php\?[^"\']+)["\']')
|
||||
return self._fix(play)
|
||||
def _get(self, url):
|
||||
if not url:
|
||||
return ""
|
||||
url = self._fix(url)
|
||||
headers = dict(self.HEADERS)
|
||||
headers["Referer"] = self.BASE_URL + "/"
|
||||
try:
|
||||
r = self.session.get(url, headers=headers, timeout=12, verify=False)
|
||||
if not r.encoding or r.encoding.lower() == "iso-8859-1":
|
||||
r.encoding = r.apparent_encoding or "utf-8"
|
||||
return r.text
|
||||
except requests.RequestException:
|
||||
return ""
|
||||
def _match(self, text, pattern, default=""):
|
||||
m = re.search(pattern, text or "", re.S | re.I)
|
||||
if not m:
|
||||
return default
|
||||
return m.group(1) if m.lastindex else m.group(0)
|
||||
def _clean(self, text):
|
||||
text = re.sub(r'<script[\s\S]*?</script>|<style[\s\S]*?</style>', ' ', text or '', flags=re.I)
|
||||
text = re.sub(r'<[^>]+>', ' ', text)
|
||||
text = text.replace(' ', ' ').replace('&amp;', '&').replace('&', '&').replace('&', '&').replace('"', '"').replace(''', "'").replace('<', '<').replace('>', '>')
|
||||
return re.sub(r'\s+', ' ', text).strip()
|
||||
def _fix(self, url):
|
||||
url = (url or "").strip().replace("\\/", "/")
|
||||
if not url:
|
||||
return ""
|
||||
if url.startswith("//"):
|
||||
return "https:" + url
|
||||
if url.startswith("/"):
|
||||
return self.BASE_URL + url
|
||||
return url
|
||||
def _to_int(self, value, default=1):
|
||||
try:
|
||||
return int(value)
|
||||
except Exception:
|
||||
return default
|
||||
@@ -0,0 +1,347 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
import re
|
||||
import json
|
||||
import urllib.parse
|
||||
from urllib.parse import urljoin, quote
|
||||
import sys
|
||||
sys.path.append('..')
|
||||
from base.spider import Spider
|
||||
from bs4 import BeautifulSoup
|
||||
|
||||
class Spider(Spider):
|
||||
def getName(self):
|
||||
return "香肠派对"
|
||||
|
||||
def init(self, extend=""):
|
||||
self.host = "https://xiang512.xiang.party/xcpd"
|
||||
pass
|
||||
|
||||
def header(self):
|
||||
return {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/134.0.0.0 Safari/537.36',
|
||||
'Referer': self.host
|
||||
}
|
||||
|
||||
def homeContent(self, filter):
|
||||
result = {"class": [], "filters": {}, "list": []}
|
||||
|
||||
# 分类列表
|
||||
classes = [
|
||||
{"type_id": "1", "type_name": "在线看片"},
|
||||
{"type_id": "2", "type_name": "无需等待"},
|
||||
{"type_id": "3", "type_name": "不用下载"},
|
||||
{"type_id": "4", "type_name": "全部免费"}
|
||||
]
|
||||
result["class"] = classes
|
||||
|
||||
# 获取首页视频
|
||||
url = f"{self.host}/"
|
||||
rsp = self.fetch(url, headers=self.header())
|
||||
if rsp.status_code != 200:
|
||||
return result
|
||||
|
||||
root = BeautifulSoup(rsp.text, 'html.parser')
|
||||
videos = []
|
||||
|
||||
# 查找视频列表
|
||||
items = root.select('ul.thumbnail-group.clearfix li')
|
||||
for item in items:
|
||||
try:
|
||||
a = item.select_one('a.thumbnail')
|
||||
if not a:
|
||||
continue
|
||||
href = a.get('href', '')
|
||||
vod_id = re.search(r'/vod(?:detail|play)/(\d+)', href)
|
||||
if not vod_id:
|
||||
continue
|
||||
vod_id = vod_id.group(1)
|
||||
|
||||
img = a.select_one('img')
|
||||
pic = img.get('src', '') if img else ''
|
||||
|
||||
info = item.select_one('.video-info')
|
||||
if info:
|
||||
h5 = info.select_one('h5 a')
|
||||
name = h5.get('title', '') if h5 else ''
|
||||
if not name:
|
||||
name = h5.text.strip() if h5 else ''
|
||||
p = info.select_one('p')
|
||||
remarks = p.text.strip() if p else ''
|
||||
else:
|
||||
name = a.get('title', '')
|
||||
remarks = ''
|
||||
|
||||
videos.append({
|
||||
"vod_id": vod_id,
|
||||
"vod_name": name,
|
||||
"vod_pic": pic,
|
||||
"vod_remarks": remarks
|
||||
})
|
||||
if len(videos) >= 20:
|
||||
break
|
||||
except:
|
||||
continue
|
||||
|
||||
result["list"] = videos
|
||||
return result
|
||||
|
||||
def homeVideoContent(self):
|
||||
return self.homeContent(False)
|
||||
|
||||
def categoryContent(self, tid, pg, filter, extend):
|
||||
p = int(pg)
|
||||
# 修复分页URL格式
|
||||
url = f"{self.host}/vodtype/{tid}-{p}.html"
|
||||
rsp = self.fetch(url, headers=self.header())
|
||||
if rsp.status_code != 200:
|
||||
return {"list": [], "page": p, "pagecount": 1}
|
||||
|
||||
root = BeautifulSoup(rsp.text, 'html.parser')
|
||||
videos = []
|
||||
|
||||
# 提取总页数（从“共XX条数据,当前X/913页”）
|
||||
pagecount = p
|
||||
page_info = root.find(string=re.compile(r'共\d+条数据,当前\d+/(\d+)页'))
|
||||
if page_info:
|
||||
try:
|
||||
pagecount = int(re.search(r'/(\d+)页', page_info).group(1))
|
||||
except:
|
||||
pass
|
||||
|
||||
# 提取视频列表
|
||||
items = root.select('ul.thumbnail-group.clearfix li')
|
||||
for item in items:
|
||||
try:
|
||||
a = item.select_one('a.thumbnail')
|
||||
if not a:
|
||||
continue
|
||||
href = a.get('href', '')
|
||||
vod_id = re.search(r'/vod(?:detail|play)/(\d+)', href)
|
||||
if not vod_id:
|
||||
continue
|
||||
vod_id = vod_id.group(1)
|
||||
|
||||
img = a.select_one('img')
|
||||
pic = img.get('src', '') if img else ''
|
||||
|
||||
info = item.select_one('.video-info')
|
||||
if info:
|
||||
h5 = info.select_one('h5 a')
|
||||
name = h5.get('title', '') if h5 else ''
|
||||
if not name:
|
||||
name = h5.text.strip() if h5 else ''
|
||||
p_elem = info.select_one('p')
|
||||
remarks = p_elem.text.strip() if p_elem else ''
|
||||
else:
|
||||
name = a.get('title', '')
|
||||
remarks = ''
|
||||
|
||||
videos.append({
|
||||
"vod_id": vod_id,
|
||||
"vod_name": name,
|
||||
"vod_pic": pic,
|
||||
"vod_remarks": remarks
|
||||
})
|
||||
except:
|
||||
continue
|
||||
|
||||
return {
|
||||
"list": videos,
|
||||
"page": p,
|
||||
"pagecount": pagecount
|
||||
}
|
||||
|
||||
def detailContent(self, ids):
|
||||
vid = ids[0] if isinstance(ids, list) else ids.split(",")[0]
|
||||
url = f"{self.host}/voddetail/{vid}.html"
|
||||
rsp = self.fetch(url, headers=self.header())
|
||||
if rsp.status_code != 200:
|
||||
return {"list": []}
|
||||
|
||||
root = BeautifulSoup(rsp.text, 'html.parser')
|
||||
|
||||
# 标题
|
||||
title = ""
|
||||
h1 = root.select_one('h1.appel-title')
|
||||
if h1:
|
||||
title = h1.text.strip()
|
||||
if not title:
|
||||
title_elem = root.select_one('title')
|
||||
if title_elem:
|
||||
title = title_elem.text.replace('视频介绍--香肠派对', '').strip()
|
||||
|
||||
# 图片
|
||||
pic = ""
|
||||
img = root.select_one('img.appel-img')
|
||||
if img:
|
||||
pic = img.get('src', '')
|
||||
if not pic:
|
||||
img = root.select_one('.detail-poster img')
|
||||
if img:
|
||||
pic = img.get('src', '')
|
||||
|
||||
# 描述
|
||||
desc = ""
|
||||
desc_elem = root.select_one('.detail-content')
|
||||
if desc_elem:
|
||||
desc = desc_elem.text.strip()
|
||||
if not desc:
|
||||
desc_elem = root.select_one('.appel-content')
|
||||
if desc_elem:
|
||||
desc = desc_elem.text.strip()
|
||||
|
||||
# 播放列表
|
||||
play_from_list = []
|
||||
play_url_list = []
|
||||
|
||||
# 查找线路
|
||||
tabs = root.select('.detail-tab li a')
|
||||
play_blocks = root.select('ul.detail-play-list')
|
||||
|
||||
for i, block in enumerate(play_blocks):
|
||||
line_name = tabs[i].text.strip() if i < len(tabs) else f"线路{i+1}"
|
||||
urls = []
|
||||
for a in block.select('a'):
|
||||
href = a.get('href', '')
|
||||
if href:
|
||||
full_url = urljoin(self.host, href)
|
||||
name = a.text.strip() or f"第{len(urls)+1}集"
|
||||
urls.append(f"{name}${full_url}")
|
||||
if urls:
|
||||
play_from_list.append(line_name)
|
||||
play_url_list.append("#".join(urls))
|
||||
|
||||
# 如果没有找到，尝试其他选择器
|
||||
if not play_from_list:
|
||||
lines = root.select('.ff-playurl-tab li a')
|
||||
for i, block in enumerate(root.select('.ff-playurl-tab-pane')):
|
||||
line_name = lines[i].text.strip() if i < len(lines) else f"线路{i+1}"
|
||||
urls = []
|
||||
for a in block.select('a'):
|
||||
href = a.get('href', '')
|
||||
if href:
|
||||
full_url = urljoin(self.host, href)
|
||||
name = a.text.strip() or f"第{len(urls)+1}集"
|
||||
urls.append(f"{name}${full_url}")
|
||||
if urls:
|
||||
play_from_list.append(line_name)
|
||||
play_url_list.append("#".join(urls))
|
||||
|
||||
vod_play_from = "$$$".join(play_from_list) if play_from_list else ""
|
||||
vod_play_url = "$$$".join(play_url_list) if play_url_list else ""
|
||||
|
||||
return {"list": [{
|
||||
"vod_id": vid,
|
||||
"vod_name": title,
|
||||
"vod_pic": pic,
|
||||
"vod_content": desc,
|
||||
"vod_play_from": vod_play_from,
|
||||
"vod_play_url": vod_play_url
|
||||
}]}
|
||||
|
||||
def searchContent(self, key, quick, pg="1"):
|
||||
p = int(pg)
|
||||
url = f"{self.host}/vodsearch/-------------.html?wd={quote(key)}&page={p}"
|
||||
rsp = self.fetch(url, headers=self.header())
|
||||
if rsp.status_code != 200:
|
||||
return {"list": []}
|
||||
|
||||
root = BeautifulSoup(rsp.text, 'html.parser')
|
||||
videos = []
|
||||
|
||||
items = root.select('ul.thumbnail-group.clearfix li')
|
||||
for item in items:
|
||||
try:
|
||||
a = item.select_one('a.thumbnail')
|
||||
if not a:
|
||||
continue
|
||||
href = a.get('href', '')
|
||||
vod_id = re.search(r'/vod(?:detail|play)/(\d+)', href)
|
||||
if not vod_id:
|
||||
continue
|
||||
vod_id = vod_id.group(1)
|
||||
|
||||
img = a.select_one('img')
|
||||
pic = img.get('src', '') if img else ''
|
||||
|
||||
info = item.select_one('.video-info')
|
||||
if info:
|
||||
h5 = info.select_one('h5 a')
|
||||
name = h5.get('title', '') if h5 else ''
|
||||
if not name:
|
||||
name = h5.text.strip() if h5 else ''
|
||||
p_elem = info.select_one('p')
|
||||
remarks = p_elem.text.strip() if p_elem else ''
|
||||
else:
|
||||
name = a.get('title', '')
|
||||
remarks = ''
|
||||
|
||||
videos.append({
|
||||
"vod_id": vod_id,
|
||||
"vod_name": name,
|
||||
"vod_pic": pic,
|
||||
"vod_remarks": remarks
|
||||
})
|
||||
except:
|
||||
continue
|
||||
|
||||
return {"list": videos, "page": p}
|
||||
|
||||
def playerContent(self, flag, id, vipFlags):
|
||||
# 构建播放页URL
|
||||
if id.startswith('http'):
|
||||
play_url = id
|
||||
else:
|
||||
play_url = urljoin(self.host, id)
|
||||
|
||||
rsp = self.fetch(play_url, headers=self.header())
|
||||
if rsp.status_code != 200:
|
||||
return {"parse": 0, "playUrl": play_url}
|
||||
|
||||
html = rsp.text
|
||||
|
||||
# 方法1：从 player_aaaa 提取
|
||||
match = re.search(r'var player_aaaa\s*=\s*({.*?});', html, re.DOTALL)
|
||||
if match:
|
||||
try:
|
||||
js_str = match.group(1)
|
||||
js_str = re.sub(r'(\w+):', r'"\1":', js_str)
|
||||
player_data = json.loads(js_str)
|
||||
if player_data.get('url'):
|
||||
return {"parse": 0, "playUrl": player_data['url']}
|
||||
except:
|
||||
pass
|
||||
|
||||
# 方法2：从 iframe 提取（关键修复）
|
||||
# 匹配 id="playleft" 的 td 中的 iframe
|
||||
iframe_match = re.search(r'<td[^>]*id="playleft"[^>]*>.*?<iframe[^>]+src="([^"]+)"', html, re.DOTALL)
|
||||
if iframe_match:
|
||||
iframe_url = iframe_match.group(1)
|
||||
# 提取 url 参数
|
||||
m3u8_match = re.search(r'[?&]url=([^&]+)', iframe_url)
|
||||
if m3u8_match:
|
||||
m3u8_url = urllib.parse.unquote(m3u8_match.group(1))
|
||||
return {"parse": 0, "playUrl": m3u8_url}
|
||||
# 如果 iframe 本身就是 m3u8
|
||||
if '.m3u8' in iframe_url:
|
||||
return {"parse": 0, "playUrl": iframe_url}
|
||||
|
||||
# 方法3：直接查找 iframe
|
||||
iframe_match2 = re.search(r'<iframe[^>]+src="([^"]+)"', html)
|
||||
if iframe_match2:
|
||||
iframe_url = iframe_match2.group(1)
|
||||
m3u8_match = re.search(r'[?&]url=([^&]+)', iframe_url)
|
||||
if m3u8_match:
|
||||
m3u8_url = urllib.parse.unquote(m3u8_match.group(1))
|
||||
return {"parse": 0, "playUrl": m3u8_url}
|
||||
|
||||
# 方法4：直接查找 m3u8
|
||||
m3u8 = re.search(r'https?://[^"\']+\.m3u8[^"\']*', html)
|
||||
if m3u8:
|
||||
return {"parse": 0, "playUrl": m3u8.group(0)}
|
||||
|
||||
# 方法5：让系统解析
|
||||
return {"parse": 1, "url": play_url}
|
||||
|
||||
def localProxy(self, params):
|
||||
return [200, "video/MP2T", ""]
|
||||
@@ -0,0 +1,137 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
import re
|
||||
import urllib.parse
|
||||
import requests
|
||||
|
||||
try:
|
||||
from base.spider import Spider as BaseSpider
|
||||
except ImportError:
|
||||
class BaseSpider:
|
||||
pass
|
||||
|
||||
class Spider(BaseSpider):
|
||||
BASE_URL = "https://madou.club"
|
||||
DASH_URL = "https://dash.madou.club"
|
||||
HEADERS = {
|
||||
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
|
||||
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
|
||||
"Referer": BASE_URL + "/",
|
||||
}
|
||||
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.name = "麻豆社"
|
||||
self.session = requests.Session()
|
||||
self.session.headers.update(self.HEADERS)
|
||||
self._class_cache = None
|
||||
|
||||
def init(self, extend="{}"):
|
||||
return None
|
||||
|
||||
def getName(self):
|
||||
return self.name
|
||||
|
||||
def homeContent(self, filter):
|
||||
html = self._get(self.BASE_URL + "/")
|
||||
return {"class": self._classes(html), "filters": {}, "list": self._parse_list(html), "parse": 0, "jx": 0}
|
||||
|
||||
def homeVideoContent(self):
|
||||
return {"list": self._parse_list(self._get(self.BASE_URL + "/"))}
|
||||
|
||||
def categoryContent(self, tid, pg, filter, extend):
|
||||
page = self._to_int(pg, 1)
|
||||
base = tid if str(tid).startswith("http") else self.BASE_URL + "/category/" + str(tid).strip("/")
|
||||
url = base.rstrip("/") if page <= 1 else base.rstrip("/") + "/page/" + str(page)
|
||||
data = self._parse_list(self._get(url))
|
||||
return {"page": page, "pagecount": page if len(data) < 10 else page + 1, "limit": 20, "total": 99999, "list": data, "parse": 0, "jx": 0}
|
||||
|
||||
def detailContent(self, ids):
|
||||
result = {"list": [], "parse": 0, "jx": 0}
|
||||
if not ids:
|
||||
return result
|
||||
url = ids[0]
|
||||
html = self._get(url)
|
||||
name = self._clean(self._match(html, r'<h1[^>]*class=["\']article-title["\'][^>]*>(.*?)</h1>') or self._match(html, r'<title>(.*?)</title>').split("-")[0])
|
||||
pic = self._match(html, r'shareimage\s*:\s*["\']([^"\']+)') or self._match(html, r'<img[^>]+data-src=["\']([^"\']+)') or self._match(html, r'<img[^>]+src=["\']([^"\']+)')
|
||||
cate = self._clean(self._match(html, r'分类：\s*<a[^>]*>(.*?)</a>'))
|
||||
remarks = self._clean(self._match(html, r'观看\((.*?)\)'))
|
||||
tag_block = self._match(html, r'<div[^>]+class=["\']article-tags["\'][^>]*>(.*?)</div>')
|
||||
tags = ",".join([self._clean(x) for x in re.findall(r'<a[^>]*>(.*?)</a>', tag_block, re.S)])
|
||||
iframe = self._match(html, r'<iframe[^>]+src=["\']?([^"\'\s>]+)')
|
||||
play_id = urllib.parse.urljoin(self.BASE_URL, iframe or url)
|
||||
result["list"].append({"vod_id": url, "vod_name": name, "vod_pic": urllib.parse.urljoin(self.BASE_URL, pic), "type_name": cate, "vod_year": "", "vod_area": "", "vod_remarks": remarks, "vod_actor": tags, "vod_director": "", "vod_content": name, "vod_play_from": "DPlayer", "vod_play_url": name + "$" + play_id})
|
||||
return result
|
||||
|
||||
def searchContent(self, key, quick, pg="1"):
|
||||
page = self._to_int(pg, 1)
|
||||
q = urllib.parse.quote(str(key))
|
||||
url = self.BASE_URL + "/?s=" + q if page <= 1 else self.BASE_URL + "/page/" + str(page) + "?s=" + q
|
||||
data = self._parse_list(self._get(url))
|
||||
return {"page": page, "pagecount": page if len(data) < 10 else page + 1, "limit": 20, "total": 99999, "list": data, "parse": 0, "jx": 0}
|
||||
|
||||
def playerContent(self, flag, id, vipFlags):
|
||||
result = {"parse": 0, "playUrl": "", "url": id or "", "jx": 0, "header": {"User-Agent": self.HEADERS["User-Agent"], "Referer": self.BASE_URL + "/"}}
|
||||
if not id:
|
||||
return result
|
||||
play_page = id
|
||||
if "dash.madou.club/share/" not in play_page:
|
||||
html = self._get(play_page)
|
||||
play_page = urllib.parse.urljoin(self.BASE_URL, self._match(html, r'<iframe[^>]+src=["\']?([^"\'\s>]+)') or play_page)
|
||||
html = self._get(play_page, {"Referer": self.BASE_URL + "/"})
|
||||
token = self._match(html, r'var\s+token\s*=\s*["\']([^"\']*)')
|
||||
m3u8 = self._match(html, r'var\s+m3u8\s*=\s*["\']([^"\']+\.m3u8)["\']')
|
||||
if m3u8:
|
||||
url = urllib.parse.urljoin(self.DASH_URL, m3u8)
|
||||
result["url"] = url + (("&" if "?" in url else "?") + "token=" + token if token else "")
|
||||
result["header"] = {"User-Agent": self.HEADERS["User-Agent"], "Referer": play_page, "Origin": self.BASE_URL}
|
||||
return result
|
||||
|
||||
def _classes(self, html=None):
|
||||
if self._class_cache:
|
||||
return self._class_cache
|
||||
html = html or self._get(self.BASE_URL + "/")
|
||||
classes, seen = [], set()
|
||||
for href, name in re.findall(r'<a[^>]+href=["\'](https://madou\.club/category/[^"\']+)["\'][^>]*>(.*?)</a>', html, re.S):
|
||||
name = self._clean(name)
|
||||
key = href.rstrip("/")
|
||||
if key not in seen and name:
|
||||
seen.add(key)
|
||||
classes.append({"type_id": href, "type_name": name})
|
||||
self._class_cache = classes
|
||||
return classes
|
||||
|
||||
def _parse_list(self, html):
|
||||
data = []
|
||||
blocks = re.findall(r'<article\b.*?</article>', html, re.S) or re.findall(r'<li>.*?</li>', html, re.S)
|
||||
for item in blocks:
|
||||
href = self._match(item, r'<a[^>]+href=["\']([^"\']+\.html)["\']')
|
||||
name = self._clean(self._match(item, r'<h2[^>]*>.*?<a[^>]*>(.*?)</a>') or self._match(item, r'<a[^>]*>(?:<span.*?</span>)?\s*(.*?)</a>'))
|
||||
pic = self._match(item, r'<img[^>]+data-src=["\']([^"\']+)') or self._match(item, r'<img[^>]+src=["\']([^"\']+)')
|
||||
remarks = self._clean(self._match(item, r'<time[^>]*>(.*?)</time>') or self._match(item, r'观看\((.*?)\)'))
|
||||
if href and name:
|
||||
data.append({"vod_id": urllib.parse.urljoin(self.BASE_URL, href), "vod_name": name, "vod_pic": urllib.parse.urljoin(self.BASE_URL, pic), "vod_remarks": remarks})
|
||||
return data
|
||||
|
||||
def _get(self, url, headers=None):
|
||||
h = dict(self.HEADERS)
|
||||
if headers:
|
||||
h.update(headers)
|
||||
try:
|
||||
return self.session.get(url, headers=h, timeout=15, verify=False).text
|
||||
except Exception:
|
||||
return ""
|
||||
|
||||
def _match(self, text, pattern):
|
||||
m = re.search(pattern, text or "", re.S | re.I)
|
||||
return m.group(1).strip() if m else ""
|
||||
|
||||
def _clean(self, text):
|
||||
text = re.sub(r'<.*?>', '', text or '')
|
||||
text = text.replace(' ', ' ').replace('&', '&').replace('&', '&').replace('"', '"')
|
||||
return re.sub(r'\s+', ' ', text).strip()
|
||||
|
||||
def _to_int(self, value, default=0):
|
||||
try:
|
||||
return int(value)
|
||||
except Exception:
|
||||
return default
|
||||
@@ -1922,7 +1922,17 @@
|
||||
"ua": "okhttp",
|
||||
"url": "https://raw.githubusercontent.com/FGBLH/HKL/refs/heads/main/xxx视频资源.txt"
|
||||
},
|
||||
|
||||
{
|
||||
"name": "🔞午夜剧场",
|
||||
"type": 0,
|
||||
"playerType": 2,
|
||||
"epg": "https://epg.112114.xyz/?ch={name}&date={date}",
|
||||
"logo": "https://epg.112114.xyz/logo/{name}.png",
|
||||
"url": "https://raw.githubusercontent.com/FGBLH/HKL/refs/heads/main/午夜剧场.txt",
|
||||
"header": {
|
||||
"X-Api-key": "8692bd33270440d4d2941b814b81a25a1eb84a7205532971714c4299c57449e0..0..1738210005..5cf2c4ad-043b-4234-83a2-e84ae917"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "台灣景點直播(freeman)",
|
||||
"playerType": 2,
|
||||
|
||||
@@ -132,6 +132,17 @@
|
||||
"ua": "okhttp",
|
||||
"url": "https://raw.githubusercontent.com/FGBLH/HKL/refs/heads/main/xxx视频资源.txt"
|
||||
},
|
||||
{
|
||||
"name": "🔞午夜剧场",
|
||||
"type": 0,
|
||||
"playerType": 2,
|
||||
"epg": "https://epg.112114.xyz/?ch={name}&date={date}",
|
||||
"logo": "https://epg.112114.xyz/logo/{name}.png",
|
||||
"url": "https://raw.githubusercontent.com/FGBLH/HKL/refs/heads/main/午夜剧场.txt",
|
||||
"header": {
|
||||
"X-Api-key": "8692bd33270440d4d2941b814b81a25a1eb84a7205532971714c4299c57449e0..0..1738210005..5cf2c4ad-043b-4234-83a2-e84ae917"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "台灣景點直播(freeman)",
|
||||
"playerType": 2,
|
||||
|
||||
+109
-1
@@ -10,9 +10,117 @@
|
||||
],
|
||||
"logo" : ".美.gif",
|
||||
"wallpaper": "https://picsum.photos/1080/",
|
||||
"notice" : "版本：115.07.26.Ver.2",
|
||||
"notice" : "版本：115.07.27.Ver.2",
|
||||
"sites" : [
|
||||
|
||||
{
|
||||
"key": "真实人妻",
|
||||
"name": "🔞真实人妻.py",
|
||||
"type": 3,
|
||||
"api": "./py/真实人妻.py"
|
||||
},
|
||||
{
|
||||
"key": "猫咪TV",
|
||||
"name": "🔞咪TV.py",
|
||||
"type": 3,
|
||||
"api": "./py/猫咪TV.py"
|
||||
},
|
||||
{
|
||||
"key": "麻豆社",
|
||||
"name": "🔞麻豆社.py",
|
||||
"type": 3,
|
||||
"api": "./py/麻豆社.py"
|
||||
},
|
||||
{
|
||||
"key": "prsd",
|
||||
"name": "🔞怦然心动.py",
|
||||
"type": 3,
|
||||
"api": "./py/怦然心动.py"
|
||||
},
|
||||
{
|
||||
"key": "lyt",
|
||||
"name": "🔞撸一天.py",
|
||||
"type": 3,
|
||||
"api": "./py/撸一天.py"
|
||||
},
|
||||
{
|
||||
"key": "scpd",
|
||||
"name": "🔞香肠派对.py",
|
||||
"type": 3,
|
||||
"api": "./py/香肠派对.py"
|
||||
},
|
||||
{
|
||||
"key": "8X8X",
|
||||
"name": "🔞8X8X.py",
|
||||
"type": 3,
|
||||
"api": "./py/8X8X.py"
|
||||
},
|
||||
{
|
||||
"key": "Jable",
|
||||
"name": "🔞Jable.py",
|
||||
"type": 3,
|
||||
"api": "./py/Jable.py"
|
||||
},
|
||||
{
|
||||
"key": "Xvideos",
|
||||
"name": "🔞Xvideos.py",
|
||||
"type": 3,
|
||||
"api": "./py/Xvideos.py"
|
||||
},
|
||||
{
|
||||
"key": "Pornhub",
|
||||
"name": "🔞Pornhub.py",
|
||||
"type": 3,
|
||||
"api": "./py/Pornhub.py"
|
||||
},
|
||||
{
|
||||
"key": "xhamster",
|
||||
"name": "🔞xhamster.py",
|
||||
"type": 3,
|
||||
"api": "./py/xhamster.py"
|
||||
},
|
||||
{
|
||||
"key": "eporner",
|
||||
"name": "🔞EPORNER.py",
|
||||
"type": 3,
|
||||
"api": "./py/EPORNER.py"
|
||||
},
|
||||
{
|
||||
"key": "91porn",
|
||||
"name": "🔞91porn.py",
|
||||
"type": 3,
|
||||
"api": "./py/91porn.py"
|
||||
},
|
||||
{
|
||||
"key": "fullhd",
|
||||
"name": "🔞FullHD.py",
|
||||
"type": 3,
|
||||
"api": "./py/FullHD.py"
|
||||
},
|
||||
{
|
||||
"key": "JAV36",
|
||||
"name": "🔞JAV36.py",
|
||||
"type": 3,
|
||||
"api": "./py/JAV36.py"
|
||||
},
|
||||
{
|
||||
"key": "ggsp",
|
||||
"name": "🔞久久視頻.py",
|
||||
"type": 3,
|
||||
"api": "./py/久久視頻.py"
|
||||
},
|
||||
{
|
||||
"key": "TOPTV",
|
||||
"name": "🔞TOPTV.py",
|
||||
"type": 3,
|
||||
"api": "./py/TOPTV.py"
|
||||
},
|
||||
{
|
||||
"key": "VHUB",
|
||||
"name": "🔞VHUB.py",
|
||||
"type": 3,
|
||||
"api": "./py/VHUB[成人].py"
|
||||
},
|
||||
|
||||
{
|
||||
"key" : "麻豆",
|
||||
|
||||
Reference in New Issue
Block a user