591 lines
23 KiB
Python
591 lines
23 KiB
Python
"""
|
||
@header({
|
||
searchable: 1,
|
||
filterable: 1,
|
||
quickSearch: 1,
|
||
title: '好色TV[密]',
|
||
lang: 'hipy'
|
||
})
|
||
"""
|
||
|
||
import re
|
||
import sys
|
||
import urllib.parse
|
||
import threading
|
||
import time
|
||
import requests
|
||
from pyquery import PyQuery as pq
|
||
|
||
sys.path.append('..')
|
||
from base.spider import Spider
|
||
|
||
class Spider(Spider):
|
||
def __init__(self):
|
||
# 基础配置
|
||
self.name = '好色TV（优）'
|
||
self.host = 'https://m.ml0987.online/'
|
||
self.candidate_hosts = [
|
||
"https://m.ml0987.online/"
|
||
]
|
||
self.headers = {
|
||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
|
||
'Referer': self.host
|
||
}
|
||
self.timeout = 5000
|
||
|
||
# 分类映射
|
||
self.class_map = {
|
||
'视频': {'type_id': 'list', 'url_suffix': ''},
|
||
'周榜': {'type_id': 'top7', 'url_suffix': 'top7'},
|
||
'月榜': {'type_id': 'top', 'url_suffix': 'top'},
|
||
'5分钟+': {'type_id': '5min', 'url_suffix': '5min'},
|
||
'10分钟+': {'type_id': 'long', 'url_suffix': 'long'}
|
||
}
|
||
|
||
def getName(self):
|
||
return self.name
|
||
|
||
def init(self, extend=""):
|
||
# 尝试获取最快可用域名
|
||
self.host = self.get_fastest_host()
|
||
self.headers['Referer'] = self.host
|
||
|
||
def isVideoFormat(self, url):
|
||
if not url:
|
||
return False
|
||
return any(fmt in url.lower() for fmt in ['.mp4', '.m3u8', '.flv', '.avi'])
|
||
|
||
def manualVideoCheck(self):
|
||
def check(url):
|
||
if not self.isVideoFormat(url):
|
||
return False
|
||
try:
|
||
resp = self.fetch(url, headers=self.headers, method='HEAD', timeout=3)
|
||
return resp.status_code in (200, 302) and 'video' in resp.headers.get('Content-Type', '')
|
||
except:
|
||
return False
|
||
return check
|
||
|
||
def get_fastest_host(self):
|
||
"""测试候选域名，返回最快可用的"""
|
||
results = {}
|
||
threads = []
|
||
|
||
def test_host(url):
|
||
try:
|
||
start_time = time.time()
|
||
resp = requests.head(url, headers=self.headers, timeout=2, allow_redirects=False)
|
||
if resp.status_code in (200, 301, 302):
|
||
delay = (time.time() - start_time) * 1000
|
||
results[url] = delay
|
||
else:
|
||
results[url] = float('inf')
|
||
except:
|
||
results[url] = float('inf')
|
||
|
||
for host in self.candidate_hosts:
|
||
t = threading.Thread(target=test_host, args=(host,))
|
||
threads.append(t)
|
||
t.start()
|
||
for t in threads:
|
||
t.join()
|
||
|
||
valid_hosts = [(h, d) for h, d in results.items() if d != float('inf')]
|
||
return valid_hosts[0][0] if valid_hosts else self.candidate_hosts[0]
|
||
|
||
def homeContent(self, filter):
|
||
result = {}
|
||
# 构造分类列表
|
||
classes = []
|
||
for name, info in self.class_map.items():
|
||
classes.append({
|
||
'type_name': name,
|
||
'type_id': info['type_id']
|
||
})
|
||
result['class'] = classes
|
||
|
||
try:
|
||
# 获取首页内容
|
||
html = self.fetch_with_retry(self.host, retry=2, timeout=5).text
|
||
data = pq(html)
|
||
|
||
# 提取视频列表
|
||
vlist = []
|
||
items = data('.row .col-xs-6.col-md-3')
|
||
for item in items.items():
|
||
try:
|
||
title = item('h5').text().strip()
|
||
if not title:
|
||
continue
|
||
|
||
# 提取图片URL
|
||
style = item('.image').attr('style') or ''
|
||
pic_match = re.search(r'url\(["\']?([^"\']+)["\']?\)', style)
|
||
vod_pic = pic_match.group(1) if pic_match else ''
|
||
if vod_pic and not vod_pic.startswith('http'):
|
||
vod_pic = f"{self.host.rstrip('/')}/{vod_pic.lstrip('/')}"
|
||
|
||
# 提取时长备注
|
||
desc = item('.duration').text().strip() or '未知'
|
||
|
||
# 提取视频ID
|
||
href = item('a').attr('href') or ''
|
||
if not href:
|
||
continue
|
||
vod_id = href.split('/')[-1]
|
||
if not vod_id.endswith('.htm'):
|
||
vod_id += '.htm'
|
||
|
||
vlist.append({
|
||
'vod_id': vod_id,
|
||
'vod_name': title,
|
||
'vod_pic': vod_pic,
|
||
'vod_remarks': desc
|
||
})
|
||
except Exception as e:
|
||
print(f"解析首页视频项失败: {e}")
|
||
continue
|
||
|
||
result['list'] = vlist
|
||
except Exception as e:
|
||
print(f"首页解析失败: {e}")
|
||
result['list'] = []
|
||
return result
|
||
|
||
def homeVideoContent(self):
|
||
return []
|
||
|
||
def categoryContent(self, tid, pg, filter, extend):
|
||
result = {}
|
||
try:
|
||
# 匹配分类信息
|
||
cate_info = None
|
||
for name, info in self.class_map.items():
|
||
if info['type_id'] == tid:
|
||
cate_info = info
|
||
break
|
||
|
||
if not cate_info:
|
||
result['list'] = []
|
||
return result
|
||
|
||
# 关键修复：区分视频分类与其他分类的URL格式
|
||
if tid == 'list': # 视频分类（type_id为list）
|
||
url = f"{self.host}list-{pg}.htm" # 格式：list-1.htm、list-2.htm
|
||
else: # 其他分类（周榜/月榜等）：xxx_list-{pg}.htm
|
||
url = f"{self.host}{cate_info['url_suffix']}_list-{pg}.htm"
|
||
|
||
# 请求分类页
|
||
html = self.fetch(url, headers=self.headers, timeout=8).text
|
||
html = html.encode('utf-8', errors='ignore').decode('utf-8')
|
||
data = pq(html)
|
||
|
||
# 提取视频列表
|
||
vlist = []
|
||
items = data('.row .col-xs-6.col-md-3')
|
||
for item in items.items():
|
||
try:
|
||
title = item('h5').text().strip()
|
||
if not title:
|
||
continue
|
||
|
||
style = item('.image').attr('style') or ''
|
||
pic_match = re.search(r'url\(["\']?([^"\']+)["\']?\)', style)
|
||
vod_pic = pic_match.group(1) if pic_match else ''
|
||
if vod_pic and not vod_pic.startswith('http'):
|
||
vod_pic = f"{self.host.rstrip('/')}/{vod_pic.lstrip('/')}"
|
||
|
||
desc = item('.duration').text().strip() or '未知'
|
||
|
||
href = item('a').attr('href') or ''
|
||
if not href:
|
||
continue
|
||
vod_id = href.split('/')[-1]
|
||
if not vod_id.endswith('.htm'):
|
||
vod_id += '.htm'
|
||
|
||
vlist.append({
|
||
'vod_id': vod_id,
|
||
'vod_name': title,
|
||
'vod_pic': vod_pic,
|
||
'vod_remarks': desc
|
||
})
|
||
except Exception as e:
|
||
print(f"解析分类视频项失败: {e}")
|
||
continue
|
||
|
||
# 提取总页数
|
||
pagecount = 1
|
||
try:
|
||
pagination = data('.pagination1 li a')
|
||
page_nums = []
|
||
for a in pagination.items():
|
||
text = a.text().strip()
|
||
if text.isdigit():
|
||
page_nums.append(int(text))
|
||
if page_nums:
|
||
pagecount = max(page_nums)
|
||
except:
|
||
pagecount = 1
|
||
|
||
result['list'] = vlist
|
||
result['page'] = pg
|
||
result['pagecount'] = pagecount
|
||
result['limit'] = len(vlist)
|
||
result['total'] = 999999
|
||
except Exception as e:
|
||
print(f"分类解析失败: {e}")
|
||
result['list'] = []
|
||
result['page'] = pg
|
||
result['pagecount'] = 1
|
||
result['limit'] = 0
|
||
result['total'] = 0
|
||
return result
|
||
|
||
def detailContent(self, ids):
|
||
try:
|
||
if not ids or not ids[0]:
|
||
return {'list': []}
|
||
|
||
vod_id = ids[0].strip()
|
||
if not vod_id.endswith('.htm'):
|
||
vod_id += '.htm'
|
||
url = f"{self.host}{vod_id.lstrip('/')}"
|
||
|
||
html = self.fetch_with_retry(url, retry=2, timeout=8).text
|
||
html = html.encode('utf-8', errors='ignore').decode('utf-8')
|
||
data = pq(html)
|
||
|
||
# 提取标题
|
||
title = data('.panel-title, .video-title, h1').text().strip() or '未知标题'
|
||
|
||
# 提取封面图
|
||
vod_pic = ''
|
||
poster_style = data('.vjs-poster').attr('style') or ''
|
||
pic_match = re.search(r'url\(["\']?([^"\']+)["\']?\)', poster_style)
|
||
if pic_match:
|
||
vod_pic = pic_match.group(1)
|
||
if not vod_pic:
|
||
vod_pic = data('.video-pic img, .vjs-poster img, .thumbnail img').attr('src') or ''
|
||
if vod_pic and not vod_pic.startswith('http'):
|
||
vod_pic = f"{self.host}{vod_pic.lstrip('/')}"
|
||
|
||
# 提取时长和观看量
|
||
duration = '未知'
|
||
views = '未知'
|
||
info_items = data('.panel-body .col-md-3, .video-info .info-item, .info p')
|
||
for item in info_items.items():
|
||
text = item.text().strip()
|
||
if '时长' in text or 'duration' in text.lower():
|
||
duration = text.replace('时长：', '').replace('时长', '').strip()
|
||
elif '观看' in text or 'views' in text.lower():
|
||
views_match = re.search(r'(\d+\.?\d*[kK]?)次观看', text)
|
||
if views_match:
|
||
views = views_match.group(1)
|
||
else:
|
||
views = text.replace('观看：', '').replace('观看', '').strip()
|
||
remarks = f"{duration} | {views}"
|
||
|
||
# 简化版播放线路提取 - 直接基于找到的链接生成第二条线路
|
||
video_urls = []
|
||
|
||
# 首先尝试提取任意一个m3u8链接
|
||
found_url = None
|
||
|
||
# 方法1: 从video标签提取
|
||
video_element = data('video#video-play_html5_api')
|
||
if video_element:
|
||
video_src = video_element.attr('src')
|
||
if video_src and '.m3u8' in video_src:
|
||
found_url = video_src
|
||
print(f"从video标签找到链接: {found_url}")
|
||
|
||
# 方法2: 从source标签提取
|
||
if not found_url:
|
||
source_element = data('source#video-source')
|
||
if source_element:
|
||
source_src = source_element.attr('src')
|
||
if source_src and '.m3u8' in source_src:
|
||
found_url = source_src
|
||
print(f"从source标签找到链接: {found_url}")
|
||
|
||
# 方法3: 正则搜索
|
||
if not found_url:
|
||
m3u8_matches = re.findall(r'https?://[^\s"\']+\.m3u8[^\s"\']*', html)
|
||
if m3u8_matches:
|
||
found_url = m3u8_matches[0]
|
||
print(f"通过正则找到链接: {found_url}")
|
||
|
||
# 清理找到的URL
|
||
if found_url:
|
||
found_url = found_url.replace('\\/', '/').replace('\\u002F', '/').replace('\\"', '')
|
||
if not found_url.startswith('http'):
|
||
found_url = f"https:{found_url}" if found_url.startswith('//') else f"https://{found_url}"
|
||
|
||
# 关键修改：将HD线路放在前面
|
||
if 'hdcdn.online' in found_url:
|
||
# 如果找到的是HD线路，直接添加，然后生成主线路
|
||
video_urls.append(found_url)
|
||
second_url = found_url.replace('hdcdn.online', 'hsex.tv')
|
||
video_urls.append(second_url)
|
||
print(f"生成主线路: {second_url}")
|
||
elif 'hsex.tv' in found_url:
|
||
# 如果找到的是主线路，先生成HD线路，再添加主线路
|
||
second_url = found_url.replace('hsex.tv', 'hdcdn.online')
|
||
video_urls.append(second_url) # HD线路在前
|
||
video_urls.append(found_url) # 主线路在后
|
||
print(f"生成HD线路: {second_url}")
|
||
else:
|
||
# 如果是其他域名，直接添加
|
||
video_urls.append(found_url)
|
||
video_urls.append(found_url) # 复制一份作为备用
|
||
print(f"复制备用线路: {found_url}")
|
||
|
||
print(f"最终播放线路: {video_urls}")
|
||
|
||
# 构建播放源信息 - 确保HD线路优先显示
|
||
play_from = []
|
||
play_url = []
|
||
|
||
for i, video_url in enumerate(video_urls):
|
||
if 'hdcdn.online' in video_url:
|
||
line_name = 'HD线路' # HD线路优先
|
||
elif 'hsex.tv' in video_url:
|
||
line_name = '主线路'
|
||
else:
|
||
line_name = f'线路{i+1}'
|
||
|
||
play_from.append(line_name)
|
||
play_url.append(f'正片${video_url}')
|
||
|
||
# 如果没有找到任何线路
|
||
if not play_from:
|
||
play_from = ['好色TV']
|
||
play_url = ['正片$暂无播放地址']
|
||
|
||
# 确保有两条线路（即使只有一条也复制一份）
|
||
if len(play_from) == 1:
|
||
play_from.append(f'{play_from[0]}-备用')
|
||
play_url.append(play_url[0])
|
||
|
||
vod = {
|
||
'vod_id': vod_id,
|
||
'vod_name': title,
|
||
'vod_pic': vod_pic,
|
||
'vod_remarks': remarks,
|
||
'vod_play_from': '$$$'.join(play_from),
|
||
'vod_play_url': '$$$'.join(play_url)
|
||
}
|
||
return {'list': [vod]}
|
||
except Exception as e:
|
||
print(f"详情解析失败: {e}")
|
||
import traceback
|
||
traceback.print_exc()
|
||
return {'list': []}
|
||
|
||
def searchContent(self, key, quick, pg=1):
|
||
try:
|
||
# 关键词合法性校验
|
||
if not key.strip():
|
||
print("搜索关键词不能为空")
|
||
return {'list': [], 'page': int(pg), 'pagecount': 1, 'limit': 0, 'total': 0}
|
||
|
||
# 编码关键词
|
||
encoded_key = urllib.parse.quote(key.strip(), encoding='utf-8', errors='replace')
|
||
|
||
# 修复搜索翻页：根据页码构造正确的搜索URL
|
||
if int(pg) == 1:
|
||
# 第一页：/search.htm?search=关键词&sort=new
|
||
search_url = f"{self.host}search.htm"
|
||
else:
|
||
# 第二页及以后：/search-页码.htm?search=关键词&sort=new
|
||
search_url = f"{self.host}search-{pg}.htm"
|
||
|
||
# 搜索参数 - 添加 sort=new 参数
|
||
params = {
|
||
'search': encoded_key,
|
||
'sort': 'new' # 新增排序参数
|
||
}
|
||
|
||
# 发起请求
|
||
resp = self.fetch(
|
||
url=search_url,
|
||
headers=self.headers,
|
||
params=params,
|
||
timeout=8
|
||
)
|
||
|
||
if resp.status_code not in (200, 302):
|
||
print(f"搜索页面请求失败，URL：{resp.url}，状态码：{resp.status_code}")
|
||
return {'list': [], 'page': int(pg), 'pagecount': 1, 'limit': 0, 'total': 0}
|
||
|
||
# 处理页面内容
|
||
html = resp.text.encode('utf-8', errors='ignore').decode('utf-8')
|
||
data = pq(html)
|
||
|
||
# 检测无结果场景
|
||
no_result_texts = ['没有找到相关视频', '无搜索结果', 'No results found', '未找到匹配内容']
|
||
no_result = any(data(f'div:contains("{text}"), p:contains("{text}")').text() for text in no_result_texts)
|
||
if no_result:
|
||
print(f"搜索关键词「{key}」第{pg}页无结果")
|
||
return {'list': [], 'page': int(pg), 'pagecount': 1, 'limit': 0, 'total': 0}
|
||
|
||
# 解析搜索结果
|
||
vlist = []
|
||
items = data('.row .col-xs-6.col-md-3')
|
||
for item in items.items():
|
||
try:
|
||
title = item('h5').text().strip()
|
||
if not title:
|
||
continue
|
||
|
||
style = item('.image').attr('style') or ''
|
||
pic_match = re.search(r'url\(["\']?([^"\']+)["\']?\)', style)
|
||
vod_pic = pic_match.group(1) if pic_match else ''
|
||
if vod_pic and not vod_pic.startswith(('http://', 'https://')):
|
||
vod_pic = f"{self.host.rstrip('/')}/{vod_pic.lstrip('/')}"
|
||
|
||
desc = item('.duration').text().strip() or '未知时长'
|
||
|
||
href = item('a').attr('href') or ''
|
||
if not href:
|
||
continue
|
||
vod_id = href.split('/')[-1]
|
||
if not vod_id.endswith('.htm'):
|
||
vod_id += '.htm'
|
||
|
||
vlist.append({
|
||
'vod_id': vod_id,
|
||
'vod_name': title,
|
||
'vod_pic': vod_pic,
|
||
'vod_remarks': desc
|
||
})
|
||
except Exception as e:
|
||
print(f"解析单条搜索结果失败：{e}（跳过该条）")
|
||
continue
|
||
|
||
# 解析总页数
|
||
pagecount = 1
|
||
try:
|
||
pagination = data('.pagination1 li a')
|
||
page_nums = []
|
||
for a in pagination.items():
|
||
text = a.text().strip()
|
||
if text.isdigit():
|
||
page_nums.append(int(text))
|
||
if page_nums:
|
||
pagecount = max(page_nums)
|
||
print(f"搜索关键词「{key}」分页解析完成，共{pagecount}页")
|
||
except Exception as e:
|
||
print(f"解析分页失败（默认单页）：{e}")
|
||
pagecount = 1
|
||
|
||
# 返回结果
|
||
total = len(vlist) * pagecount
|
||
print(f"搜索关键词「{key}」第{pg}页处理完成，结果{len(vlist)}条，总页数{pagecount}")
|
||
return {
|
||
'list': vlist,
|
||
'page': int(pg),
|
||
'pagecount': pagecount,
|
||
'limit': len(vlist),
|
||
'total': total
|
||
}
|
||
except Exception as e:
|
||
print(f"搜索功能整体异常：{e}")
|
||
return {
|
||
'list': [],
|
||
'page': int(pg),
|
||
'pagecount': 1,
|
||
'limit': 0,
|
||
'total': 0
|
||
}
|
||
|
||
def playerContent(self, flag, id, vipFlags):
|
||
headers = self.headers.copy()
|
||
headers.update({
|
||
'Referer': self.host,
|
||
'Origin': self.host.rstrip('/'),
|
||
'Host': urllib.parse.urlparse(self.host).netloc,
|
||
})
|
||
|
||
return {
|
||
'parse': 1,
|
||
'url': id,
|
||
'header': headers,
|
||
'double': True
|
||
}
|
||
|
||
def localProxy(self, param):
|
||
try:
|
||
url = param['url']
|
||
if url and not url.startswith(('http://', 'https://')):
|
||
url = f"{self.host.rstrip('/')}/{url.lstrip('/')}"
|
||
|
||
img_headers = self.headers.copy()
|
||
img_headers.update({'Accept': 'image/avif,image/webp,image/apng,image/svg+xml,image/*,*/*;q=0.8'})
|
||
|
||
res = self.fetch(url, headers=img_headers, timeout=10)
|
||
content_type = res.headers.get('Content-Type', 'image/jpeg')
|
||
|
||
return [200, content_type, res.content]
|
||
except Exception as e:
|
||
print(f"图片代理失败: {e}")
|
||
return [200, 'image/jpeg', b'']
|
||
|
||
def fetch_with_retry(self, url, retry=2, timeout=5):
|
||
for i in range(retry + 1):
|
||
try:
|
||
resp = self.fetch(url, headers=self.headers, timeout=timeout)
|
||
if resp.status_code in (200, 301, 302):
|
||
return resp
|
||
print(f"请求{url}返回状态码{resp.status_code}，重试中...")
|
||
except Exception as e:
|
||
print(f"第{i+1}次请求{url}失败: {e}")
|
||
if i < retry:
|
||
time.sleep(0.5)
|
||
return type('obj', (object,), {'text': '', 'status_code': 404})
|
||
|
||
def fetch(self, url, headers=None, timeout=5, method='GET', params=None):
|
||
headers = headers or self.headers
|
||
params = params or {}
|
||
try:
|
||
# 直接请求目标URL
|
||
if method.upper() == 'GET':
|
||
resp = requests.get(
|
||
url,
|
||
headers=headers,
|
||
timeout=timeout,
|
||
allow_redirects=True,
|
||
params=params
|
||
)
|
||
elif method.upper() == 'HEAD':
|
||
resp = requests.head(
|
||
url,
|
||
headers=headers,
|
||
timeout=timeout,
|
||
allow_redirects=False,
|
||
params=params
|
||
)
|
||
else:
|
||
resp = requests.get(
|
||
url,
|
||
headers=headers,
|
||
timeout=timeout,
|
||
allow_redirects=True,
|
||
params=params
|
||
)
|
||
|
||
# 自动适配编码，避免中文乱码
|
||
if 'charset' in resp.headers.get('Content-Type', '').lower():
|
||
resp.encoding = resp.apparent_encoding
|
||
else:
|
||
resp.encoding = 'utf-8'
|
||
return resp
|
||
except Exception as e:
|
||
print(f"网络请求失败({url}): {e}")
|
||
return type('obj', (object,), {
|
||
'text': '',
|
||
'status_code': 500,
|
||
'headers': {},
|
||
'url': url
|
||
}) |