2025-05-29 00:07:03 +08:00
|
|
|
|
# -*- coding: utf-8 -*-
|
|
|
|
|
|
# by @嗷呜
|
|
|
|
|
|
import json
|
|
|
|
|
|
import re
|
|
|
|
|
|
import sys
|
|
|
|
|
|
from base64 import b64decode, b64encode
|
|
|
|
|
|
from urllib.parse import urlparse
|
|
|
|
|
|
|
|
|
|
|
|
import requests
|
|
|
|
|
|
from pyquery import PyQuery as pq
|
|
|
|
|
|
from requests import Session
|
|
|
|
|
|
sys.path.append('..')
|
|
|
|
|
|
from base.spider import Spider
|
|
|
|
|
|
|
|
|
|
|
|
class Spider(Spider):
|
|
|
|
|
|
|
|
|
|
|
|
def init(self, extend=""):
|
|
|
|
|
|
'''
|
|
|
|
|
|
内置代理配置：真心jar为例
|
|
|
|
|
|
{
|
|
|
|
|
|
"key": "Phb",
|
|
|
|
|
|
"name": "Phb",
|
|
|
|
|
|
"type": 3,
|
|
|
|
|
|
"searchable": 1,
|
|
|
|
|
|
"quickSearch": 1,
|
|
|
|
|
|
"filterable": 1,
|
|
|
|
|
|
"api": "./py/Phb.py",
|
|
|
|
|
|
"ext": {
|
|
|
|
|
|
"http": "http://127.0.0.1:1072",
|
|
|
|
|
|
"https": "http://127.0.0.1:1072"
|
|
|
|
|
|
}
|
|
|
|
|
|
},
|
|
|
|
|
|
注：http(s)代理都是http
|
|
|
|
|
|
'''
|
|
|
|
|
|
try:self.proxies = json.loads(extend)
|
|
|
|
|
|
except:self.proxies = {}
|
|
|
|
|
|
self.headers = {
|
|
|
|
|
|
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.5410.0 Safari/537.36',
|
|
|
|
|
|
'pragma': 'no-cache',
|
|
|
|
|
|
'cache-control': 'no-cache',
|
|
|
|
|
|
'sec-ch-ua-platform': '"Windows"',
|
|
|
|
|
|
'sec-ch-ua': '"Not(A:Brand";v="99", "Google Chrome";v="133", "Chromium";v="133"',
|
|
|
|
|
|
'dnt': '1',
|
|
|
|
|
|
'sec-ch-ua-mobile': '?0',
|
|
|
|
|
|
'sec-fetch-site': 'cross-site',
|
|
|
|
|
|
'sec-fetch-mode': 'cors',
|
|
|
|
|
|
'sec-fetch-dest': 'empty',
|
|
|
|
|
|
'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8',
|
|
|
|
|
|
'priority': 'u=1, i',
|
|
|
|
|
|
}
|
|
|
|
|
|
self.host = self.gethost()
|
|
|
|
|
|
self.headers.update({'referer': f'{self.host}/', 'origin': self.host})
|
|
|
|
|
|
self.session = Session()
|
|
|
|
|
|
self.session.proxies.update(self.proxies)
|
|
|
|
|
|
self.session.headers.update(self.headers)
|
2025-06-03 01:37:06 +08:00
|
|
|
|
|
2025-06-03 01:54:18 +08:00
|
|
|
|
# --- 外部导入 Cookie 逻辑开始 ---
|
|
|
|
|
|
raw_cookie_data = '' # 用于暂存获取到的原始 cookie 数据
|
|
|
|
|
|
|
|
|
|
|
|
# 1. 从 extendDict 中尝试获取 'cookie' 字段
|
|
|
|
|
|
if 'cookie' in self.proxies: # self.proxies 实际上就是 extendDict
|
|
|
|
|
|
raw_cookie_data = self.proxies['cookie']
|
|
|
|
|
|
|
|
|
|
|
|
# 2. 如果 extendDict 中有 'json' 字段，从该 URL 获取 JSON 并提取 cookie
|
|
|
|
|
|
if 'json' in self.proxies:
|
|
|
|
|
|
try:
|
|
|
|
|
|
# 注意：这里假设 self.fetch 是一个已有的方法来执行请求
|
|
|
|
|
|
# 如果没有，你需要替换为 requests.get() 或其他请求方式
|
|
|
|
|
|
r = requests.get(self.proxies['json'], timeout=10, proxies=self.proxies, headers=self.headers)
|
|
|
|
|
|
r.raise_for_status() # 检查请求是否成功
|
|
|
|
|
|
if 'cookie' in r.json():
|
|
|
|
|
|
raw_cookie_data = r.json()['cookie']
|
|
|
|
|
|
except Exception as e:
|
|
|
|
|
|
print(f"从 JSON URL 获取 Cookie 失败: {e}")
|
|
|
|
|
|
raw_cookie_data = '' # 获取失败则清空
|
|
|
|
|
|
|
|
|
|
|
|
# 3. 如果 raw_cookie_data 是一个 URL (http/https开头)，则请求该 URL 获取纯文本 Cookie
|
|
|
|
|
|
if isinstance(raw_cookie_data, str) and raw_cookie_data.startswith('http'):
|
|
|
|
|
|
try:
|
|
|
|
|
|
r = requests.get(raw_cookie_data, timeout=10, proxies=self.proxies, headers=self.headers)
|
|
|
|
|
|
r.raise_for_status()
|
|
|
|
|
|
raw_cookie_data = r.text.strip()
|
|
|
|
|
|
except Exception as e:
|
|
|
|
|
|
print(f"从纯文本 URL 获取 Cookie 失败: {e}")
|
|
|
|
|
|
raw_cookie_data = ''
|
|
|
|
|
|
|
|
|
|
|
|
# 4. 将获取到的原始 Cookie 数据解析并更新到 session 中
|
|
|
|
|
|
# 如果 raw_cookie_data 仍然为空或 '{}'，则不处理
|
|
|
|
|
|
if raw_cookie_data and raw_cookie_data != '{}':
|
|
|
|
|
|
cookies_to_set = {}
|
|
|
|
|
|
if isinstance(raw_cookie_data, dict):
|
|
|
|
|
|
# 如果直接是字典类型，直接使用
|
|
|
|
|
|
cookies_to_set = raw_cookie_data
|
|
|
|
|
|
elif isinstance(raw_cookie_data, str):
|
|
|
|
|
|
try:
|
|
|
|
|
|
# 尝试解析为 JSON 字典 (例如 {"name": "value"})
|
|
|
|
|
|
cookies_to_set = json.loads(raw_cookie_data)
|
|
|
|
|
|
except json.JSONDecodeError:
|
|
|
|
|
|
# 如果不是 JSON，尝试按字符串格式解析 (例如 "name1=value1; name2=value2")
|
|
|
|
|
|
for part in raw_cookie_data.split('; '):
|
|
|
|
|
|
if '=' in part:
|
|
|
|
|
|
key, value = part.split('=', 1)
|
|
|
|
|
|
cookies_to_set[key.strip()] = value.strip()
|
|
|
|
|
|
|
|
|
|
|
|
if cookies_to_set:
|
|
|
|
|
|
self.session.cookies.update(cookies_to_set)
|
|
|
|
|
|
print("Cookie 已成功加载并更新到会话。")
|
|
|
|
|
|
else:
|
|
|
|
|
|
print("未解析到有效的 Cookie 数据。")
|
|
|
|
|
|
else:
|
|
|
|
|
|
print("未指定外部 Cookie 或 Cookie 数据为空。")
|
|
|
|
|
|
# --- 外部导入 Cookie 逻辑结束 ---
|
2025-06-03 01:37:06 +08:00
|
|
|
|
|
2025-05-29 00:07:03 +08:00
|
|
|
|
pass
|
|
|
|
|
|
|
|
|
|
|
|
def getName(self):
|
|
|
|
|
|
pass
|
|
|
|
|
|
|
|
|
|
|
|
def isVideoFormat(self, url):
|
|
|
|
|
|
pass
|
|
|
|
|
|
|
|
|
|
|
|
def manualVideoCheck(self):
|
|
|
|
|
|
pass
|
|
|
|
|
|
|
|
|
|
|
|
def destroy(self):
|
|
|
|
|
|
pass
|
|
|
|
|
|
|
|
|
|
|
|
def homeContent(self, filter):
|
|
|
|
|
|
result = {}
|
|
|
|
|
|
cateManual = {
|
|
|
|
|
|
"视频": "/video",
|
|
|
|
|
|
"片单": "/playlists",
|
|
|
|
|
|
"频道": "/channels",
|
|
|
|
|
|
"分类": "/categories",
|
|
|
|
|
|
"明星": "/pornstars"
|
|
|
|
|
|
}
|
|
|
|
|
|
classes = []
|
|
|
|
|
|
filters = {}
|
|
|
|
|
|
for k in cateManual:
|
|
|
|
|
|
classes.append({
|
|
|
|
|
|
'type_name': k,
|
|
|
|
|
|
'type_id': cateManual[k]
|
|
|
|
|
|
})
|
|
|
|
|
|
result['class'] = classes
|
|
|
|
|
|
result['filters'] = filters
|
|
|
|
|
|
return result
|
|
|
|
|
|
|
|
|
|
|
|
def homeVideoContent(self):
|
|
|
|
|
|
data = self.getpq('/recommended')
|
|
|
|
|
|
vhtml = data("#recommendedListings .pcVideoListItem .phimage")
|
|
|
|
|
|
return {'list': self.getlist(vhtml)}
|
|
|
|
|
|
|
|
|
|
|
|
def categoryContent(self, tid, pg, filter, extend):
|
|
|
|
|
|
vdata = []
|
|
|
|
|
|
result = {}
|
|
|
|
|
|
result['page'] = pg
|
|
|
|
|
|
result['pagecount'] = 9999
|
|
|
|
|
|
result['limit'] = 90
|
|
|
|
|
|
result['total'] = 999999
|
|
|
|
|
|
if tid == '/video' or '_this_video' in tid:
|
|
|
|
|
|
pagestr = f'&' if '?' in tid else f'?'
|
|
|
|
|
|
tid = tid.split('_this_video')[0]
|
|
|
|
|
|
data = self.getpq(f'{tid}{pagestr}page={pg}')
|
|
|
|
|
|
vdata = self.getlist(data('#videoCategory .pcVideoListItem'))
|
|
|
|
|
|
elif tid == '/playlists':
|
|
|
|
|
|
data = self.getpq(f'{tid}?page={pg}')
|
|
|
|
|
|
vhtml = data('#playListSection li')
|
|
|
|
|
|
vdata = []
|
|
|
|
|
|
for i in vhtml.items():
|
|
|
|
|
|
vdata.append({
|
|
|
|
|
|
'vod_id': 'playlists_click_' + i('.thumbnail-info-wrapper .display-block a').attr('href'),
|
|
|
|
|
|
'vod_name': i('.thumbnail-info-wrapper .display-block a').attr('title'),
|
|
|
|
|
|
'vod_pic': self.proxy(i('.largeThumb').attr('src')),
|
|
|
|
|
|
'vod_tag': 'folder',
|
|
|
|
|
|
'vod_remarks': i('.playlist-videos .number').text(),
|
|
|
|
|
|
'style': {"type": "rect", "ratio": 1.33}
|
|
|
|
|
|
})
|
|
|
|
|
|
elif tid == '/channels':
|
|
|
|
|
|
data = self.getpq(f'{tid}?o=rk&page={pg}')
|
|
|
|
|
|
vhtml = data('#filterChannelsSection li .description')
|
|
|
|
|
|
vdata = []
|
|
|
|
|
|
for i in vhtml.items():
|
|
|
|
|
|
vdata.append({
|
|
|
|
|
|
'vod_id': 'director_click_' + i('.avatar a').attr('href'),
|
|
|
|
|
|
'vod_name': i('.avatar img').attr('alt'),
|
|
|
|
|
|
'vod_pic': self.proxy(i('.avatar img').attr('src')),
|
|
|
|
|
|
'vod_tag': 'folder',
|
|
|
|
|
|
'vod_remarks': i('.descriptionContainer ul li').eq(-1).text(),
|
|
|
|
|
|
'style': {"type": "rect", "ratio": 1.33}
|
|
|
|
|
|
})
|
|
|
|
|
|
elif tid == '/categories' and pg == '1':
|
|
|
|
|
|
result['pagecount'] = 1
|
|
|
|
|
|
data = self.getpq(f'{tid}')
|
|
|
|
|
|
vhtml = data('.categoriesListSection li .relativeWrapper')
|
|
|
|
|
|
vdata = []
|
|
|
|
|
|
for i in vhtml.items():
|
|
|
|
|
|
vdata.append({
|
|
|
|
|
|
'vod_id': i('a').attr('href') + '_this_video',
|
|
|
|
|
|
'vod_name': i('a').attr('alt'),
|
|
|
|
|
|
'vod_pic': self.proxy(i('a img').attr('src')),
|
|
|
|
|
|
'vod_tag': 'folder',
|
|
|
|
|
|
'style': {"type": "rect", "ratio": 1.33}
|
|
|
|
|
|
})
|
|
|
|
|
|
elif tid == '/pornstars':
|
|
|
|
|
|
data = self.getpq(f'{tid}?o=t&page={pg}')
|
|
|
|
|
|
vhtml = data('#popularPornstars .performerCard .wrap')
|
|
|
|
|
|
vdata = []
|
|
|
|
|
|
for i in vhtml.items():
|
|
|
|
|
|
vdata.append({
|
|
|
|
|
|
'vod_id': 'pornstars_click_' + i('a').attr('href'),
|
|
|
|
|
|
'vod_name': i('.performerCardName').text(),
|
|
|
|
|
|
'vod_pic': self.proxy(i('a img').attr('src')),
|
|
|
|
|
|
'vod_tag': 'folder',
|
|
|
|
|
|
'vod_year': i('.performerVideosViewsCount span').eq(0).text(),
|
|
|
|
|
|
'vod_remarks': i('.performerVideosViewsCount span').eq(-1).text(),
|
|
|
|
|
|
'style': {"type": "rect", "ratio": 1.33}
|
|
|
|
|
|
})
|
|
|
|
|
|
elif 'playlists_click' in tid:
|
|
|
|
|
|
tid = tid.split('click_')[-1]
|
|
|
|
|
|
if pg == '1':
|
|
|
|
|
|
hdata = self.getpq(tid)
|
|
|
|
|
|
self.token = hdata('#searchInput').attr('data-token')
|
|
|
|
|
|
vdata = self.getlist(hdata('#videoPlaylist .pcVideoListItem .phimage'))
|
|
|
|
|
|
else:
|
|
|
|
|
|
tid = tid.split('playlist/')[-1]
|
|
|
|
|
|
data = self.getpq(f'/playlist/viewChunked?id={tid}&token={self.token}&page={pg}')
|
|
|
|
|
|
vdata = self.getlist(data('.pcVideoListItem .phimage'))
|
|
|
|
|
|
elif 'director_click' in tid:
|
|
|
|
|
|
tid = tid.split('click_')[-1]
|
|
|
|
|
|
data = self.getpq(f'{tid}/videos?page={pg}')
|
|
|
|
|
|
vdata = self.getlist(data('#showAllChanelVideos .pcVideoListItem .phimage'))
|
|
|
|
|
|
elif 'pornstars_click' in tid:
|
|
|
|
|
|
tid = tid.split('click_')[-1]
|
|
|
|
|
|
data = self.getpq(f'{tid}/videos?page={pg}')
|
|
|
|
|
|
vdata = self.getlist(data('#mostRecentVideosSection .pcVideoListItem .phimage'))
|
|
|
|
|
|
result['list'] = vdata
|
|
|
|
|
|
return result
|
|
|
|
|
|
|
|
|
|
|
|
def detailContent(self, ids):
|
|
|
|
|
|
url = f"{self.host}{ids[0]}"
|
|
|
|
|
|
data = self.getpq(ids[0])
|
|
|
|
|
|
vn = data('meta[property="og:title"]').attr('content')
|
|
|
|
|
|
dtext = data('.userInfo .usernameWrap a')
|
|
|
|
|
|
pdtitle = '[a=cr:' + json.dumps(
|
|
|
|
|
|
{'id': 'director_click_' + dtext.attr('href'), 'name': dtext.text()}) + '/]' + dtext.text() + '[/a]'
|
|
|
|
|
|
vod = {
|
|
|
|
|
|
'vod_name': vn,
|
|
|
|
|
|
'vod_director': pdtitle,
|
|
|
|
|
|
'vod_remarks': (data('.userInfo').text() + ' / ' + data('.ratingInfo').text()).replace('\n', ' / '),
|
|
|
|
|
|
'vod_play_from': 'Pornhub',
|
|
|
|
|
|
'vod_play_url': ''
|
|
|
|
|
|
}
|
|
|
|
|
|
js_content = data("#player script").eq(0).text()
|
|
|
|
|
|
plist = [f"{vn}${self.e64(f'{1}@@@@{url}')}"]
|
|
|
|
|
|
try:
|
|
|
|
|
|
pattern = r'"mediaDefinitions":\s*(\[.*?\]),\s*"isVertical"'
|
|
|
|
|
|
match = re.search(pattern, js_content, re.DOTALL)
|
|
|
|
|
|
if match:
|
|
|
|
|
|
json_str = match.group(1)
|
|
|
|
|
|
udata = json.loads(json_str)
|
|
|
|
|
|
plist = [
|
|
|
|
|
|
f"{media['height']}${self.e64(f'{0}@@@@{url}')}"
|
|
|
|
|
|
for media in udata[:-1]
|
|
|
|
|
|
if (url := media.get('videoUrl'))
|
|
|
|
|
|
]
|
|
|
|
|
|
except Exception as e:
|
|
|
|
|
|
print(f"提取mediaDefinitions失败: {str(e)}")
|
|
|
|
|
|
vod['vod_play_url'] = '#'.join(plist)
|
|
|
|
|
|
return {'list': [vod]}
|
|
|
|
|
|
|
|
|
|
|
|
def searchContent(self, key, quick, pg="1"):
|
|
|
|
|
|
data = self.getpq(f'/video/search?search={key}&page={pg}')
|
|
|
|
|
|
return {'list': self.getlist(data('#videoSearchResult .pcVideoListItem .phimage'))}
|
|
|
|
|
|
|
|
|
|
|
|
def playerContent(self, flag, id, vipFlags):
|
|
|
|
|
|
ids = self.d64(id).split('@@@@')
|
|
|
|
|
|
if '.m3u8' in ids[1]: ids[1] = self.proxy(ids[1], 'm3u8')
|
|
|
|
|
|
return {'parse': int(ids[0]), 'url': ids[1], 'header': self.headers}
|
|
|
|
|
|
|
|
|
|
|
|
def localProxy(self, param):
|
|
|
|
|
|
url = self.d64(param.get('url'))
|
|
|
|
|
|
if param.get('type') == 'm3u8':
|
|
|
|
|
|
return self.m3Proxy(url)
|
|
|
|
|
|
else:
|
|
|
|
|
|
return self.tsProxy(url)
|
|
|
|
|
|
|
|
|
|
|
|
def m3Proxy(self, url):
|
|
|
|
|
|
ydata = requests.get(url, headers=self.headers, proxies=self.proxies, allow_redirects=False)
|
|
|
|
|
|
data = ydata.content.decode('utf-8')
|
|
|
|
|
|
if ydata.headers.get('Location'):
|
|
|
|
|
|
url = ydata.headers['Location']
|
|
|
|
|
|
data = requests.get(url, headers=self.headers, proxies=self.proxies).content.decode('utf-8')
|
|
|
|
|
|
lines = data.strip().split('\n')
|
|
|
|
|
|
last_r = url[:url.rfind('/')]
|
|
|
|
|
|
parsed_url = urlparse(url)
|
|
|
|
|
|
durl = parsed_url.scheme + "://" + parsed_url.netloc
|
|
|
|
|
|
for index, string in enumerate(lines):
|
|
|
|
|
|
if '#EXT' not in string:
|
|
|
|
|
|
if 'http' not in string:
|
|
|
|
|
|
domain = last_r if string.count('/') < 2 else durl
|
|
|
|
|
|
string = domain + ('' if string.startswith('/') else '/') + string
|
|
|
|
|
|
lines[index] = self.proxy(string, string.split('.')[-1].split('?')[0])
|
|
|
|
|
|
data = '\n'.join(lines)
|
|
|
|
|
|
return [200, "application/vnd.apple.mpegur", data]
|
|
|
|
|
|
|
|
|
|
|
|
def tsProxy(self, url):
|
|
|
|
|
|
data = requests.get(url, headers=self.headers, proxies=self.proxies, stream=True)
|
|
|
|
|
|
return [200, data.headers['Content-Type'], data.content]
|
|
|
|
|
|
|
|
|
|
|
|
def gethost(self):
|
|
|
|
|
|
try:
|
|
|
|
|
|
response = requests.get('https://www.pornhub.com', headers=self.headers, proxies=self.proxies,
|
|
|
|
|
|
allow_redirects=False)
|
|
|
|
|
|
return response.headers['Location'][:-1]
|
|
|
|
|
|
except Exception as e:
|
|
|
|
|
|
print(f"获取主页失败: {str(e)}")
|
|
|
|
|
|
return "https://www.pornhub.com"
|
|
|
|
|
|
|
|
|
|
|
|
def e64(self, text):
|
|
|
|
|
|
try:
|
|
|
|
|
|
text_bytes = text.encode('utf-8')
|
|
|
|
|
|
encoded_bytes = b64encode(text_bytes)
|
|
|
|
|
|
return encoded_bytes.decode('utf-8')
|
|
|
|
|
|
except Exception as e:
|
|
|
|
|
|
print(f"Base64编码错误: {str(e)}")
|
|
|
|
|
|
return ""
|
|
|
|
|
|
|
|
|
|
|
|
def d64(self, encoded_text):
|
|
|
|
|
|
try:
|
|
|
|
|
|
encoded_bytes = encoded_text.encode('utf-8')
|
|
|
|
|
|
decoded_bytes = b64decode(encoded_bytes)
|
|
|
|
|
|
return decoded_bytes.decode('utf-8')
|
|
|
|
|
|
except Exception as e:
|
|
|
|
|
|
print(f"Base64解码错误: {str(e)}")
|
|
|
|
|
|
return ""
|
|
|
|
|
|
|
|
|
|
|
|
def getlist(self, data):
|
|
|
|
|
|
vlist = []
|
|
|
|
|
|
for i in data.items():
|
|
|
|
|
|
vlist.append({
|
|
|
|
|
|
'vod_id': i('a').attr('href'),
|
|
|
|
|
|
'vod_name': i('a').attr('title'),
|
|
|
|
|
|
'vod_pic': self.proxy(i('img').attr('src')),
|
|
|
|
|
|
'vod_remarks': i('.bgShadeEffect').text() or i('.duration').text(),
|
|
|
|
|
|
'style': {'ratio': 1.33, 'type': 'rect'}
|
|
|
|
|
|
})
|
|
|
|
|
|
return vlist
|
|
|
|
|
|
|
|
|
|
|
|
def getpq(self, path):
|
|
|
|
|
|
try:
|
|
|
|
|
|
response = self.session.get(f'{self.host}{path}').text
|
|
|
|
|
|
return pq(response.encode('utf-8'))
|
|
|
|
|
|
except Exception as e:
|
|
|
|
|
|
print(f"请求失败: , {str(e)}")
|
|
|
|
|
|
return None
|
|
|
|
|
|
|
|
|
|
|
|
def proxy(self, data, type='img'):
|
|
|
|
|
|
if data and len(self.proxies):return f"{self.getProxyUrl()}&url={self.e64(data)}&type={type}"
|
|
|
|
|
|
else:return data
|
