yeyin/tvbox_collect
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Sync all projects

Browse Source
This commit is contained in:
github-actions[bot]
2026-07-04 22:59:41 +00:00
parent 38822ce558
commit 3c707f4a32
13 changed files with 6638 additions and 5501 deletions
Download Patch File Download Diff File Expand all files Collapse all files
FGBLH/py/小鸭子看看.py
+489
View File
@@ -0,0 +1,489 @@
# coding=utf-8
import re
import json
import time
from urllib.parse import quote, urljoin, urlparse, parse_qs
import sys
# 导入外部库
from bs4 import BeautifulSoup
import gzip
sys.path.append("..")
from base.spider import Spider
class Spider(Spider):
def __init__(self):
self.name = "小鸭子看看"
self.hosts = {
"main": "https://xiaoyakankan.com",
"tw": "https://tw.xiaoyakankan.com"
}
self.default_host = "tw"
self.ua = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
# 视频格式支持
self.VIDEO_FORMATS = ['.m3u8', '.mp4', '.flv', '.avi', '.mkv', '.mov']
def getName(self):
return self.name
def init(self, extend=""):
if extend:
try:
config = json.loads(extend)
if config.get("host") in self.hosts:
self.default_host = config["host"]
self.log(f"已切换默认域名至：{self.hosts[self.default_host]}", "INFO")
except:
self.log("初始化参数解析失败，使用默认tw子域名", "WARNING")
def log(self, msg, level="INFO"):
print(f"[{level}] [{self.name}] {time.strftime('%Y-%m-%d %H:%M:%S')} - {msg}")
def get_current_host(self):
return self.hosts[self.default_host]
def homeContent(self, filter):
result = {}
result['class'] = [
{"type_name": "电影", "type_id": "10", "land": "1", "filters": [
{"key": "class", "name": "类型", "value": [
{"n": "全部", "v": "10"},
{"n": "动作片", "v": "1001"},
{"n": "喜剧片", "v": "1002"},
{"n": "爱情片", "v": "1003"},
{"n": "科幻片", "v": "1004"},
{"n": "恐怖片", "v": "1005"},
{"n": "剧情片", "v": "1006"},
{"n": "战争片", "v": "1007"},
{"n": "纪录片", "v": "1008"},
{"n": "微电影", "v": "1009"},
{"n": "动漫电影", "v": "1010"},
{"n": "奇幻片", "v": "1011"},
{"n": "动画片", "v": "1013"},
{"n": "犯罪片", "v": "1014"},
{"n": "悬疑片", "v": "1016"},
{"n": "欧美片", "v": "1017"},
{"n": "邵氏电影", "v": "1019"},
{"n": "同性片", "v": "1021"},
{"n": "家庭片", "v": "1024"},
{"n": "古装片", "v": "1025"},
{"n": "历史片", "v": "1026"},
{"n": "4K电影", "v": "1027"}
]}
]},
{"type_name": "连续剧", "type_id": "11", "land": "1", "filters": [
{"key": "class", "name": "地区类型", "value": [
{"n": "全部", "v": "11"},
{"n": "国产剧", "v": "1101"},
{"n": "香港剧", "v": "1102"},
{"n": "台湾剧", "v": "1105"},
{"n": "韩国剧", "v": "1103"},
{"n": "欧美剧", "v": "1104"},
{"n": "日本剧", "v": "1106"},
{"n": "泰国剧", "v": "1108"},
{"n": "港台剧", "v": "1110"},
{"n": "日韩剧", "v": "1111"},
{"n": "东南亚剧", "v": "1112"},
{"n": "海外剧", "v": "1107"}
]}
]},
{"type_name": "综艺", "type_id": "12", "land": "1", "filters": [
{"key": "class", "name": "地区类型", "value": [
{"n": "全部", "v": "12"},
{"n": "内地综艺", "v": "1201"},
{"n": "港台综艺", "v": "1202"},
{"n": "日韩综艺", "v": "1203"},
{"n": "欧美综艺", "v": "1204"},
{"n": "国外综艺", "v": "1205"}
]}
]},
{"type_name": "动漫", "type_id": "13", "land": "1", "filters": [
{"key": "class", "name": "地区类型", "value": [
{"n": "全部", "v": "13"},
{"n": "国产动漫", "v": "1301"},
{"n": "日韩动漫", "v": "1302"},
{"n": "欧美动漫", "v": "1303"},
{"n": "海外动漫", "v": "1305"},
{"n": "里番", "v": "1307"}
]}
]},
{"type_name": "福利", "type_id": "15", "land": "1", "filters": [
{"key": "class", "name": "地区类型", "value": [
{"n": "全部", "v": "15"},
{"n": "韩国情色片", "v": "1551"},
{"n": "日本情色片", "v": "1552"},
{"n": "大陆情色片", "v": "1555"},
{"n": "香港情色片", "v": "1553"},
{"n": "台湾情色片", "v": "1554"},
{"n": "美国情色片", "v": "1556"},
{"n": "欧洲情色片", "v": "1557"},
{"n": "印度情色片", "v": "1558"},
{"n": "东南亚情色片", "v": "1559"},
{"n": "其它情色片", "v": "1550"}
]}
]}
]
# 将所有筛选器数据添加进 result['filters'] 中
result['filters'] = {
"10": result['class'][0]['filters'],
"11": result['class'][1]['filters'],
"12": result['class'][2]['filters'],
"13": result['class'][3]['filters'],
"15": result['class'][4]['filters'],
}
return result
def homeVideoContent(self):
try:
url = self.get_current_host()
r = self.fetch(url, headers={"User-Agent": self.ua})
if r.status_code != 200:
self.log(f"首页推荐请求失败，状态码：{r.status_code}", "ERROR")
return {'list': []}
# 使用新的正则表达式来获取视频列表项
pattern = r'<a class="link" href="(/post/[^"]+\.html)".*?<img[^>]*data-src="([^"]+)".*?alt="([^"]+)".*?(?:<div class="tag1[^>]*>([^<]+)</div>)?.*?(?:<div class="tag2">([^<]+)</div>)?'
matches = re.findall(pattern, r.text, re.DOTALL)
video_list = []
for match in matches[:12]: # 限制12个结果
try:
link, img_src, title, tag1, tag2 = match
vod_id_match = re.search(r'/post/(.*?)\.html', link)
if not vod_id_match:
continue
vod_id = vod_id_match.group(1)
# 组合备注信息
remarks = []
if tag1:
remarks.append(tag1.strip())
if tag2:
remarks.append(tag2.strip())
vod_remarks = " / ".join(remarks) if remarks else "最新"
# 处理图片URL
if img_src.startswith('//'):
img_url = 'https:' + img_src
elif not img_src.startswith('http'):
img_url = urljoin(self.get_current_host(), img_src)
else:
img_url = img_src
vod = {
'vod_id': vod_id,
'vod_name': title.strip(),
'vod_pic': img_url,
'vod_remarks': vod_remarks
}
video_list.append(vod)
except Exception as e:
self.log(f"首页推荐项解析失败：{str(e)}", "ERROR")
continue
self.log(f"首页推荐成功解析{len(video_list)}个项", "INFO")
return {'list': video_list}
except Exception as e:
self.log(f"首页推荐内容获取失败：{str(e)}", "ERROR")
return {'list': []}
def categoryContent(self, tid, pg, filter, extend):
result = {'list': [], 'page': pg, 'pagecount': 1, 'limit': 40, 'total': 0}
try:
# 修复：检查 extend 参数，以支持筛选功能
filter_tid = tid
if extend and 'class' in extend and extend['class']:
filter_tid = extend['class']
# 修复分类URL构建，使用 filter_tid
url = f"{self.get_current_host()}/cat/{filter_tid}"
if int(pg) > 1:
url = f"{url}-{pg}"
url = f"{url}.html"
r = self.fetch(url, headers={"User-Agent": self.ua})
if r.status_code != 200:
self.log(f"分类页请求失败，URL：{url}，状态码：{r.status_code}", "ERROR")
return result
# 修复：使用更健壮的正则来提取所有视频列表项
items = re.findall(r'<div class="item">(.*?)<a class="title"', r.text, re.DOTALL)
for item in items:
try:
link_match = re.search(r'<a class="link" href="(/post/[^"]+\.html)"', item)
img_match = re.search(r'<img[^>]*data-src="([^"]+)"', item)
title_match = re.search(r'data-src="[^"]+" alt="([^"]+)"', item)
tag1_match = re.search(r'<div class="tag1[^>]*>([^<]+)</div>', item)
tag2_match = re.search(r'<div class="tag2">([^<]+)</div>', item)
if not link_match or not img_match or not title_match:
continue
link = link_match.group(1)
img_src = img_match.group(1)
title = title_match.group(1).strip()
vod_id = re.search(r'/post/(.*?)\.html', link).group(1)
remarks = []
if tag1_match:
remarks.append(tag1_match.group(1).strip())
if tag2_match:
remarks.append(tag2_match.group(1).strip())
vod_remarks = " / ".join(remarks) if remarks else "分类内容"
# 处理图片URL
if img_src.startswith('//'):
img_url = 'https:' + img_src
elif not img_src.startswith('http'):
img_url = urljoin(self.get_current_host(), img_src)
else:
img_url = img_src
vod = {
'vod_id': vod_id,
'vod_name': title,
'vod_pic': img_url,
'vod_remarks': vod_remarks
}
result['list'].append(vod)
except Exception as e:
self.log(f"分类项解析失败：{str(e)}", "ERROR")
continue
# 修复：使用更健壮的正则来提取分页信息
page_pattern = r'/cat/\d+-(\d+)\.html'
page_matches = re.findall(page_pattern, r.text)
if page_matches:
page_nums = [int(num) for num in page_matches if num.isdigit()]
result['pagecount'] = max(page_nums) if page_nums else 1
else:
result['pagecount'] = int(pg)
self.log(f"分类{tid}第{pg}页：解析{len(result['list'])}项", "INFO")
return result
except Exception as e:
self.log(f"分类内容获取失败：{str(e)}", "ERROR")
return result
def detailContent(self, ids):
result = {"list": []}
if not ids:
return result
vod_id = ids[0]
try:
detail_url = f"{self.get_current_host()}/post/{vod_id}.html"
r = self.fetch(detail_url, headers={"User-Agent": self.ua})
if r.status_code != 200:
self.log(f"详情页请求失败，状态码：{r.status_code}", "ERROR")
return result
soup = BeautifulSoup(r.text, 'html.parser')
# 提取标题
title_tag = soup.find('title')
title = title_tag.text.replace(" - 小鴨看看", "").strip() if title_tag else "未知标题"
# 提取封面图
cover_tag = soup.find('img', {'data-poster': True})
cover_url = ""
if cover_tag and cover_tag.get('data-poster'):
cover_url = cover_tag['data-poster']
if cover_url.startswith('//'):
cover_url = 'https:' + cover_url
elif not cover_url.startswith('http'):
cover_url = urljoin(self.get_current_host(), cover_url)
# 提取描述
desc_tag = soup.find('meta', {'name': 'description'})
desc = desc_tag['content'].strip() if desc_tag and desc_tag.get('content') else ""
# 提取播放线路和剧集
play_sources = []
play_urls = []
# 从JavaScript中提取播放信息
pp_data = None
script_pattern = re.search(r'var pp\s*=\s*({.*?});', r.text, re.DOTALL)
if script_pattern:
try:
pp_data = json.loads(script_pattern.group(1))
except Exception as e:
self.log(f"解析JavaScript播放信息失败：{str(e)}", "ERROR")
# 查找所有播放线路的容器
source_blocks = soup.find_all('div', class_='source')
for idx, block in enumerate(source_blocks):
source_name_tag = block.find('span', class_='name')
source_name = source_name_tag.text.strip() if source_name_tag else f"线路{idx+1}"
resolution_tag = block.find('span', class_='res')
resolution = resolution_tag.text.strip() if resolution_tag else ""
# 组合线路名称和分辨率
full_source_name = f"{source_name} ({resolution})" if resolution else source_name
play_sources.append(full_source_name)
episodes = []
if pp_data and 'lines' in pp_data and len(pp_data['lines']) > idx:
urls = pp_data['lines'][idx][3]
if isinstance(urls, list) and urls:
for ep_idx, url in enumerate(urls):
if isinstance(url, str) and any(url.endswith(fmt) for fmt in self.VIDEO_FORMATS):
# 修复集数命名逻辑
episode_name_match = re.search(r'ep-([\d\w]+)', url)
if episode_name_match:
episode_name = f"第{episode_name_match.group(1)}集"
elif len(urls) == 1:
episode_name = "全集"
else:
episode_name = f"第{ep_idx+1}集"
episodes.append(f"{episode_name}${url}")
if episodes:
play_urls.append("#".join(episodes))
else:
play_urls.append("")
vod = {
"vod_id": vod_id,
"vod_name": title,
"vod_pic": cover_url,
"vod_content": desc,
"vod_play_from": "$$$".join(play_sources) if play_sources else "",
"vod_play_url": "$$$".join(play_urls) if play_urls else ""
}
result["list"].append(vod)
self.log(f"详情页解析成功，ID：{vod_id}", "INFO")
return result
except Exception as e:
self.log(f"详情页解析失败，ID：{vod_id}，错误：{str(e)}", "ERROR")
return result
def playerContent(self, flag, id, vipFlags):
try:
# 如果id已经是URL，直接返回
if id.startswith('http'):
return {
"parse": 0,
"playUrl": '',
"url": id,
"header": {
"User-Agent": self.ua,
"Referer": self.get_current_host() + "/"
}
}
# 这是一个简单的播放器URL解析，如果原始URL本身就是有效的播放地址，就直接返回
return {
"parse": 0,
"playUrl": '',
"url": id,
"header": {
"User-Agent": self.ua,
"Referer": self.get_current_host() + "/"
}
}
except Exception as e:
self.log(f"播放地址解析失败：{str(e)}", "ERROR")
return {"parse": 0, "playUrl": '', "url": id, "header": {"User-Agent": self.ua}}
def searchContent(self, key, quick):
result = {"list": []}
try:
# 构造Google搜索URL（带站点限定）
google_search_url = f"https://www.google.com/search?q={quote(key)}&sitesearch=xiaoyakankan.com"
self.log(f"构造Google搜索URL: {google_search_url}")
# 伪装更多请求头
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": "https://www.google.com/",
"Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
"Accept-Encoding": "gzip, deflate, br",
"Connection": "keep-alive"
}
r = self.fetch(google_search_url, headers=headers, timeout=10)
if r.status_code != 200:
self.log(f"Google搜索请求失败，状态码：{r.status_code}，内容：{r.text[:200]}", "ERROR")
return result
# 处理gzip压缩响应
if 'gzip' in r.headers.get('Content-Encoding', ''):
r._content = gzip.decompress(r.content)
try:
soup = BeautifulSoup(r.text, 'html.parser')
# 寻找所有包含搜索结果的a标签
all_links = soup.find_all('a', href=re.compile(r'/url\?q='))
for a_tag in all_links[:15]: # 限制最多15个结果
link = a_tag['href']
# 解析真实URL
parsed_url = urlparse(link)
query_params = parse_qs(parsed_url.query)
if 'q' in query_params:
real_link = query_params['q'][0]
# 检查链接是否属于目标站点
if self.get_current_host() in real_link:
# 尝试从链接中提取影片ID
vod_id_match = re.search(r'/post/([^/]+)\.html', real_link)
if not vod_id_match:
continue
vod_id = vod_id_match.group(1)
# 获取标题和图片（这里因为Google搜索结果没有图片，所以图片留空）
title_tag = a_tag.find('h3')
if not title_tag:
# 有时标题在父级或其他元素中
title_tag = a_tag.find('div', class_='g')
title = title_tag.text.strip() if title_tag else "未知标题"
vod = {
"vod_id": vod_id,
"vod_name": title,
"vod_pic": "",
"vod_remarks": "Google搜索结果"
}
result["list"].append(vod)
except Exception as e:
self.log(f"解析Google搜索结果失败：{str(e)}", "ERROR")
return result
self.log(f"Google搜索成功解析{len(result['list'])}个项", "INFO")
return result
except Exception as e:
self.log(f"搜索内容获取失败：{str(e)}", "ERROR")
return result
def isVideoFormat(self, url):
"""判断是否为视频格式"""
return any(url.lower().endswith(fmt) for fmt in self.VIDEO_FORMATS)
def manualVideoCheck(self):
pass
def localProxy(self, param):
pass
FGBLH/py/星河影视.py
+480
View File
@@ -0,0 +1,480 @@
# -*- coding: utf-8 -*-
# 星河影视 xhkan.top - TVBox/PY Spider 兼容修复版
# 重点：按 TVBox Py Spider 标准方法返回；分类页无 SSR 列表时自动回退首页分区数据；保留原 /api/player/resolve 播放解析。
import sys
import re
import json
import base64
import urllib.parse
sys.path.append('..')
from base.spider import Spider
class Spider(Spider):
host = 'https://xhkan.top'
ua = ('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 '
'(KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36')
# xhkan 详情接口里的 cat 是数字；网页分类路径是 slug
classes = [
{'type_id': '1', 'type_name': '电影'},
{'type_id': '2', 'type_name': '电视剧'},
{'type_id': '3', 'type_name': '综艺'},
{'type_id': '4', 'type_name': '动漫'},
{'type_id': '6', 'type_name': '短剧'},
]
slug_map = {'1': 'movie', '2': 'tv', '3': 'variety', '4': 'anime', '6': 'short-drama'}
cat_name_map = {'1': '电影', '2': '电视剧', '3': '综艺', '4': '动漫', '6': '短剧'}
source_names = {'qq': '腾讯', 'qiyi': '爱奇艺', 'youku': '优酷', 'mgtv': '芒果', 'bilibili': '哔哩'}
sites = ['qq', 'qiyi', 'youku', 'mgtv', 'bilibili']
block_words = ('预告', '片花', 'trailer', 'teaser')
def init(self, extend=''):
self.hosts = [self.host]
try:
if extend:
ext = json.loads(extend) if isinstance(extend, str) and extend.strip().startswith('{') else extend
site = ''
if isinstance(ext, dict):
site = ext.get('site') or ext.get('host') or ''
elif isinstance(ext, str):
site = ext
if site:
self.hosts = [i.strip().rstrip('/') for i in site.split(',') if i.strip()]
self.host = self.hosts[0]
except Exception:
pass
def getName(self):
return '星河影视'
def isVideoFormat(self, url):
return False
def manualVideoCheck(self):
return False
def destroy(self):
pass
def localProxy(self, param):
return None
# ============ 标准 TVBox 方法 ============
def homeContent(self, filter):
filters = {}
for c in self.classes:
filters[c['type_id']] = [
{'key': 'sort', 'name': '排序', 'value': [
{'n': '最新', 'v': 'time'}, {'n': '热度', 'v': 'hits'}, {'n': '评分', 'v': 'score'}
]},
{'key': 'type', 'name': '类型', 'value': [
{'n': '全部', 'v': ''}, {'n': '喜剧', 'v': '喜剧'}, {'n': '爱情', 'v': '爱情'},
{'n': '动作', 'v': '动作'}, {'n': '剧情', 'v': '剧情'}, {'n': '悬疑', 'v': '悬疑'},
{'n': '犯罪', 'v': '犯罪'}, {'n': '科幻', 'v': '科幻'}, {'n': '动画', 'v': '动画'},
{'n': '其他', 'v': '其他'}
]},
{'key': 'area', 'name': '地区', 'value': [
{'n': '全部', 'v': ''}, {'n': '大陆', 'v': '大陆'}, {'n': '香港', 'v': '香港'},
{'n': '台湾', 'v': '台湾'}, {'n': '美国', 'v': '美国'}, {'n': '韩国', 'v': '韩国'},
{'n': '日本', 'v': '日本'}, {'n': '泰国', 'v': '泰国'}, {'n': '其他', 'v': '其他'}
]},
{'key': 'year', 'name': '年份', 'value': [{'n': '全部', 'v': ''}] + [
{'n': str(y), 'v': str(y)} for y in range(2026, 2014, -1)
]}
]
return {'class': self.classes, 'filters': filters}
def homeVideoContent(self):
html = self._get_first_text(['/'])
return {'list': self._parse_cards(html)[:40]}
def categoryContent(self, tid, pg, filter, extend):
tid = str(tid or '1')
page = int(pg or 1)
extend = extend or {}
slug = self.slug_map.get(tid, tid)
# 1. 优先尝试可能的 JSON API，兼容站点后续改版
videos = self._try_category_apis(tid, slug, page, extend)
# 2. 再尝试网页分类路径
if not videos:
paths = self._build_category_paths(slug, page, extend)
for p in paths:
html = self._get_first_text([p])
videos = self._parse_cards(html)
if videos:
break
# 3. 当前站分类页可能只渲染筛选栏、不直接输出列表，回退首页对应分类热播数据
if not videos:
html = self._get_first_text(['/'])
all_videos = self._parse_cards(html)
videos = [v for v in all_videos if str(v.get('vod_id', '')).split('@', 1)[0] == tid]
return {'list': videos, 'page': page, 'pagecount': page + 1, 'limit': 30, 'total': 999999}
def searchContent(self, key, quick, pg='1'):
page = int(pg or 1)
kw = str(key or '').strip()
if not kw:
return {'list': [], 'page': page}
videos = []
# 1. 兼容常见搜索 API / 搜索页参数
paths = [
'/api/search?keyword=%s&page=%s' % (urllib.parse.quote(kw), page),
'/api/search?wd=%s&page=%s' % (urllib.parse.quote(kw), page),
'/search?keyword=%s&page=%s' % (urllib.parse.quote(kw), page),
'/search?q=%s&page=%s' % (urllib.parse.quote(kw), page),
]
for p in paths:
txt = self._get_first_text([p])
if not txt:
continue
st = txt.strip()
if st.startswith('{') or st.startswith('['):
try:
videos = self._parse_json_list(json.loads(st))
except Exception:
videos = []
else:
videos = self._parse_cards(txt)
if videos:
break
# 2. 搜索 API 不可用时，至少从首页已渲染资源里本地匹配，保证壳内不空白
if not videos:
html = self._get_first_text(['/'])
videos = [v for v in self._parse_cards(html) if kw.lower() in v.get('vod_name', '').lower()]
return {'list': videos, 'page': page, 'pagecount': page + 1, 'limit': 30, 'total': 999999}
def detailContent(self, ids):
if not ids:
return {'list': []}
raw = str(ids[0])
cat, vod_id = self._split_vid(raw)
if not vod_id:
return {'list': []}
detail = None
for site in self.sites:
try:
api = '/api/detail?cat=%s&id=%s&site=%s' % (cat, urllib.parse.quote(vod_id), site)
txt = self._get_first_text([api])
data = json.loads(txt)
if data.get('errno') == 0 and data.get('data'):
detail = data.get('data')
break
except Exception:
continue
# API 失败时，解析详情页 HTML 兜底
if not detail:
html = self._get_first_text(['/detail/%s/%s' % (cat, urllib.parse.quote(vod_id))])
return {'list': [self._detail_from_html(cat, vod_id, html)]}
title = detail.get('title') or detail.get('name') or vod_id
if self._blocked_title(title):
return {'list': []}
vod = {
'vod_id': '%s@%s' % (cat, vod_id),
'vod_name': title,
'vod_pic': self._abs_img(detail.get('cover') or detail.get('pic') or detail.get('poster') or ''),
'vod_remarks': detail.get('remarks') or detail.get('status') or '',
'vod_year': str(detail.get('year') or detail.get('pubdate') or ''),
'vod_area': self._join(detail.get('area') or ''),
'vod_actor': self._join(detail.get('actors') or detail.get('actor') or ''),
'vod_director': self._join(detail.get('directors') or detail.get('director') or ''),
'vod_content': self._clean_text(detail.get('desc') or detail.get('intro') or detail.get('description') or ''),
}
play_from, play_urls = [], []
allep = detail.get('allepidetail') or {}
if isinstance(allep, dict):
for site, eps in allep.items():
if not isinstance(eps, list) or not eps:
continue
urls = []
for idx, ep in enumerate(eps, 1):
ep_no = ep.get('playlink_num') or ep.get('episode') or idx
name = ep.get('title') or ('第%s集' % str(ep_no).zfill(2) if str(ep_no).isdigit() else str(ep_no))
raw_url = ep.get('url') or ep.get('play_url') or ''
if not raw_url:
continue
pid = self._enc({'cat': cat, 'vod_id': vod_id, 'source': site, 'episode': int(ep_no) if str(ep_no).isdigit() else idx, 'playUrl': raw_url})
urls.append('%s$%s' % (name, pid))
if urls:
play_from.append(self.source_names.get(site, site))
play_urls.append('#'.join(urls))
vod['vod_play_from'] = '$$$'.join(play_from)
vod['vod_play_url'] = '$$$'.join(play_urls)
return {'list': [vod]}
def playerContent(self, flag, id, vipFlags):
try:
obj = self._dec(str(id or ''))
if not isinstance(obj, dict):
return {'parse': 0, 'url': str(id or ''), 'header': {'User-Agent': self.ua, 'Referer': self.host + '/'}}
play_url = obj.get('playUrl') or ''
payload = {
'vodId': obj.get('vod_id') or obj.get('vodId') or 'direct',
'source': obj.get('source') or 'qq',
'episode': int(obj.get('episode') or 1),
'category': int(obj.get('cat') or obj.get('category') or 2),
'playUrl': play_url
}
self._get_first_text(['/api/player/token'])
txt = self._post_first_json('/api/player/resolve', payload)
data = json.loads(txt) if txt else {}
url = data.get('url') if data.get('success') else ''
return {'parse': 0, 'url': url or play_url or '', 'header': {'User-Agent': self.ua, 'Referer': self.host + '/'}}
except Exception:
return {'parse': 0, 'url': ''}
# ============ 分类 / API 兜底 ============
def _build_category_paths(self, slug, page, extend):
params = {}
for k in ('type', 'area', 'year', 'sort'):
if extend.get(k):
params[k] = extend.get(k)
if page > 1:
params['page'] = str(page)
q = ('?' + urllib.parse.urlencode(params)) if params else ''
base = '/short-drama' if slug == 'short-drama' else '/category/' + slug
paths = [base + q]
if page > 1:
paths.append(base + '/page/%s' % page)
paths.append(base + '?page=%s' % page)
return paths
def _try_category_apis(self, tid, slug, page, extend):
params = {
'cat': tid,
'category': tid,
'type': extend.get('type', ''),
'area': extend.get('area', ''),
'year': extend.get('year', ''),
'sort': extend.get('sort', ''),
'page': str(page),
'limit': '30'
}
q1 = urllib.parse.urlencode(params)
q2 = urllib.parse.urlencode(dict(params, cat=slug, category=slug))
paths = [
'/api/list?' + q1,
'/api/vod/list?' + q1,
'/api/category?' + q1,
'/api/category?' + q2,
'/api/videos?' + q1,
'/api/search?cat=%s&page=%s' % (urllib.parse.quote(tid), page),
'/api/search?category=%s&page=%s' % (urllib.parse.quote(slug), page),
]
for p in paths:
txt = self._get_first_text([p])
if not txt:
continue
try:
obj = json.loads(txt)
videos = self._parse_json_list(obj)
if videos:
return videos
except Exception:
continue
return []
# ============ 解析工具 ============
def _parse_cards(self, html):
html = html or ''
videos, seen = [], set()
# 适配 /detail/2/xxxx，下一版如果改成完整域名也能匹配
pattern = re.compile(r'<a[^>]+href=["\'](?:https?://[^/]+)?/detail/(\d+)/([^"\'#?]+)[^"\']*["\'][^>]*>(.*?)</a>', re.S | re.I)
for m in pattern.finditer(html):
cat = m.group(1)
vid = urllib.parse.unquote(m.group(2))
block = m.group(3)
title = self._extract_title(block)
if not title or self._blocked_title(title):
continue
pic = self._first_match(block, r'(?:data-src|src)=["\']([^"\']+)["\']') or ''
remark = self._first_match(block, r'(全\d+集|更新至\d+集|\d{4}-\d{2}-\d{2}期|\d+期|正片)') or ''
vod_id = '%s@%s' % (cat, vid)
if vod_id in seen:
continue
seen.add(vod_id)
videos.append({'vod_id': vod_id, 'vod_name': title, 'vod_pic': self._abs_img(pic), 'vod_remarks': remark})
return videos
def _parse_json_list(self, obj):
arr = []
if isinstance(obj, dict):
data = obj.get('data', obj)
if isinstance(data, dict):
for k in ('list', 'items', 'records', 'result', 'data'):
if isinstance(data.get(k), list):
arr = data.get(k)
break
elif isinstance(data, list):
arr = data
if not arr:
for k in ('list', 'items', 'records', 'result'):
if isinstance(obj.get(k), list):
arr = obj.get(k)
break
elif isinstance(obj, list):
arr = obj
videos = []
for it in arr or []:
if not isinstance(it, dict):
continue
title = it.get('title') or it.get('name') or it.get('vod_name') or it.get('videoName') or ''
if not title or self._blocked_title(title):
continue
cat = str(it.get('cat') or it.get('category') or it.get('type') or it.get('type_id') or it.get('cid') or '2')
if cat in self.slug_map:
pass
else:
# slug 转数字
for k, v in self.slug_map.items():
if str(cat) == v:
cat = k
break
vid = str(it.get('id') or it.get('vod_id') or it.get('vid') or it.get('episode_id') or '')
if not vid:
continue
videos.append({
'vod_id': '%s@%s' % (cat, vid),
'vod_name': self._clean_text(title),
'vod_pic': self._abs_img(it.get('cover') or it.get('pic') or it.get('poster') or it.get('vod_pic') or ''),
'vod_remarks': it.get('remarks') or it.get('status') or it.get('vod_remarks') or ''
})
return videos
def _detail_from_html(self, cat, vod_id, html):
title = self._first_match(html, r'<h1[^>]*>(.*?)</h1>') or vod_id
title = self._clean_text(title)
pic = self._first_match(html, r'<img[^>]+alt=["\']%s["\'][^>]+(?:src|data-src)=["\']([^"\']+)' % re.escape(title)) or self._first_match(html, r'<img[^>]+(?:src|data-src)=["\']([^"\']+)["\']')
content = self._first_match(html, r'###?\s*简介\s*(.*?)\s*(?:展开全部|选集|</)')
# 播放集数从详情页 /play/cat/id/ep?s=source 提取
eps = []
ep_re = re.compile(r'href=["\'](?:https?://[^/]+)?/play/(\d+)/([^/"\']+)/(\d+)\?s=([^"\'&]+)[^"\']*["\'][^>]*>(.*?)</a>', re.S | re.I)
for mm in ep_re.finditer(html or ''):
c, vid, ep, src, name = mm.group(1), urllib.parse.unquote(mm.group(2)), mm.group(3), mm.group(4), self._clean_text(mm.group(5))
if c != str(cat) or vid != str(vod_id):
continue
pid = self._enc({'cat': c, 'vod_id': vid, 'source': src, 'episode': int(ep), 'playUrl': ''})
eps.append('%s$%s' % (name or ('第%s集' % ep), pid))
vod = {
'vod_id': '%s@%s' % (cat, vod_id),
'vod_name': title,
'vod_pic': self._abs_img(pic),
'vod_content': self._clean_text(content),
'vod_play_from': '星河',
'vod_play_url': '#'.join(eps)
}
return vod
def _extract_title(self, block):
title = self._first_match(block, r'alt=["\']([^"\']+)["\']') or self._first_match(block, r'title=["\']([^"\']+)["\']')
if title:
return self._clean_text(title)
text = self._clean_text(block)
# 首页卡片常见顺序：简介 + 状态 + 类型 + 标题，取最后一个较短片段
parts = re.split(r'(?:全\d+集|更新至\d+集|\d{4}-\d{2}-\d{2}期|\d+期|正片|其他|剧情|喜剧|爱情|动作|悬疑|犯罪|动画|原创|都市|网剧|少儿)', text)
cand = parts[-1].strip() if parts else text
if not cand or len(cand) > 40:
cand = text[-40:].strip()
return cand
def _blocked_title(self, title):
t = (title or '').lower()
return any(w.lower() in t for w in self.block_words)
def _split_vid(self, raw):
raw = str(raw)
if '@' in raw:
return raw.split('@', 1)
m = re.search(r'/detail/(\d+)/([^/?#]+)', raw)
if m:
return m.group(1), urllib.parse.unquote(m.group(2))
return '2', raw
def _headers(self):
return {
'User-Agent': self.ua,
'Accept': 'application/json,text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Referer': self.host + '/',
}
def _get_first_text(self, paths, timeout=20):
for base in getattr(self, 'hosts', [self.host]):
base = base.rstrip('/')
for p in paths:
url = p if str(p).startswith('http') else base + (p if str(p).startswith('/') else '/' + str(p))
try:
r = self.fetch(url, headers=self._headers(), timeout=timeout, verify=False)
if hasattr(r, 'text'):
txt = r.text
else:
content = getattr(r, 'content', b'')
txt = content.decode('utf-8', 'ignore') if isinstance(content, bytes) else str(content)
if txt:
return txt
except Exception:
continue
return ''
def _post_first_json(self, path, payload, timeout=20):
for base in getattr(self, 'hosts', [self.host]):
url = base.rstrip('/') + path
try:
r = self.fetch(url, headers={**self._headers(), 'Content-Type': 'application/json'}, data=json.dumps(payload).encode('utf-8'), method='POST', timeout=timeout, verify=False)
if hasattr(r, 'text'):
return r.text
content = getattr(r, 'content', b'')
return content.decode('utf-8', 'ignore') if isinstance(content, bytes) else str(content)
except Exception:
continue
return ''
def _enc(self, obj):
return base64.urlsafe_b64encode(json.dumps(obj, ensure_ascii=False, separators=(',', ':')).encode('utf-8')).decode('utf-8').rstrip('=')
def _dec(self, s):
try:
return json.loads(base64.urlsafe_b64decode((s + '=' * (-len(s) % 4)).encode()).decode('utf-8'))
except Exception:
return s
def _abs_img(self, url):
url = str(url or '').strip()
if not url:
return ''
if url.startswith('//'):
return 'https:' + url
if url.startswith('/'):
return self.host.rstrip('/') + url
return url
def _clean_text(self, text):
text = re.sub(r'<script[\s\S]*?</script>|<style[\s\S]*?</style>', ' ', str(text or ''), flags=re.I)
text = re.sub(r'<[^>]+>', ' ', text)
for a, b in {'&nbsp;': ' ', '&amp;': '&', '&quot;': '"', '&#39;': "'", '&lt;': '<', '&gt;': '>'}.items():
text = text.replace(a, b)
return re.sub(r'\s+', ' ', text).strip()
def _first_match(self, text, pattern):
m = re.search(pattern, text or '', re.S | re.I)
return self._clean_text(m.group(1)) if m else ''
def _join(self, v):
if isinstance(v, list):
return '/'.join([str(x.get('name') if isinstance(x, dict) else x) for x in v])
return str(v or '')
FGBLH/xxx视频资源
+4 -1
View File
@@ -54,8 +54,9 @@ CCTV16奥林匹克1080p,https://php.jdshipin.com:2096/TVOD/iptv.php?id=cctv16
澳门体育1080p,http://cdn6.163189.xyz/163189/amty
纬来体育,rtmp://f13h.mine.nu/sat/tv721
广东珠江1080p,http://m.061899.xyz/mg/gdzj
11,https://www.fulleroticmovies.net/get_stream/4047-360.mp4
港台三级(140部),#genre#
港台三级(142部),#genre#
1色降2之血玫瑰,https://vip1.lz-cdn1.com/20220331/733_58b741b7/index.m3u8
2色降2之萬里驅魔,https://m3u8.cdn202511.com/videos/202411/21/673e5ba03276de039d31a162/7cd5f8/index.m3u8
3倩女幽魂,https://jkunnzyx.com/20250423/nU0wWqCw/2000kb/hls/index.m3u8
@@ -196,6 +197,8 @@ CCTV16奥林匹克1080p,https://php.jdshipin.com:2096/TVOD/iptv.php?id=cctv16
138贴身情人,https://v8.ppqrrs.com/wjv8/202310/12/PgMkXNrS8Q1/video/index.m3u8
139山中艳谭,https://v8.ppqrrs.com/wjv8/202310/10/hLztMZdFui1/video/index.m3u8
140俏表妹,https://v8.ppqrrs.com/wjv8/202310/10/ptwbuUDLQD1/video/index.m3u8
141莲雾斩道,https://v8.ppqrrs.com/wjv8/202310/10/ggvbaajsBi1/video/index.m3u8
142丛林快活女,https://v8.ppqrrs.com/wjv8/202310/09/6f4DrSakf31/video/index.m3u8
传媒系列(34部),#genre#
1麻豆传媒MDSR-0009-1.苏语棠.艾熙.极品嫂子.夏日欲火无套乱伦.情色文学.4P,https://m3md.n6uem8.xyz/doudou/ms/dfc18a8a868268864bc36d1c8__746738/hls/1/index.m3u8
FGBLH/海豚666.json
+12
View File
@@ -111,6 +111,12 @@
"name": "🐬麻花影视.py",
"type": 3,
"api": "https://ghfast.top/https://raw.githubusercontent.com/FGBLH/GHK/refs/heads/main/py/麻花影视.py"
},
{
"key": "XH",
"name": "🐬星河影视.py",
"type": 3,
"api": "https://ghfast.top/https://raw.githubusercontent.com/FGBLH/GHK/refs/heads/main/py/星河影视.py"
},
{
"key": "guanfeng",
@@ -172,6 +178,12 @@
"type": 3,
"api": "https://ghfast.top/https://raw.githubusercontent.com/FGBLH/GHK/refs/heads/main/py/采集聚合.py"
},
{
"key": "xyzkk",
"name": "🐬小鸭子看看.py 有🔞",
"type": 3,
"api": "https://ghfast.top/https://raw.githubusercontent.com/FGBLH/GHK/refs/heads/main/py/小鸭子看看.py"
},
{
"key": "kf",
"name": "🐬咖啡体育直播.py",
FGBLH/海豚py.json
+12
View File
@@ -70,6 +70,12 @@
"name": "🐬麻花影视.py",
"type": 3,
"api": "https://ghfast.top/https://raw.githubusercontent.com/FGBLH/GHK/refs/heads/main/py/麻花影视.py"
},
{
"key": "XH",
"name": "🐬星河影视.py",
"type": 3,
"api": "https://ghfast.top/https://raw.githubusercontent.com/FGBLH/GHK/refs/heads/main/py/星河影视.py"
},
{
"key": "guanfeng",
@@ -124,6 +130,12 @@
"name": "🐬七味.py(关梯)",
"type": 3,
"api": "https://ghfast.top/https://raw.githubusercontent.com/FGBLH/GHK/refs/heads/main/py/七味.py"
},
{
"key": "xyzkk",
"name": "🐬小鸭子看看.py 有🔞",
"type": 3,
"api": "https://ghfast.top/https://raw.githubusercontent.com/FGBLH/GHK/refs/heads/main/py/小鸭子看看.py"
},
{
"key": "kf",
FGBLH/海豚无18加555.json
+6
View File
@@ -111,6 +111,12 @@
"name": "🐬麻花影视.py",
"type": 3,
"api": "https://ghfast.top/https://raw.githubusercontent.com/FGBLH/GHK/refs/heads/main/py/麻花影视.py"
},
{
"key": "XH",
"name": "🐬星河影视.py",
"type": 3,
"api": "https://ghfast.top/https://raw.githubusercontent.com/FGBLH/GHK/refs/heads/main/py/星河影视.py"
},
{
"key": "guanfeng",
FGBLH/鱼壳海豚.json
+13 -1
View File
@@ -24,7 +24,7 @@
"api":"https://file.icve.com.cn/file_doc/249/899/3E7E0C8A023B624CEC6BDCC200F06F02.js",
"ext":"https://cdn.waimaimingtang.com/file/images/bwc/20251023002031-6064033c16.js"
},
{"key":"YK",
{"key":"YKvm",
"name":"🐬优酷视频 海豚影视交流群 TG：@hshsjk9[追剧]",
"type":3,
"api":"https://file.icve.com.cn/file_doc/249/899/3E7E0C8A023B624CEC6BDCC200F06F02.js",
@@ -142,6 +142,12 @@
"name": "🐬麻花影视.py[追剧]",
"type": 3,
"api": "https://ghfast.top/https://raw.githubusercontent.com/FGBLH/GHK/refs/heads/main/py/麻花影视.py"
},
{
"key": "XH",
"name": "🐬星河影视.py",
"type": 3,
"api": "https://ghfast.top/https://raw.githubusercontent.com/FGBLH/GHK/refs/heads/main/py/星河影视.py"
},
{
"key": "guanfeng",
@@ -203,6 +209,12 @@
"type": 3,
"api": "https://ghfast.top/https://raw.githubusercontent.com/FGBLH/GHK/refs/heads/main/py/采集聚合.py"
},
{
"key": "xyzkk",
"name": "🐬小鸭子看看.py 有🔞[追剧]",
"type": 3,
"api": "https://ghfast.top/https://raw.githubusercontent.com/FGBLH/GHK/refs/heads/main/py/小鸭子看看.py"
},
{
"key": "fY",
"name": "🐬枫叶影院.py(关梯)[追剧]",
FGBLH/鱼壳海豚py.json
+12
View File
@@ -94,6 +94,12 @@
"name": "🐬麻花影视.py[追剧]",
"type": 3,
"api": "https://ghfast.top/https://raw.githubusercontent.com/FGBLH/GHK/refs/heads/main/py/麻花影视.py"
},
{
"key": "XH",
"name": "🐬星河影视.py[追剧]",
"type": 3,
"api": "https://ghfast.top/https://raw.githubusercontent.com/FGBLH/GHK/refs/heads/main/py/星河影视.py"
},
{
"key": "guanfeng",
@@ -148,6 +154,12 @@
"name": "🐬七味.py(关梯)[追剧]",
"type": 3,
"api": "https://ghfast.top/https://raw.githubusercontent.com/FGBLH/GHK/refs/heads/main/py/七味.py"
},
{
"key": "xyzkk",
"name": "🐬小鸭子看看.py 有🔞[追剧]",
"type": 3,
"api": "https://ghfast.top/https://raw.githubusercontent.com/FGBLH/GHK/refs/heads/main/py/小鸭子看看.py"
},
{
"key": "cjjh",
FGBLH/鱼壳海豚无18加.json
+9 -3
View File
@@ -24,7 +24,7 @@
"api":"https://file.icve.com.cn/file_doc/249/899/3E7E0C8A023B624CEC6BDCC200F06F02.js",
"ext":"https://cdn.waimaimingtang.com/file/images/bwc/20251023002031-6064033c16.js"
},
{"key":"YK",
{"key":"YKvm",
"name":"🐬优酷视频 海豚影视交流群 TG：@hshsjk9",
"type":3,
"api":"https://file.icve.com.cn/file_doc/249/899/3E7E0C8A023B624CEC6BDCC200F06F02.js",
@@ -78,7 +78,7 @@
},
{
"key": "sm",
"name": "🐬熊猫直播",
"name": "🐬韩国熊猫直播.py",
"type": 3,
"api": "https://ghfast.top/https://raw.githubusercontent.com/FGBLH/GHK/refs/heads/main/py/熊猫直播.py"
},
@@ -103,7 +103,7 @@
},
{
"key": "ww",
"name": "🐬哇哇APP.py(关梯)[追剧]",
"name": "🐬哇哇APP.py(关梯)",
"type": 3,
"api": "https://ghfast.top/https://raw.githubusercontent.com/FGBLH/GHK/refs/heads/main/py/哇哇APP.py"
},
@@ -142,6 +142,12 @@
"name": "🐬麻花影视.py",
"type": 3,
"api": "https://ghfast.top/https://raw.githubusercontent.com/FGBLH/GHK/refs/heads/main/py/麻花影视.py"
},
{
"key": "XH",
"name": "🐬星河影视.py",
"type": 3,
"api": "https://ghfast.top/https://raw.githubusercontent.com/FGBLH/GHK/refs/heads/main/py/星河影视.py"
},
{
"key": "guanfeng",