This commit is contained in:
pricema
2025-10-07 01:38:18 +08:00
parent 6e8af5c540
commit 6d799713f8
414 changed files with 115992 additions and 1 deletions
+97
View File
@@ -0,0 +1,97 @@
# -*- coding: utf-8 -*-
# by @嗷呜
import sys
sys.path.append('..')
from base.spider import Spider
class Spider(Spider):
def init(self, extend=""):
'''
example:
{
"key": "py_appV2",
"name": "xxx",
"type": 3,
"searchable": 1,
"quickSearch": 1,
"filterable": 1,
"api": "./py/APPV2.py",
"ext": "http://cmsyt.lyyytv.cn"
}
'''
self.host=extend
pass
def getName(self):
pass
def isVideoFormat(self, url):
pass
def manualVideoCheck(self):
pass
def destroy(self):
pass
headers = {
'User-Agent': 'okhttp/4.12.0',
}
def homeContent(self, filter):
data = self.fetch(f"{self.host}//api.php/app/nav?token=",headers=self.headers).json()
keys = ["class", "area", "lang", "year", "letter", "by", "sort"]
filters = {}
classes = []
for item in data['list']:
has_non_empty_field = False
jsontype_extend = item["type_extend"]
classes.append({"type_name": item["type_name"], "type_id": item["type_id"]})
for key in keys:
if key in jsontype_extend and jsontype_extend[key].strip() != "":
has_non_empty_field = True
break
if has_non_empty_field:
filters[str(item["type_id"])] = []
for dkey in jsontype_extend:
if dkey in keys and jsontype_extend[dkey].strip() != "":
values = jsontype_extend[dkey].split(",")
value_array = [{"n": value.strip(), "v": value.strip()} for value in values if
value.strip() != ""]
filters[str(item["type_id"])].append({"key": dkey, "name": dkey, "value": value_array})
result = {}
result["class"] = classes
result["filters"] = filters
return result
def homeVideoContent(self):
data=self.fetch(f"{self.host}/api.php/app/index_video?token=",headers=self.headers).json()
videos=[]
for item in data['list']:videos.extend(item['vlist'])
return {'list':videos}
def categoryContent(self, tid, pg, filter, extend):
params = {'tid':tid,'class':extend.get('class',''),'area':extend.get('area',''),'lang':extend.get('lang',''),'year':extend.get('year',''),'limit':'18','pg':pg}
data=self.fetch(f"{self.host}/api.php/app/video",params=params,headers=self.headers).json()
return data
def detailContent(self, ids):
data=self.fetch(f"{self.host}/api.php/app/video_detail?id={ids[0]}",headers=self.headers).json()
return {'list':[data['data']]}
def searchContent(self, key, quick, pg="1"):
data=self.fetch(f"{self.host}/api.php/app/search?text={key}&pg={pg}",headers=self.headers).json()
videos=data['list']
for item in data['list']:
item.pop('type', None)
return {'list':videos,'page':pg}
def playerContent(self, flag, id, vipFlags):
return {'jx':1,'playUrl':'','parse': 1, 'url': id, 'header': self.headers}
def localProxy(self, param):
pass
+301
View File
@@ -0,0 +1,301 @@
# -*- coding: utf-8 -*-
# by @嗷呜
import json
import sys
import time
from concurrent.futures import ThreadPoolExecutor, as_completed
from urllib.parse import quote
from Crypto.Hash import MD5
import requests
sys.path.append('..')
from base.spider import Spider
class Spider(Spider):
def init(self, extend=""):
self.session = requests.Session()
self.session.headers.update(self.headers)
self.session.cookies.update(self.cookie)
self.get_ctoken()
pass
def getName(self):
pass
def isVideoFormat(self, url):
pass
def manualVideoCheck(self):
pass
def destroy(self):
pass
host='https://www.youku.com'
shost='https://search.youku.com'
h5host='https://acs.youku.com'
ihost='https://v.youku.com'
headers = {
'User-Agent': 'Mozilla/5.0 (; Windows 10.0.26100.3194_64 ) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.82 Electron/14.2.0 Safari/537.36 Node/14.17.0 YoukuDesktop/9.2.60 UOSYouku (2.0.1)-Electron(UTDID ZYmGMAAAACkDAMU8hbiMmYdd;CHANNEL official;ZREAL 0;BTYPE TM2013;BRAND TIMI;BUILDVER 9.2.60.1001)',
'Referer': f'{host}/'
}
cookie={
"__ysuid": "17416134165380iB",
"__aysid": "1741613416541WbD",
"xlly_s": "1",
"isI18n": "false",
"cna": "bNdVIKmmsHgCAXW9W6yrQ1/s",
"__ayft": "1741672162330",
"__arpvid": "1741672162331FBKgrn-1741672162342",
"__ayscnt": "1",
"__aypstp": "1",
"__ayspstp": "3",
"tfstk": "gZbiib4JpG-6DqW-B98_2rwPuFrd1fTXQt3vHEp4YpJIBA3OgrWcwOi90RTOo9XVQ5tAM5NcK_CP6Ep97K2ce1XDc59v3KXAgGFLyzC11ET2n8U8yoyib67M3xL25e8gS8pbyzC1_ET4e8URWTsSnHv2uh8VTeJBgEuN3d-ELQAWuKWV36PHGpJ2uEWVTxvicLX1ewyUXYSekxMf-CxMEqpnoqVvshvP_pABOwvXjL5wKqeulm52np_zpkfCDGW9Ot4uKFIRwZtP7vP9_gfAr3KEpDWXSIfWRay-DHIc_Z-hAzkD1i5Ooi5LZ0O5YO_1mUc476YMI3R6xzucUnRlNe_zemKdm172xMwr2L7CTgIkbvndhFAVh3_YFV9Ng__52U4SQKIdZZjc4diE4EUxlFrfKmiXbBOHeP72v7sAahuTtWm78hRB1yV3tmg9bBOEhWVnq5KwOBL5."
}
def homeContent(self, filter):
result = {}
categories = ["电视剧", "电影", "综艺", "动漫", "少儿", "纪录片", "文化", "亲子", "教育", "搞笑", "生活",
"体育", "音乐", "游戏"]
classes = [{'type_name': category, 'type_id': category} for category in categories]
filters = {}
self.typeid = {}
with ThreadPoolExecutor(max_workers=len(categories)) as executor:
tasks = {
executor.submit(self.cf, {'type': category}, True): category
for category in categories
}
for future in as_completed(tasks):
try:
category = tasks[future]
session, ft = future.result()
filters[category] = ft
self.typeid[category] = session
except Exception as e:
print(f"处理分类 {tasks[future]} 时出错: {str(e)}")
result['class'] = classes
result['filters'] = filters
return result
def homeVideoContent(self):
try:
vlist = []
params={"ms_codes":"2019061000","params":"{\"debug\":0,\"gray\":0,\"pageNo\":1,\"utdid\":\"ZYmGMAAAACkDAMU8hbiMmYdd\",\"userId\":\"\",\"bizKey\":\"YOUKU_WEB\",\"appPackageKey\":\"com.youku.YouKu\",\"showNodeList\":0,\"reqSubNode\":0,\"nodeKey\":\"WEBHOME\",\"bizContext\":\"{\\\"spmA\\\":\\\"a2hja\\\"}\"}","system_info":"{\"device\":\"pcweb\",\"os\":\"pcweb\",\"ver\":\"1.0.0.0\",\"userAgent\":\"Mozilla/5.0 (; Windows 10.0.26100.3194_64 ) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.82 Electron/14.2.0 Safari/537.36 Node/14.17.0 YoukuDesktop/9.2.60 UOSYouku (2.0.1)-Electron(UTDID ZYmGMAAAACkDAMU8hbiMmYdd;CHANNEL official;ZREAL 0;BTYPE TM2013;BRAND TIMI;BUILDVER 9.2.60.1001)\",\"guid\":\"1590141704165YXe\",\"appPackageKey\":\"com.youku.pcweb\",\"young\":0,\"brand\":\"\",\"network\":\"\",\"ouid\":\"\",\"idfa\":\"\",\"scale\":\"\",\"operator\":\"\",\"resolution\":\"\",\"pid\":\"\",\"childGender\":0,\"zx\":0}"}
data=self.getdata(f'{self.h5host}/h5/mtop.youku.columbus.home.query/1.0/',params)
okey=list(data['data'].keys())[0]
for i in data['data'][okey]['data']['nodes'][0]['nodes'][-1]['nodes'][0]['nodes']:
if i.get('nodes') and i['nodes'][0].get('data'):
i=i['nodes'][0]['data']
if i.get('assignId'):
vlist.append({
'vod_id': i['assignId'],
'vod_name': i.get('title'),
'vod_pic': i.get('vImg') or i.get('img'),
'vod_year': i.get('mark',{}).get('data',{}).get('text'),
'vod_remarks': i.get('summary')
})
return {'list': vlist}
except Exception as e:
print(f"处理主页视频数据时出错: {str(e)}")
return {'list': []}
def categoryContent(self, tid, pg, filter, extend):
result = {}
vlist = []
result['page'] = pg
result['limit'] = 90
result['total'] = 999999
pagecount = 9999
params = {'type': tid}
id = self.typeid[tid]
params.update(extend)
if pg == '1':
id=self.cf(params)
data=self.session.get(f'{self.host}/category/data?session={id}&params={quote(json.dumps(params))}&pageNo={pg}').json()
try:
data=data['data']['filterData']
for i in data['listData']:
if i.get('videoLink') and 's=' in i['videoLink']:
vlist.append({
'vod_id': i.get('videoLink').split('s=')[-1],
'vod_name': i.get('title'),
'vod_pic': i.get('img'),
'vod_year': i.get('rightTagText'),
'vod_remarks': i.get('summary')
})
self.typeid[tid]=quote(json.dumps(data['session']))
except:
pagecount=pg
result['list'] = vlist
result['pagecount'] = pagecount
return result
def detailContent(self, ids):
try:
data=self.session.get(f'{self.ihost}/v_getvideo_info/?showId={ids[0]}').json()
v=data['data']
vod = {
'type_name': v.get('showVideotype'),
'vod_year': v.get('lastUpdate'),
'vod_remarks': v.get('rc_title'),
'vod_actor': v.get('_personNameStr'),
'vod_content': v.get('showdesc'),
'vod_play_from': '优酷',
'vod_play_url': ''
}
params={"biz":"new_detail_web2","videoId":v.get('vid'),"scene":"web_page","componentVersion":"3","ip":data.get('ip'),"debug":0,"utdid":"ZYmGMAAAACkDAMU8hbiMmYdd","userId":0,"platform":"pc","nextSession":"","gray":0,"source":"pcNoPrev","showId":ids[0]}
sdata,index=self.getinfo(params)
pdata=sdata['nodes']
if index > len(pdata):
batch_size = len(pdata)
total_batches = ((index + batch_size - 1) // batch_size) - 1
ssj = json.loads(sdata['data']['session'])
with ThreadPoolExecutor(max_workers=total_batches) as executor:
futures = []
for batch in range(total_batches):
start = batch_size + 1 + (batch * batch_size)
end = start + batch_size - 1
next_session = ssj.copy()
next_session.update({
"itemStartStage": start,
"itemEndStage": min(end, index)
})
current_params = params.copy()
current_params['nextSession'] = json.dumps(next_session)
futures.append((start, executor.submit(self.getvinfo, current_params)))
futures.sort(key=lambda x: x[0])
for _, future in futures:
try:
result = future.result()
pdata.extend(result['nodes'])
except Exception as e:
print(f"Error fetching data: {str(e)}")
vod['vod_play_url'] = '#'.join([f"{i['data'].get('title')}${i['data']['action'].get('value')}" for i in pdata])
return {'list': [vod]}
except Exception as e:
print(e)
return {'list': [{'vod_play_from': '哎呀翻车啦', 'vod_play_url': f'呜呜呜${self.host}'}]}
def searchContent(self, key, quick, pg="1"):
data=self.session.get(f'{self.shost}/api/search?pg={pg}&keyword={key}').json()
vlist = []
for i in data['pageComponentList']:
if i.get('commonData') and (i['commonData'].get('showId') or i['commonData'].get('realShowId')):
i=i['commonData']
vlist.append({
'vod_id': i.get('showId') or i.get('realShowId'),
'vod_name': i['titleDTO'].get('displayName'),
'vod_pic': i['posterDTO'].get('vThumbUrl'),
'vod_year': i.get('feature'),
'vod_remarks': i.get('updateNotice')
})
return {'list': vlist, 'page': pg}
def playerContent(self, flag, id, vipFlags):
return {'jx':1,'parse': 1, 'url': f"{self.ihost}/video?vid={id}", 'header': ''}
def localProxy(self, param):
pass
def cf(self,params,b=False):
response = self.session.get(f'{self.host}/category/data?params={quote(json.dumps(params))}&optionRefresh=1&pageNo=1').json()
data=response['data']['filterData']
session=quote(json.dumps(data['session']))
if b:
return session,self.get_filter_data(data['filter']['filterData'][1:])
return session
def process_key(self, key):
if '_' not in key:
return key
parts = key.split('_')
result = parts[0]
for part in parts[1:]:
if part:
result += part[0].upper() + part[1:]
return result
def get_filter_data(self, data):
result = []
try:
for item in data:
if not item.get('subFilter'):
continue
first_sub = item['subFilter'][0]
if not first_sub.get('filterType'):
continue
filter_item = {
'key': self.process_key(first_sub['filterType']),
'name': first_sub['title'],
'value': []
}
for sub in item['subFilter']:
if 'value' in sub:
filter_item['value'].append({
'n': sub['title'],
'v': sub['value']
})
if filter_item['value']:
result.append(filter_item)
except Exception as e:
print(f"处理筛选数据时出错: {str(e)}")
return result
def get_ctoken(self):
data=self.session.get(f'{self.h5host}/h5/mtop.ykrec.recommendservice.recommend/1.0/?jsv=2.6.1&appKey=24679788')
def md5(self,t,text):
h = MD5.new()
token=self.session.cookies.get('_m_h5_tk').split('_')[0]
data=f"{token}&{t}&24679788&{text}"
h.update(data.encode('utf-8'))
return h.hexdigest()
def getdata(self, url, params, recursion_count=0, max_recursion=3):
data = json.dumps(params)
t = int(time.time() * 1000)
jsdata = {
'appKey': '24679788',
't': t,
'sign': self.md5(t, data),
'data': data
}
response = self.session.get(url, params=jsdata)
if '令牌过期' in response.text:
if recursion_count >= max_recursion:
raise Exception("达到最大递归次数,无法继续请求")
self.get_ctoken()
return self.getdata(url, params, recursion_count + 1, max_recursion)
else:
return response.json()
def getvinfo(self,params):
body = {
"ms_codes": "2019030100",
"params": json.dumps(params),
"system_info": "{\"os\":\"iku\",\"device\":\"iku\",\"ver\":\"9.2.9\",\"appPackageKey\":\"com.youku.iku\",\"appPackageId\":\"pcweb\"}"
}
data = self.getdata(f'{self.h5host}/h5/mtop.youku.columbus.gateway.new.execute/1.0/', body)
okey = list(data['data'].keys())[0]
i = data['data'][okey]['data']
return i
def getinfo(self,params):
i = self.getvinfo(params)
jdata=i['nodes'][0]['nodes'][3]
info=i['data']['extra']['episodeTotal']
if i['data']['extra']['showCategory'] in ['电影','游戏']:
jdata = i['nodes'][0]['nodes'][4]
return jdata,info
+790
View File
@@ -0,0 +1,790 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# 偷乐短剧爬虫
import sys
import json
import re
import time
import urllib.parse
import requests
from bs4 import BeautifulSoup
# 导入基础类
sys.path.append('../../')
try:
from base.spider import Spider
except ImportError:
# 本地调试时的替代实现
class Spider:
def init(self, extend=""):
pass
class Spider(Spider):
def __init__(self):
# 网站主URL
self.siteUrl = "https://www.toule.top"
# 根据网站实际结构,分类链接格式为: /index.php/vod/show/class/分类名/id/1.html
# 分类ID映射 - 从网站中提取的分类
self.cateManual = {
"男频": "/index.php/vod/show/class/%E7%94%B7%E9%A2%91/id/1.html",
"女频": "/index.php/vod/show/class/%E5%A5%B3%E9%A2%91/id/1.html",
"都市": "/index.php/vod/show/class/%E9%83%BD%E5%B8%82/id/1.html",
"赘婿": "/index.php/vod/show/class/%E8%B5%98%E5%A9%BF/id/1.html",
"战神": "/index.php/vod/show/class/%E6%88%98%E7%A5%9E/id/1.html",
"古代言情": "/index.php/vod/show/class/%E5%8F%A4%E4%BB%A3%E8%A8%80%E6%83%85/id/1.html",
"现代言情": "/index.php/vod/show/class/%E7%8E%B0%E4%BB%A3%E8%A8%80%E6%83%85/id/1.html",
"历史": "/index.php/vod/show/class/%E5%8E%86%E5%8F%B2/id/1.html",
"玄幻": "/index.php/vod/show/class/%E7%8E%84%E5%B9%BB/id/1.html",
"搞笑": "/index.php/vod/show/class/%E6%90%9E%E7%AC%91/id/1.html",
"甜宠": "/index.php/vod/show/class/%E7%94%9C%E5%AE%A0/id/1.html",
"励志": "/index.php/vod/show/class/%E5%8A%B1%E5%BF%97/id/1.html",
"逆袭": "/index.php/vod/show/class/%E9%80%86%E8%A2%AD/id/1.html",
"穿越": "/index.php/vod/show/class/%E7%A9%BF%E8%B6%8A/id/1.html",
"古装": "/index.php/vod/show/class/%E5%8F%A4%E8%A3%85/id/1.html"
}
# 请求头
self.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",
"Referer": "https://www.toule.top/",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
"Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
"Accept-Encoding": "gzip, deflate, br",
"Connection": "keep-alive",
}
# 缓存
self.cache = {}
self.cache_timeout = {}
def getName(self):
return "偷乐短剧"
def init(self, extend=""):
# 初始化方法,可以留空
return
def isVideoFormat(self, url):
"""判断是否为视频格式"""
video_formats = ['.mp4', '.m3u8', '.ts', '.flv', '.avi', '.mkv', '.mov', '.rmvb', '.3gp']
for format in video_formats:
if format in url.lower():
return True
return False
def manualVideoCheck(self):
"""是否需要手动检查视频"""
return False
# 工具方法 - 网络请求
def fetch(self, url, headers=None, data=None, method="GET"):
"""统一的网络请求方法"""
try:
if headers is None:
headers = self.headers.copy()
if method.upper() == "GET":
response = requests.get(url, headers=headers, params=data, timeout=10,verify=False)
else: # POST
response = requests.post(url, headers=headers, data=data, timeout=10,verify=False)
response.raise_for_status()
response.encoding = response.apparent_encoding or 'utf-8'
return response
except Exception as e:
self.log(f"请求失败: {url}, 错误: {str(e)}", "ERROR")
return None
# 缓存方法
def getCache(self, key, timeout=3600):
"""获取缓存数据"""
if key in self.cache and key in self.cache_timeout:
if time.time() < self.cache_timeout[key]:
return self.cache[key]
else:
del self.cache[key]
del self.cache_timeout[key]
return None
def setCache(self, key, value, timeout=3600):
"""设置缓存数据"""
self.cache[key] = value
self.cache_timeout[key] = time.time() + timeout
# 日志方法
def log(self, msg, level='INFO'):
"""记录日志"""
levels = {
'DEBUG': 0,
'INFO': 1,
'WARNING': 2,
'ERROR': 3
}
current_level = 'INFO' # 可以设置为DEBUG以获取更多信息
if levels.get(level, 4) >= levels.get(current_level, 1):
print(f"[{level}] {time.strftime('%Y-%m-%d %H:%M:%S')} - {msg}")
# 辅助方法 - 从URL中提取视频ID
def extractVodId(self, url):
"""从URL中提取视频ID"""
# 路径格式: /index.php/vod/play/id/9024/sid/1/nid/1.html
match = re.search(r'/id/(\d+)/', url)
if match:
return match.group(1)
return ""
# 辅助方法 - 从网页内容中提取分类
def extractCategories(self, text):
"""从网页内容中提取分类标签"""
cats = []
# 匹配标签字符串,例如: "男频,逆袭,亲情,短剧"
if "," in text:
parts = text.split(",")
for part in parts:
part = part.strip()
if part and part != "短剧":
cats.append(part)
return cats
# 主要接口实现
def homeContent(self, filter):
"""获取首页分类及内容"""
result = {}
classes = []
# 从缓存获取
cache_key = 'home_classes'
cached_classes = self.getCache(cache_key)
if cached_classes:
classes = cached_classes
else:
# 使用预定义的分类
for k, v in self.cateManual.items():
classes.append({
'type_id': v, # 使用完整URL路径作为type_id
'type_name': k
})
# 保存到缓存
self.setCache(cache_key, classes, 24*3600) # 缓存24小时
result['class'] = classes
# 获取首页推荐视频
videos = self.homeVideoContent().get('list', [])
result['list'] = videos
return result
def homeVideoContent(self):
"""获取首页推荐视频内容"""
result = {'list': []}
videos = []
# 从缓存获取
cache_key = 'home_videos'
cached_videos = self.getCache(cache_key)
if cached_videos:
return {'list': cached_videos}
try:
response = self.fetch(self.siteUrl)
if response and response.status_code == 200:
html = response.text
soup = BeautifulSoup(html, 'html.parser')
# 查找最新更新区域
latest_section = soup.find('h2', text=lambda t: t and '最新更新' in t)
if latest_section:
container = latest_section.parent # 获取容器
if container:
# 查找所有 li.item 元素
items = container.find_all('li', class_='item')
for item in items:
try:
# 获取链接和标题
title_link = item.find('h3')
if not title_link:
continue
title = title_link.text.strip()
# 获取第一个链接作为详情页链接
link_tag = item.find('a')
if not link_tag:
continue
link = link_tag.get('href', '')
if not link.startswith('http'):
link = urllib.parse.urljoin(self.siteUrl, link)
# 提取ID
vid = self.extractVodId(link)
if not vid:
continue
# 获取图片
img_tag = item.find('img')
img_url = ""
if img_tag:
img_url = img_tag.get('src', img_tag.get('data-src', ''))
if img_url and not img_url.startswith('http'):
img_url = urllib.parse.urljoin(self.siteUrl, img_url)
# 获取备注信息
remarks = ""
remarks_tag = item.find('span', class_='remarks')
if remarks_tag:
remarks = remarks_tag.text.strip()
# 获取标签信息
tags = ""
tags_tag = item.find('span', class_='tags')
if tags_tag:
tags = tags_tag.text.strip()
# 合并备注和标签
if remarks and tags:
remarks = f"{remarks} | {tags}"
elif tags:
remarks = tags
# 构建视频项
videos.append({
'vod_id': vid,
'vod_name': title,
'vod_pic': img_url,
'vod_remarks': remarks
})
except Exception as e:
self.log(f"处理视频项时出错: {str(e)}", "ERROR")
continue
# 保存到缓存
self.setCache(cache_key, videos, 3600) # 缓存1小时
except Exception as e:
self.log(f"获取首页视频内容发生错误: {str(e)}", "ERROR")
result['list'] = videos
return result
def categoryContent(self, tid, pg, filter, extend):
"""获取分类内容"""
result = {}
videos = []
# 处理页码
if pg is None:
pg = 1
else:
pg = int(pg)
# 构建分类URL - tid是完整的URL路径
if tid.startswith("/"):
# 替换页码,URL格式可能像: /index.php/vod/show/class/男频/id/1.html
if pg > 1:
if "html" in tid:
category_url = tid.replace(".html", f"/page/{pg}.html")
else:
category_url = f"{tid}/page/{pg}.html"
else:
category_url = tid
full_url = urllib.parse.urljoin(self.siteUrl, category_url)
else:
# 如果tid不是URL路径,可能是旧版分类ID,尝试查找对应URL
category_url = ""
for name, url in self.cateManual.items():
if name == tid:
category_url = url
break
if not category_url:
self.log(f"未找到分类ID对应的URL: {tid}", "ERROR")
result['list'] = []
result['page'] = pg
result['pagecount'] = 1
result['limit'] = 0
result['total'] = 0
return result
# 处理页码
if pg > 1:
if "html" in category_url:
category_url = category_url.replace(".html", f"/page/{pg}.html")
else:
category_url = f"{category_url}/page/{pg}.html"
full_url = urllib.parse.urljoin(self.siteUrl, category_url)
# 请求分类页
try:
response = self.fetch(full_url)
if response and response.status_code == 200:
html = response.text
soup = BeautifulSoup(html, 'html.parser')
# 查找视频项,根据实际HTML结构调整
items = soup.find_all('li', class_='item')
for item in items:
try:
# 获取链接和标题
title_tag = item.find('h3')
if not title_tag:
continue
title = title_tag.text.strip()
# 获取链接
link_tag = item.find('a')
if not link_tag:
continue
link = link_tag.get('href', '')
if not link.startswith('http'):
link = urllib.parse.urljoin(self.siteUrl, link)
# 提取ID
vid = self.extractVodId(link)
if not vid:
continue
# 获取图片
img_tag = item.find('img')
img_url = ""
if img_tag:
img_url = img_tag.get('src', img_tag.get('data-src', ''))
if img_url and not img_url.startswith('http'):
img_url = urllib.parse.urljoin(self.siteUrl, img_url)
# 获取备注信息
remarks = ""
remarks_tag = item.find('span', class_='remarks')
if remarks_tag:
remarks = remarks_tag.text.strip()
# 获取标签信息
tags = ""
tags_tag = item.find('span', class_='tags')
if tags_tag:
tags = tags_tag.text.strip()
# 合并备注和标签
if remarks and tags:
remarks = f"{remarks} | {tags}"
elif tags:
remarks = tags
# 构建视频项
videos.append({
'vod_id': vid,
'vod_name': title,
'vod_pic': img_url,
'vod_remarks': remarks
})
except Exception as e:
self.log(f"处理分类视频项时出错: {str(e)}", "ERROR")
continue
# 查找分页信息
# 默认值
total = len(videos)
pagecount = 1
limit = 20
# 尝试查找分页元素
pagination = soup.find('ul', class_='page')
if pagination:
# 查找最后一页的链接
last_page_links = pagination.find_all('a')
for link in last_page_links:
page_text = link.text.strip()
if page_text.isdigit():
pagecount = max(pagecount, int(page_text))
except Exception as e:
self.log(f"获取分类内容发生错误: {str(e)}", "ERROR")
result['list'] = videos
result['page'] = pg
result['pagecount'] = pagecount
result['limit'] = limit
result['total'] = total
return result
def detailContent(self, ids):
"""获取详情内容"""
result = {}
if not ids or len(ids) == 0:
return result
# 视频ID
vid = ids[0]
# 构建播放页URL
play_url = f"{self.siteUrl}/index.php/vod/play/id/{vid}/sid/1/nid/1.html"
try:
response = self.fetch(play_url)
if not response or response.status_code != 200:
return result
html = response.text
soup = BeautifulSoup(html, 'html.parser')
# 提取视频基本信息
# 标题
title = ""
title_tag = soup.find('h1', class_='items-title')
if title_tag:
title = title_tag.text.strip()
# 图片
pic = ""
pic_tag = soup.find('img', class_='thumb')
if pic_tag:
pic = pic_tag.get('src', '')
if pic and not pic.startswith('http'):
pic = urllib.parse.urljoin(self.siteUrl, pic)
# 简介
desc = ""
desc_tag = soup.find('div', class_='text-content')
if desc_tag:
desc = desc_tag.text.strip()
# 标签/分类
tags = []
tags_container = soup.find('span', class_='items-tags')
if tags_container:
tag_links = tags_container.find_all('a')
for tag in tag_links:
tag_text = tag.text.strip()
if tag_text:
tags.append(tag_text)
# 提取播放列表
play_from = "偷乐短剧"
play_list = []
# 查找播放列表区域
play_area = soup.find('div', class_='swiper-wrapper')
if play_area:
# 查找所有剧集链接
episode_links = play_area.find_all('a')
for ep in episode_links:
ep_title = ep.text.strip()
ep_url = ep.get('href', '')
if ep_url:
# 直接使用URL作为ID
if not ep_url.startswith('http'):
ep_url = urllib.parse.urljoin(self.siteUrl, ep_url)
# 提取集数信息
ep_num = ep_title
if ep_num.isdigit():
ep_num = f"{ep_num}"
play_list.append(f"{ep_num}${ep_url}")
# 如果没有找到播放列表,查找播放按钮
if not play_list:
play_btn = soup.find('a', class_='btn-play')
if play_btn:
play_url = play_btn.get('href', '')
if play_url:
if not play_url.startswith('http'):
play_url = urllib.parse.urljoin(self.siteUrl, play_url)
play_list.append(f"播放${play_url}")
# 如果仍然没有找到播放链接,使用播放页URL
if not play_list:
play_url = f"{self.siteUrl}/index.php/vod/play/id/{vid}/sid/1/nid/1.html"
play_list.append(f"播放${play_url}")
# 提取更多信息(导演、演员等)
director = ""
actor = ""
year = ""
area = ""
remarks = ""
# 查找备注信息
meta_items = soup.find_all('div', class_='meta-item')
for item in meta_items:
item_title = item.find('span', class_='item-title')
item_content = item.find('span', class_='item-content')
if item_title and item_content:
title_text = item_title.text.strip()
content_text = item_content.text.strip()
if "导演" in title_text:
director = content_text
elif "主演" in title_text:
actor = content_text
elif "年份" in title_text:
year = content_text
elif "地区" in title_text:
area = content_text
elif "简介" in title_text:
if not desc:
desc = content_text
elif "状态" in title_text:
remarks = content_text
# 如果没有从meta-item中获取到remarks
if not remarks:
remarks_tag = soup.find('span', class_='remarks')
if remarks_tag:
remarks = remarks_tag.text.strip()
# 构建标准数据结构
vod = {
"vod_id": vid,
"vod_name": title,
"vod_pic": pic,
"vod_year": year,
"vod_area": area,
"vod_remarks": remarks,
"vod_actor": actor,
"vod_director": director,
"vod_content": desc,
"type_name": ",".join(tags),
"vod_play_from": play_from,
"vod_play_url": "#".join(play_list)
}
result = {
'list': [vod]
}
except Exception as e:
self.log(f"获取详情内容时出错: {str(e)}", "ERROR")
return result
def searchContent(self, key, quick, pg=1):
"""搜索功能"""
result = {}
videos = []
# 构建搜索URL和参数
search_url = f"{self.siteUrl}/index.php/vod/search.html"
params = {"wd": key}
try:
response = self.fetch(search_url, data=params)
if response and response.status_code == 200:
html = response.text
soup = BeautifulSoup(html, 'html.parser')
# 查找搜索结果项
search_items = soup.find_all('li', class_='item')
for item in search_items:
try:
# 获取标题
title_tag = item.find('h3')
if not title_tag:
continue
title = title_tag.text.strip()
# 获取链接
link_tag = item.find('a')
if not link_tag:
continue
link = link_tag.get('href', '')
if not link.startswith('http'):
link = urllib.parse.urljoin(self.siteUrl, link)
# 提取视频ID
vid = self.extractVodId(link)
if not vid:
continue
# 获取图片
img_tag = item.find('img')
img_url = ""
if img_tag:
img_url = img_tag.get('src', img_tag.get('data-src', ''))
if img_url and not img_url.startswith('http'):
img_url = urllib.parse.urljoin(self.siteUrl, img_url)
# 获取备注信息
remarks = ""
remarks_tag = item.find('span', class_='remarks')
if remarks_tag:
remarks = remarks_tag.text.strip()
# 获取标签信息
tags = ""
tags_tag = item.find('span', class_='tags')
if tags_tag:
tags = tags_tag.text.strip()
# 合并备注和标签
if remarks and tags:
remarks = f"{remarks} | {tags}"
elif tags:
remarks = tags
# 构建视频项
videos.append({
'vod_id': vid,
'vod_name': title,
'vod_pic': img_url,
'vod_remarks': remarks
})
except Exception as e:
self.log(f"处理搜索结果时出错: {str(e)}", "ERROR")
continue
except Exception as e:
self.log(f"搜索功能发生错误: {str(e)}", "ERROR")
result['list'] = videos
return result
def searchContentPage(self, key, quick, pg=1):
return self.searchContent(key, quick, pg)
def playerContent(self, flag, id, vipFlags):
"""获取播放内容"""
result = {}
try:
# 判断是否已经是视频URL
if self.isVideoFormat(id):
result["parse"] = 0
result["url"] = id
result["playUrl"] = ""
result["header"] = json.dumps(self.headers)
return result
# 判断是否是完整的页面URL
if id.startswith(('http://', 'https://')):
play_url = id
# 尝试作为相对路径处理
elif id.startswith('/'):
play_url = urllib.parse.urljoin(self.siteUrl, id)
# 假设是视频ID,构建播放页面URL
else:
# 检查是否是"视频ID_集数"格式
parts = id.split('_')
if len(parts) > 1 and parts[0].isdigit():
vid = parts[0]
nid = parts[1]
play_url = f"{self.siteUrl}/index.php/vod/play/id/{vid}/sid/1/nid/{nid}.html"
else:
# 直接当作视频ID处理
play_url = f"{self.siteUrl}/index.php/vod/play/id/{id}/sid/1/nid/1.html"
# 访问播放页获取真实播放地址
try:
self.log(f"正在解析播放页面: {play_url}")
response = self.fetch(play_url)
if response and response.status_code == 200:
html = response.text
# 查找player_aaaa变量
player_match = re.search(r'var\s+player_aaaa\s*=\s*({.*?});', html, re.DOTALL)
if player_match:
try:
player_data = json.loads(player_match.group(1))
if 'url' in player_data:
video_url = player_data['url']
if not video_url.startswith('http'):
video_url = urllib.parse.urljoin(self.siteUrl, video_url)
self.log(f"从player_aaaa获取到视频地址: {video_url}")
result["parse"] = 0
result["url"] = video_url
result["playUrl"] = ""
result["header"] = json.dumps(self.headers)
return result
except json.JSONDecodeError as e:
self.log(f"解析player_aaaa JSON出错: {str(e)}", "ERROR")
# 如果player_aaaa解析失败,尝试其他方式
# 1. 查找video标签
video_match = re.search(r'<video[^>]*src=["\'](.*?)["\']', html)
if video_match:
video_url = video_match.group(1)
if not video_url.startswith('http'):
video_url = urllib.parse.urljoin(self.siteUrl, video_url)
self.log(f"从video标签找到视频地址: {video_url}")
result["parse"] = 0
result["url"] = video_url
result["playUrl"] = ""
result["header"] = json.dumps(self.headers)
return result
# 2. 查找iframe
iframe_match = re.search(r'<iframe[^>]*src=["\'](.*?)["\']', html)
if iframe_match:
iframe_url = iframe_match.group(1)
if not iframe_url.startswith('http'):
iframe_url = urllib.parse.urljoin(self.siteUrl, iframe_url)
self.log(f"找到iframe,正在解析: {iframe_url}")
# 访问iframe内容
iframe_response = self.fetch(iframe_url)
if iframe_response and iframe_response.status_code == 200:
iframe_html = iframe_response.text
# 在iframe内容中查找视频地址
iframe_video_match = re.search(r'(https?://[^\'"]+\.(mp4|m3u8|ts))', iframe_html)
if iframe_video_match:
video_url = iframe_video_match.group(1)
self.log(f"从iframe中找到视频地址: {video_url}")
result["parse"] = 0
result["url"] = video_url
result["playUrl"] = ""
result["header"] = json.dumps({
"User-Agent": self.headers["User-Agent"],
"Referer": iframe_url
})
return result
# 3. 查找任何可能的视频URL
url_match = re.search(r'(https?://[^\'"]+\.(mp4|m3u8|ts))', html)
if url_match:
video_url = url_match.group(1)
self.log(f"找到可能的视频地址: {video_url}")
result["parse"] = 0
result["url"] = video_url
result["playUrl"] = ""
result["header"] = json.dumps(self.headers)
return result
except Exception as e:
self.log(f"解析播放地址时出错: {str(e)}", "ERROR")
# 如果所有方式都失败,返回外部解析标志
self.log("未找到直接可用的视频地址,需要外部解析", "WARNING")
result["parse"] = 1 # 表示需要外部解析
result["url"] = play_url # 返回播放页面URL
result["playUrl"] = ""
result["header"] = json.dumps(self.headers)
except Exception as e:
self.log(f"获取播放内容时出错: {str(e)}", "ERROR")
return result
def localProxy(self, param):
"""本地代理"""
return [404, "text/plain", {}, "Not Found"]
+222
View File
@@ -0,0 +1,222 @@
# -*- coding: utf-8 -*-
# by @嗷呜
import re
import sys
from Crypto.Hash import MD5
sys.path.append('..')
from Crypto.Cipher import AES
from Crypto.Util.Padding import pad, unpad
from urllib.parse import quote, urlparse
from base64 import b64encode, b64decode
import json
import time
from base.spider import Spider
class Spider(Spider):
def init(self, extend=""):
self.host = self.gethost()
pass
def getName(self):
pass
def isVideoFormat(self, url):
pass
def manualVideoCheck(self):
pass
def action(self, action):
pass
def destroy(self):
pass
def homeContent(self, filter):
data = self.getdata("/api.php/getappapi.index/initV119")
dy = {"class": "类型", "area": "地区", "lang": "语言", "year": "年份", "letter": "字母", "by": "排序",
"sort": "排序"}
filters = {}
classes = []
json_data = data["type_list"]
homedata = data["banner_list"][8:]
for item in json_data:
if item["type_name"] == "全部":
continue
has_non_empty_field = False
jsontype_extend = json.loads(item["type_extend"])
homedata.extend(item["recommend_list"])
jsontype_extend["sort"] = "最新,最热,最赞"
classes.append({"type_name": item["type_name"], "type_id": item["type_id"]})
for key in dy:
if key in jsontype_extend and jsontype_extend[key].strip() != "":
has_non_empty_field = True
break
if has_non_empty_field:
filters[str(item["type_id"])] = []
for dkey in jsontype_extend:
if dkey in dy and jsontype_extend[dkey].strip() != "":
values = jsontype_extend[dkey].split(",")
value_array = [{"n": value.strip(), "v": value.strip()} for value in values if
value.strip() != ""]
filters[str(item["type_id"])].append({"key": dkey, "name": dy[dkey], "value": value_array})
result = {}
result["class"] = classes
result["filters"] = filters
result["list"] = homedata[1:]
return result
def homeVideoContent(self):
pass
def categoryContent(self, tid, pg, filter, extend):
body = {"area": extend.get('area', '全部'), "year": extend.get('year', '全部'), "type_id": tid, "page": pg,
"sort": extend.get('sort', '最新'), "lang": extend.get('lang', '全部'),
"class": extend.get('class', '全部')}
result = {}
data = self.getdata("/api.php/getappapi.index/typeFilterVodList", body)
result["list"] = data["recommend_list"]
result["page"] = pg
result["pagecount"] = 9999
result["limit"] = 90
result["total"] = 999999
return result
def detailContent(self, ids):
body = f"vod_id={ids[0]}"
data = self.getdata("/api.php/getappapi.index/vodDetail", body)
vod = data["vod"]
play = []
names = []
for itt in data["vod_play_list"]:
a = []
names.append(itt["player_info"]["show"])
for it in itt['urls']:
it['user_agent']=itt["player_info"].get("user_agent")
it["parse"]=itt["player_info"].get("parse")
a.append(f"{it['name']}${self.e64(json.dumps(it))}")
play.append("#".join(a))
vod["vod_play_from"] = "$$$".join(names)
vod["vod_play_url"] = "$$$".join(play)
result = {"list": [vod]}
return result
def searchContent(self, key, quick, pg="1"):
body = f"keywords={key}&type_id=0&page={pg}"
data = self.getdata("/api.php/getappapi.index/searchList", body)
result = {"list": data["search_list"], "page": pg}
return result
def playerContent(self, flag, id, vipFlags):
ids = json.loads(self.d64(id))
h = {"User-Agent": (ids['user_agent'] or "okhttp/3.14.9")}
try:
if re.search(r'url=', ids['parse_api_url']):
data = self.fetch(ids['parse_api_url'], headers=h, timeout=10).json()
url = data.get('url') or data['data'].get('url')
else:
body = f"parse_api={ids.get('parse') or ids['parse_api_url'].replace(ids['url'], '')}&url={quote(self.aes(ids['url'], True))}&token={ids.get('token')}"
b = self.getdata("/api.php/getappapi.index/vodParse", body)['json']
url = json.loads(b)['url']
if 'error' in url: raise ValueError(f"解析失败: {url}")
p = 0
except Exception as e:
print('错误信息:', e)
url, p = ids['url'], 1
if re.search(r'\.jpg|\.png|\.jpeg', url):
url = self.Mproxy(url)
result = {}
result["parse"] = p
result["url"] = url
result["header"] = h
return result
def localProxy(self, param):
return self.Mlocal(param)
def gethost(self):
headers = {
'User-Agent': 'okhttp/3.14.9'
}
host = self.fetch('https://jingyu-1312635929.cos.ap-nanjing.myqcloud.com/1.json',
headers=headers).text.strip()
return host
phend = {
'User-Agent': 'Dalvik/2.1.0 (Linux; U; Android 11; M2012K10C Build/RP1A.200720.011)',
'allowCrossProtocolRedirects': 'true'
}
def aes(self, operation, text):
key = "4d83b87c4c5ea111".encode("utf-8")
iv = key
if operation == "encrypt":
cipher = AES.new(key, AES.MODE_CBC, iv)
ct_bytes = cipher.encrypt(pad(text.encode("utf-8"), AES.block_size))
ct = b64encode(ct_bytes).decode("utf-8")
return ct
elif operation == "decrypt":
cipher = AES.new(key, AES.MODE_CBC, iv)
pt = unpad(cipher.decrypt(b64decode(text)), AES.block_size)
return pt.decode("utf-8")
def header(self):
t = str(int(time.time()))
header = {"Referer":self.host,
"User-Agent": "okhttp/3.14.9", "app-version-code": "300", "app-ui-mode": "light",
"app-api-verify-time": t, "app-user-device-id": self.md5(t),
"app-api-verify-sign": self.aes("encrypt", t),
"Content-Type": "application/x-www-form-urlencoded; charset=UTF-8"}
return header
def getdata(self, path, data=None):
vdata = self.post(f"{self.host}{path}", headers=self.header(), data=data, timeout=10).json()['data']
data1 = self.aes("decrypt", vdata)
return json.loads(data1)
def Mproxy(self, url):
return self.getProxyUrl() + "&url=" + b64encode(url.encode('utf-8')).decode('utf-8') + "&type=m3u8"
def Mlocal(self, param,header=None):
url = self.d64(param["url"])
ydata = self.fetch(url, headers=header, allow_redirects=False)
data = ydata.content.decode('utf-8')
if ydata.headers.get('Location'):
url = ydata.headers['Location']
data = self.fetch(url, headers=header).content.decode('utf-8')
parsed_url = urlparse(url)
durl = parsed_url.scheme + "://" + parsed_url.netloc
lines = data.strip().split('\n')
for index, string in enumerate(lines):
if '#EXT' not in string and 'http' not in string:
last_slash_index = string.rfind('/')
lpath = string[:last_slash_index + 1]
lines[index] = durl + ('' if lpath.startswith('/') else '/') + lpath
data = '\n'.join(lines)
return [200, "application/vnd.apple.mpegur", data]
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 md5(self, text):
h = MD5.new()
h.update(text.encode('utf-8'))
return h.hexdigest()
+329
View File
@@ -0,0 +1,329 @@
# coding=utf-8
# !/usr/bin/python
"""
作者 丢丢喵推荐 🚓 内容均从互联网收集而来 仅供交流学习使用 版权归原创者所有 如侵犯了您的权益 请通知作者 将及时删除侵权内容
====================Diudiumiao====================
"""
from Crypto.Util.Padding import unpad
from Crypto.Util.Padding import pad
from urllib.parse import unquote
from Crypto.Cipher import ARC4
from urllib.parse import quote
from base.spider import Spider
from Crypto.Cipher import AES
from datetime import datetime
from bs4 import BeautifulSoup
from base64 import b64decode
import urllib.request
import urllib.parse
import datetime
import binascii
import requests
import base64
import json
import time
import sys
import re
import os
sys.path.append('..')
xurl = "https://djw1.com"
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'
}
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 = {"class": []}
detail = requests.get(url=xurl + "/all/", headers=headerx)
detail.encoding = "utf-8"
res = detail.text
doc = BeautifulSoup(res, "lxml")
soups = doc.find_all('section', class_="container items")
for soup in soups:
vods = soup.find_all('li')
for vod in vods:
id = vod.find('a')['href']
name = vod.text.strip()
result["class"].append({"type_id": id, "type_name": "" + name})
return result
def homeVideoContent(self):
pass
def categoryContent(self, cid, pg, filter, ext):
result = {}
videos = []
if pg:
page = int(pg)
else:
page = 1
url = f'{cid}page/{str(page)}/'
detail = requests.get(url=url, headers=headerx)
detail.encoding = "utf-8"
res = detail.text
doc = BeautifulSoup(res, "lxml")
soups = doc.find_all('section', class_="container items")
for soup in soups:
vods = soup.find_all('li')
for vod in vods:
name = vod.find('img')['alt']
ids = vod.find('a', class_="image-line")
id = ids['href']
pic = vod.find('img')['src']
remark = self.extract_middle_text(str(vod), 'class="remarks light">', '<', 0)
video = {
"vod_id": id,
"vod_name": name,
"vod_pic": pic,
"vod_remarks": '▶️' + remark
}
videos.append(video)
result = {'list': videos}
result['page'] = pg
result['pagecount'] = 9999
result['limit'] = 90
result['total'] = 999999
return result
def detailContent(self, ids):
did = ids[0]
result = {}
videos = []
xianlu = ''
bofang = ''
if 'http' not in did:
did = xurl + did
res = requests.get(url=did, headers=headerx)
res.encoding = "utf-8"
res = res.text
doc = BeautifulSoup(res, "lxml")
url = 'https://fs-im-kefu.7moor-fs1.com/ly/4d2c3f00-7d4c-11e5-af15-41bf63ae4ea0/1732707176882/jiduo.txt'
response = requests.get(url)
response.encoding = 'utf-8'
code = response.text
name = self.extract_middle_text(code, "s1='", "'", 0)
Jumps = self.extract_middle_text(code, "s2='", "'", 0)
content = '集多为您介绍剧情📢' + self.extract_middle_text(res,'class="info-detail">','<', 0)
remarks = self.extract_middle_text(res, 'class="info-mark">', '<', 0)
year = self.extract_middle_text(res, 'class="info-addtime">', '<', 0)
if name not in content:
bofang = Jumps
xianlu = '1'
else:
soups = doc.find('div', class_="ep-list-items")
soup = soups.find_all('a')
for sou in soup:
id = sou['href']
name = sou.text.strip()
bofang = bofang + name + '$' + id + '#'
bofang = bofang[:-1]
xianlu = '专线'
videos.append({
"vod_id": did,
"vod_remarks": remarks,
"vod_year": year,
"vod_content": content,
"vod_play_from": xianlu,
"vod_play_url": bofang
})
result['list'] = videos
return result
def playerContent(self, flag, id, vipFlags):
res = requests.get(url=id, headers=headerx)
res.encoding = "utf-8"
res = res.text
url = self.extract_middle_text(res, '"wwm3u8":"', '"', 0).replace('\\', '')
result = {}
result["parse"] = 0
result["playUrl"] = ''
result["url"] = url
result["header"] = headerx
return result
def searchContentPage(self, key, quick, pg):
result = {}
videos = []
if pg:
page = int(pg)
else:
page = 1
url = f'{xurl}/search/{key}/page/{str(page)}/'
detail = requests.get(url=url, headers=headerx)
detail.encoding = "utf-8"
res = detail.text
doc = BeautifulSoup(res, "lxml")
soups = doc.find_all('section', class_="container items")
for soup in soups:
vods = soup.find_all('li')
for vod in vods:
name = vod.find('img')['alt']
ids = vod.find('a', class_="image-line")
id = ids['href']
pic = vod.find('img')['src']
remark = self.extract_middle_text(str(vod), 'class="remarks light">', '<', 0)
video = {
"vod_id": id,
"vod_name": name,
"vod_pic": pic,
"vod_remarks": '▶️' + remark
}
videos.append(video)
result['list'] = videos
result['page'] = pg
result['pagecount'] = 9999
result['limit'] = 90
result['total'] = 999999
return result
def searchContent(self, key, quick, pg="1"):
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
+314
View File
@@ -0,0 +1,314 @@
# coding=utf-8
# !/usr/bin/python
"""
作者 丢丢喵 🚓 内容均从互联网收集而来 仅供交流学习使用 版权归原创者所有 如侵犯了您的权益 请通知作者 将及时删除侵权内容
====================Diudiumiao====================
"""
from Crypto.Util.Padding import unpad
from Crypto.Util.Padding import pad
from urllib.parse import unquote
from Crypto.Cipher import ARC4
from urllib.parse import quote
from base.spider import Spider
from Crypto.Cipher import AES
from datetime import datetime
from bs4 import BeautifulSoup
from base64 import b64decode
import urllib.request
import urllib.parse
import datetime
import binascii
import requests
import base64
import json
import time
import sys
import re
import os
sys.path.append('..')
xurl = "https://search.bilibili.com"
xurl1 = "https://api.live.bilibili.com"
headerx = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36 Edg/129.0.0.0'
}
class Spider(Spider):
global xurl
global xurl1
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": "", "type_name": "舞蹈"},
{"type_id": "音乐", "type_name": "音乐"},
{"type_id": "手游", "type_name": "手游"},
{"type_id": "网游", "type_name": "网游"},
{"type_id": "单机游戏", "type_name": "单机游戏"},
{"type_id": "虚拟主播", "type_name": "虚拟主播"},
{"type_id": "电台", "type_name": "电台"},
{"type_id": "体育", "type_name": "体育"},
{"type_id": "聊天", "type_name": "聊天"},
{"type_id": "娱乐", "type_name": "娱乐"},
{"type_id": "电影", "type_name": "影视"},
{"type_id": "新闻", "type_name": "新闻"}]
}
return result
def homeVideoContent(self):
pass
def categoryContent(self, cid, pg, filter, ext):
result = {}
videos = []
if pg:
page = int(pg)
else:
page = 1
url = f'{xurl}/live?keyword={cid}&page={str(page)}'
detail = requests.get(url=url, headers=headerx)
detail.encoding = "utf-8"
res = detail.text
doc = BeautifulSoup(res, "lxml")
soups = doc.find_all('div', class_="video-list-item")
for vod in soups:
names = vod.find('h3', class_="bili-live-card__info--tit")
name = names.text.strip().replace('直播中', '')
id = names.find('a')['href']
id = self.extract_middle_text(id, 'bilibili.com/', '?', 0)
pic = vod.find('img')['src']
if 'http' not in pic:
pic = "https:" + pic
remarks = vod.find('a', class_="bili-live-card__info--uname")
remark = remarks.text.strip()
video = {
"vod_id": id,
"vod_name": name,
"vod_pic": pic,
"vod_remarks": remark
}
videos.append(video)
result = {'list': videos}
result['page'] = pg
result['pagecount'] = 9999
result['limit'] = 90
result['total'] = 999999
return result
def detailContent(self, ids):
did = ids[0]
result = {}
videos = []
xianlu = ''
bofang = ''
url = f'{xurl1}/xlive/web-room/v2/index/getRoomPlayInfo?room_id={did}&platform=web&protocol=0,1&format=0,1,2&codec=0,1'
detail = requests.get(url=url, headers=headerx)
detail.encoding = "utf-8"
data = detail.json()
content = '欢迎观看哔哩直播'
setup = data['data']['playurl_info']['playurl']['stream']
nam = 0
for vod in setup:
try:
host = vod['format'][nam]['codec'][0]['url_info'][1]['host']
except (KeyError, IndexError):
continue
base = vod['format'][nam]['codec'][0]['base_url']
extra = vod['format'][nam]['codec'][0]['url_info'][1]['extra']
id = host + base + extra
nam = nam + 1
namc = f"{nam}号线路"
bofang = bofang + namc + '$' + id + '#'
bofang = bofang[:-1]
xianlu = '哔哩专线'
videos.append({
"vod_id": did,
"vod_content": content,
"vod_play_from": xianlu,
"vod_play_url": bofang
})
result['list'] = videos
return result
def playerContent(self, flag, id, vipFlags):
result = {}
result["parse"] = 0
result["playUrl"] = ''
result["url"] = id
result["header"] = headerx
return result
def searchContentPage(self, key, quick, pg):
result = {}
videos = []
if pg:
page = int(pg)
else:
page = 1
url = f'{xurl}/live?keyword={key}&page={str(page)}'
detail = requests.get(url=url, headers=headerx)
detail.encoding = "utf-8"
res = detail.text
doc = BeautifulSoup(res, "lxml")
soups = doc.find_all('div', class_="video-list-item")
for vod in soups:
names = vod.find('h3', class_="bili-live-card__info--tit")
name = names.text.strip().replace('直播中', '')
id = names.find('a')['href']
id = self.extract_middle_text(id, 'bilibili.com/', '?', 0)
pic = vod.find('img')['src']
if 'http' not in pic:
pic = "https:" + pic
remarks = vod.find('a', class_="bili-live-card__info--uname")
remark = remarks.text.strip()
video = {
"vod_id": id,
"vod_name": name,
"vod_pic": pic,
"vod_remarks": remark
}
videos.append(video)
result['list'] = videos
result['page'] = pg
result['pagecount'] = 9999
result['limit'] = 90
result['total'] = 999999
return result
def searchContent(self, key, quick, pg="1"):
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
+343
View File
@@ -0,0 +1,343 @@
# coding = utf-8
# !/usr/bin/python
"""
"""
from Crypto.Util.Padding import unpad
from Crypto.Util.Padding import pad
from urllib.parse import unquote
from Crypto.Cipher import ARC4
from urllib.parse import quote
from base.spider import Spider
from Crypto.Cipher import AES
from bs4 import BeautifulSoup
from base64 import b64decode
import urllib.request
import urllib.parse
import binascii
import requests
import base64
import json
import time
import sys
import re
import os
sys.path.append('..')
xurl = "https://app.whjzjx.cn"
headers = {
'User-Agent': 'Linux; Android 12; Pixel 3 XL) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.101 Mobile Safari/537.36'
}
headerf = {
"platform": "1",
"user_agent": "Mozilla/5.0 (Linux; Android 9; V1938T Build/PQ3A.190705.08211809; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/91.0.4472.114 Safari/537.36",
"content-type": "application/json; charset=utf-8"
}
times = int(time.time() * 1000)
data = {
"device": "2a50580e69d38388c94c93605241fb306",
"package_name": "com.jz.xydj",
"android_id": "ec1280db12795506",
"install_first_open": True,
"first_install_time": 1752505243345,
"last_update_time": 1752505243345,
"report_link_url": "",
"authorization": "",
"timestamp": times
}
plain_text = json.dumps(data, separators=(',', ':'), ensure_ascii=False)
key = "B@ecf920Od8A4df7"
key_bytes = key.encode('utf-8')
plain_bytes = plain_text.encode('utf-8')
cipher = AES.new(key_bytes, AES.MODE_ECB)
padded_data = pad(plain_bytes, AES.block_size)
ciphertext = cipher.encrypt(padded_data)
encrypted = base64.b64encode(ciphertext).decode('utf-8')
response = requests.post("https://u.shytkjgs.com/user/v3/account/login", headers=headerf, data=encrypted)
response_data = response.json()
Authorization = response_data['data']['token']
headerx = {
'authorization': Authorization,
'platform': '1',
'version_name': '3.8.3.1'
}
class Spider(Spider):
global xurl
global headerx
global headers
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": "1", "type_name": "剧场"},
{"type_id": "3", "type_name": "新剧"},
{"type_id": "2", "type_name": "热播"},
{"type_id": "7", "type_name": "星选"},
{"type_id": "5", "type_name": "阳光"}],
}
return result
def homeVideoContent(self):
videos = []
url= f'{xurl}/v1/theater/home_page?theater_class_id=1&class2_id=4&page_num=1&page_size=24'
detail = requests.get(url=url, headers=headerx)
detail.encoding = "utf-8"
if detail.status_code == 200:
data = detail.json()
for vod in data['data']['list']:
name = vod['theater']['title']
id = vod['theater']['id']
pic = vod['theater']['cover_url']
remark = vod['theater']['play_amount_str']
video = {
"vod_id": id,
"vod_name": name,
"vod_pic": pic,
"vod_remarks": remark
}
videos.append(video)
result = {'list': videos}
return result
def categoryContent(self, cid, pg, filter, ext):
result = {}
videos = []
url = f'{xurl}/v1/theater/home_page?theater_class_id={cid}&page_num={pg}&page_size=24'
detail = requests.get(url=url,headers=headerx)
detail.encoding = "utf-8"
if detail.status_code == 200:
data = detail.json()
for vod in data['data']['list']:
name = vod['theater']['title']
id = vod['theater']['id']
pic = vod['theater']['cover_url']
remark = vod['theater']['theme']
video = {
"vod_id": id,
"vod_name": name,
"vod_pic": pic,
"vod_remarks": remark
}
videos.append(video)
result = {'list': videos}
result['page'] = pg
result['pagecount'] = 9999
result['limit'] = 90
result['total'] = 999999
return result
def detailContent(self, ids):
did = ids[0]
result = {}
videos = []
xianlu = ''
bofang = ''
url = f'{xurl}/v2/theater_parent/detail?theater_parent_id={did}'
detail = requests.get(url=url, headers=headerx)
detail.encoding = "utf-8"
if detail.status_code == 200:
data = detail.json()
url = 'https://fs-im-kefu.7moor-fs1.com/ly/4d2c3f00-7d4c-11e5-af15-41bf63ae4ea0/1732707176882/jiduo.txt'
response = requests.get(url)
response.encoding = 'utf-8'
code = response.text
name = self.extract_middle_text(code, "s1='", "'", 0)
Jumps = self.extract_middle_text(code, "s2='", "'", 0)
content = '剧情:' + data['data']['introduction']
area = data['data']['desc_tags'][0]
remarks = data['data']['filing']
# 修复剧集只有一集的问题 - 检查theaters数据是否存在且不为空
if 'theaters' in data['data'] and data['data']['theaters']:
for sou in data['data']['theaters']:
id = sou['son_video_url']
name = sou['num']
bofang = bofang + str(name) + '$' + id + '#'
bofang = bofang[:-1] if bofang.endswith('#') else bofang
xianlu = '星芽'
else:
# 如果没有theaters数据,检查是否有单个视频URL
if 'video_url' in data['data'] and data['data']['video_url']:
bofang = '1$' + data['data']['video_url']
xianlu = '星芽'
else:
bofang = Jumps
xianlu = '1'
videos.append({
"vod_id": did,
"vod_content": content,
"vod_remarks": remarks,
"vod_area": area,
"vod_play_from": xianlu,
"vod_play_url": bofang
})
result['list'] = videos
return result
def playerContent(self, flag, id, vipFlags):
result = {}
result["parse"] = 0
result["playUrl"] = ''
result["url"] = id
result["header"] = headers
return result
def searchContentPage(self, key, quick, page):
result = {}
videos = []
payload = {
"text": key
}
url = f"{xurl}/v3/search"
detail = requests.post(url=url, headers=headerx, json=payload)
if detail.status_code == 200:
detail.encoding = "utf-8"
data = detail.json()
for vod in data['data']['theater']['search_data']:
name = vod['title']
id = vod['id']
pic = vod['cover_url']
remark = vod['score_str']
video = {
"vod_id": id,
"vod_name": name,
"vod_pic": pic,
"vod_remarks": remark
}
videos.append(video)
result['list'] = videos
result['page'] = page
result['pagecount'] = 9999
result['limit'] = 90
result['total'] = 999999
return result
def searchContent(self, key, quick, pg="1"):
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
+248
View File
@@ -0,0 +1,248 @@
# -*- coding: utf-8 -*-
# by @嗷呜
import random
import sys
from base64 import b64encode, b64decode
from concurrent.futures import ThreadPoolExecutor, as_completed
from urllib.parse import urlencode
sys.path.append('..')
from base.spider import Spider
class Spider(Spider):
def init(self, extend=""):
self.did = self.random_str(32)
pass
def getName(self):
pass
def isVideoFormat(self, url):
pass
def manualVideoCheck(self):
pass
def destroy(self):
pass
rhost = 'https://www.iqiyi.com'
hhost='https://mesh.if.iqiyi.com'
dhost='https://miniapp.iqiyi.com'
headers = {
'Origin': rhost,
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/132.0.0.0 Safari/537.36',
'Referer': f'{rhost}/',
}
def homeContent(self, filter):
result = {}
cateManual = {
"全部": "1009",
"电影": "1",
"剧集": "2",
"综艺": "6",
"动漫": "4",
"儿童": "15",
"微剧": "35",
"纪录片": "3"
}
classes = []
filters = {}
for k in cateManual:
classes.append({
'type_name': k,
'type_id': cateManual[k]
})
with ThreadPoolExecutor(max_workers=len(classes)) as executor:
results = executor.map(self.getf, classes)
for id, ft in results:
if len(ft):filters[id] = ft
result['class'] = classes
result['filters'] = filters
return result
def homeVideoContent(self):
data=self.fetch(f'{self.hhost}/portal/lw/v5/channel/recommend?v=13.014.21150', headers=self.headers).json()
vlist = []
for i in data['items'][1:]:
for j in i['video'][0]['data']:
id = j.get('firstId')
pic=j.get('prevue',{}).get('image_url') or j.get('album_image_url_hover')
if id and pic:
pu=j.get('prevue',{}).get('page_url') or j.get('page_url').split('?')[0]
id = f'{id}@{self.e64(pu)}'
vlist.append({
'vod_id': id,
'vod_name': j.get('display_name'),
'vod_pic': pic,
'vod_year': j.get('sns_score'),
'vod_remarks': j.get('dq_updatestatus') or j.get('rank_prefix')
})
return {'list':vlist}
def categoryContent(self, tid, pg, filter, extend):
if pg == "1":
self.sid = ''
new_data = {'mode':'24'}
for key, value in extend.items():
if value:
key_value_pairs = self.d64(value).split(',')
for pair in key_value_pairs:
k, v = pair.split('=')
if k in new_data:
new_data[k] += "," + v
else:
new_data[k] = v
path=f'/portal/lw/videolib/data?uid=&passport_id=&ret_num=60&version=13.014.21150&device_id={self.did}&channel_id={tid}&page_id={pg}&session={self.sid}&os=&conduit_id=&vip=0&auth&recent_selected_tag=&ad=%5B%7B%22lm%22:%225%22,%22ai%22:%225%22,%22fp%22:%226%22,%22sei%22:%22Sa867aa9d326e2bd8654d8c2a8636055e%22,%22position%22:%22library%22%7D%5D&adExt=%7B%22r%22:%221.2.1-ares6-pure%22%7D&dfp=a12f96215b2f7842a98c082799ca0c3d9236be00946701b106829754d8ece3aaf8&filter={urlencode(new_data)}'
data=self.fetch(f'{self.hhost}{path}', headers=self.headers).json()
self.sid = data['session']
videos = []
for i in data['data']:
id = i.get('firstId') or i.get('tv_id')
if not id:
id=i.get('play_url').split(';')[0].split('=')[-1]
if id and not i.get('h'):
id=f'{id}@{self.e64(i.get("page_url"))}'
videos.append({
'vod_id': id,
'vod_name': i.get('display_name'),
'vod_pic': i.get('album_image_url_hover'),
'vod_year': i.get('sns_score'),
'vod_remarks': i.get('dq_updatestatus') or i.get('pay_mark')
})
result = {}
result['list'] = videos
result['page'] = pg
result['pagecount'] = 9999
result['limit'] = 90
result['total'] = 999999
return result
def detailContent(self, ids):
ids = ids[0].split('@')
ids[-1] = self.d64(ids[-1])
data = self.fetch(f'{self.dhost}/h5/mina/baidu/play/body/v1/{ids[0]}/', headers=self.headers).json()
v=data['data']['playInfo']
vod = {
'vod_name': v.get('albumName'),
'type_name': v.get('tags'),
'vod_year': v.get('albumYear'),
'vod_remarks': v.get('updateStrategy'),
'vod_actor': v.get('mainActors'),
'vod_director': v.get('directors'),
'vod_content': v.get('albumDesc'),
'vod_play_from': '爱奇艺',
'vod_play_url': ''
}
if data.get('data') and data['data'].get('videoList') and data['data']['videoList'].get('videos'):
purl=[f'{i["shortTitle"]}${i["pageUrl"]}' for i in data['data']['videoList']['videos']]
pg=data['data']['videoList'].get('totalPages')
if pg and pg > 1:
id = v['albumId']
pages = list(range(2, pg + 1))
page_results = {}
with ThreadPoolExecutor(max_workers=10) as executor:
future_to_page = {
executor.submit(self.fetch_page_data, page, id): page
for page in pages
}
for future in as_completed(future_to_page):
page = future_to_page[future]
try:
result = future.result()
page_results[page] = result
except Exception as e:
print(f"Error fetching page {page}: {e}")
for page in sorted(page_results.keys()):
purl.extend(page_results[page])
vod['vod_play_url'] = '#'.join(purl)
else:
vdata=self.fetch(f'{self.dhost}/h5/mina/baidu/play/head/v1/{ids[0]}/', headers=self.headers).json()
v=vdata['data']['playInfo']
vod = {
'vod_name': v.get('shortTitle'),
'type_name': v.get('channelName'),
'vod_year': v.get('year'),
'vod_remarks': v.get('focus'),
'vod_actor': v.get('mainActors'),
'vod_director': v.get('directors'),
'vod_content': v.get('desc'),
'vod_play_from': '爱奇艺',
'vod_play_url': f'{v.get("shortTitle")}${ids[-1]}'
}
return {'list':[vod]}
def searchContent(self, key, quick, pg="1"):
data=self.fetch(f'{self.hhost}/portal/lw/search/homePageV3?key={key}&current_page={pg}&mode=1&source=input&suggest=&version=13.014.21150&pageNum={pg}&pageSize=25&pu=&u={self.did}&scale=150&token=&userVip=0&conduit=&vipType=-1&os=&osShortName=win10&dataType=&appMode=', headers=self.headers).json()
videos = []
vdata=data['data']['templates']
for i in data['data']['templates']:
if i.get('intentAlbumInfos'):
vdata=[{'albumInfo': c} for c in i['intentAlbumInfos']]+vdata
for i in vdata:
if i.get('albumInfo') and (i['albumInfo'].get('playQipuId','') or i['albumInfo'].get('qipuId')) and i['albumInfo'].get('pageUrl'):
b=i['albumInfo']
id=f"{(b.get('playQipuId','') or b.get('qipuId'))}@{self.e64(b.get('pageUrl'))}"
videos.append({
'vod_id': id,
'vod_name': b.get('title'),
'vod_pic': b.get('img'),
'vod_year': (b.get('year',{}) or {}).get('value'),
'vod_remarks': b.get('subscriptContent') or b.get('channel') or b.get('vipTips')
})
return {'list':videos,'page':pg}
def playerContent(self, flag, id, vipFlags):
return {'jx':1,'parse': 1, 'url': id, 'header': ''}
def localProxy(self, param):
pass
def fetch_page_data(self, page, id):
try:
url = f'{self.dhost}/h5/mina/avlist/{page}/{id}/'
data = self.fetch(url, headers=self.headers).json()
return [f'{i["shortTitle"]}${i["pageUrl"]}' for i in data['data']['videoList']['videos']]
except:
return []
def getf(self,body):
data=self.fetch(f'{self.hhost}/portal/lw/videolib/tag?channel_id={body["type_id"]}&tagAdd=&selected_tag_name=&version=13.014.21150&device={self.did}&uid=', headers=self.headers).json()
ft = []
# for i in data[:-1]:
for i in data:
try:
value_array = [{"n": value['text'], "v": self.e64(value['tag_param'])} for value in i['tags'] if
value.get('tag_param')]
ft.append({"key": i['group'], "name": i['group'], "value": value_array})
except:
print(i)
return (body['type_id'], ft)
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: str):
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 random_str(self,length=16):
hex_chars = '0123456789abcdef'
return ''.join(random.choice(hex_chars) for _ in range(length))
+109
View File
@@ -0,0 +1,109 @@
# -*- coding: utf-8 -*-
# by @嗷呜
import json
import sys
from pyquery import PyQuery as pq
sys.path.append('..')
from base.spider import Spider
class Spider(Spider):
def init(self, extend=""):
pass
def getName(self):
pass
def isVideoFormat(self, url):
pass
def manualVideoCheck(self):
pass
def destroy(self):
pass
host='http://www.toule.top'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36',
'Referer':f'{host}/',
'Origin':host
}
def homeContent(self, filter):
data=self.getpq()
result = {}
classes = []
for k in data('.swiper-wrapper .swiper-slide').items():
classes.append({
'type_name': k.text(),
'type_id': k.text()
})
result['class'] = classes
result['list'] = self.getlist(data('.container.items ul li'))
return result
def homeVideoContent(self):
pass
def categoryContent(self, tid, pg, filter, extend):
data=self.getpq(f"/index.php/vod/show/class/{tid}/id/1/page/{pg}.html")
result = {}
result['list'] = self.getlist(data('.container.items ul li'))
result['page'] = pg
result['pagecount'] = 9999
result['limit'] = 90
result['total'] = 999999
return result
def detailContent(self, ids):
data=self.getpq(ids[0])
v=data('.container.detail-content')
vod = {
'vod_remarks': v('.items-tags a').text(),
'vod_content': v('.text-content .detail').text(),
'vod_play_from': '爱看短剧',
'vod_play_url': '#'.join([f"{i.text()}${i('a').attr('href')}" for i in data('.swiper-wrapper .swiper-slide').items()])
}
return {'list':[vod]}
def searchContent(self, key, quick, pg="1"):
data=self.getpq(f"/index.php/vod/search/page/{pg}/wd/{key}.html")
return {'list':self.getlist(data('.container.items ul li')),'page':pg}
def playerContent(self, flag, id, vipFlags):
data=self.getpq(id)
try:
jstr=data('.player-content script').eq(0).text()
jt=json.loads(jstr.split('=',1)[-1])
p,url=0,jt['url']
except Exception as e:
print(f"获取播放地址失败: {e}")
p,url=1,f'{self.host}{id}'
return {'parse': p, 'url': url, 'header': self.headers}
def localProxy(self, param):
pass
def liveContent(self, url):
pass
def getpq(self, path=''):
data=self.fetch(f"{self.host}{path}",headers=self.headers).text
try:
return pq(data)
except Exception as e:
print(f"{str(e)}")
return pq(data.encode('utf-8'))
def getlist(self,data):
videos = []
for i in data.items():
videos.append({
'vod_id': i('.image-line').attr('href'),
'vod_name': i('img').attr('alt'),
'vod_pic': i('img').attr('src'),
'vod_remarks': i('.remarks.light').text()
})
return videos
+279
View File
@@ -0,0 +1,279 @@
# coding=utf-8
# !/usr/bin/python
# by嗷呜(finally)
import sys
import os
sys.path.append("..")
import re
import hashlib
import hmac
import random
import string
from Crypto.Util.Padding import unpad
from concurrent.futures import ThreadPoolExecutor
from Crypto.PublicKey import RSA
from Crypto.Cipher import PKCS1_v1_5, AES
from base64 import b64encode, b64decode
import json
import time
from base.spider import Spider
class Spider(Spider):
def getName(self):
return "电影猎手"
def init(self, extend=""):
self.device = self.device_id()
self.host = self.gethost()
pass
def isVideoFormat(self, url):
pass
def manualVideoCheck(self):
pass
def action(self, action):
pass
def destroy(self):
pass
t = str(int(time.time()))
def homeContent(self, filter):
result = {}
filters = {}
classes = []
bba = self.url()
data = self.fetch(f"{self.host}/api/v1/app/config?pack={bba[0]}&signature={bba[1]}", headers=self.header()).text
data1 = self.aes(data)
dy = {"class":"类型","area":"地区","lang":"语言","year":"年份","letter":"字母","by":"排序","sort":"排序"}
data1['data']['movie_screen']['sort'].pop(0)
for item in data1['data']['movie_screen']['sort']:
item['n'] = item.pop('name')
item['v'] = item.pop('value')
for item in data1['data']['movie_screen']['filter']:
has_non_empty_field = False
classes.append({"type_name": item["name"], "type_id": str(item["id"])})
for key in dy:
if key in item and item[key]:
has_non_empty_field = True
break
if has_non_empty_field:
filters[str(item["id"])] = []
filters[str(item["id"])].append(
{"key": 'sort', "name": '排序', "value": data1['data']['movie_screen']['sort']})
for dkey in item:
if dkey in dy and item[dkey]:
item[dkey].pop(0)
value_array = [
{"n": value.strip(), "v": value.strip()}
for value in item[dkey]
if value.strip() != ""
]
filters[str(item["id"])].append(
{"key": dkey, "name": dy[dkey], "value": value_array}
)
result["class"] = classes
result["filters"] = filters
return result
def homeVideoContent(self):
bba = self.url()
url = f'{self.host}/api/v1/movie/index_recommend?pack={bba[0]}&signature={bba[1]}'
data = self.fetch(url, headers=self.header()).json()
videos = []
for item in data['data']:
if len(item['list']) > 0:
for it in item['list']:
try:
videos.append(self.voides(it))
except Exception as e:
continue
result = {"list": videos}
return result
def categoryContent(self, tid, pg, filter, extend):
body = {"type_id": tid, "sort": extend.get("sort", "by_default"), "class": extend.get("class", "类型"),
"area": extend.get("area", "地区"), "year": extend.get("year", "年份"), "page": str(pg),
"pageSize": "21"}
result = {}
list = []
bba = self.url(body)
url = f"{self.host}/api/v1/movie/screen/list?pack={bba[0]}&signature={bba[1]}"
data = self.fetch(url, headers=self.header()).json()['data']['list']
for item in data:
list.append(self.voides(item))
result["list"] = list
result["page"] = pg
result["pagecount"] = 9999
result["limit"] = 90
result["total"] = 999999
return result
def detailContent(self, ids):
body = {"id": ids[0]}
bba = self.url(body)
url = f'{self.host}/api/v1/movie/detail?pack={bba[0]}&signature={bba[1]}'
data = self.fetch(url, headers=self.header()).json()['data']
video = {'vod_name': data.get('name'),'type_name': data.get('type_name'),'vod_year': data.get('year'),'vod_area': data.get('area'),'vod_remarks': data.get('dynami'),'vod_content': data.get('content')}
play = []
names = []
tasks = []
for itt in data["play_from"]:
name = itt["name"]
a = []
if len(itt["list"]) > 0:
names.append(name)
play.append(self.playeach(itt['list']))
else:
tasks.append({"movie_id": ids[0], "from_code": itt["code"]})
names.append(name)
if tasks:
with ThreadPoolExecutor(max_workers=len(tasks)) as executor:
results = executor.map(self.playlist, tasks)
for result in results:
if result:
play.append(result)
else:
play.append("")
video["vod_play_from"] = "$$$".join(names)
video["vod_play_url"] = "$$$".join(play)
result = {"list": [video]}
return result
def searchContent(self, key, quick, pg=1):
body = {"keyword": key, "sort": "", "type_id": "0", "page": str(pg), "pageSize": "10",
"res_type": "by_movie_name"}
bba = self.url(body)
url = f"{self.host}/api/v1/movie/search?pack={bba[0]}&signature={bba[1]}"
data = self.fetch(url, headers=self.header()).json()['data'].get('list')
videos = []
for it in data:
try:
videos.append(self.voides(it))
except Exception as e:
continue
result = {"list": videos, "page": pg}
return result
def playerContent(self, flag, id, vipFlags):
url = id
if "m3u8" not in url and "mp4" not in url:
try:
add = id.split('|||')
data = {"from_code": add[0], "play_url": add[1], "episode_id": add[2], "type": "play"}
bba = self.url(data)
data2 = self.fetch(f"{self.host}/api/v1/movie_addr/parse_url?pack={bba[0]}&signature={bba[1]}",
headers=self.header()).json()['data']
url = data2.get('play_url') or data2.get('download_url')
try:
url1 = self.fetch(url, headers=self.header(), allow_redirects=False).headers['Location']
if url1 and "http" in url1:
url = url1
except:
pass
except Exception as e:
pass
if '.jpg' in url or '.jpeg' in url or '.png' in url:
url = self.getProxyUrl() + "&url=" + b64encode(url.encode('utf-8')).decode('utf-8') + "&type=m3u8"
result = {}
result["parse"] = 0
result["url"] = url
result["header"] = {'user-agent': 'okhttp/4.9.2'}
return result
def localProxy(self, param):
url = b64decode(param["url"]).decode('utf-8')
durl = url[:url.rfind('/')]
data = self.fetch(url, headers=self.header()).content.decode("utf-8")
lines = data.strip().split('\n')
for index, string in enumerate(lines):
# if 'URI="' in string and 'http' not in string:
# lines[index] = index
# 暂时预留,貌似用不到
if '#EXT' not in string and 'http' not in string:
lines[index] = durl + ('' if string.startswith('/') else '/') + string
data = '\n'.join(lines)
return [200, "application/vnd.apple.mpegur", data]
def device_id(self):
characters = string.ascii_lowercase + string.digits
random_string = ''.join(random.choices(characters, k=32))
return random_string
def gethost(self):
headers = {
'User-Agent': 'okhttp/4.9.2',
'Connection': 'Keep-Alive',
}
response = self.fetch('https://app-site.ecoliving168.com/domain_v5.json', headers=headers).json()
url = response['api_service'].replace('/api/', '')
return url
def header(self):
headers = {
'User-Agent': 'Android',
'Accept': 'application/prs.55App.v2+json',
'timestamp': self.t,
'x-client-setting': '{"pure-mode":1}',
'x-client-uuid': '{"device_id":' + self.device + '}, "type":1,"brand":"Redmi", "model":"M2012K10C", "system_version":30, "sdk_version":"3.1.0.7"}',
'x-client-version': '3096 '
}
return headers
def url(self, id=None):
if not id:
id = {}
id["timestamp"] = self.t
public_key = 'MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEA02F/kPg5A2NX4qZ5JSns+bjhVMCC6JbTiTKpbgNgiXU+Kkorg6Dj76gS68gB8llhbUKCXjIdygnHPrxVHWfzmzisq9P9awmXBkCk74Skglx2LKHa/mNz9ivg6YzQ5pQFUEWS0DfomGBXVtqvBlOXMCRxp69oWaMsnfjnBV+0J7vHbXzUIkqBLdXSNfM9Ag5qdRDrJC3CqB65EJ3ARWVzZTTcXSdMW9i3qzEZPawPNPe5yPYbMZIoXLcrqvEZnRK1oak67/ihf7iwPJqdc+68ZYEmmdqwunOvRdjq89fQMVelmqcRD9RYe08v+xDxG9Co9z7hcXGTsUquMxkh29uNawIDAQAB'
encrypted_text = json.dumps(id)
public_key = RSA.import_key(b64decode(public_key))
cipher = PKCS1_v1_5.new(public_key)
encrypted_message = cipher.encrypt(encrypted_text.encode('utf-8'))
encrypted_message_base64 = b64encode(encrypted_message).decode('utf-8')
result = encrypted_message_base64.replace('+', '-').replace('/', '_').replace('=', '')
key = '635a580fcb5dc6e60caa39c31a7bde48'
sign = hmac.new(key.encode(), result.encode(), hashlib.md5).hexdigest()
return result, sign
def playlist(self, body):
try:
bba = self.url(body)
url = f'{self.host}/api/v1/movie_addr/list?pack={bba[0]}&signature={bba[1]}'
data = self.fetch(url, headers=self.header()).json()['data']
return self.playeach(data)
except Exception:
return []
def playeach(self,data):
play_urls = []
for it in data:
if re.search(r"mp4|m3u8", it["play_url"]):
play_urls.append(f"{it['episode_name']}${it['play_url']}")
else:
play_urls.append(
f"{it['episode_name']}${it['from_code']}|||{it['play_url']}|||{it['episode_id']}"
)
return '#'.join(play_urls)
def voides(self, item):
if item['name'] or item['title']:
voide = {
"vod_id": item.get('id') or item.get('click'),
'vod_name': item.get('name') or item.get('title'),
'vod_pic': item.get('cover') or item.get('image'),
'vod_year': item.get('year') or item.get('label'),
'vod_remarks': item.get('dynamic') or item.get('sub_title')
}
return voide
def aes(self, text):
text = text.replace('-', '+').replace('_', '/') + '=='
key = b"e6d5de5fcc51f53d"
iv = b"2f13eef7dfc6c613"
cipher = AES.new(key, AES.MODE_CBC, iv)
pt = unpad(cipher.decrypt(b64decode(text)), AES.block_size).decode("utf-8")
return json.loads(pt)
+156
View File
@@ -0,0 +1,156 @@
# -*- coding: utf-8 -*-
# by @嗷呜
import sys
sys.path.append('..')
from base.spider import Spider
class Spider(Spider):
def init(self, extend=""):
pass
def getName(self):
return "甜圈短剧"
def isVideoFormat(self, url):
return True
def manualVideoCheck(self):
return False
def destroy(self):
pass
# 更新为新的域名
ahost = 'https://mov.cenguigui.cn'
headers = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/134.0.0.0 Safari/537.36',
'sec-ch-ua-platform': '"macOS"',
'sec-ch-ua': '"Not/A)Brand";v="8", "Chromium";v="134", "Google Chrome";v="134"',
'DNT': '1',
'sec-ch-ua-mobile': '?0',
'Sec-Fetch-Site': 'cross-site',
'Sec-Fetch-Mode': 'no-cors',
'Sec-Fetch-Dest': 'video',
'Sec-Fetch-Storage-Access': 'active',
'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
}
def homeContent(self, filter):
result = {'class': [{'type_id': '推荐榜', 'type_name': '🔥 推荐榜'},
{'type_id': '新剧', 'type_name': '🎬 新剧'},
{'type_id': '逆袭', 'type_name': '🎬 逆袭'},
{'type_id': '霸总', 'type_name': '🎬 霸总'},
{'type_id': '现代言情', 'type_name': '🎬 现代言情'},
{'type_id': '打脸虐渣', 'type_name': '🎬 打脸虐渣'},
{'type_id': '豪门恩怨', 'type_name': '🎬 豪门恩怨'},
{'type_id': '神豪', 'type_name': '🎬 神豪'},
{'type_id': '马甲', 'type_name': '🎬 马甲'},
{'type_id': '都市日常', 'type_name': '🎬 都市日常'},
{'type_id': '战神归来', 'type_name': '🎬 战神归来'},
{'type_id': '小人物', 'type_name': '🎬 小人物'},
{'type_id': '女性成长', 'type_name': '🎬 女性成长'},
{'type_id': '大女主', 'type_name': '🎬 大女主'},
{'type_id': '穿越', 'type_name': '🎬 穿越'},
{'type_id': '都市修仙', 'type_name': '🎬 都市修仙'},
{'type_id': '强者回归', 'type_name': '🎬 强者回归'},
{'type_id': '亲情', 'type_name': '🎬 亲情'},
{'type_id': '古装', 'type_name': '🎬 古装'},
{'type_id': '重生', 'type_name': '🎬 重生'},
{'type_id': '闪婚', 'type_name': '🎬 闪婚'},
{'type_id': '赘婿逆袭', 'type_name': '🎬 赘婿逆袭'},
{'type_id': '虐恋', 'type_name': '🎬 虐恋'},
{'type_id': '追妻', 'type_name': '🎬 追妻'},
{'type_id': '天下无敌', 'type_name': '🎬 天下无敌'},
{'type_id': '家庭伦理', 'type_name': '🎬 家庭伦理'},
{'type_id': '萌宝', 'type_name': '🎬 萌宝'},
{'type_id': '古风权谋', 'type_name': '🎬 古风权谋'},
{'type_id': '职场', 'type_name': '🎬 职场'},
{'type_id': '奇幻脑洞', 'type_name': '🎬 奇幻脑洞'},
{'type_id': '异能', 'type_name': '🎬 异能'},
{'type_id': '无敌神医', 'type_name': '🎬 无敌神医'},
{'type_id': '古风言情', 'type_name': '🎬 古风言情'},
{'type_id': '传承觉醒', 'type_name': '🎬 传承觉醒'},
{'type_id': '现言甜宠', 'type_name': '🎬 现言甜宠'},
{'type_id': '奇幻爱情', 'type_name': '🎬 奇幻爱情'},
{'type_id': '乡村', 'type_name': '🎬 乡村'},
{'type_id': '历史古代', 'type_name': '🎬 历史古代'},
{'type_id': '王妃', 'type_name': '🎬 王妃'},
{'type_id': '高手下山', 'type_name': '🎬 高手下山'},
{'type_id': '娱乐圈', 'type_name': '🎬 娱乐圈'},
{'type_id': '强强联合', 'type_name': '🎬 强强联合'},
{'type_id': '破镜重圆', 'type_name': '🎬 破镜重圆'},
{'type_id': '暗恋成真', 'type_name': '🎬 暗恋成真'},
{'type_id': '民国', 'type_name': '🎬 民国'},
{'type_id': '欢喜冤家', 'type_name': '🎬 欢喜冤家'},
{'type_id': '系统', 'type_name': '🎬 系统'},
{'type_id': '真假千金', 'type_name': '🎬 真假千金'},
{'type_id': '龙王', 'type_name': '🎬 龙王'},
{'type_id': '校园', 'type_name': '🎬 校园'},
{'type_id': '穿书', 'type_name': '🎬 穿书'},
{'type_id': '女帝', 'type_name': '🎬 女帝'},
{'type_id': '团宠', 'type_name': '🎬 团宠'},
{'type_id': '年代爱情', 'type_name': '🎬 年代爱情'},
{'type_id': '玄幻仙侠', 'type_name': '🎬 玄幻仙侠'},
{'type_id': '青梅竹马', 'type_name': '🎬 青梅竹马'},
{'type_id': '悬疑推理', 'type_name': '🎬 悬疑推理'},
{'type_id': '皇后', 'type_name': '🎬 皇后'},
{'type_id': '替身', 'type_name': '🎬 替身'},
{'type_id': '大叔', 'type_name': '🎬 大叔'},
{'type_id': '喜剧', 'type_name': '🎬 喜剧'},
{'type_id': '剧情', 'type_name': '🎬 剧情'}]}
return result
def homeVideoContent(self):
return []
def categoryContent(self, tid, pg, filter, extend):
params = {
'classname': tid,
'offset': str((int(pg) - 1)),
}
# 更新请求路径为 /duanju/api.php
data = self.fetch(f'{self.ahost}/duanju/api.php', params=params, headers=self.headers).json()
videos = []
for k in data['data']:
videos.append({
'vod_id': k.get('book_id'),
'vod_name': k.get('title'),
'vod_pic': k.get('cover'),
'vod_year': k.get('score'),
'vod_remarks': f"{k.get('sub_title')}|{k.get('episode_cnt')}"
})
result = {}
result['list'] = videos
result['page'] = pg
result['pagecount'] = 9999
result['limit'] = 90
result['total'] = 999999
return result
def detailContent(self, ids):
# 更新请求路径为 /duanju/api.php
v = self.fetch(f'{self.ahost}/duanju/api.php', params={'book_id': ids[0]}, headers=self.headers).json()
vod = {
'vod_id': ids[0],
'vod_name': v.get('title'),
'type_name': v.get('category'),
'vod_year': v.get('time'),
'vod_remarks': v.get('duration'),
'vod_content': v.get('desc'),
'vod_play_from': '爱看短剧',
'vod_play_url': '#'.join([f"{i['title']}${i['video_id']}" for i in v['data']])
}
return {'list': [vod]}
def searchContent(self, key, quick, pg="1"):
return self.categoryContent(key, pg, True, {})
def playerContent(self, flag, id, vipFlags):
# 更新请求路径为 /duanju/api.php
data = self.fetch(f'{self.ahost}/duanju/api.php', params={'video_id': id}, headers=self.headers).json()
return {'parse': 0, 'url': data['data']['url'], 'header': self.headers}
def localProxy(self, param):
pass
+767
View File
@@ -0,0 +1,767 @@
# -*- coding: utf-8 -*-
# by @嗷呜
import json
import re
import sys
import time
from base64 import b64decode, b64encode
from urllib.parse import parse_qs
import requests
from pyquery import PyQuery as pq
sys.path.append('..')
from base.spider import Spider
from concurrent.futures import ThreadPoolExecutor
class Spider(Spider):
def init(self, extend=""):
tid = 'douyin'
headers = self.gethr(0, tid)
response = requests.head(self.hosts[tid], headers=headers)
ttwid = response.cookies.get('ttwid')
headers.update({
'authority': self.hosts[tid].split('//')[-1],
'cookie': f'ttwid={ttwid}' if ttwid else ''
})
self.dyheaders = headers
pass
def getName(self):
pass
def isVideoFormat(self, url):
pass
def manualVideoCheck(self):
pass
def destroy(self):
pass
headers = [
{
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36 Edg/126.0.0.0"
},
{
"User-Agent": "Dart/3.4 (dart:io)"
}
]
excepturl = 'https://www.baidu.com'
hosts = {
"huya": ["https://www.huya.com","https://mp.huya.com"],
"douyin": "https://live.douyin.com",
"douyu": "https://www.douyu.com",
"wangyi": "https://cc.163.com",
"bili": ["https://api.live.bilibili.com", "https://api.bilibili.com"]
}
referers = {
"huya": "https://live.cdn.huya.com",
"douyin": "https://live.douyin.com",
"douyu": "https://m.douyu.com",
"bili": "https://live.bilibili.com"
}
playheaders = {
"wangyi": {
"User-Agent": "ExoPlayer",
"Connection": "Keep-Alive",
"Icy-MetaData": "1"
},
"bili": {
'Accept': '*/*',
'Icy-MetaData': '1',
'referer': referers['bili'],
'user-agent': headers[0]['User-Agent']
},
'douyin': {
'User-Agent': 'libmpv',
'Icy-MetaData': '1'
},
'huya': {
'User-Agent': 'ExoPlayer',
'Connection': 'Keep-Alive',
'Icy-MetaData': '1'
},
'douyu': {
'User-Agent': 'libmpv',
'Icy-MetaData': '1'
}
}
def process_bili(self):
try:
self.blfdata = self.fetch(
f'{self.hosts["bili"][0]}/room/v1/Area/getList?need_entrance=1&parent_id=0',
headers=self.gethr(0, 'bili')
).json()
return ('bili', [{'key': 'cate', 'name': '分类',
'value': [{'n': i['name'], 'v': str(i['id'])}
for i in self.blfdata['data']]}])
except Exception as e:
print(f"bili处理错误: {e}")
return 'bili', None
def process_douyin(self):
try:
data = self.getpq(self.hosts['douyin'], headers=self.dyheaders)('script')
for i in data.items():
if 'categoryData' in i.text():
content = i.text()
start = content.find('{')
end = content.rfind('}') + 1
if start != -1 and end != -1:
json_str = content[start:end]
json_str = json_str.replace('\\"', '"')
try:
self.dyifdata = json.loads(json_str)
return ('douyin', [{'key': 'cate', 'name': '分类',
'value': [{'n': i['partition']['title'],
'v': f"{i['partition']['id_str']}@@{i['partition']['title']}"}
for i in self.dyifdata['categoryData']]}])
except json.JSONDecodeError as e:
print(f"douyin解析错误: {e}")
return 'douyin', None
except Exception as e:
print(f"douyin请求或处理错误: {e}")
return 'douyin', None
def process_douyu(self):
try:
self.dyufdata = self.fetch(
f'{self.referers["douyu"]}/api/cate/list',
headers=self.headers[1]
).json()
return ('douyu', [{'key': 'cate', 'name': '分类',
'value': [{'n': i['cate1Name'], 'v': str(i['cate1Id'])}
for i in self.dyufdata['data']['cate1Info']]}])
except Exception as e:
print(f"douyu错误: {e}")
return 'douyu', None
def homeContent(self, filter):
result = {}
cateManual = {
"虎牙": "huya",
"抖音": "douyin",
"斗鱼": "douyu",
"网易": "wangyi"
}
classes = []
filters = {
'huya': [{'key': 'cate', 'name': '分类',
'value': [{'n': '网游', 'v': '1'}, {'n': '单机', 'v': '2'},
{'n': '娱乐', 'v': '8'}, {'n': '手游', 'v': '3'}]}]
}
with ThreadPoolExecutor(max_workers=3) as executor:
futures = {
executor.submit(self.process_bili): 'bili',
executor.submit(self.process_douyin): 'douyin',
executor.submit(self.process_douyu): 'douyu'
}
for future in futures:
platform, filter_data = future.result()
if filter_data:
filters[platform] = filter_data
for k in cateManual:
classes.append({
'type_name': k,
'type_id': cateManual[k]
})
result['class'] = classes
result['filters'] = filters
return result
def homeVideoContent(self):
pass
def categoryContent(self, tid, pg, filter, extend):
vdata = []
result = {}
pagecount = 9999
result['page'] = pg
result['limit'] = 90
result['total'] = 999999
if tid == 'wangyi':
vdata, pagecount = self.wyccContent(tid, pg, filter, extend, vdata)
elif 'bili' in tid:
vdata, pagecount = self.biliContent(tid, pg, filter, extend, vdata)
elif 'huya' in tid:
vdata, pagecount = self.huyaContent(tid, pg, filter, extend, vdata)
elif 'douyin' in tid:
vdata, pagecount = self.douyinContent(tid, pg, filter, extend, vdata)
elif 'douyu' in tid:
vdata, pagecount = self.douyuContent(tid, pg, filter, extend, vdata)
result['list'] = vdata
result['pagecount'] = pagecount
return result
def wyccContent(self, tid, pg, filter, extend, vdata):
params = {
'format': 'json',
'start': (int(pg) - 1) * 20,
'size': '20',
}
response = self.fetch(f'{self.hosts[tid]}/api/category/live/', params=params, headers=self.headers[0]).json()
for i in response['lives']:
if i.get('cuteid'):
bvdata = self.buildvod(
vod_id=f"{tid}@@{i['cuteid']}",
vod_name=i.get('title'),
vod_pic=i.get('cover'),
vod_remarks=i.get('nickname'),
style={"type": "rect", "ratio": 1.33}
)
vdata.append(bvdata)
return vdata, 9999
def biliContent(self, tid, pg, filter, extend, vdata):
if extend.get('cate') and pg == '1' and 'click' not in tid:
for i in self.blfdata['data']:
if str(i['id']) == extend['cate']:
for j in i['list']:
v = self.buildvod(
vod_id=f"click_{tid}@@{i['id']}@@{j['id']}",
vod_name=j.get('name'),
vod_pic=j.get('pic'),
vod_tag=1,
style={"type": "oval", "ratio": 1}
)
vdata.append(v)
return vdata, 1
else:
path = f'/xlive/web-interface/v1/second/getListByArea?platform=web&sort=online&page_size=30&page={pg}'
if 'click' in tid:
ids = tid.split('_')[1].split('@@')
tid = ids[0]
path = f'/xlive/web-interface/v1/second/getList?platform=web&parent_area_id={ids[1]}&area_id={ids[-1]}&sort_type=&page={pg}'
data = self.fetch(f'{self.hosts[tid][0]}{path}', headers=self.gethr(0, tid)).json()
for i in data['data']['list']:
if i.get('roomid'):
data = self.buildvod(
f"{tid}@@{i['roomid']}",
i.get('title'),
i.get('cover'),
i.get('watched_show', {}).get('text_large'),
0,
i.get('uname'),
style={"type": "rect", "ratio": 1.33}
)
vdata.append(data)
return vdata, 9999
def huyaContent(self, tid, pg, filter, extend, vdata):
if extend.get('cate') and pg == '1' and 'click' not in tid:
id = extend.get('cate')
data = self.fetch(f'{self.referers[tid]}/liveconfig/game/bussLive?bussType={id}',
headers=self.headers[1]).json()
for i in data['data']:
v = self.buildvod(
vod_id=f"click_{tid}@@{int(i['gid'])}",
vod_name=i.get('gameFullName'),
vod_pic=f'https://huyaimg.msstatic.com/cdnimage/game/{int(i["gid"])}-MS.jpg',
vod_tag=1,
style={"type": "oval", "ratio": 1}
)
vdata.append(v)
return vdata, 1
else:
gid = ''
if 'click' in tid:
ids = tid.split('_')[1].split('@@')
tid = ids[0]
gid = f'&gameId={ids[1]}'
data = self.fetch(f'{self.hosts[tid][0]}/cache.php?m=LiveList&do=getLiveListByPage&tagAll=0{gid}&page={pg}',
headers=self.headers[1]).json()
for i in data['data']['datas']:
if i.get('profileRoom'):
v = self.buildvod(
f"{tid}@@{i['profileRoom']}",
i.get('introduction'),
i.get('screenshot'),
str(int(i.get('totalCount', '1')) / 10000) + '',
0,
i.get('nick'),
style={"type": "rect", "ratio": 1.33}
)
vdata.append(v)
return vdata, 9999
def douyinContent(self, tid, pg, filter, extend, vdata):
if extend.get('cate') and pg == '1' and 'click' not in tid:
ids = extend.get('cate').split('@@')
for i in self.dyifdata['categoryData']:
c = i['partition']
if c['id_str'] == ids[0] and c['title'] == ids[1]:
vlist = i['sub_partition'].copy()
vlist.insert(0, {'partition': c})
for j in vlist:
j = j['partition']
v = self.buildvod(
vod_id=f"click_{tid}@@{j['id_str']}@@{j['type']}",
vod_name=j.get('title'),
vod_pic='https://p3-pc-weboff.byteimg.com/tos-cn-i-9r5gewecjs/pwa_v3/512x512-1.png',
vod_tag=1,
style={"type": "oval", "ratio": 1}
)
vdata.append(v)
return vdata, 1
else:
path = f'/webcast/web/partition/detail/room/?aid=6383&app_name=douyin_web&live_id=1&device_platform=web&count=15&offset={(int(pg) - 1) * 15}&partition=720&partition_type=1'
if 'click' in tid:
ids = tid.split('_')[1].split('@@')
tid = ids[0]
path = f'/webcast/web/partition/detail/room/?aid=6383&app_name=douyin_web&live_id=1&device_platform=web&count=15&offset={(int(pg) - 1) * 15}&partition={ids[1]}&partition_type={ids[-1]}&req_from=2'
data = self.fetch(f'{self.hosts[tid]}{path}', headers=self.dyheaders).json()
for i in data['data']['data']:
v = self.buildvod(
vod_id=f"{tid}@@{i['web_rid']}",
vod_name=i['room'].get('title'),
vod_pic=i['room']['cover'].get('url_list')[0],
vod_year=i.get('user_count_str'),
vod_remarks=i['room']['owner'].get('nickname'),
style={"type": "rect", "ratio": 1.33}
)
vdata.append(v)
return vdata, 9999
def douyuContent(self, tid, pg, filter, extend, vdata):
if extend.get('cate') and pg == '1' and 'click' not in tid:
for i in self.dyufdata['data']['cate2Info']:
if str(i['cate1Id']) == extend['cate']:
v = self.buildvod(
vod_id=f"click_{tid}@@{i['cate2Id']}",
vod_name=i.get('cate2Name'),
vod_pic=i.get('icon'),
vod_remarks=i.get('count'),
vod_tag=1,
style={"type": "oval", "ratio": 1}
)
vdata.append(v)
return vdata, 1
else:
path = f'/japi/weblist/apinc/allpage/6/{pg}'
if 'click' in tid:
ids = tid.split('_')[1].split('@@')
tid = ids[0]
path = f'/gapi/rkc/directory/mixList/2_{ids[1]}/{pg}'
url = f'{self.hosts[tid]}{path}'
data = self.fetch(url, headers=self.headers[1]).json()
for i in data['data']['rl']:
v = self.buildvod(
vod_id=f"{tid}@@{i['rid']}",
vod_name=i.get('rn'),
vod_pic=i.get('rs16'),
vod_year=str(int(i.get('ol', 1)) / 10000) + '',
vod_remarks=i.get('nn'),
style={"type": "rect", "ratio": 1.33}
)
vdata.append(v)
return vdata, 9999
def detailContent(self, ids):
ids = ids[0].split('@@')
if ids[0] == 'wangyi':
vod = self.wyccDetail(ids)
elif ids[0] == 'bili':
vod = self.biliDetail(ids)
elif ids[0] == 'huya':
vod = self.huyaDetail(ids)
elif ids[0] == 'douyin':
vod = self.douyinDetail(ids)
elif ids[0] == 'douyu':
vod = self.douyuDetail(ids)
return {'list': [vod]}
def wyccDetail(self, ids):
try:
vdata = self.getpq(f'{self.hosts[ids[0]]}/{ids[1]}', self.headers[0])('script').eq(-1).text()
def get_quality_name(vbr):
if vbr <= 600:
return "标清"
elif vbr <= 1000:
return "高清"
elif vbr <= 2000:
return "超清"
else:
return "蓝光"
data = json.loads(vdata)['props']['pageProps']['roomInfoInitData']
name = data['live'].get('title', ids[0])
vod = self.buildvod(vod_name=data.get('keywords_suffix'), vod_remarks=data['live'].get('title'),
vod_content=data.get('description_suffix'))
resolution_data = data['live']['quickplay']['resolution']
all_streams = {}
sorted_qualities = sorted(resolution_data.items(),
key=lambda x: x[1]['vbr'],
reverse=True)
for quality, data in sorted_qualities:
vbr = data['vbr']
quality_name = get_quality_name(vbr)
for cdn_name, url in data['cdn'].items():
if cdn_name not in all_streams and type(url) == str and url.startswith('http'):
all_streams[cdn_name] = []
if isinstance(url, str) and url.startswith('http'):
all_streams[cdn_name].extend([quality_name, url])
plists = []
names = []
for i, (cdn_name, stream_list) in enumerate(all_streams.items(), 1):
names.append(f'线路{i}')
pstr = f"{name}${ids[0]}@@{self.e64(json.dumps(stream_list))}"
plists.append(pstr)
vod['vod_play_from'] = "$$$".join(names)
vod['vod_play_url'] = "$$$".join(plists)
return vod
except Exception as e:
return self.handle_exception(e)
def biliDetail(self, ids):
try:
vdata = self.fetch(
f'{self.hosts[ids[0]][0]}/xlive/web-room/v1/index/getInfoByRoom?room_id={ids[1]}&wts={int(time.time())}',
headers=self.gethr(0, ids[0])).json()
v = vdata['data']['room_info']
vod = self.buildvod(
vod_name=v.get('title'),
type_name=v.get('parent_area_name') + '/' + v.get('area_name'),
vod_remarks=v.get('tags'),
vod_play_from=v.get('title'),
)
data = self.fetch(
f'{self.hosts[ids[0]][0]}/xlive/web-room/v2/index/getRoomPlayInfo?room_id={ids[1]}&protocol=0%2C1&format=0%2C1%2C2&codec=0%2C1&platform=web',
headers=self.gethr(0, ids[0])).json()
vdnams = data['data']['playurl_info']['playurl']['g_qn_desc']
all_accept_qns = []
streams = data['data']['playurl_info']['playurl']['stream']
for stream in streams:
for format_item in stream['format']:
for codec in format_item['codec']:
if 'accept_qn' in codec:
all_accept_qns.append(codec['accept_qn'])
max_accept_qn = max(all_accept_qns, key=len) if all_accept_qns else []
quality_map = {
item['qn']: item['desc']
for item in vdnams
}
quality_names = [f"{quality_map.get(qn)}${ids[0]}@@{ids[1]}@@{qn}" for qn in max_accept_qn]
vod['vod_play_url'] = "#".join(quality_names)
return vod
except Exception as e:
return self.handle_exception(e)
def huyaDetail(self, ids):
try:
vdata = self.fetch(f'{self.hosts[ids[0]][1]}/cache.php?m=Live&do=profileRoom&roomid={ids[1]}',
headers=self.headers[0]).json()
v = vdata['data']['liveData']
vod = self.buildvod(
vod_name=v.get('introduction'),
type_name=v.get('gameFullName'),
vod_director=v.get('nick'),
vod_remarks=v.get('contentIntro'),
)
data = dict(reversed(list(vdata['data']['stream'].items())))
names = []
plist = []
for stream_type, stream_data in data.items():
if isinstance(stream_data, dict) and 'multiLine' in stream_data and 'rateArray' in stream_data:
names.append(f"线路{len(names) + 1}")
qualities = sorted(
stream_data['rateArray'],
key=lambda x: (x['iBitRate'], x['sDisplayName']),
reverse=True
)
cdn_urls = []
for cdn in stream_data['multiLine']:
quality_urls = []
for quality in qualities:
quality_name = quality['sDisplayName']
bit_rate = quality['iBitRate']
base_url = cdn['url']
if bit_rate > 0:
if '.m3u8' in base_url:
new_url = base_url.replace(
'ratio=2000',
f'ratio={bit_rate}'
)
else:
new_url = base_url.replace(
'imgplus.flv',
f'imgplus_{bit_rate}.flv'
)
else:
new_url = base_url
quality_urls.extend([quality_name, new_url])
encoded_urls = self.e64(json.dumps(quality_urls))
cdn_urls.append(f"{cdn['cdnType']}${ids[0]}@@{encoded_urls}")
if cdn_urls:
plist.append('#'.join(cdn_urls))
vod['vod_play_from'] = "$$$".join(names)
vod['vod_play_url'] = "$$$".join(plist)
return vod
except Exception as e:
return self.handle_exception(e)
def douyinDetail(self, ids):
url = f'{self.hosts[ids[0]]}/webcast/room/web/enter/?aid=6383&app_name=douyin_web&live_id=1&device_platform=web&enter_from=web_live&web_rid={ids[1]}&room_id_str=&enter_source=&Room-Enter-User-Login-Ab=0&is_need_double_stream=false&cookie_enabled=true&screen_width=1980&screen_height=1080&browser_language=zh-CN&browser_platform=Win32&browser_name=Edge&browser_version=125.0.0.0'
data = self.fetch(url, headers=self.dyheaders).json()
try:
vdata = data['data']['data'][0]
vod = self.buildvod(
vod_name=vdata['title'],
vod_remarks=vdata['user_count_str'],
)
resolution_data = vdata['stream_url']['live_core_sdk_data']['pull_data']['options']['qualities']
stream_json = vdata['stream_url']['live_core_sdk_data']['pull_data']['stream_data']
stream_json = json.loads(stream_json)
available_types = []
if any(sdk_key in stream_json['data'] and 'main' in stream_json['data'][sdk_key] for sdk_key in
stream_json['data']):
available_types.append('main')
if any(sdk_key in stream_json['data'] and 'backup' in stream_json['data'][sdk_key] for sdk_key in
stream_json['data']):
available_types.append('backup')
plist = []
for line_type in available_types:
format_arrays = {'flv': [], 'hls': [], 'lls': []}
qualities = sorted(resolution_data, key=lambda x: x['level'], reverse=True)
for quality in qualities:
sdk_key = quality['sdk_key']
if sdk_key in stream_json['data'] and line_type in stream_json['data'][sdk_key]:
stream_info = stream_json['data'][sdk_key][line_type]
if stream_info.get('flv'):
format_arrays['flv'].extend([quality['name'], stream_info['flv']])
if stream_info.get('hls'):
format_arrays['hls'].extend([quality['name'], stream_info['hls']])
if stream_info.get('lls'):
format_arrays['lls'].extend([quality['name'], stream_info['lls']])
format_urls = []
for format_name, url_array in format_arrays.items():
if url_array:
encoded_urls = self.e64(json.dumps(url_array))
format_urls.append(f"{format_name}${ids[0]}@@{encoded_urls}")
if format_urls:
plist.append('#'.join(format_urls))
names = ['线路1', '线路2'][:len(plist)]
vod['vod_play_from'] = "$$$".join(names)
vod['vod_play_url'] = "$$$".join(plist)
return vod
except Exception as e:
return self.handle_exception(e)
def douyuDetail(self, ids):
headers = self.gethr(0, zr=f'{self.hosts[ids[0]]}/{ids[1]}')
try:
data = self.fetch(f'{self.hosts[ids[0]]}/betard/{ids[1]}', headers=headers).json()
vname = data['room']['room_name']
vod = self.buildvod(
vod_name=vname,
vod_remarks=data['room'].get('second_lvl_name'),
vod_director=data['room'].get('nickname'),
)
vdata = self.fetch(f'{self.hosts[ids[0]]}/swf_api/homeH5Enc?rids={ids[1]}', headers=headers).json()
json_body = vdata['data']
json_body = {"html": self.douyu_text(json_body[f'room{ids[1]}']), "rid": ids[1]}
sign = self.post('http://alive.nsapps.cn/api/AllLive/DouyuSign', json=json_body, headers=self.headers[1]).json()['data']
body = f'{sign}&cdn=&rate=-1&ver=Douyu_223061205&iar=1&ive=1&hevc=0&fa=0'
body=self.params_to_json(body)
nubdata = self.post(f'{self.hosts[ids[0]]}/lapi/live/getH5Play/{ids[1]}', data=body, headers=headers).json()
plist = []
names = []
for i,x in enumerate(nubdata['data']['cdnsWithName']):
names.append(f'线路{i+1}')
d = {'sign': sign, 'cdn': x['cdn'], 'id': ids[1]}
plist.append(
f'{vname}${ids[0]}@@{self.e64(json.dumps(d))}@@{self.e64(json.dumps(nubdata["data"]["multirates"]))}')
vod['vod_play_from'] = "$$$".join(names)
vod['vod_play_url'] = "$$$".join(plist)
return vod
except Exception as e:
return self.handle_exception(e)
def douyu_text(self, text):
function_positions = [m.start() for m in re.finditer('function', text)]
total_functions = len(function_positions)
if total_functions % 2 == 0:
target_index = total_functions // 2 + 1
else:
target_index = (total_functions - 1) // 2 + 1
if total_functions >= target_index:
cut_position = function_positions[target_index - 1]
ctext = text[4:cut_position]
return re.sub(r'eval\(strc\)\([\w\d,]+\)', 'strc', ctext)
return text
def searchContent(self, key, quick, pg="1"):
pass
def playerContent(self, flag, id, vipFlags):
try:
ids = id.split('@@')
p = 1
if ids[0] in ['wangyi', 'douyin','huya']:
p, url = 0, json.loads(self.d64(ids[1]))
elif ids[0] == 'bili':
p, url = self.biliplay(ids)
elif ids[0] == 'huya':
p, url = 0, json.loads(self.d64(ids[1]))
elif ids[0] == 'douyu':
p, url = self.douyuplay(ids)
return {'parse': p, 'url': url, 'header': self.playheaders[ids[0]]}
except Exception as e:
return {'parse': 1, 'url': self.excepturl, 'header': self.headers[0]}
def biliplay(self, ids):
try:
data = self.fetch(
f'{self.hosts[ids[0]][0]}/xlive/web-room/v2/index/getRoomPlayInfo?room_id={ids[1]}&protocol=0,1&format=0,2&codec=0&platform=web&qn={ids[2]}',
headers=self.gethr(0, ids[0])).json()
urls = []
line_index = 1
for stream in data['data']['playurl_info']['playurl']['stream']:
for format_item in stream['format']:
for codec in format_item['codec']:
for url_info in codec['url_info']:
full_url = f"{url_info['host']}/{codec['base_url'].lstrip('/')}{url_info['extra']}"
urls.extend([f"线路{line_index}", full_url])
line_index += 1
return 0, urls
except Exception as e:
return 1, self.excepturl
def douyuplay(self, ids):
try:
sdata = json.loads(self.d64(ids[1]))
headers = self.gethr(0, zr=f'{self.hosts[ids[0]]}/{sdata["id"]}')
ldata = json.loads(self.d64(ids[2]))
result_obj = {}
with ThreadPoolExecutor(max_workers=len(ldata)) as executor:
futures = [
executor.submit(
self.douyufp,
sdata,
quality,
headers,
self.hosts[ids[0]],
result_obj
) for quality in ldata
]
for future in futures:
future.result()
result = []
for bit in sorted(result_obj.keys(), reverse=True):
result.extend(result_obj[bit])
if result:
return 0, result
return 1, self.excepturl
except Exception as e:
return 1, self.excepturl
def douyufp(self, sdata, quality, headers, host, result_obj):
try:
body = f'{sdata["sign"]}&cdn={sdata["cdn"]}&rate={quality["rate"]}'
body=self.params_to_json(body)
data = self.post(f'{host}/lapi/live/getH5Play/{sdata["id"]}',
data=body, headers=headers).json()
if data.get('data'):
play_url = data['data']['rtmp_url'] + '/' + data['data']['rtmp_live']
bit = quality.get('bit', 0)
if bit not in result_obj:
result_obj[bit] = []
result_obj[bit].extend([quality['name'], play_url])
except Exception as e:
print(f"Error fetching {quality['name']}: {str(e)}")
def localProxy(self, param):
pass
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 josn_to_params(self, params, skip_empty=False):
query = []
for k, v in params.items():
if skip_empty and not v:
continue
query.append(f"{k}={v}")
return "&".join(query)
def params_to_json(self, query_string):
parsed_data = parse_qs(query_string)
result = {key: value[0] for key, value in parsed_data.items()}
return result
def buildvod(self, vod_id='', vod_name='', vod_pic='', vod_year='', vod_tag='', vod_remarks='', style='',
type_name='', vod_area='', vod_actor='', vod_director='',
vod_content='', vod_play_from='', vod_play_url=''):
vod = {
'vod_id': vod_id,
'vod_name': vod_name,
'vod_pic': vod_pic,
'vod_year': vod_year,
'vod_tag': 'folder' if vod_tag else '',
'vod_remarks': vod_remarks,
'style': style,
'type_name': type_name,
'vod_area': vod_area,
'vod_actor': vod_actor,
'vod_director': vod_director,
'vod_content': vod_content,
'vod_play_from': vod_play_from,
'vod_play_url': vod_play_url
}
vod = {key: value for key, value in vod.items() if value}
return vod
def getpq(self, url, headers=None, cookies=None):
data = self.fetch(url, headers=headers, cookies=cookies).text
try:
return pq(data)
except Exception as e:
print(f"解析页面错误: {str(e)}")
return pq(data.encode('utf-8'))
def gethr(self, index, rf='', zr=''):
headers = self.headers[index]
if zr:
headers['referer'] = zr
else:
headers['referer'] = f"{self.referers[rf]}/"
return headers
def handle_exception(self, e):
print(f"报错: {str(e)}")
return {'vod_play_from': '哎呀翻车啦', 'vod_play_url': f'翻车啦${self.excepturl}'}
+323
View File
@@ -0,0 +1,323 @@
# -*- coding: utf-8 -*-
# by @嗷呜
import json
import sys
import uuid
import copy
sys.path.append('..')
from base.spider import Spider
from concurrent.futures import ThreadPoolExecutor, as_completed
class Spider(Spider):
def init(self, extend=""):
self.dbody = {
"page_params": {
"channel_id": "",
"filter_params": "sort=75",
"page_type": "channel_operation",
"page_id": "channel_list_second_page"
}
}
self.body = self.dbody
pass
def getName(self):
pass
def isVideoFormat(self, url):
pass
def manualVideoCheck(self):
pass
def destroy(self):
pass
host = 'https://v.qq.com'
apihost = 'https://pbaccess.video.qq.com'
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',
'origin': host,
'referer': f'{host}/'
}
def homeContent(self, filter):
cdata = {
"电视剧": "100113",
"电影": "100173",
"综艺": "100109",
"纪录片": "100105",
"动漫": "100119",
"少儿": "100150",
"短剧": "110755"
}
result = {}
classes = []
filters = {}
for k in cdata:
classes.append({
'type_name': k,
'type_id': cdata[k]
})
with ThreadPoolExecutor(max_workers=len(classes)) as executor:
futures = [executor.submit(self.get_filter_data, item['type_id']) for item in classes]
for future in futures:
cid, data = future.result()
if not data.get('data', {}).get('module_list_datas'):
continue
filter_dict = {}
try:
items = data['data']['module_list_datas'][-1]['module_datas'][-1]['item_data_lists']['item_datas']
for item in items:
if not item.get('item_params', {}).get('index_item_key'):
continue
params = item['item_params']
filter_key = params['index_item_key']
if filter_key not in filter_dict:
filter_dict[filter_key] = {
'key': filter_key,
'name': params['index_name'],
'value': []
}
filter_dict[filter_key]['value'].append({
'n': params['option_name'],
'v': params['option_value']
})
except (IndexError, KeyError):
continue
filters[cid] = list(filter_dict.values())
result['class'] = classes
result['filters'] = filters
return result
def homeVideoContent(self):
json_data = {'page_context':None,'page_params':{'page_id':'100101','page_type':'channel','skip_privacy_types':'0','support_click_scan':'1','new_mark_label_enabled':'1','ams_cookies':'',},'page_bypass_params':{'params':{'caller_id':'','data_mode':'default','page_id':'','page_type':'channel','platform_id':'2','user_mode':'default',},'scene':'channel','abtest_bypass_id':'',}}
data = self.post(f'{self.apihost}/trpc.vector_layout.page_view.PageService/getPage',headers=self.headers, json=json_data).json()
vlist = []
for it in data['data']['CardList'][0]['children_list']['list']['cards']:
if it.get('params'):
p = it['params']
tag = json.loads(p.get('uni_imgtag', '{}') or p.get('imgtag', '{}') or '{}')
id = it.get('id') or p.get('cid')
name = p.get('mz_title') or p.get('title')
if name and 'http' not in id:
vlist.append({
'vod_id': id,
'vod_name': name,
'vod_pic': p.get('image_url'),
'vod_year': tag.get('tag_2', {}).get('text'),
'vod_remarks': tag.get('tag_4', {}).get('text')
})
return {'list': vlist}
def categoryContent(self, tid, pg, filter, extend):
result = {}
params = {
"sort": extend.get('sort', '75'),
"attr": extend.get('attr', '-1'),
"itype": extend.get('itype', '-1'),
"ipay": extend.get('ipay', '-1'),
"iarea": extend.get('iarea', '-1'),
"iyear": extend.get('iyear', '-1'),
"theater": extend.get('theater', '-1'),
"award": extend.get('award', '-1'),
"recommend": extend.get('recommend', '-1')
}
if pg == '1':
self.body = self.dbody.copy()
self.body['page_params']['channel_id'] = tid
self.body['page_params']['filter_params'] = self.josn_to_params(params)
data = self.post(
f'{self.apihost}/trpc.universal_backend_service.page_server_rpc.PageServer/GetPageData?video_appid=1000005&vplatform=2&vversion_name=8.9.10&new_mark_label_enabled=1',
json=self.body, headers=self.headers).json()
ndata = data['data']
if ndata['has_next_page']:
result['pagecount'] = 9999
self.body['page_context'] = ndata['next_page_context']
else:
result['pagecount'] = int(pg)
vlist = []
for its in ndata['module_list_datas'][-1]['module_datas'][-1]['item_data_lists']['item_datas']:
id = its.get('item_params', {}).get('cid')
if id:
p = its['item_params']
tag = json.loads(p.get('uni_imgtag', '{}') or p.get('imgtag', '{}') or '{}')
name = p.get('mz_title') or p.get('title')
pic = p.get('new_pic_hz') or p.get('new_pic_vt')
vlist.append({
'vod_id': id,
'vod_name': name,
'vod_pic': pic,
'vod_year': tag.get('tag_2', {}).get('text'),
'vod_remarks': tag.get('tag_4', {}).get('text')
})
result['list'] = vlist
result['page'] = pg
result['limit'] = 90
result['total'] = 999999
return result
def detailContent(self, ids):
vbody = {"page_params":{"req_from":"web","cid":ids[0],"vid":"","lid":"","page_type":"detail_operation","page_id":"detail_page_introduction"},"has_cache":1}
body = {"page_params":{"req_from":"web_vsite","page_id":"vsite_episode_list","page_type":"detail_operation","id_type":"1","page_size":"","cid":ids[0],"vid":"","lid":"","page_num":"","page_context":"","detail_page_type":"1"},"has_cache":1}
with ThreadPoolExecutor(max_workers=2) as executor:
future_detail = executor.submit(self.get_vdata, vbody)
future_episodes = executor.submit(self.get_vdata, body)
vdata = future_detail.result()
data = future_episodes.result()
pdata = self.process_tabs(data, body, ids)
if not pdata:
return self.handle_exception(None, "No pdata available")
try:
star_list = vdata['data']['module_list_datas'][0]['module_datas'][0]['item_data_lists']['item_datas'][
0].get('sub_items', {}).get('star_list', {}).get('item_datas', [])
actors = [star['item_params']['name'] for star in star_list]
names = ['腾讯视频', '预告片']
plist, ylist = self.process_pdata(pdata, ids)
if not plist:
del names[0]
if not ylist:
del names[1]
vod = self.build_vod(vdata, actors, plist, ylist, names)
return {'list': [vod]}
except Exception as e:
return self.handle_exception(e, "Error processing detail")
def searchContent(self, key, quick, pg="1"):
headers = self.headers.copy()
headers.update({'Content-Type': 'application/json'})
body = {'version':'25021101','clientType':1,'filterValue':'','uuid':str(uuid.uuid4()),'retry':0,'query':key,'pagenum':int(pg)-1,'pagesize':30,'queryFrom':0,'searchDatakey':'','transInfo':'','isneedQc':True,'preQid':'','adClientInfo':'','extraInfo':{'isNewMarkLabel':'1','multi_terminal_pc':'1','themeType':'1',},}
data = self.post(f'{self.apihost}/trpc.videosearch.mobile_search.MultiTerminalSearch/MbSearch?vplatform=2',
json=body, headers=headers).json()
vlist = []
vname=["电视剧", "电影", "综艺", "纪录片", "动漫", "少儿", "短剧"]
v=data['data']['normalList']['itemList']
d=data['data']['areaBoxList'][0]['itemList']
q=v+d
if v[0].get('doc') and v[0]['doc'].get('id') =='MainNeed':q=d+v
for k in q:
if k.get('doc') and k.get('videoInfo') and k['doc'].get('id') and '外站' not in k['videoInfo'].get('subTitle') and k['videoInfo'].get('title') and k['videoInfo'].get('typeName') in vname:
img_tag = k.get('videoInfo', {}).get('imgTag')
if img_tag is not None and isinstance(img_tag, str):
try:
tag = json.loads(img_tag)
except json.JSONDecodeError as e:
tag = {}
else:
tag = {}
pic = k.get('videoInfo', {}).get('imgUrl')
vlist.append({
'vod_id': k['doc']['id'],
'vod_name': self.removeHtmlTags(k['videoInfo']['title']),
'vod_pic': pic,
'vod_year': k['videoInfo'].get('typeName') +' '+ tag.get('tag_2', {}).get('text', ''),
'vod_remarks': tag.get('tag_4', {}).get('text', '')
})
return {'list': vlist, 'page': pg}
def playerContent(self, flag, id, vipFlags):
ids = id.split('@')
url = f"{self.host}/x/cover/{ids[0]}/{ids[1]}.html"
return {'jx':1,'parse': 1, 'url': url, 'header': ''}
def localProxy(self, param):
pass
def get_filter_data(self, cid):
hbody = self.dbody.copy()
hbody['page_params']['channel_id'] = cid
data = self.post(
f'{self.apihost}/trpc.universal_backend_service.page_server_rpc.PageServer/GetPageData?video_appid=1000005&vplatform=2&vversion_name=8.9.10&new_mark_label_enabled=1',
json=hbody, headers=self.headers).json()
return cid, data
def get_vdata(self, body):
try:
vdata = self.post(
f'{self.apihost}/trpc.universal_backend_service.page_server_rpc.PageServer/GetPageData?video_appid=3000010&vplatform=2&vversion_name=8.2.96',
json=body, headers=self.headers
).json()
return vdata
except Exception as e:
print(f"Error in get_vdata: {str(e)}")
return {'data': {'module_list_datas': []}}
def process_pdata(self, pdata, ids):
plist = []
ylist = []
for k in pdata:
if k.get('item_id'):
pid = f"{k['item_params']['union_title']}${ids[0]}@{k['item_id']}"
if '预告' in k['item_params']['union_title']:
ylist.append(pid)
else:
plist.append(pid)
return plist, ylist
def build_vod(self, vdata, actors, plist, ylist, names):
d = vdata['data']['module_list_datas'][0]['module_datas'][0]['item_data_lists']['item_datas'][0]['item_params']
urls = []
if plist:
urls.append('#'.join(plist))
if ylist:
urls.append('#'.join(ylist))
vod = {
'type_name': d.get('sub_genre', ''),
'vod_name': d.get('title', ''),
'vod_year': d.get('year', ''),
'vod_area': d.get('area_name', ''),
'vod_remarks': d.get('holly_online_time', '') or d.get('hotval', ''),
'vod_actor': ','.join(actors),
'vod_content': d.get('cover_description', ''),
'vod_play_from': '$$$'.join(names),
'vod_play_url': '$$$'.join(urls)
}
return vod
def handle_exception(self, e, message):
print(f"{message}: {str(e)}")
return {'list': [{'vod_play_from': '哎呀翻车啦', 'vod_play_url': '翻车啦#555'}]}
def process_tabs(self, data, body, ids):
try:
pdata = data['data']['module_list_datas'][-1]['module_datas'][-1]['item_data_lists']['item_datas']
tabs = data['data']['module_list_datas'][-1]['module_datas'][-1]['module_params'].get('tabs')
if tabs and len(json.loads(tabs)):
tabs = json.loads(tabs)
remaining_tabs = tabs[1:]
task_queue = []
for tab in remaining_tabs:
nbody = copy.deepcopy(body)
nbody['page_params']['page_context'] = tab['page_context']
task_queue.append(nbody)
with ThreadPoolExecutor(max_workers=10) as executor:
future_map = {executor.submit(self.get_vdata, task): idx for idx, task in enumerate(task_queue)}
results = [None] * len(task_queue)
for future in as_completed(future_map.keys()):
idx = future_map[future]
results[idx] = future.result()
for result in results:
if result:
page_data = result['data']['module_list_datas'][-1]['module_datas'][-1]['item_data_lists'][
'item_datas']
pdata.extend(page_data)
return pdata
except Exception as e:
print(f"Error processing episodes: {str(e)}")
return []
def josn_to_params(self, params, skip_empty=False):
query = []
for k, v in params.items():
if skip_empty and not v:
continue
query.append(f"{k}={v}")
return "&".join(query)
+205
View File
@@ -0,0 +1,205 @@
# -*- coding: utf-8 -*-
# by @嗷呜
import sys
import time
from concurrent.futures import ThreadPoolExecutor, as_completed
sys.path.append('..')
from base.spider import Spider
class Spider(Spider):
def init(self, extend=""):
pass
def getName(self):
pass
def isVideoFormat(self, url):
pass
def manualVideoCheck(self):
pass
def destroy(self):
pass
rhost='https://www.mgtv.com'
host='https://pianku.api.mgtv.com'
vhost='https://pcweb.api.mgtv.com'
mhost='https://dc.bz.mgtv.com'
shost='https://mobileso.bz.mgtv.com'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; ) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.6478.61 Chrome/126.0.6478.61 Not/A)Brand/8 Safari/537.36',
'origin': rhost,
'referer': f'{rhost}/'
}
def homeContent(self, filter):
result = {}
cateManual = {
"电影": "3",
"电视剧": "2",
"综艺": "1",
"动画": "50",
"少儿": "10",
"纪录片": "51",
"教育": "115"
}
classes = []
filters = {}
for k in cateManual:
classes.append({
'type_name': k,
'type_id': cateManual[k]
})
with ThreadPoolExecutor(max_workers=len(classes)) as executor:
results = executor.map(self.getf, classes)
for id, ft in results:
if len(ft):filters[id] = ft
result['class'] = classes
result['filters'] = filters
return result
def homeVideoContent(self):
data=self.fetch(f'{self.mhost}/dynamic/v1/channel/index/0/0/0/1000000/0/0/17/1354?type=17&version=5.0&t={str(int(time.time()*1000))}&_support=10000000', headers=self.headers).json()
videoList = []
for i in data['data']:
if i.get('DSLList') and len(i['DSLList']):
for j in i['DSLList']:
if j.get('data') and j['data'].get('items') and len(j['data']['items']):
for k in j['data']['items']:
videoList.append({
'vod_id': k["videoId"],
'vod_name': k['videoName'],
'vod_pic': k['img'],
'vod_year': k.get('cornerTitle'),
'vod_remarks': k.get('time') or k.get('desc'),
})
return {'list':videoList}
def categoryContent(self, tid, pg, filter, extend):
body={
'allowedRC': '1',
'platform': 'pcweb',
'channelId': tid,
'pn': pg,
'pc': '80',
'hudong': '1',
'_support': '10000000'
}
body.update(extend)
data=self.fetch(f'{self.host}/rider/list/pcweb/v3', params=body, headers=self.headers).json()
videoList = []
for i in data['data']['hitDocs']:
videoList.append({
'vod_id': i["playPartId"],
'vod_name': i['title'],
'vod_pic': i['img'],
'vod_year': (i.get('rightCorner',{}) or {}).get('text') or i.get('year'),
'vod_remarks': i['updateInfo']
})
result = {}
result['list'] = videoList
result['page'] = pg
result['pagecount'] = 9999
result['limit'] = 90
result['total'] = 999999
return result
def detailContent(self, ids):
vbody={'allowedRC': '1', 'vid': ids[0], 'type': 'b', '_support': '10000000'}
vdata=self.fetch(f'{self.vhost}/video/info', params=vbody, headers=self.headers).json()
d=vdata['data']['info']['detail']
vod = {
'vod_name': vdata['data']['info']['title'],
'type_name': d.get('kind'),
'vod_year': d.get('releaseTime'),
'vod_area': d.get('area'),
'vod_lang': d.get('language'),
'vod_remarks': d.get('updateInfo'),
'vod_actor': d.get('leader'),
'vod_director': d.get('director'),
'vod_content': d.get('story'),
'vod_play_from': '芒果TV',
'vod_play_url': ''
}
data,pdata=self.fetch_page_data('1', ids[0],True)
pagecount=data['data'].get('total_page') or 1
if int(pagecount)>1:
pages = list(range(2, pagecount+1))
page_results = {}
with ThreadPoolExecutor(max_workers=10) as executor:
future_to_page = {
executor.submit(self.fetch_page_data, page, ids[0]): page
for page in pages
}
for future in as_completed(future_to_page):
page = future_to_page[future]
try:
result = future.result()
page_results[page] = result
except Exception as e:
print(f"Error fetching page {page}: {e}")
for page in sorted(page_results.keys()):
pdata.extend(page_results[page])
vod['vod_play_url'] = '#'.join(pdata)
return {'list':[vod]}
def searchContent(self, key, quick, pg="1"):
data=self.fetch(f'{self.shost}/applet/search/v1?channelCode=mobile-wxap&q={key}&pn={pg}&pc=10&_support=10000000', headers=self.headers).json()
videoList = []
for i in data['data']['contents']:
if i.get('data') and len(i['data']):
k = i['data'][0]
if k.get('vid') and k.get('img'):
try:
videoList.append({
'vod_id': k['vid'],
'vod_name': k['title'],
'vod_pic': k['img'],
'vod_year': (i.get('rightTopCorner',{}) or {}).get('text') or i.get('year'),
'vod_remarks': '/'.join(i.get('desc',[])),
})
except:
print(k)
return {'list':videoList,'page':pg}
def playerContent(self, flag, id, vipFlags):
id=f'{self.rhost}{id}'
return {'jx':1,'parse': 1, 'url': id, 'header': ''}
def localProxy(self, param):
pass
def getf(self, body):
params = {
'allowedRC': '1',
'channelId': body['type_id'],
'platform': 'pcweb',
'_support': '10000000',
}
data = self.fetch(f'{self.host}/rider/config/channel/v1', params=params, headers=self.headers).json()
ft = []
for i in data['data']['listItems']:
try:
value_array = [{"n": value['tagName'], "v": value['tagId']} for value in i['items'] if
value.get('tagName')]
ft.append({"key": i['eName'], "name": i['typeName'], "value": value_array})
except:
print(i)
return body['type_id'], ft
def fetch_page_data(self, page, id, b=False):
body = {'version': '5.5.35', 'video_id': id, 'page': page, 'size': '30',
'platform': '4', 'src': 'mgtv', 'allowedRC': '1', '_support': '10000000'}
data = self.fetch(f'{self.vhost}/episode/list', params=body, headers=self.headers).json()
ldata = [f'{i["t3"]}${i["url"]}' for i in data['data']['list']]
if b:
return data, ldata
else:
return ldata
+182
View File
@@ -0,0 +1,182 @@
# -*- coding: utf-8 -*-
# by @嗷呜
import json
import random
import string
import sys
from base64 import b64decode, b64encode
from urllib.parse import quote, unquote
sys.path.append('..')
import concurrent.futures
from base.spider import Spider
class Spider(Spider):
def init(self, extend=""):
pass
def getName(self):
pass
def isVideoFormat(self, url):
pass
def manualVideoCheck(self):
pass
def destroy(self):
pass
host='https://xy.51gy.top'
headers = {
'User-Agent': 'okhttp/4.9.1',
'mark-time': 'null',
'fn-api-version': '3.1.9',
'versionCode': '19',
'product': 'gysg',
'sg': '22664e555e0015684f988833803b3055',
}
def homeContent(self, filter):
data=self.fetch(f"{self.host}/api.php/vod/type", headers=self.headers).json()
result,filters,videos = {},{},[]
classes = [{'type_id': i['type_name'], 'type_name': i['type_name']} for i in data['list'][1:]]
body={'token':'', 'type_id':data['list'][0]['type_id']}
ldata=self.post(f"{self.host}/api.php/vod/category", data=body, headers=self.headers).json()
for i in ldata['data']['banner']:
videos.append({
'vod_id':i.get('vod_id'),
'vod_name':i.get('vod_name'),
'vod_pic':i.get('vod_pic_thumb')
})
with concurrent.futures.ThreadPoolExecutor(max_workers=len(classes)) as executor:
future_to_aid = {executor.submit(self.fts, aid): aid for aid in classes}
for future in concurrent.futures.as_completed(future_to_aid):
aid = future_to_aid[future]
try:
aid_id, fts = future.result()
filters[aid_id] = fts
except Exception as e:
print(f"Error processing aid {aid}: {e}")
result['class'] = classes
result['filters'] = filters
result['list'] = videos
return result
def homeVideoContent(self):
pass
def categoryContent(self, tid, pg, filter, extend):
params={'state':extend.get('state',tid) or tid,'class':extend.get('classes','全部'),'area':extend.get('area','全部'),'year':extend.get('year','全部'),'lang':extend.get('lang','全部'),'version':extend.get('version','全部'),'pg':pg}
data=self.fetch(f"{self.host}/api.php/vod/list", params=params, headers=self.headers).json()
result = {}
videos = []
for i in data['data']['list']:
if str(i.get('vod_id', 0)) != '0':
videos.append({
'vod_id': i.get('vod_id'),
'vod_name': i.get('vod_name'),
'vod_pic': i.get('vod_pic'),
'vod_year': f"{i.get('vod_score')}",
'vod_remarks': i.get('vod_remarks')
})
result['list'] = videos
result['page'] = pg
result['pagecount'] = 9999
result['limit'] = 90
result['total'] = 999999
return result
def detailContent(self, ids):
body={'ids':ids[0],'uni_code':self.getunc(),'ac':'detail','token':''}
data=self.post(f"{self.host}/api.php/vod/detail2", data=body, headers=self.headers).json()
v=data['data']
vod = {
'type_name': v.get('type_name'),
'vod_year': v.get('vod_year'),
'vod_area': v.get('vod_area'),
'vod_lang': v.get('vod_lang'),
'vod_remarks': v.get('vod_remarks'),
'vod_actor': v.get('vod_actor'),
'vod_director': v.get('vod_director'),
'vod_content': v.get('vod_content')
}
n,p=[],[]
for i in v['vod_play_list']:
pp=i['player_info']
n.append(pp['show'])
np=[]
for j in i['urls']:
cd={'parse':pp.get('parse'),'url':j['url'],'headers':pp.get('headers')}
np.append(f"{j['name']}${self.e64(json.dumps(cd))}")
p.append('#'.join(np))
vod.update({'vod_play_from':'$$$'.join(n),'vod_play_url':'$$$'.join(p)})
return {'list':[vod]}
def searchContent(self, key, quick, pg="1"):
data=self.fetch(f"{self.host}/api.php/vod/search", params={'keywords':key,'type':'1','pg':pg}, headers=self.headers).json()
return {'list':data['list'],'page':pg}
def playerContent(self, flag, id, vipFlags):
ids=json.loads(self.d64(id))
headers = {}
urls=ids['url']
if ids.get('headers'):
hs=ids['headers'].split('=>',1)
headers[hs[0].strip()]=hs[-1].strip()
if isinstance(ids.get('parse'), list) and len(ids['parse']) > 0:
urls=[]
for i,x in enumerate(ids['parse']):
su=f"{self.getProxyUrl()}&url={quote(x+ids['url'])}"
urls.extend([f'解析{i+1}',su])
return {'parse': 0, 'url': urls, 'header': headers}
def localProxy(self, param):
try:
body = {'url':unquote(param['url'])}
data=self.post(f"{self.host}/api.php/vod/m_jie_xi", data=body, headers=self.headers).json()
url=data.get('url') or data['data'].get('url')
return [302,'video/MP2T',None,{'Location':url}]
except:
return []
def liveContent(self, url):
pass
def fts(self, tdata):
params={'state':tdata['type_id'],'pg':'1'}
data = self.fetch(f"{self.host}/api.php/vod/list", params=params, headers=self.headers).json()
ftks = ["classes", "area", "lang", "year", "version", "state"]
filter = [
{
'name': k,
'key': k,
'value': [{'n': i, 'v': i} for i in v.split(',')]
}
for k, v in data['data']['classes']["type_extend"].items()
if k in ftks and v
]
return tdata['type_id'],filter
def getunc(self):
chars = string.ascii_lowercase + string.digits
data = ''.join(random.choice(chars) for _ in range(16))
return self.e64(data)
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:
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:
return ""
+225
View File
@@ -0,0 +1,225 @@
# -*- coding: utf-8 -*-
# by @嗷呜
import json
import sys
import threading
import uuid
import requests
sys.path.append('..')
from base.spider import Spider
import time
from Crypto.Hash import MD5, SHA1
class Spider(Spider):
'''
配置示例:
{
"key": "xxxx",
"name": "xxxx",
"type": 3,
"api": ".所在路径/金牌.py",
"searchable": 1,
"quickSearch": 1,
"filterable": 1,
"changeable": 1,
"ext": {
"site": "https://www.jiabaide.cn,域名2,域名3"
}
},
'''
def init(self, extend=""):
if extend:
hosts=json.loads(extend)['site']
self.host = self.host_late(hosts)
pass
def getName(self):
pass
def isVideoFormat(self, url):
pass
def manualVideoCheck(self):
pass
def destroy(self):
pass
def homeContent(self, filter):
cdata = self.fetch(f"{self.host}/api/mw-movie/anonymous/get/filer/type", headers=self.getheaders()).json()
fdata = self.fetch(f"{self.host}/api/mw-movie/anonymous/v1/get/filer/list", headers=self.getheaders()).json()
result = {}
classes = []
filters={}
for k in cdata['data']:
classes.append({
'type_name': k['typeName'],
'type_id': str(k['typeId']),
})
sort_values = [{"n": "最近更新", "v": "2"},{"n": "人气高低", "v": "3"}, {"n": "评分高低", "v": "4"}]
for tid, d in fdata['data'].items():
current_sort_values = sort_values.copy()
if tid == '1':
del current_sort_values[0]
filters[tid] = [
{"key": "type", "name": "类型",
"value": [{"n": i["itemText"], "v": i["itemValue"]} for i in d["typeList"]]},
*([] if not d["plotList"] else [{"key": "v_class", "name": "剧情",
"value": [{"n": i["itemText"], "v": i["itemText"]}
for i in d["plotList"]]}]),
{"key": "area", "name": "地区",
"value": [{"n": i["itemText"], "v": i["itemText"]} for i in d["districtList"]]},
{"key": "year", "name": "年份",
"value": [{"n": i["itemText"], "v": i["itemText"]} for i in d["yearList"]]},
{"key": "lang", "name": "语言",
"value": [{"n": i["itemText"], "v": i["itemText"]} for i in d["languageList"]]},
{"key": "sort", "name": "排序", "value": current_sort_values}
]
result['class'] = classes
result['filters'] = filters
return result
def homeVideoContent(self):
data1 = self.fetch(f"{self.host}/api/mw-movie/anonymous/v1/home/all/list", headers=self.getheaders()).json()
data2=self.fetch(f"{self.host}/api/mw-movie/anonymous/home/hotSearch",headers=self.getheaders()).json()
data=[]
for i in data1['data'].values():
data.extend(i['list'])
data.extend(data2['data'])
vods=self.getvod(data)
return {'list':vods}
def categoryContent(self, tid, pg, filter, extend):
params = {
"area": extend.get('area', ''),
"filterStatus": "1",
"lang": extend.get('lang', ''),
"pageNum": pg,
"pageSize": "30",
"sort": extend.get('sort', '1'),
"sortBy": "1",
"type": extend.get('type', ''),
"type1": tid,
"v_class": extend.get('v_class', ''),
"year": extend.get('year', '')
}
data = self.fetch(f"{self.host}/api/mw-movie/anonymous/video/list?{self.js(params)}", headers=self.getheaders(params)).json()
result = {}
result['list'] = self.getvod(data['data']['list'])
result['page'] = pg
result['pagecount'] = 9999
result['limit'] = 90
result['total'] = 999999
return result
def detailContent(self, ids):
data=self.fetch(f"{self.host}/api/mw-movie/anonymous/video/detail?id={ids[0]}",headers=self.getheaders({'id':ids[0]})).json()
vod=self.getvod([data['data']])[0]
vod['vod_play_from']='金牌'
vod['vod_play_url'] = '#'.join(
f"{i['name'] if len(vod['episodelist']) > 1 else vod['vod_name']}${ids[0]}@@{i['nid']}" for i in
vod['episodelist'])
vod.pop('episodelist', None)
return {'list':[vod]}
def searchContent(self, key, quick, pg="1"):
params = {
"keyword": key,
"pageNum": pg,
"pageSize": "8",
"sourceCode": "1"
}
data=self.fetch(f"{self.host}/api/mw-movie/anonymous/video/searchByWord?{self.js(params)}",headers=self.getheaders(params)).json()
vods=self.getvod(data['data']['result']['list'])
return {'list':vods,'page':pg}
def playerContent(self, flag, id, vipFlags):
self.header = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; ) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.6478.61 Chrome/126.0.6478.61 Not/A)Brand/8 Safari/537.36',
'sec-ch-ua-platform': '"Windows"',
'DNT': '1',
'sec-ch-ua': '"Not/A)Brand";v="8", "Chromium";v="126", "Google Chrome";v="126"',
'sec-ch-ua-mobile': '?0',
'Origin': self.host,
'Referer': f'{self.host}/'
}
ids=id.split('@@')
pdata = self.fetch(f"{self.host}/api/mw-movie/anonymous/v2/video/episode/url?clientType=1&id={ids[0]}&nid={ids[1]}",headers=self.getheaders({'clientType':'1','id': ids[0], 'nid': ids[1]})).json()
vlist=[]
for i in pdata['data']['list']:vlist.extend([i['resolutionName'],i['url']])
return {'parse':0,'url':vlist,'header':self.header}
def localProxy(self, param):
pass
def host_late(self, url_list):
if isinstance(url_list, str):
urls = [u.strip() for u in url_list.split(',')]
else:
urls = url_list
if len(urls) <= 1:
return urls[0] if urls else ''
results = {}
threads = []
def test_host(url):
try:
start_time = time.time()
response = requests.head(url, timeout=1.0, allow_redirects=False)
delay = (time.time() - start_time) * 1000
results[url] = delay
except Exception as e:
results[url] = float('inf')
for url in urls:
t = threading.Thread(target=test_host, args=(url,))
threads.append(t)
t.start()
for t in threads:
t.join()
return min(results.items(), key=lambda x: x[1])[0]
def md5(self, sign_key):
md5_hash = MD5.new()
md5_hash.update(sign_key.encode('utf-8'))
md5_result = md5_hash.hexdigest()
return md5_result
def js(self, param):
return '&'.join(f"{k}={v}" for k, v in param.items())
def getheaders(self, param=None):
if param is None:param = {}
t=str(int(time.time()*1000))
param['key']='cb808529bae6b6be45ecfab29a4889bc'
param['t']=t
sha1_hash = SHA1.new()
sha1_hash.update(self.md5(self.js(param)).encode('utf-8'))
sign = sha1_hash.hexdigest()
deviceid = str(uuid.uuid4())
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; ) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.6478.61 Chrome/126.0.6478.61 Not/A)Brand/8 Safari/537.36',
'Accept': 'application/json, text/plain, */*',
'sign': sign,
't': t,
'deviceid':deviceid
}
return headers
def convert_field_name(self, field):
field = field.lower()
if field.startswith('vod') and len(field) > 3:
field = field.replace('vod', 'vod_')
if field.startswith('type') and len(field) > 4:
field = field.replace('type', 'type_')
return field
def getvod(self, array):
return [{self.convert_field_name(k): v for k, v in item.items()} for item in array]
+147
View File
@@ -0,0 +1,147 @@
from base.spider import Spider
import re,sys,json
sys.path.append('..')
class Spider(Spider):
api_host = 'https://api.jinlidj.com'
origin = 'https://www.jinlidj.com'
api_path = '/api/search'
headers = {
'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/138.0.0.0 Safari/537.36",
'Content-Type': "application/json",
'accept-language': "zh-CN,zh;q=0.9",
'cache-control': "no-cache",
'origin': origin,
'pragma': "no-cache",
'priority': "u=1, i",
'referer': origin+'/',
'sec-ch-ua': "\"Not)A;Brand\";v=\"8\", \"Chromium\";v=\"138\", \"Google Chrome\";v=\"138\"",
'sec-ch-ua-mobile': "?0",
'sec-ch-ua-platform': "\"Windows\"",
'sec-fetch-dest': "empty",
'sec-fetch-mode': "cors",
'sec-fetch-site': "same-site"
}
def homeContent(self, filter):
return {'class': [{'type_id': 1, 'type_name': '情感关系'}, {'type_id': 2, 'type_name': '成长逆袭'}, {'type_id': 3, 'type_name': '奇幻异能'}, {'type_id': 4, 'type_name': '战斗热血'}, {'type_id': 5, 'type_name': '伦理现实'}, {'type_id': 6, 'type_name': '时空穿越'}, {'type_id': 7, 'type_name': '权谋身份'}]}
def homeVideoContent(self):
payload = {
"page": 1,
"limit": 24,
"type_id": "",
"year": "",
"keyword": ""
}
response = self.post(f"{self.api_host}{self.api_path}", data=json.dumps(payload), headers=self.headers).json()
data = response['data']
videos = []
for i in data['list']:
videos.append({
'vod_id': i.get('vod_id'),
'vod_name': i.get('vod_name'),
'vod_class': i.get('vod_class'),
'vod_pic': i.get('vod_pic'),
'vod_year': i.get('vod_year'),
'vod_remarks': i.get('vod_total')+'',
'vod_score': i.get('vod_score')
})
return {'list': videos}
def detailContent(self, ids):
response = self.post(f'{self.api_host}/api/detail/{ids[0]}', data=json.dumps({}), headers=self.headers).json()
data = response['data']
videos = []
vod_play_url = ''
for name,url in data['player'].items():
vod_play_url += f'{name}${url}#'
vod_play_url.rstrip('#')
videos.append({
'vod_id': data.get('vod_id'),
'vod_name': data.get('vod_name'),
'vod_content': data.get('vod_blurb'),
'vod_remarks': '集数:' + data.get('vod_total'),
"vod_director": data.get('vod_director'),
"vod_actor": data.get('vod_actor'),
'vod_year': data.get('vod_year'),
'vod_area': data.get('vod_area'),
'vod_play_from': '锦鲤短剧',
'vod_play_url': vod_play_url
})
return {'list': videos}
def searchContent(self, key, quick, pg="1"):
payload = {
"page": pg,
"limit": 24,
"type_id": "",
"keyword": key
}
response = self.post(f'{self.api_host}{self.api_path}', data=json.dumps(payload), headers=self.headers).json()
data = response['data']
videos = []
for i in data['list']:
videos.append({
"vod_id": i['vod_id'],
"vod_name": i['vod_name'],
"vod_class": i['vod_class'],
"vod_pic": i['vod_pic'],
'vod_year': i.get('vod_year'),
"vod_remarks": i['vod_total'] + ''
})
return {'list': videos, 'page': pg, 'total': data['total'], 'limit': 24}
def categoryContent(self, tid, pg, filter, extend):
payload = {
"page": pg,
"limit": 24,
"type_id": tid,
"year": "",
"keyword": ""
}
response = self.post(f'{self.api_host}{self.api_path}', data=json.dumps(payload), headers=self.headers).json()
data = response['data']
videos = []
for i in data['list']:
videos.append({
'vod_id': i.get('vod_id'),
'vod_name': i.get('vod_name'),
'vod_class': i.get('vod_class'),
'vod_pic': i.get('vod_pic'),
'vod_remarks': i.get('vod_total')+'',
'vod_year': i.get('vod_year'),
'vod_score': i.get('vod_score')
})
return {'list': videos}
def playerContent(self, flag, id, vipflags):
parse = 0
header = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/138.0.0.0 Safari/537.36'}
try:
response = self.fetch(id, headers=self.headers).text
match = re.search(r'let\s+data\s*=\s*(\{[^}]*http[^}]*\});', response, re.IGNORECASE)
data = match.group(1)
data2 = json.loads(data)
url = data2['url']
except Exception:
url, parse, header = id, 1, self.headers
return {'parse': parse, 'url': url,'header': header}
def init(self, extend=''):
pass
def getName(self):
pass
def isVideoFormat(self, url):
pass
def manualVideoCheck(self):
pass
def destroy(self):
pass
def localProxy(self, param):
pass
+220
View File
@@ -0,0 +1,220 @@
# -*- coding: utf-8 -*-
# by @嗷呜
import json
import random
import sys
from base64 import b64encode, b64decode
from concurrent.futures import ThreadPoolExecutor
sys.path.append('..')
from base.spider import Spider
class Spider(Spider):
def init(self, extend=""):
did=self.getdid()
self.headers.update({'deviceId': did})
token=self.gettk()
self.headers.update({'token': token})
pass
def getName(self):
pass
def isVideoFormat(self, url):
pass
def manualVideoCheck(self):
pass
def destroy(self):
pass
host='http://ldys.sq1005.top'
headers = {
'User-Agent': 'okhttp/4.12.0',
'client': 'app',
'deviceType': 'Android'
}
def homeContent(self, filter):
data=self.post(f"{self.host}/api/v1/app/screen/screenType", headers=self.headers).json()
result = {}
cate = {
"类型": "classify",
"地区": "region",
"年份": "year"
}
sort={
'key':'sreecnTypeEnum',
'name': '排序',
'value':[{'n':'最新','v':'NEWEST'},{'n':'人气','v':'POPULARITY'},{'n':'评分','v':'COLLECT'},{'n':'热搜','v':'HOT'}]
}
classes = []
filters = {}
for k in data['data']:
classes.append({
'type_name': k['name'],
'type_id': k['id']
})
filters[k['id']] = []
for v in k['children']:
filters[k['id']].append({
'name': v['name'],
'key': cate[v['name']],
'value':[{'n':i['name'],'v':i['name']} for i in v['children']]
})
filters[k['id']].append(sort)
result['class'] = classes
result['filters'] = filters
return result
def homeVideoContent(self):
jdata={"condition":64,"pageNum":1,"pageSize":40}
data=self.post(f"{self.host}/api/v1/app/recommend/recommendSubList", headers=self.headers, json=jdata).json()
return {'list':self.getlist(data['data']['records'])}
def categoryContent(self, tid, pg, filter, extend):
jdata = {
'condition': {
'sreecnTypeEnum': 'NEWEST',
'typeId': tid,
},
'pageNum': int(pg),
'pageSize': 40,
}
jdata['condition'].update(extend)
data = self.post(f"{self.host}/api/v1/app/screen/screenMovie", headers=self.headers, json=jdata).json()
result = {}
result['list'] = self.getlist(data['data']['records'])
result['page'] = pg
result['pagecount'] = 9999
result['limit'] = 90
result['total'] = 999999
return result
def detailContent(self, ids):
ids = ids[0].split('@@')
jdata = {"id": int(ids[0]), "typeId": ids[-1]}
v = self.post(f"{self.host}/api/v1/app/play/movieDesc", headers=self.headers, json=jdata).json()
v = v['data']
vod = {
'type_name': v.get('classify'),
'vod_year': v.get('year'),
'vod_area': v.get('area'),
'vod_actor': v.get('star'),
'vod_director': v.get('director'),
'vod_content': v.get('introduce'),
'vod_play_from': '',
'vod_play_url': ''
}
c = self.post(f"{self.host}/api/v1/app/play/movieDetails", headers=self.headers, json=jdata).json()
l = c['data']['moviePlayerList']
n = {str(i['id']): i['moviePlayerName'] for i in l}
m = jdata.copy()
m.update({'playerId': str(l[0]['id'])})
pd = self.getv(m, c['data']['episodeList'])
if len(l)-1:
with ThreadPoolExecutor(max_workers=len(l)-1) as executor:
future_to_player = {executor.submit(self.getd, jdata, player): player for player in l[1:]}
for future in future_to_player:
try:
o,p = future.result()
pd.update(self.getv(o,p))
except Exception as e:
print(f"请求失败: {e}")
w, e = [],[]
for i, x in pd.items():
if x:
w.append(n[i])
e.append(x)
vod['vod_play_from'] = '$$$'.join(w)
vod['vod_play_url'] = '$$$'.join(e)
return {'list': [vod]}
def searchContent(self, key, quick, pg="1"):
jdata={
"condition": {
"value": key
},
"pageNum": int(pg),
"pageSize": 40
}
data=self.post(f"{self.host}/api/v1/app/search/searchMovie", headers=self.headers, json=jdata).json()
return {'list':self.getlist(data['data']['records']),'page':pg}
def playerContent(self, flag, id, vipFlags):
jdata=json.loads(self.d64(id))
data = self.post(f"{self.host}/api/v1/app/play/movieDetails", headers=self.headers, json=jdata).json()
try:
params={'playerUrl':data['data']['url'],'playerId':jdata['playerId']}
pd=self.fetch(f"{self.host}/api/v1/app/play/analysisMovieUrl", headers=self.headers, params=params).json()
url,p=pd['data'],0
except Exception as e:
print(f"请求失败: {e}")
url,p=data['data']['url'],0
return {'parse': p, 'url': url, 'header': {'User-Agent': 'okhttp/4.12.0'}}
def localProxy(self, param):
pass
def liveContent(self, url):
pass
def gettk(self):
data=self.fetch(f"{self.host}/api/v1/app/user/visitorInfo", headers=self.headers).json()
return data['data']['token']
def getdid(self):
did=self.getCache('ldid')
if not did:
hex_chars = '0123456789abcdef'
did =''.join(random.choice(hex_chars) for _ in range(16))
self.setCache('ldid',did)
return did
def getd(self,jdata,player):
x = jdata.copy()
x.update({'playerId': str(player['id'])})
response = self.post(f"{self.host}/api/v1/app/play/movieDetails", headers=self.headers, json=x).json()
return x, response['data']['episodeList']
def getv(self,d,c):
f={d['playerId']:''}
g=[]
for i in c:
j=d.copy()
j.update({'episodeId':str(i['id'])})
g.append(f"{i['episode']}${self.e64(json.dumps(j))}")
f[d['playerId']]='#'.join(g)
return f
def getlist(self,data):
videos = []
for i in data:
videos.append({
'vod_id': f"{i['id']}@@{i['typeId']}",
'vod_name': i.get('name'),
'vod_pic': i.get('cover'),
'vod_year': i.get('year'),
'vod_remarks': i.get('totalEpisode')
})
return videos
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 ""