Add files via upload
This commit is contained in:
yigedashu
+591
@@ -0,0 +1,591 @@
|
||||
"""
|
||||
@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
|
||||
})
|
||||
@@ -0,0 +1,543 @@
|
||||
"""
|
||||
@header({
|
||||
searchable: 1,
|
||||
filterable: 1,
|
||||
quickSearch: 1,
|
||||
title: '好色™ Tv',
|
||||
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://hsex.icu/'
|
||||
self.candidate_hosts = [
|
||||
"https://hsex.icu/",
|
||||
"https://hsex1.icu/",
|
||||
"https://hsex.tv/"
|
||||
]
|
||||
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（关键修复：视频分类url_suffix设为空，适配list-{pg}.htm格式）
|
||||
self.class_map = {
|
||||
'视频': {'type_id': 'list', 'url_suffix': ''}, # 修复点1：视频分类后缀为空
|
||||
'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}"
|
||||
|
||||
# 提取播放地址
|
||||
video_url = ''
|
||||
m3u8_match = re.search(r'videoUrl\s*=\s*["\']([^"\']+\.m3u8)["\']', html)
|
||||
if m3u8_match:
|
||||
video_url = m3u8_match.group(1)
|
||||
if not video_url:
|
||||
source = data('source[src*=".m3u8"], source[src*=".mp4"]')
|
||||
video_url = source.attr('src') or ''
|
||||
if not video_url:
|
||||
js_matches = re.findall(r'(https?://[^\s"\']+\.(?:m3u8|mp4))', html)
|
||||
if js_matches:
|
||||
video_url = js_matches[0]
|
||||
|
||||
if video_url and not video_url.startswith('http'):
|
||||
video_url = f"{self.host}{video_url.lstrip('/')}"
|
||||
|
||||
vod = {
|
||||
'vod_id': vod_id,
|
||||
'vod_name': title,
|
||||
'vod_pic': vod_pic,
|
||||
'vod_remarks': remarks,
|
||||
'vod_play_from': '好色TV（优）',
|
||||
'vod_play_url': f'正片${video_url}' if video_url else '正片$暂无地址'
|
||||
}
|
||||
return {'list': [vod]}
|
||||
except Exception as e:
|
||||
print(f"详情解析失败: {e}")
|
||||
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')
|
||||
|
||||
# 构造搜索URL
|
||||
search_url = f"{self.host}search.htm"
|
||||
params = {
|
||||
'search': encoded_key,
|
||||
'page': int(pg)
|
||||
}
|
||||
|
||||
# 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（修复点2：补全page键的引号，修正语法错误）
|
||||
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), # 原代码此处缺少引号，导致语法错误
|
||||
'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,
|
||||
})
|
||||
|
||||
# 根据rule中的double设置
|
||||
return {
|
||||
'parse': 1, # 根据rule中的play_parse设置
|
||||
'url': id,
|
||||
'header': headers,
|
||||
'double': True # 根据rule中的double设置
|
||||
}
|
||||
|
||||
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(f'https://vpsdn.leuse.top/proxy?single=true&url={urllib.parse.quote(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:
|
||||
if method.upper() == 'GET':
|
||||
resp = requests.get(
|
||||
f'https://vpsdn.leuse.top/proxy?single=true&url={urllib.parse.quote(url)}',
|
||||
headers=headers,
|
||||
timeout=timeout,
|
||||
allow_redirects=True,
|
||||
params=params # 支持GET请求带参数，适配搜索分页
|
||||
)
|
||||
elif method.upper() == 'HEAD':
|
||||
resp = requests.head(
|
||||
f'https://vpsdn.leuse.top/proxy?single=true&url={urllib.parse.quote(url)}',
|
||||
headers=headers,
|
||||
timeout=timeout,
|
||||
allow_redirects=False,
|
||||
params=params
|
||||
)
|
||||
else:
|
||||
resp = requests.get( # 默认GET请求，兼容其他方法调用
|
||||
f'https://vpsdn.leuse.top/proxy?single=true&url={urllib.parse.quote(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}")
|
||||
# 返回统一格式空响应，避免后续逻辑崩溃
|
||||
return type('obj', (object,), {
|
||||
'text': '',
|
||||
'status_code': 500,
|
||||
'headers': {},
|
||||
'url': url
|
||||
})
|
||||
|
||||
|
||||
# ------------------------------
|
||||
# 可选测试代码（运行时注释或删除，用于验证功能）
|
||||
# ------------------------------
|
||||
if __name__ == "__main__":
|
||||
# 初始化爬虫
|
||||
spider = Spider()
|
||||
spider.init()
|
||||
|
||||
# 测试首页内容
|
||||
print("=== 测试首页 ===")
|
||||
home_data = spider.homeContent(filter='')
|
||||
print(f"首页分类数：{len(home_data['class'])}")
|
||||
print(f"首页视频数：{len(home_data['list'])}")
|
||||
|
||||
# 测试视频分类（修复后的数据获取）
|
||||
print("\n=== 测试视频分类（第1页） ===")
|
||||
cate_data = spider.categoryContent(tid='list', pg=1, filter='', extend='')
|
||||
print(f"视频分类第1页视频数：{len(cate_data['list'])}")
|
||||
print(f"视频分类总页数：{cate_data['pagecount']}")
|
||||
|
||||
# 测试搜索功能（修复语法错误后）
|
||||
print("\n=== 测试搜索（关键词：测试） ===")
|
||||
search_data = spider.searchContent(key="测试", quick=False, pg=1)
|
||||
print(f"搜索结果数：{len(search_data['list'])}")
|
||||
print(f"搜索总页数：{search_data['pagecount']}")
|
||||
@@ -0,0 +1,82 @@
|
||||
"""
|
||||
@header({
|
||||
searchable: 1,
|
||||
filterable: 1,
|
||||
quickSearch: 1,
|
||||
title: '色播聚合',
|
||||
lang: 'hipy'
|
||||
})
|
||||
"""
|
||||
|
||||
#coding=utf-8
|
||||
#!/usr/bin/python
|
||||
import sys
|
||||
sys.path.append('..')
|
||||
from base.spider import Spider
|
||||
|
||||
class Spider(Spider):
|
||||
def init(self,extend=""):
|
||||
self.base_url='http://api.hclyz.com:81/mf'
|
||||
|
||||
def homeContent(self,filter):
|
||||
classes = [{"type_name": "色播聚合","type_id":"/json.txt"}]
|
||||
result = {"class": classes}
|
||||
return result
|
||||
|
||||
def categoryContent(self,tid,pg,filter,extend):
|
||||
home = self.fetch(f'{self.base_url}/json.txt').json()
|
||||
data = home.get("pingtai")[1:]
|
||||
videos = [
|
||||
{
|
||||
"vod_id": "/" + item['address'],
|
||||
"vod_name": item['title'],
|
||||
"vod_pic": item['xinimg'].replace("http://cdn.gcufbd.top/img/",
|
||||
"https://slink.ltd/https://raw.githubusercontent.com/fish2018/lib/refs/heads/main/imgs/"),
|
||||
"vod_remarks": item['Number'],
|
||||
"style": {"type": "rect", "ratio": 1.33}
|
||||
} for item in sorted(data, key=lambda x: int(x['Number']), reverse=True)
|
||||
]
|
||||
result = {
|
||||
"page": pg,
|
||||
"pagecount": 1,
|
||||
"limit": len(videos),
|
||||
"total": len(videos),
|
||||
"list": videos
|
||||
}
|
||||
return result
|
||||
|
||||
def detailContent(self,array):
|
||||
id = array[0]
|
||||
data = self.fetch(f'{self.base_url}/{id}').json()
|
||||
zhubo = data['zhubo']
|
||||
playUrls = '#'.join([f"{vod['title']}${vod['address']}" for vod in zhubo])
|
||||
vod = [{
|
||||
"vod_play_from": 'sebo',
|
||||
"vod_play_url": playUrls,
|
||||
"vod_content": 'https://github.com/fish2018',
|
||||
}]
|
||||
result = {"list": vod}
|
||||
return result
|
||||
|
||||
def playerContent(self,flag,id,vipFlags):
|
||||
result = {
|
||||
'parse': 0,
|
||||
'url': id
|
||||
}
|
||||
return result
|
||||
|
||||
def getName(self):
|
||||
return '色播聚合'
|
||||
|
||||
def homeVideoContent(self):
|
||||
pass
|
||||
def isVideoFormat(self,url):
|
||||
pass
|
||||
def manualVideoCheck(self):
|
||||
pass
|
||||
def searchContent(self,key,quick):
|
||||
pass
|
||||
def destroy(self):
|
||||
pass
|
||||
def localProxy(self, param):
|
||||
pass
|
||||
@@ -0,0 +1,154 @@
|
||||
"""
|
||||
@header({
|
||||
searchable: 1,
|
||||
filterable: 1,
|
||||
quickSearch: 1,
|
||||
title: '首页',
|
||||
lang: 'hipy'
|
||||
})
|
||||
"""
|
||||
|
||||
# coding=utf-8
|
||||
# !/usr/bin/python
|
||||
import sys
|
||||
import requests
|
||||
import datetime
|
||||
from bs4 import BeautifulSoup
|
||||
import re
|
||||
import base64
|
||||
from base.spider import Spider
|
||||
import json
|
||||
|
||||
sys.path.append('..')
|
||||
xurl = "http://xjj2.716888.xyz"
|
||||
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',
|
||||
'Cookie':'mk_encrypt_c21f969b5f03d33d43e04f8f136e7682=390e11f0d5ae13b2787e6a72db11527f'
|
||||
}
|
||||
|
||||
|
||||
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 homeContent(self, filter):
|
||||
pass
|
||||
|
||||
def homeVideoContent(self):
|
||||
id = ['4k/4k.php', 'djxjj/dj1.php', 'zj/jipinyz/jipinyz.php', 'zj/xuejie/xuejie.php', 'zj/kawayi/kawayi.php',
|
||||
'zj/nennen/nennen.php', 'zj/heji1/heji1.php', 'zj/sihuawd/sihuawd.php', 'zj/wanmeisc/wanmeisc.php',
|
||||
'zj/manyao/manyao.php', 'zj/sihuadd/sihuadd.php', 'zj/qingchun/qingchun.php', 'zj/cos/cos.php',
|
||||
'zj/jingpinbz/jingpinbz.php', 'zj/jipinll/jipinll.php', 'zj/nideym/nideym.php', 'zj/tianmei/tianmei.php',
|
||||
'zj/yusi/yusi.php', 'zj/shuaige/shuaige.php', 'zj/rewu/rewu.php', 'zj/jingpinsc/jingpinsc.php']
|
||||
name = ['随机', 'DJ姐姐', '极品钰足', '学姐系列', '卡哇伊', '嫩嫩系列', '美女舞蹈', '丝滑舞蹈', '完美身材',
|
||||
'慢摇系列', '丝滑吊带', '清纯系列', 'COS系列', '精品变装', '极品罗丽', '你的裕梦', '甜妹系列',
|
||||
'御丝系列', '帅哥哥', '热舞系列', '精品收藏']
|
||||
pic = ['https://img0.baidu.com/it/u=2236794495,926227820&fm=253&fmt=auto&app=138&f=JPEG?w=1091&h=500',
|
||||
'https://pic.rmb.bdstatic.com/mvideo/e17d86ce4489a02870ace9a25a804c3e',
|
||||
'https://img1.baidu.com/it/u=4087009209,613234683&fm=253&fmt=auto&app=138&f=JPEG?w=500&h=364',
|
||||
'https://img1.baidu.com/it/u=2347706654,3055017263&fm=253&fmt=auto&app=138&f=JPEG?w=500&h=750',
|
||||
'https://img2.baidu.com/it/u=3715511725,1094436549&fm=253&fmt=auto&app=138&f=JPEG?w=500&h=1083',
|
||||
'https://img2.baidu.com/it/u=2560410906,3760952489&fm=253&fmt=auto&app=138&f=JPEG?w=500&h=750',
|
||||
'https://img0.baidu.com/it/u=4119328645,2294770712&fm=253&fmt=auto&app=138&f=JPEG?w=500&h=750',
|
||||
'https://img1.baidu.com/it/u=3167365498,4156845177&fm=253&fmt=auto&app=120&f=JPEG?w=355&h=631',
|
||||
'https://img2.baidu.com/it/u=2214691242,2295609938&fm=253&fmt=auto&app=120&f=JPEG?w=800&h=973',
|
||||
'https://img1.baidu.com/it/u=3930123826,1131807820&fm=253&fmt=auto&app=138&f=JPEG?w=889&h=500',
|
||||
'https://img2.baidu.com/it/u=3998619741,1128428746&fm=253&fmt=auto&app=138&f=JPEG?w=500&h=594',
|
||||
'https://img2.baidu.com/it/u=1507871502,2316279678&fm=253&fmt=auto&app=138&f=JPEG?w=500&h=768',
|
||||
'https://img0.baidu.com/it/u=2245878765,4037513957&fm=253&fmt=auto&app=138&f=JPEG?w=617&h=411',
|
||||
'https://img1.baidu.com/it/u=3623293272,829752126&fm=253&fmt=auto&app=138&f=JPEG?w=285&h=285',
|
||||
'https://img2.baidu.com/it/u=1922261112,3647796435&fm=253&fmt=auto&app=120&f=JPEG?w=500&h=542',
|
||||
'https://img1.baidu.com/it/u=3970043028,2042301564&fm=253&fmt=auto&app=120&f=JPEG?w=500&h=889',
|
||||
'https://img2.baidu.com/it/u=3229384329,3046902124&fm=253&fmt=auto&app=120&f=JPEG?w=800&h=800',
|
||||
'https://img1.baidu.com/it/u=3113661564,2558849413&fm=253&fmt=auto&app=138&f=JPEG?w=500&h=500',
|
||||
'https://img1.baidu.com/it/u=2361496550,3302335162&fm=253&fmt=auto&app=138&f=JPEG?w=333&h=500',
|
||||
'https://img1.baidu.com/it/u=270105183,1595166255&fm=253&fmt=auto&app=120&f=JPEG?w=800&h=500',
|
||||
'https://img1.baidu.com/it/u=4071105902,825241031&fm=253&fmt=auto&app=138&f=JPEG?w=235&h=340']
|
||||
list_length = len(id)
|
||||
videos = []
|
||||
for i in range(list_length):
|
||||
print(id[i])
|
||||
video = {
|
||||
"vod_id": id[i],
|
||||
"vod_name": name[i],
|
||||
"vod_pic": pic[i],
|
||||
"vod_remarks": '播放20个',
|
||||
}
|
||||
videos.append(video)
|
||||
|
||||
result = {'list': videos}
|
||||
|
||||
return result
|
||||
|
||||
def categoryContent(self, cid, pg, filter, ext):
|
||||
pass
|
||||
|
||||
def detailContent(self, ids):
|
||||
videos = []
|
||||
result = {}
|
||||
did = ids[0]
|
||||
for i in range(1, 21):
|
||||
playurl = ""
|
||||
for j in range(1, i + 1):
|
||||
playurl += f"{j}$/fenlei/{did}#"
|
||||
playurl = playurl[:-1]
|
||||
|
||||
videos.append({
|
||||
"vod_id": '',
|
||||
"vod_name": '',
|
||||
"vod_pic": "",
|
||||
"type_name": '',
|
||||
"vod_year": "",
|
||||
"vod_area": "",
|
||||
"vod_remarks": "",
|
||||
"vod_actor": "",
|
||||
"vod_director": "",
|
||||
"vod_content": "",
|
||||
"vod_play_from": "GK推荐",
|
||||
"vod_play_url": playurl
|
||||
})
|
||||
|
||||
result['list'] = videos
|
||||
return result
|
||||
|
||||
def playerContent(self, flag, id, vipFlags):
|
||||
result = {}
|
||||
response = requests.get(url=xurl + id, headers=headerx, allow_redirects=False)
|
||||
|
||||
location_header = response.headers.get('Location')
|
||||
if 'http' in location_header:
|
||||
purl = location_header
|
||||
else:
|
||||
purl = 'http:' + location_header
|
||||
result["parse"] = 0
|
||||
result["playUrl"] = ''
|
||||
result["url"] = purl
|
||||
result["header"] = headerx
|
||||
return result
|
||||
|
||||
def searchContentPage(self, key, quick, page):
|
||||
pass
|
||||
|
||||
def searchContent(self, key, quick):
|
||||
return self.searchContentPage(key, quick, '1')
|
||||
|
||||
def localProxy(self, params):
|
||||
if params['type'] == "m3u8":
|
||||
return self.proxyM3u8(params)
|
||||
elif params['type'] == "media":
|
||||
return self.proxyMedia(params)
|
||||
elif params['type'] == "ts":
|
||||
return self.proxyTs(params)
|
||||
return None
|
||||
@@ -0,0 +1,196 @@
|
||||
"""
|
||||
@header({
|
||||
searchable: 1,
|
||||
filterable: 1,
|
||||
quickSearch: 1,
|
||||
title: '小红薯APP',
|
||||
lang: 'hipy'
|
||||
})
|
||||
"""
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# by @嗷呜
|
||||
import json
|
||||
import random
|
||||
import string
|
||||
import sys
|
||||
import time
|
||||
from base64 import b64decode
|
||||
from Crypto.Cipher import AES
|
||||
from Crypto.Hash import MD5
|
||||
from Crypto.Util.Padding import unpad
|
||||
sys.path.append('..')
|
||||
from base.spider import Spider
|
||||
|
||||
|
||||
class Spider(Spider):
|
||||
|
||||
def init(self, extend=""):
|
||||
self.did = self.getdid()
|
||||
self.token,self.phost,self.host = self.gettoken()
|
||||
pass
|
||||
|
||||
def isVideoFormat(self, url):
|
||||
pass
|
||||
|
||||
def manualVideoCheck(self):
|
||||
pass
|
||||
|
||||
def destroy(self):
|
||||
pass
|
||||
|
||||
hs = ['fhoumpjjih', 'dyfcbkggxn', 'rggwiyhqtg', 'bpbbmplfxc']
|
||||
|
||||
def homeContent(self, filter):
|
||||
data = self.fetch(f'{self.host}/api/video/queryClassifyList?mark=4', headers=self.headers()).json()['encData']
|
||||
data1 = self.aes(data)
|
||||
result = {}
|
||||
classes = []
|
||||
for k in data1['data']:
|
||||
classes.append({'type_name': k['classifyTitle'], 'type_id': k['classifyId']})
|
||||
result['class'] = classes
|
||||
return result
|
||||
|
||||
def homeVideoContent(self):
|
||||
pass
|
||||
|
||||
def categoryContent(self, tid, pg, filter, extend):
|
||||
path=f'/api/short/video/getShortVideos?classifyId={tid}&videoMark=4&page={pg}&pageSize=20'
|
||||
result = {}
|
||||
videos = []
|
||||
data=self.fetch(f'{self.host}{path}', headers=self.headers()).json()['encData']
|
||||
vdata=self.aes(data)
|
||||
for k in vdata['data']:
|
||||
videos.append({"vod_id": k['videoId'], 'vod_name': k.get('title'), 'vod_pic': self.getProxyUrl() + '&url=' + k['coverImg'],
|
||||
'vod_remarks': self.dtim(k.get('playTime')),'style': {"type": "rect", "ratio": 1.33}})
|
||||
result["list"] = videos
|
||||
result["page"] = pg
|
||||
result["pagecount"] = 9999
|
||||
result["limit"] = 90
|
||||
result["total"] = 999999
|
||||
return result
|
||||
|
||||
def detailContent(self, ids):
|
||||
path = f'/api/video/getVideoById?videoId={ids[0]}'
|
||||
data = self.fetch(f'{self.host}{path}', headers=self.headers()).json()['encData']
|
||||
v = self.aes(data)
|
||||
d=f'{v["title"]}$auth_key={v["authKey"]}&path={v["videoUrl"]}'
|
||||
vod = {'vod_name': v["title"], 'type_name': ''.join(v.get('tagTitles',[])),'vod_play_from': v.get('nickName') or "小红书官方", 'vod_play_url': d}
|
||||
result = {"list": [vod]}
|
||||
return result
|
||||
|
||||
def searchContent(self, key, quick, pg='1'):
|
||||
pass
|
||||
|
||||
def playerContent(self, flag, id, vipFlags):
|
||||
h=self.headers()
|
||||
h['Authorization'] = h.pop('aut')
|
||||
del h['deviceid']
|
||||
result = {"parse": 0, "url": f"{self.host}/api/m3u8/decode/authPath?{id}", "header": h}
|
||||
return result
|
||||
|
||||
def localProxy(self, param):
|
||||
return self.action(param)
|
||||
|
||||
def md5(self, text):
|
||||
h = MD5.new()
|
||||
h.update(text.encode('utf-8'))
|
||||
return h.hexdigest()
|
||||
|
||||
def aes(self, word):
|
||||
key = b64decode("SmhiR2NpT2lKSVV6STFOaQ==")
|
||||
iv = key
|
||||
cipher = AES.new(key, AES.MODE_CBC, iv)
|
||||
decrypted = unpad(cipher.decrypt(b64decode(word)), AES.block_size)
|
||||
return json.loads(decrypted.decode('utf-8'))
|
||||
|
||||
def dtim(self, seconds):
|
||||
try:
|
||||
seconds = int(seconds)
|
||||
hours = seconds // 3600
|
||||
remaining_seconds = seconds % 3600
|
||||
minutes = remaining_seconds // 60
|
||||
remaining_seconds = remaining_seconds % 60
|
||||
|
||||
formatted_minutes = str(minutes).zfill(2)
|
||||
formatted_seconds = str(remaining_seconds).zfill(2)
|
||||
|
||||
if hours > 0:
|
||||
formatted_hours = str(hours).zfill(2)
|
||||
return f"{formatted_hours}:{formatted_minutes}:{formatted_seconds}"
|
||||
else:
|
||||
return f"{formatted_minutes}:{formatted_seconds}"
|
||||
except:
|
||||
return ''
|
||||
|
||||
def getdid(self):
|
||||
did = self.getCache('did')
|
||||
if not did:
|
||||
t = str(int(time.time()))
|
||||
did = self.md5(t)
|
||||
self.setCache('did', did)
|
||||
return did
|
||||
|
||||
def getsign(self):
|
||||
t=str(int(time.time() * 1000))
|
||||
return self.md5(t[3:8]),t
|
||||
|
||||
def gettoken(self, i=0, max_attempts=10):
|
||||
if i >= len(self.hs) or i >= max_attempts:
|
||||
return ''
|
||||
current_domain = f"https://{''.join(random.choices(string.ascii_lowercase + string.digits, k=random.randint(5, 10)))}.{self.hs[i]}.work"
|
||||
try:
|
||||
sign,t=self.getsign()
|
||||
url = f'{current_domain}/api/user/traveler'
|
||||
headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Linux; Android 11; M2012K10C Build/RP1A.200720.011; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/87.0.4280.141 Mobile Safari/537.36;SuiRui/xhs/ver=1.2.6',
|
||||
'deviceid': self.did, 't': t, 's': sign, }
|
||||
data = {'deviceId': self.did, 'tt': 'U', 'code': '', 'chCode': 'dafe13'}
|
||||
data1 = self.post(url, json=data, headers=headers)
|
||||
data1.raise_for_status()
|
||||
data2 = data1.json()['data']
|
||||
return data2['token'], data2['imgDomain'],current_domain
|
||||
except:
|
||||
return self.gettoken(i+1, max_attempts)
|
||||
|
||||
def headers(self):
|
||||
sign,t=self.getsign()
|
||||
henda = {
|
||||
'User-Agent': 'Mozilla/5.0 (Linux; Android 11; M2012K10C Build/RP1A.200720.011; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/87.0.4280.141 Mobile Safari/537.36;SuiRui/xhs/ver=1.2.6',
|
||||
'deviceid': self.did, 't': t, 's': sign, 'aut': self.token}
|
||||
return henda
|
||||
|
||||
def action(self, param):
|
||||
headers = {
|
||||
'User-Agent': 'Dalvik/2.1.0 (Linux; U; Android 11; M2012K10C Build/RP1A.200720.011)'}
|
||||
data = self.fetch(f'{self.phost}{param["url"]}', headers=headers)
|
||||
type=data.headers.get('Content-Type').split(';')[0]
|
||||
base64_data = self.img(data.content, 100, '2020-zq3-888')
|
||||
return [200, type, base64_data]
|
||||
|
||||
def img(self, data: bytes, length: int, key: str):
|
||||
GIF = b'\x47\x49\x46'
|
||||
JPG = b'\xFF\xD8\xFF'
|
||||
PNG = b'\x89\x50\x4E\x47\x0D\x0A\x1A\x0A'
|
||||
|
||||
def is_dont_need_decode_for_gif(data):
|
||||
return len(data) > 2 and data[:3] == GIF
|
||||
|
||||
def is_dont_need_decode_for_jpg(data):
|
||||
return len(data) > 7 and data[:3] == JPG
|
||||
|
||||
def is_dont_need_decode_for_png(data):
|
||||
return len(data) > 7 and data[1:8] == PNG[1:8]
|
||||
|
||||
if is_dont_need_decode_for_png(data):
|
||||
return data
|
||||
elif is_dont_need_decode_for_gif(data):
|
||||
return data
|
||||
elif is_dont_need_decode_for_jpg(data):
|
||||
return data
|
||||
else:
|
||||
key_bytes = key.encode('utf-8')
|
||||
result = bytearray(data)
|
||||
for i in range(length):
|
||||
result[i] ^= key_bytes[i % len(key_bytes)]
|
||||
return bytes(result)
|
||||
+260
@@ -0,0 +1,260 @@
|
||||
"""
|
||||
@header({
|
||||
searchable: 1,
|
||||
filterable: 1,
|
||||
quickSearch: 1,
|
||||
title: '首页',
|
||||
lang: 'hipy'
|
||||
})
|
||||
"""
|
||||
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
import re
|
||||
from base.spider import Spider
|
||||
import sys
|
||||
import json
|
||||
import base64
|
||||
import urllib.parse
|
||||
|
||||
sys.path.append('..')
|
||||
|
||||
murl = "https://3642.7rnr.com/web/index.html"
|
||||
headerx = {
|
||||
'User-Agent': "Mozilla/5.0 (Linux; Android 13; M2102J2SC Build/TKQ1.221114.001; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/143.0.7499.3 Mobile Safari/537.36",
|
||||
'Accept-Encoding': "gzip, deflate, br, zstd"
|
||||
}
|
||||
response = requests.get(murl, allow_redirects=True)
|
||||
xurl = response.url
|
||||
nurl = xurl + '/web/abcdefg.ashx'
|
||||
pm = ''
|
||||
|
||||
class Spider(Spider):
|
||||
global xurl
|
||||
global headerx
|
||||
|
||||
def getName(self):
|
||||
return "首页"
|
||||
|
||||
def init(self, extend):
|
||||
pass
|
||||
|
||||
def isVideoFormat(self, url):
|
||||
pass
|
||||
|
||||
def manualVideoCheck(self):
|
||||
pass
|
||||
|
||||
def homeContent(self, filter):
|
||||
result = {}
|
||||
result = {"class": [{"type_id": "1003", "type_name": "亚洲无码"},
|
||||
{"type_id": "3022", "type_name": "欧美无码"},
|
||||
{"type_id": "3026", "type_name": "中文字幕"},
|
||||
{"type_id": "3025", "type_name": "经典三级"},
|
||||
{"type_id": "5", "type_name": "国产主播"},
|
||||
{"type_id": "134", "type_name": "韩国主播"},
|
||||
{"type_id": "3137", "type_name": "ＡＳＭＲ"},
|
||||
{"type_id": "3138", "type_name": "恐怖色情"},
|
||||
{"type_id": "131", "type_name": "网红视频"},
|
||||
{"type_id": "132", "type_name": "国产视频"},
|
||||
{"type_id": "3023", "type_name": "人妖伪娘"},
|
||||
{"type_id": "130", "type_name": "动漫卡通"},
|
||||
{"type_id": "3088", "type_name": "华人原创"},
|
||||
{"type_id": "3135", "type_name": "ＪＶＩＤ"},
|
||||
{"type_id": "3136", "type_name": "ＳＷＡＧ"},
|
||||
{"type_id": "3134", "type_name": "明星换脸"}]}
|
||||
return result
|
||||
|
||||
def homeVideoContent(self):
|
||||
videos = []
|
||||
try:
|
||||
payload = {
|
||||
'action': "getindexdata",
|
||||
't': "1762753963537691",
|
||||
's': "5ad87a586f5aae9c2ca4f913d45f8958"}
|
||||
detail = requests.post(url=nurl, data=payload, headers=headerx)
|
||||
detail.encoding = "utf-8"
|
||||
res = detail.json()
|
||||
video_list = res.get("videos", [])
|
||||
|
||||
for video in video_list:
|
||||
name = video.get("title", "")
|
||||
id = video.get("id", "")
|
||||
pic = video.get("coverimg", "")
|
||||
remarks = video.get("updatedate", "")
|
||||
video = {
|
||||
"vod_id": id,
|
||||
"vod_name": name,
|
||||
"vod_pic": pic,
|
||||
"vod_remarks": remarks
|
||||
}
|
||||
videos.append(video)
|
||||
|
||||
result = {'list': videos}
|
||||
return result
|
||||
except:
|
||||
pass
|
||||
|
||||
def categoryContent(self, cid, pg, filter, ext):
|
||||
result = {}
|
||||
videos = []
|
||||
if pg:
|
||||
page = int(pg)
|
||||
else:
|
||||
page = 1
|
||||
|
||||
if page == '1':
|
||||
payload1 = {
|
||||
'action': "getvideos",
|
||||
'vtype': {cid},
|
||||
'pageindex': "1",
|
||||
'pagesize': "12",
|
||||
'tags': "全部",
|
||||
'sortindex': "1",
|
||||
't': "176275570014518",
|
||||
's': "ff4218e4cafd552c4d0c93eb935c14f1"}
|
||||
else:
|
||||
payload1 = {
|
||||
'action': "getvideos",
|
||||
'vtype': {cid},
|
||||
'pageindex': {str(page)},
|
||||
'pagesize': "12",
|
||||
'tags': "全部",
|
||||
'sortindex': "1",
|
||||
't': "176275570014518",
|
||||
's': "ff4218e4cafd552c4d0c93eb935c14f1"}
|
||||
try:
|
||||
detail = requests.post(url=nurl, data=payload1, headers=headerx)
|
||||
detail.encoding = "utf-8"
|
||||
res = detail.json()
|
||||
video_list = res.get("videos", [])
|
||||
|
||||
for video in video_list:
|
||||
name = video.get("title", "")
|
||||
id = video.get("id", "")
|
||||
pic = video.get("coverimg", "")
|
||||
remarks = video.get("updatedate", "")
|
||||
video = {
|
||||
"vod_id": id,
|
||||
"vod_name": name,
|
||||
"vod_pic": pic,
|
||||
"vod_remarks": remarks
|
||||
}
|
||||
videos.append(video)
|
||||
|
||||
except:
|
||||
pass
|
||||
result = {'list': videos}
|
||||
result['page'] = pg
|
||||
result['pagecount'] = 99
|
||||
result['limit'] = 90
|
||||
result['total'] = 99
|
||||
return result
|
||||
|
||||
def detailContent(self, ids):
|
||||
did = ids[0]
|
||||
result = {}
|
||||
videos = []
|
||||
playurl = ''
|
||||
payload2 = {
|
||||
'action': "getvideo",
|
||||
'vid': did,
|
||||
't': "1762756475175265",
|
||||
's': "656d5b40c2122f86bc35895dc58fd113"}
|
||||
res1 = requests.post(url=nurl, data=payload2, headers=headerx)
|
||||
res1.encoding = "utf-8"
|
||||
res = res1.json()
|
||||
node = res.get("data", {}).get("Table", [{}])[0]
|
||||
|
||||
vod_id = node.get("id", "")
|
||||
vod_name = node.get("title", "")
|
||||
vod_pic = node.get("coverimg", "")
|
||||
vod_remarks = node.get("updatedate", "")
|
||||
vod_content = node.get("title", "")
|
||||
|
||||
playFrom = []
|
||||
playList = []
|
||||
if node.get("vurl"):
|
||||
base_url1 = res.get("xldata", {}).get("value", "")
|
||||
base_url2 = res.get("xldata", {}).get("value1", "")
|
||||
if base_url1:
|
||||
full_vurl1 = base_url1 + node.get("vurl", "")
|
||||
playFrom.append("播放源1")
|
||||
playList.append(full_vurl1)
|
||||
if base_url2:
|
||||
full_vurl2 = base_url2 + node.get("vurl", "")
|
||||
playFrom.append("播放源2")
|
||||
playList.append(full_vurl2)
|
||||
|
||||
videos.append({
|
||||
"vod_id": vod_id,
|
||||
"vod_name": vod_name,
|
||||
"vod_pic": vod_pic,
|
||||
"vod_remarks": vod_remarks,
|
||||
"vod_content": vod_content,
|
||||
"vod_play_from": "$$$".join(playFrom),
|
||||
"vod_play_url": "$$$".join(playList)
|
||||
})
|
||||
|
||||
result['list'] = videos
|
||||
return result
|
||||
|
||||
def playerContent(self, flag, id, vipFlags):
|
||||
parts = id.split("http")
|
||||
xiutan = 1
|
||||
if xiutan == 1:
|
||||
if len(parts) > 1:
|
||||
before_https, after_https = parts[0], 'http' + parts[1]
|
||||
result = {}
|
||||
result["parse"] = xiutan
|
||||
result["playUrl"] = ''
|
||||
result["url"] = after_https
|
||||
result["header"] = headerx
|
||||
return result
|
||||
|
||||
def searchContentPage(self, key, quick, page):
|
||||
result = {}
|
||||
videos = []
|
||||
payload3 = {
|
||||
'action': "search",
|
||||
'p': {key},
|
||||
'pageindex': {str(page)},
|
||||
'pagesize': "12",
|
||||
'channelid': "0",
|
||||
't': "1762756927087982",
|
||||
's': "2392bd117b4e6e35b5ec1fa9bc380b6f"}
|
||||
detail = requests.post(url=nurl, data=payload3, headers=headerx)
|
||||
detail.encoding = "utf-8"
|
||||
res = detail.json()
|
||||
video_list = res.get("data", [])
|
||||
for video in video_list:
|
||||
name = video.get("title", "")
|
||||
id = video.get("id", "")
|
||||
pic = video.get("imgurl", "")
|
||||
remarks = video.get("updatedate", "")
|
||||
video = {
|
||||
"vod_id": id,
|
||||
"vod_name": name,
|
||||
"vod_pic": pic,
|
||||
"vod_remarks": remarks
|
||||
}
|
||||
videos.append(video)
|
||||
|
||||
result['list'] = videos
|
||||
result['page'] = page
|
||||
result['pagecount'] = 60
|
||||
result['limit'] = 30
|
||||
result['total'] = 999999
|
||||
return result
|
||||
|
||||
def searchContent(self, key, quick):
|
||||
return self.searchContentPage(key, quick, '1')
|
||||
|
||||
def localProxy(self, params):
|
||||
if params['type'] == "m3u8":
|
||||
return self.proxyM3u8(params)
|
||||
elif params['type'] == "media":
|
||||
return self.proxyMedia(params)
|
||||
elif params['type'] == "ts":
|
||||
return self.proxyTs(params)
|
||||
return None
|
||||
+267
@@ -0,0 +1,267 @@
|
||||
"""
|
||||
@header({
|
||||
searchable: 1,
|
||||
filterable: 1,
|
||||
quickSearch: 1,
|
||||
title: 'Leospring直播',
|
||||
lang: 'hipy'
|
||||
})
|
||||
"""
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
import json
|
||||
import sys
|
||||
import traceback
|
||||
sys.path.append('..')
|
||||
from base.spider import Spider
|
||||
|
||||
class Spider(Spider):
|
||||
primary_host = 'http://api.hclyz.com:81/mf/'
|
||||
backup_host = 'http://api.maiyoux.com:81/mf/'
|
||||
host = primary_host
|
||||
platforms = []
|
||||
|
||||
def init(self, extend=""):
|
||||
if extend:
|
||||
h = extend.strip()
|
||||
if not h.endswith('/'):
|
||||
h += '/'
|
||||
self.host = h
|
||||
else:
|
||||
self.host = self.primary_host
|
||||
|
||||
content = None
|
||||
for base in [self.host, self.backup_host]:
|
||||
try:
|
||||
txt = self.fetch(base + 'json.txt').text
|
||||
data = None
|
||||
try:
|
||||
data = json.loads(txt)
|
||||
except Exception:
|
||||
data = None
|
||||
|
||||
if data is not None:
|
||||
self.host = base
|
||||
self.platforms = self._parse_catalog_json(data)
|
||||
if self.platforms:
|
||||
return
|
||||
else:
|
||||
plats = self._parse_catalog_text(txt)
|
||||
if plats:
|
||||
self.host = base
|
||||
self.platforms = plats
|
||||
return
|
||||
except Exception:
|
||||
continue
|
||||
|
||||
def _parse_catalog_json(self, data):
|
||||
items = []
|
||||
if isinstance(data, dict):
|
||||
if 'pingtai' in data and isinstance(data['pingtai'], list):
|
||||
items = data['pingtai']
|
||||
else:
|
||||
if all(isinstance(v, dict) for v in data.values()):
|
||||
items = list(data.values())
|
||||
elif isinstance(data, list):
|
||||
items = data
|
||||
|
||||
platforms = []
|
||||
for it in items:
|
||||
name = it.get('mc') or it.get('title') or it.get('name') or ''
|
||||
img = it.get('tp1') or it.get('xinimg') or it.get('img') or ''
|
||||
file = it.get('dz') or it.get('address') or it.get('file') or ''
|
||||
count = it.get('sl') or it.get('Number') or it.get('count') or 0
|
||||
try:
|
||||
count = int(count)
|
||||
except Exception:
|
||||
pass
|
||||
if name and file:
|
||||
if not file.endswith('.txt'):
|
||||
file += '.txt'
|
||||
if not file.startswith('json'):
|
||||
file = 'json' + file
|
||||
platforms.append({
|
||||
'name': name,
|
||||
'img': img,
|
||||
'file': file,
|
||||
'count': count
|
||||
})
|
||||
return platforms
|
||||
|
||||
def _parse_catalog_text(self, txt):
|
||||
plats = []
|
||||
block = txt.strip()
|
||||
if not block:
|
||||
return plats
|
||||
if block.startswith('{') and block.endswith('}'):
|
||||
block = block[1:-1]
|
||||
chunks = [c for c in block.split('|') if c.strip()]
|
||||
curr = {'mc': '', 'tp1': '', 'dz': '', 'sl': 0}
|
||||
def flush():
|
||||
if curr.get('mc') and curr.get('dz'):
|
||||
try:
|
||||
sl = int(curr.get('sl') or 0)
|
||||
except Exception:
|
||||
sl = curr.get('sl') or 0
|
||||
fname = curr.get('dz')
|
||||
if not fname.endswith('.txt'):
|
||||
fname += '.txt'
|
||||
if not fname.startswith('json'):
|
||||
fname = 'json' + fname
|
||||
plats.append({
|
||||
'name': curr.get('mc'),
|
||||
'img': curr.get('tp1'),
|
||||
'file': fname,
|
||||
'count': sl
|
||||
})
|
||||
for c in chunks:
|
||||
s = c.strip()
|
||||
if s.startswith('@mc'):
|
||||
if curr.get('mc') or curr.get('dz'):
|
||||
flush()
|
||||
curr = {'mc': '', 'tp1': '', 'dz': '', 'sl': 0}
|
||||
curr['mc'] = s.replace('@mc', '', 1)
|
||||
elif s.startswith('@tp1'):
|
||||
curr['tp1'] = s.replace('@tp1', '', 1)
|
||||
elif s.startswith('@dz'):
|
||||
curr['dz'] = s.replace('@dz', '', 1)
|
||||
elif s.startswith('@sl'):
|
||||
curr['sl'] = s.replace('@sl', '', 1)
|
||||
if curr.get('mc') or curr.get('dz'):
|
||||
flush()
|
||||
return plats
|
||||
|
||||
def _load_platform_rooms(self, file_path, pg=1):
|
||||
url_candidates = [
|
||||
self.host + file_path,
|
||||
]
|
||||
alt_path = file_path.replace('json', '', 1)
|
||||
if alt_path != file_path:
|
||||
url_candidates.insert(0, self.host + alt_path)
|
||||
|
||||
data = None
|
||||
raw = None
|
||||
for u in url_candidates:
|
||||
try:
|
||||
raw = self.fetch(u).text
|
||||
data = json.loads(raw)
|
||||
break
|
||||
except Exception:
|
||||
data = None
|
||||
continue
|
||||
|
||||
rooms = []
|
||||
if isinstance(data, dict):
|
||||
if 'zhubo' in data and isinstance(data['zhubo'], list):
|
||||
rooms = data['zhubo']
|
||||
elif 'list' in data and isinstance(data['list'], list):
|
||||
rooms = data['list']
|
||||
elif 'data' in data and isinstance(data['data'], list):
|
||||
rooms = data['data']
|
||||
elif 'rooms' in data and isinstance(data['rooms'], list):
|
||||
rooms = data['rooms']
|
||||
elif isinstance(data, list):
|
||||
rooms = data
|
||||
|
||||
videos = []
|
||||
for idx, r in enumerate(rooms or [], 1):
|
||||
title = r.get('title') or r.get('name') or r.get('nickname') or f'主播{idx}'
|
||||
address = r.get('address') or r.get('url') or r.get('stream') or ''
|
||||
img = r.get('img') or r.get('pic') or r.get('avatar') or ''
|
||||
remarks = r.get('Number') or r.get('online') or r.get('viewers') or ''
|
||||
if title and address:
|
||||
videos.append({
|
||||
'vod_id': address,
|
||||
'vod_name': title,
|
||||
'vod_pic': img,
|
||||
'vod_remarks': str(remarks)
|
||||
})
|
||||
total = len(videos)
|
||||
if pg > 1:
|
||||
start = (pg - 1) * 20
|
||||
videos = videos[start:start + 20]
|
||||
return videos, total
|
||||
|
||||
def isVideoFormat(self, url):
|
||||
return False
|
||||
|
||||
def manualVideoCheck(self):
|
||||
pass
|
||||
|
||||
def getName(self):
|
||||
return 'Leospring直播'
|
||||
|
||||
def homeContent(self, filter):
|
||||
classes = []
|
||||
for p in self.platforms:
|
||||
classes.append({
|
||||
'type_id': p['file'],
|
||||
'type_name': p['name'],
|
||||
})
|
||||
return {'class': classes}
|
||||
|
||||
def homeVideoContent(self):
|
||||
return {'list': []}
|
||||
|
||||
def _find_platform(self, tid):
|
||||
for p in self.platforms:
|
||||
if p['file'] == tid or p['name'] == tid:
|
||||
return p
|
||||
return None
|
||||
|
||||
def categoryContent(self, tid, pg, filter, extend):
|
||||
p = self._find_platform(tid)
|
||||
if not p:
|
||||
return {'list': [], 'page': pg, 'pagecount': 0, 'limit': 0, 'total': 0}
|
||||
|
||||
videos, total = self._load_platform_rooms(p['file'], int(pg))
|
||||
pagecount = (total + 19) // 20
|
||||
result = {
|
||||
'list': videos,
|
||||
'page': pg,
|
||||
'pagecount': pagecount,
|
||||
'limit': min(len(videos), 20),
|
||||
'total': total
|
||||
}
|
||||
return result
|
||||
|
||||
def searchContent(self, key, quick, pg="1"):
|
||||
key = (key or '').strip().lower()
|
||||
out = []
|
||||
if not key:
|
||||
return {'list': out}
|
||||
for p in self.platforms:
|
||||
videos, _ = self._load_platform_rooms(p['file'])
|
||||
for v in videos:
|
||||
if key in v['vod_name'].lower():
|
||||
out.append(v)
|
||||
if len(out) >= 50:
|
||||
break
|
||||
return {'list': out[:50]}
|
||||
|
||||
def detailContent(self, ids):
|
||||
try:
|
||||
address = ids[0]
|
||||
if not address:
|
||||
return {'list': []}
|
||||
|
||||
vod = {
|
||||
'vod_id': address,
|
||||
'vod_name': '直播源',
|
||||
'vod_play_from': '瑟瑟站大佬张佬',
|
||||
'vod_play_url': address,
|
||||
'vod_content': '多看少打卡',
|
||||
}
|
||||
return {'list': [vod]}
|
||||
except Exception as e:
|
||||
traceback.print_exc()
|
||||
return {'list': []}
|
||||
|
||||
def playerContent(self, flag, id, vipFlags):
|
||||
return {
|
||||
'parse': 0,
|
||||
'url': id
|
||||
}
|
||||
|
||||
def localProxy(self, param):
|
||||
pass
|
||||
@@ -0,0 +1,543 @@
|
||||
"""
|
||||
@header({
|
||||
searchable: 1,
|
||||
filterable: 1,
|
||||
quickSearch: 1,
|
||||
title: '月佬免翻版好色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://hsex.icu/'
|
||||
self.candidate_hosts = [
|
||||
"https://hsex.icu/",
|
||||
"https://hsex1.icu/",
|
||||
"https://hsex.tv/"
|
||||
]
|
||||
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（关键修复：视频分类url_suffix设为空，适配list-{pg}.htm格式）
|
||||
self.class_map = {
|
||||
'视频': {'type_id': 'list', 'url_suffix': ''}, # 修复点1：视频分类后缀为空
|
||||
'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}"
|
||||
|
||||
# 提取播放地址
|
||||
video_url = ''
|
||||
m3u8_match = re.search(r'videoUrl\s*=\s*["\']([^"\']+\.m3u8)["\']', html)
|
||||
if m3u8_match:
|
||||
video_url = m3u8_match.group(1)
|
||||
if not video_url:
|
||||
source = data('source[src*=".m3u8"], source[src*=".mp4"]')
|
||||
video_url = source.attr('src') or ''
|
||||
if not video_url:
|
||||
js_matches = re.findall(r'(https?://[^\s"\']+\.(?:m3u8|mp4))', html)
|
||||
if js_matches:
|
||||
video_url = js_matches[0]
|
||||
|
||||
if video_url and not video_url.startswith('http'):
|
||||
video_url = f"{self.host}{video_url.lstrip('/')}"
|
||||
|
||||
vod = {
|
||||
'vod_id': vod_id,
|
||||
'vod_name': title,
|
||||
'vod_pic': vod_pic,
|
||||
'vod_remarks': remarks,
|
||||
'vod_play_from': '好色TV（优）',
|
||||
'vod_play_url': f'正片${video_url}' if video_url else '正片$暂无地址'
|
||||
}
|
||||
return {'list': [vod]}
|
||||
except Exception as e:
|
||||
print(f"详情解析失败: {e}")
|
||||
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')
|
||||
|
||||
# 构造搜索URL
|
||||
search_url = f"{self.host}search.htm"
|
||||
params = {
|
||||
'search': encoded_key,
|
||||
'page': int(pg)
|
||||
}
|
||||
|
||||
# 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（修复点2：补全page键的引号，修正语法错误）
|
||||
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), # 原代码此处缺少引号，导致语法错误
|
||||
'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,
|
||||
})
|
||||
|
||||
# 根据rule中的double设置
|
||||
return {
|
||||
'parse': 1, # 根据rule中的play_parse设置
|
||||
'url': id,
|
||||
'header': headers,
|
||||
'double': True # 根据rule中的double设置
|
||||
}
|
||||
|
||||
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(f'https://vpsdn.leuse.top/proxy?single=true&url={urllib.parse.quote(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:
|
||||
if method.upper() == 'GET':
|
||||
resp = requests.get(
|
||||
f'https://vpsdn.leuse.top/proxy?single=true&url={urllib.parse.quote(url)}',
|
||||
headers=headers,
|
||||
timeout=timeout,
|
||||
allow_redirects=True,
|
||||
params=params # 支持GET请求带参数，适配搜索分页
|
||||
)
|
||||
elif method.upper() == 'HEAD':
|
||||
resp = requests.head(
|
||||
f'https://vpsdn.leuse.top/proxy?single=true&url={urllib.parse.quote(url)}',
|
||||
headers=headers,
|
||||
timeout=timeout,
|
||||
allow_redirects=False,
|
||||
params=params
|
||||
)
|
||||
else:
|
||||
resp = requests.get( # 默认GET请求，兼容其他方法调用
|
||||
f'https://vpsdn.leuse.top/proxy?single=true&url={urllib.parse.quote(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}")
|
||||
# 返回统一格式空响应，避免后续逻辑崩溃
|
||||
return type('obj', (object,), {
|
||||
'text': '',
|
||||
'status_code': 500,
|
||||
'headers': {},
|
||||
'url': url
|
||||
})
|
||||
|
||||
|
||||
# ------------------------------
|
||||
# 可选测试代码（运行时注释或删除，用于验证功能）
|
||||
# ------------------------------
|
||||
if __name__ == "__main__":
|
||||
# 初始化爬虫
|
||||
spider = Spider()
|
||||
spider.init()
|
||||
|
||||
# 测试首页内容
|
||||
print("=== 测试首页 ===")
|
||||
home_data = spider.homeContent(filter='')
|
||||
print(f"首页分类数：{len(home_data['class'])}")
|
||||
print(f"首页视频数：{len(home_data['list'])}")
|
||||
|
||||
# 测试视频分类（修复后的数据获取）
|
||||
print("\n=== 测试视频分类（第1页） ===")
|
||||
cate_data = spider.categoryContent(tid='list', pg=1, filter='', extend='')
|
||||
print(f"视频分类第1页视频数：{len(cate_data['list'])}")
|
||||
print(f"视频分类总页数：{cate_data['pagecount']}")
|
||||
|
||||
# 测试搜索功能（修复语法错误后）
|
||||
print("\n=== 测试搜索（关键词：测试） ===")
|
||||
search_data = spider.searchContent(key="测试", quick=False, pg=1)
|
||||
print(f"搜索结果数：{len(search_data['list'])}")
|
||||
print(f"搜索总页数：{search_data['pagecount']}")
|
||||
@@ -0,0 +1,256 @@
|
||||
"""
|
||||
@header({
|
||||
searchable: 1,
|
||||
filterable: 1,
|
||||
quickSearch: 1,
|
||||
title: '推特APP',
|
||||
lang: 'hipy'
|
||||
})
|
||||
"""
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# by @嗷呜
|
||||
import json
|
||||
import random
|
||||
import string
|
||||
import sys
|
||||
import time
|
||||
from base64 import b64decode
|
||||
from urllib.parse import quote
|
||||
from Crypto.Cipher import AES
|
||||
from Crypto.Hash import MD5
|
||||
from Crypto.Util.Padding import unpad
|
||||
sys.path.append('..')
|
||||
from base.spider import Spider
|
||||
|
||||
|
||||
class Spider(Spider):
|
||||
|
||||
def init(self, extend=""):
|
||||
self.did = self.getdid()
|
||||
self.token,self.phost,self.host = self.gettoken()
|
||||
pass
|
||||
|
||||
def isVideoFormat(self, url):
|
||||
pass
|
||||
|
||||
def manualVideoCheck(self):
|
||||
pass
|
||||
|
||||
def action(self, action):
|
||||
pass
|
||||
|
||||
def destroy(self):
|
||||
pass
|
||||
|
||||
hs=['wcyfhknomg','pdcqllfomw','alxhzjvean','bqeaaxzplt','hfbtpixjso']
|
||||
|
||||
ua='Mozilla/5.0 (Linux; Android 11; M2012K10C Build/RP1A.200720.011; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/87.0.4280.141 Mobile Safari/537.36;SuiRui/twitter/ver=1.4.4'
|
||||
|
||||
def homeContent(self, filter):
|
||||
data = self.fetch(f'{self.host}/api/video/classifyList', headers=self.headers()).json()['encData']
|
||||
data1 = self.aes(data)
|
||||
result = {'filters': {"1": [{"key": "fl", "name": "分类",
|
||||
"value": [{"n": "最近更新", "v": "1"}, {"n": "最多播放", "v": "2"},
|
||||
{"n": "好评榜", "v": "3"}]}], "2": [{"key": "fl", "name": "分类",
|
||||
"value": [
|
||||
{"n": "最近更新", "v": "1"},
|
||||
{"n": "最多播放", "v": "2"},
|
||||
{"n": "好评榜", "v": "3"}]}],
|
||||
"3": [{"key": "fl", "name": "分类",
|
||||
"value": [{"n": "最近更新", "v": "1"}, {"n": "最多播放", "v": "2"},
|
||||
{"n": "好评榜", "v": "3"}]}], "4": [{"key": "fl", "name": "分类",
|
||||
"value": [
|
||||
{"n": "最近更新", "v": "1"},
|
||||
{"n": "最多播放", "v": "2"},
|
||||
{"n": "好评榜", "v": "3"}]}],
|
||||
"5": [{"key": "fl", "name": "分类",
|
||||
"value": [{"n": "最近更新", "v": "1"}, {"n": "最多播放", "v": "2"},
|
||||
{"n": "好评榜", "v": "3"}]}], "6": [{"key": "fl", "name": "分类",
|
||||
"value": [
|
||||
{"n": "最近更新", "v": "1"},
|
||||
{"n": "最多播放", "v": "2"},
|
||||
{"n": "好评榜", "v": "3"}]}],
|
||||
"7": [{"key": "fl", "name": "分类",
|
||||
"value": [{"n": "最近更新", "v": "1"}, {"n": "最多播放", "v": "2"},
|
||||
{"n": "好评榜", "v": "3"}]}], "jx": [{"key": "type", "name": "精选",
|
||||
"value": [{"n": "日榜", "v": "1"},
|
||||
{"n": "周榜", "v": "2"},
|
||||
{"n": "月榜", "v": "3"},
|
||||
{"n": "总榜",
|
||||
"v": "4"}]}]}}
|
||||
classes = [{'type_name': "精选", 'type_id': "jx"}]
|
||||
for k in data1['data']:
|
||||
classes.append({'type_name': k['classifyTitle'], 'type_id': k['classifyId']})
|
||||
result['class'] = classes
|
||||
return result
|
||||
|
||||
def homeVideoContent(self):
|
||||
pass
|
||||
|
||||
def categoryContent(self, tid, pg, filter, extend):
|
||||
path = f'/api/video/queryVideoByClassifyId?pageSize=20&page={pg}&classifyId={tid}&sortType={extend.get("fl", "1")}'
|
||||
if 'click' in tid:
|
||||
path = f'/api/video/queryPersonVideoByType?pageSize=20&page={pg}&userId={tid.replace("click", "")}'
|
||||
if tid == 'jx':
|
||||
path = f'/api/video/getRankVideos?pageSize=20&page={pg}&type={extend.get("type", "1")}'
|
||||
data = self.fetch(f'{self.host}{path}', headers=self.headers()).json()['encData']
|
||||
data1 = self.aes(data)['data']
|
||||
result = {}
|
||||
videos = []
|
||||
for k in data1:
|
||||
id = f'{k.get("videoId")}?{k.get("userId")}?{k.get("nickName")}'
|
||||
if 'click' in tid:
|
||||
id = id + 'click'
|
||||
videos.append({"vod_id": id, 'vod_name': k.get('title'), 'vod_pic': self.getProxyUrl() + f"&url={k.get('coverImg')[0]}",
|
||||
'vod_remarks': self.dtim(k.get('playTime')),'style': {"type": "rect", "ratio": 1.33}})
|
||||
result["list"] = videos
|
||||
result["page"] = pg
|
||||
result["pagecount"] = 9999
|
||||
result["limit"] = 90
|
||||
result["total"] = 999999
|
||||
return result
|
||||
|
||||
def detailContent(self, ids):
|
||||
vid = ids[0].replace('click', '').split('?')
|
||||
path = f'/api/video/can/watch?videoId={vid[0]}'
|
||||
data = self.fetch(f'{self.host}{path}', headers=self.headers()).json()['encData']
|
||||
data1 = self.aes(data)['playPath']
|
||||
clj = '[a=cr:' + json.dumps({'id': vid[1] + 'click', 'name': vid[2]}) + '/]' + vid[2] + '[/a]'
|
||||
if 'click' in ids[0]:
|
||||
clj = vid[2]
|
||||
vod = {'vod_director': clj, 'vod_play_from': "推特", 'vod_play_url': vid[2] + "$" + data1}
|
||||
result = {"list": [vod]}
|
||||
return result
|
||||
|
||||
def searchContent(self, key, quick, pg='1'):
|
||||
path = f'/api/search/keyWord?pageSize=20&page={pg}&searchWord={quote(key)}&searchType=1'
|
||||
data = self.fetch(f'{self.host}{path}', headers=self.headers()).json()['encData']
|
||||
data1 = self.aes(data)['videoList']
|
||||
result = {}
|
||||
videos = []
|
||||
for k in data1:
|
||||
id = f'{k.get("videoId")}?{k.get("userId")}?{k.get("nickName")}'
|
||||
videos.append({"vod_id": id, 'vod_name': k.get('title'), 'vod_pic': self.getProxyUrl() + f"&url={k.get('coverImg')[0]}",
|
||||
'vod_remarks': self.dtim(k.get('playTime')), 'style': {"type": "rect", "ratio": 1.33}})
|
||||
result["list"] = videos
|
||||
result["page"] = pg
|
||||
result["pagecount"] = 9999
|
||||
result["limit"] = 90
|
||||
result["total"] = 999999
|
||||
return result
|
||||
|
||||
def playerContent(self, flag, id, vipFlags):
|
||||
return {"parse": 0, "url": id, "header": self.headers()}
|
||||
|
||||
def localProxy(self, param):
|
||||
return self.imgs(param)
|
||||
|
||||
def getsign(self):
|
||||
t = str(int(time.time() * 1000))
|
||||
sign = self.md5(t)
|
||||
return sign, t
|
||||
|
||||
def headers(self):
|
||||
sign, t = self.getsign()
|
||||
return {'User-Agent': self.ua,'deviceid': self.did, 't': t, 's': sign, 'aut': self.token}
|
||||
|
||||
def aes(self, word):
|
||||
key = b64decode("SmhiR2NpT2lKSVV6STFOaQ==")
|
||||
iv = key
|
||||
cipher = AES.new(key, AES.MODE_CBC, iv)
|
||||
decrypted = unpad(cipher.decrypt(b64decode(word)), AES.block_size)
|
||||
return json.loads(decrypted.decode('utf-8'))
|
||||
|
||||
def dtim(self, seconds):
|
||||
try:
|
||||
seconds = int(seconds)
|
||||
hours = seconds // 3600
|
||||
remaining_seconds = seconds % 3600
|
||||
minutes = remaining_seconds // 60
|
||||
remaining_seconds = remaining_seconds % 60
|
||||
|
||||
formatted_minutes = str(minutes).zfill(2)
|
||||
formatted_seconds = str(remaining_seconds).zfill(2)
|
||||
|
||||
if hours > 0:
|
||||
formatted_hours = str(hours).zfill(2)
|
||||
return f"{formatted_hours}:{formatted_minutes}:{formatted_seconds}"
|
||||
else:
|
||||
return f"{formatted_minutes}:{formatted_seconds}"
|
||||
except:
|
||||
return "666"
|
||||
|
||||
def gettoken(self, i=0, max_attempts=10):
|
||||
if i >= len(self.hs) or i >= max_attempts:
|
||||
return ''
|
||||
current_domain = f"https://{''.join(random.choices(string.ascii_lowercase + string.digits, k=random.randint(5, 10)))}.{self.hs[i]}.work"
|
||||
try:
|
||||
url = f'{current_domain}/api/user/traveler'
|
||||
sign, t = self.getsign()
|
||||
headers = {
|
||||
'User-Agent': self.ua,
|
||||
'Accept': 'application/json',
|
||||
'deviceid': self.did,
|
||||
't': t,
|
||||
's': sign,
|
||||
}
|
||||
data = {
|
||||
'deviceId': self.did,
|
||||
'tt': 'U',
|
||||
'code': '##X-4m6Goo4zzPi1hF##',
|
||||
'chCode': 'tt09'
|
||||
}
|
||||
response = self.post(url, json=data, headers=headers)
|
||||
response.raise_for_status()
|
||||
data1 = response.json()['data']
|
||||
return data1['token'], data1['imgDomain'], current_domain
|
||||
except Exception as e:
|
||||
return self.gettoken(i + 1, max_attempts)
|
||||
|
||||
def getdid(self):
|
||||
did = self.getCache('did')
|
||||
if not did:
|
||||
t = str(int(time.time()))
|
||||
did = self.md5(t)
|
||||
self.setCache('did', did)
|
||||
return did
|
||||
|
||||
def md5(self, text):
|
||||
h = MD5.new()
|
||||
h.update(text.encode('utf-8'))
|
||||
return h.hexdigest()
|
||||
|
||||
def imgs(self, param):
|
||||
headers = {'User-Agent': self.ua}
|
||||
url = param['url']
|
||||
data = self.fetch(f"{self.phost}{url}",headers=headers)
|
||||
bdata = self.img(data.content, 100, '2020-zq3-888')
|
||||
return [200, data.headers.get('Content-Type'), bdata]
|
||||
|
||||
def img(self, data: bytes, length: int, key: str):
|
||||
GIF = b'\x47\x49\x46'
|
||||
JPG = b'\xFF\xD8\xFF'
|
||||
PNG = b'\x89\x50\x4E\x47\x0D\x0A\x1A\x0A'
|
||||
|
||||
def is_dont_need_decode_for_gif(data):
|
||||
return len(data) > 2 and data[:3] == GIF
|
||||
|
||||
def is_dont_need_decode_for_jpg(data):
|
||||
return len(data) > 7 and data[:3] == JPG
|
||||
|
||||
def is_dont_need_decode_for_png(data):
|
||||
return len(data) > 7 and data[1:8] == PNG[1:8]
|
||||
|
||||
if is_dont_need_decode_for_png(data):
|
||||
return data
|
||||
elif is_dont_need_decode_for_gif(data):
|
||||
return data
|
||||
elif is_dont_need_decode_for_jpg(data):
|
||||
return data
|
||||
else:
|
||||
key_bytes = key.encode('utf-8')
|
||||
result = bytearray(data)
|
||||
for i in range(length):
|
||||
result[i] ^= key_bytes[i % len(key_bytes)]
|
||||
return bytes(result)
|
||||
+455
@@ -0,0 +1,455 @@
|
||||
"""
|
||||
@header({
|
||||
searchable: 1,
|
||||
filterable: 1,
|
||||
quickSearch: 1,
|
||||
title: 'http://6590ck.cc/',
|
||||
lang: 'hipy'
|
||||
})
|
||||
"""
|
||||
|
||||
import re
|
||||
import sys
|
||||
import urllib.parse
|
||||
import threading
|
||||
import time
|
||||
import requests
|
||||
import base64
|
||||
import gzip
|
||||
import json
|
||||
from io import BytesIO
|
||||
from pyquery import PyQuery as pq
|
||||
|
||||
sys.path.append('..')
|
||||
from base.spider import Spider
|
||||
|
||||
class Spider(Spider):
|
||||
def __init__(self):
|
||||
self.name = "黄色仓库"
|
||||
self.host = self.getDynamicHost()
|
||||
self.classes = self.preprocessClasses()
|
||||
|
||||
def getName(self):
|
||||
return self.name
|
||||
|
||||
def getDynamicHost(self):
|
||||
"""动态获取主机地址"""
|
||||
try:
|
||||
# 解码base64获取初始主机
|
||||
initial_host = base64.b64decode('aHR0cDovL2hzY2submV0').decode('utf-8')
|
||||
|
||||
# 获取初始页面
|
||||
response = requests.get(initial_host, headers=self.header)
|
||||
html = response.text
|
||||
|
||||
# 匹配strU参数
|
||||
strU_match = re.search(r'strU="(.*?)"', html)
|
||||
if not strU_match:
|
||||
return initial_host
|
||||
|
||||
strU = strU_match.group(1)
|
||||
locationU = strU + initial_host.rstrip('/') + '/&p=/'
|
||||
|
||||
# 获取重定向地址
|
||||
redirect_response = requests.get(locationU, headers=self.header, allow_redirects=False)
|
||||
if 'location' in redirect_response.headers:
|
||||
return redirect_response.headers['location']
|
||||
else:
|
||||
# 尝试从JSON响应中获取
|
||||
try:
|
||||
data = redirect_response.json()
|
||||
return data.get('location', initial_host)
|
||||
except:
|
||||
return initial_host
|
||||
|
||||
except Exception as e:
|
||||
print(f"获取动态主机失败: {e}")
|
||||
return "http://6590ck.cc/"
|
||||
|
||||
def preprocessClasses(self):
|
||||
"""预处理分类数据"""
|
||||
return [
|
||||
{"type_name": "日韩AV", "type_id": "1"},
|
||||
{"type_name": "国产系列", "type_id": "2"},
|
||||
{"type_name": "欧美", "type_id": "3"},
|
||||
{"type_name": "成人动漫", "type_id": "4"},
|
||||
{"type_name": "日本有码", "type_id": "7"},
|
||||
{"type_name": "一本道高清无码", "type_id": "8"},
|
||||
{"type_name": "有码中文字幕", "type_id": "9"},
|
||||
{"type_name": "日本无码", "type_id": "10"},
|
||||
{"type_name": "国产视频", "type_id": "15"},
|
||||
{"type_name": "欧美高清", "type_id": "21"},
|
||||
{"type_name": "动漫剧情", "type_id": "22"}
|
||||
]
|
||||
|
||||
def init(self, extend):
|
||||
pass
|
||||
|
||||
def isVideoFormat(self, url):
|
||||
pass
|
||||
|
||||
def manualVideoCheck(self):
|
||||
pass
|
||||
|
||||
def homeContent(self, filter):
|
||||
result = {}
|
||||
result['class'] = self.classes
|
||||
return result
|
||||
|
||||
def homeVideoContent(self):
|
||||
"""推荐内容"""
|
||||
result = {}
|
||||
try:
|
||||
url = f"{self.host.rstrip('/')}/"
|
||||
rsp = self.fetch(url)
|
||||
root = pq(rsp.text)
|
||||
|
||||
videos = []
|
||||
list_items = root('.stui-vodlist li')
|
||||
|
||||
for item in list_items.items():
|
||||
vid = item.find('a').attr('href')
|
||||
if not vid or not vid.startswith('/vodplay/'):
|
||||
continue
|
||||
|
||||
name = item.find('h4').text()
|
||||
img = item.find('a').attr('data-original')
|
||||
remark = item.find('.pic-text').text()
|
||||
|
||||
if not name or not img:
|
||||
continue
|
||||
|
||||
videos.append({
|
||||
"vod_id": vid, # 只保存相对路径
|
||||
"vod_name": name,
|
||||
"vod_pic": self.getFullUrl(img),
|
||||
"vod_remarks": remark
|
||||
})
|
||||
|
||||
result['list'] = videos
|
||||
except Exception as e:
|
||||
print(f"获取推荐内容失败: {e}")
|
||||
result['list'] = []
|
||||
|
||||
return result
|
||||
|
||||
def categoryContent(self, tid, pg, filter, extend):
|
||||
result = {}
|
||||
try:
|
||||
url = f"{self.host.rstrip('/')}/vodtype/{tid}-{pg}.html"
|
||||
rsp = self.fetch(url)
|
||||
root = pq(rsp.text)
|
||||
|
||||
videos = []
|
||||
list_items = root('.stui-vodlist li')
|
||||
|
||||
for item in list_items.items():
|
||||
vid = item.find('a').attr('href')
|
||||
if not vid or not vid.startswith('/vodplay/'):
|
||||
continue
|
||||
|
||||
name = item.find('h4').text()
|
||||
img = item.find('a').attr('data-original')
|
||||
remark = item.find('.pic-text').text()
|
||||
|
||||
if not name or not img:
|
||||
continue
|
||||
|
||||
videos.append({
|
||||
"vod_id": vid, # 只保存相对路径
|
||||
"vod_name": name,
|
||||
"vod_pic": self.getFullUrl(img),
|
||||
"vod_remarks": remark
|
||||
})
|
||||
|
||||
result['list'] = videos
|
||||
result['page'] = int(pg)
|
||||
result['pagecount'] = 9999
|
||||
result['limit'] = 6
|
||||
result['total'] = 999999
|
||||
|
||||
except Exception as e:
|
||||
print(f"获取分类内容失败: {e}")
|
||||
result['list'] = []
|
||||
result['page'] = 1
|
||||
result['pagecount'] = 1
|
||||
result['limit'] = 6
|
||||
result['total'] = 0
|
||||
|
||||
return result
|
||||
|
||||
def extractM3U8Url(self, script_text):
|
||||
"""专门提取m3u8播放链接的方法"""
|
||||
m3u8_urls = []
|
||||
|
||||
print("开始提取m3u8链接...")
|
||||
|
||||
# 方法1: 从player_aaaa JavaScript变量中提取
|
||||
player_patterns = [
|
||||
r'var\s+player_aaaa\s*=\s*({.*?});',
|
||||
r'player_aaaa\s*=\s*({.*?});',
|
||||
r'var\s+player_aaaa\s*=\s*({.*?})\s*<\/script>',
|
||||
r'player_aaaa\s*=\s*({.*?})\s*<\/script>'
|
||||
]
|
||||
|
||||
for pattern in player_patterns:
|
||||
player_match = re.search(pattern, script_text, re.DOTALL)
|
||||
if player_match:
|
||||
try:
|
||||
player_data_str = player_match.group(1)
|
||||
print(f"找到player_aaaa数据: {player_data_str[:200]}...")
|
||||
|
||||
# 修复JSON字符串
|
||||
player_data_str = player_data_str.replace('\\/', '/')
|
||||
player_data = json.loads(player_data_str)
|
||||
|
||||
m3u8_url = player_data.get('url')
|
||||
if m3u8_url and '.m3u8' in m3u8_url:
|
||||
print(f"从player_aaaa提取到m3u8: {m3u8_url}")
|
||||
# 确保URL完整
|
||||
if not m3u8_url.startswith('http'):
|
||||
if m3u8_url.startswith('//'):
|
||||
m3u8_url = 'https:' + m3u8_url
|
||||
else:
|
||||
m3u8_url = self.getFullUrl(m3u8_url)
|
||||
m3u8_urls.append(m3u8_url)
|
||||
return m3u8_urls # 找到就返回
|
||||
|
||||
except Exception as e:
|
||||
print(f"解析player_aaaa失败: {e}")
|
||||
|
||||
# 方法2: 直接搜索m3u8链接
|
||||
m3u8_patterns = [
|
||||
r'"url"\s*:\s*"([^"]+\.m3u8[^"]*)"',
|
||||
r'url\s*:\s*"([^"]+\.m3u8[^"]*)"',
|
||||
r'src\s*:\s*"([^"]+\.m3u8[^"]*)"',
|
||||
r'file\s*:\s*"([^"]+\.m3u8[^"]*)"',
|
||||
r'https?://[^\s"\'<>]+\.m3u8[^\s"\'<>]*'
|
||||
]
|
||||
|
||||
for pattern in m3u8_patterns:
|
||||
matches = re.findall(pattern, script_text)
|
||||
for match in matches:
|
||||
if '.m3u8' in match and match not in m3u8_urls:
|
||||
print(f"从正则匹配提取到m3u8: {match}")
|
||||
# 确保URL完整
|
||||
if not match.startswith('http'):
|
||||
if match.startswith('//'):
|
||||
match = 'https:' + match
|
||||
else:
|
||||
match = self.getFullUrl(match)
|
||||
m3u8_urls.append(match)
|
||||
return m3u8_urls # 找到就返回
|
||||
|
||||
print("未找到m3u8播放链接")
|
||||
return m3u8_urls
|
||||
|
||||
def detailContent(self, array):
|
||||
"""二级详情页面解析 - 修复播放链接提取及简介使用标题"""
|
||||
result = {}
|
||||
try:
|
||||
vid = array[0]
|
||||
# 确保vid是完整URL
|
||||
if not vid.startswith('http'):
|
||||
vid = self.getFullUrl(vid)
|
||||
|
||||
print(f"开始解析详情页面: {vid}")
|
||||
rsp = self.fetch(vid)
|
||||
root = pq(rsp.text)
|
||||
|
||||
# 提取基本信息
|
||||
title = root('.stui-pannel__head .title').text()
|
||||
if not title:
|
||||
title = root('title').text().split(' - ')[0]
|
||||
|
||||
# 提取封面图
|
||||
pic = root('.stui-vodlist__thumb').attr('data-original') or root('.stui-vodlist__thumb').attr('src')
|
||||
if not pic:
|
||||
pic = root('img').attr('src')
|
||||
|
||||
# 获取所有script内容
|
||||
script_text = root('script').text()
|
||||
|
||||
# 提取m3u8播放链接
|
||||
m3u8_urls = self.extractM3U8Url(script_text)
|
||||
|
||||
# 构建播放链接
|
||||
play_urls = []
|
||||
if m3u8_urls:
|
||||
for i, m3u8_url in enumerate(m3u8_urls):
|
||||
play_urls.append(f"线路{i+1}${m3u8_url}")
|
||||
else:
|
||||
# 如果没有找到m3u8链接，尝试从页面其他位置提取
|
||||
print("尝试从页面其他位置提取播放链接...")
|
||||
# 从iframe中提取
|
||||
iframe_src = root('iframe').attr('src')
|
||||
if iframe_src and 'm3u8' in iframe_src:
|
||||
if not iframe_src.startswith('http'):
|
||||
iframe_src = self.getFullUrl(iframe_src)
|
||||
play_urls.append(f"iframe线路${iframe_src}")
|
||||
else:
|
||||
# 最后使用详情页URL
|
||||
play_urls.append(f"详情页线路${vid}")
|
||||
|
||||
# 用视频标题作为简介，避免没有简介内容
|
||||
vod = {
|
||||
"vod_id": array[0], # 保持原始ID
|
||||
"vod_name": title,
|
||||
"vod_pic": self.getFullUrl(pic) if pic else "",
|
||||
"vod_content": title, # 用标题当简介
|
||||
"vod_play_from": "黄色仓库",
|
||||
"vod_play_url": "#".join(play_urls) # 使用#分隔多个播放源
|
||||
}
|
||||
|
||||
result['list'] = [vod]
|
||||
print(f"详情页解析完成，播放链接: {vod['vod_play_url']}")
|
||||
|
||||
except Exception as e:
|
||||
print(f"解析详情页面失败: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
# 返回基础信息
|
||||
result['list'] = [{
|
||||
"vod_id": array[0],
|
||||
"vod_name": "未知标题",
|
||||
"vod_pic": "",
|
||||
"vod_content": "",
|
||||
"vod_play_from": "默认线路",
|
||||
"vod_play_url": f"详情页线路${array[0]}"
|
||||
}]
|
||||
|
||||
return result
|
||||
|
||||
def searchContent(self, key, quick):
|
||||
result = {}
|
||||
try:
|
||||
# 使用搜索URL
|
||||
search_url = f"{self.host.rstrip('/')}/vodsearch/-------------.html?wd={urllib.parse.quote(key)}"
|
||||
rsp = self.fetch(search_url)
|
||||
root = pq(rsp.text)
|
||||
|
||||
videos = []
|
||||
list_items = root('.stui-vodlist li')
|
||||
|
||||
for item in list_items.items():
|
||||
vid = item.find('a').attr('href')
|
||||
if not vid or not vid.startswith('/vodplay/'):
|
||||
continue
|
||||
|
||||
name = item.find('h4').text()
|
||||
img = item.find('a').attr('data-original')
|
||||
remark = item.find('.pic-text').text()
|
||||
|
||||
if not name or not img:
|
||||
continue
|
||||
|
||||
videos.append({
|
||||
"vod_id": vid, # 只保存相对路径
|
||||
"vod_name": name,
|
||||
"vod_pic": self.getFullUrl(img),
|
||||
"vod_remarks": remark
|
||||
})
|
||||
|
||||
result['list'] = videos
|
||||
except Exception as e:
|
||||
print(f"搜索失败: {e}")
|
||||
result['list'] = []
|
||||
|
||||
return result
|
||||
|
||||
def playerContent(self, flag, id, vipFlags):
|
||||
"""播放页面解析 - 修复数组越界问题"""
|
||||
result = {}
|
||||
try:
|
||||
print(f"playerContent被调用: flag={flag}, id={id}")
|
||||
|
||||
# 如果id已经是m3u8链接，直接返回
|
||||
if id.startswith('http') and '.m3u8' in id:
|
||||
result["parse"] = 0
|
||||
result["playUrl"] = ""
|
||||
result["url"] = id
|
||||
result["header"] = self.header
|
||||
print(f"直接返回m3u8链接: {id}")
|
||||
return result
|
||||
|
||||
# 如果id是播放线路格式，提取m3u8链接
|
||||
if '#' in id:
|
||||
play_sources = id.split('#')
|
||||
for source in play_sources:
|
||||
if '$' in source:
|
||||
_, url = source.split('$', 1)
|
||||
if '.m3u8' in url:
|
||||
result["parse"] = 0
|
||||
result["playUrl"] = ""
|
||||
result["url"] = url
|
||||
result["header"] = self.header
|
||||
print(f"从播放线路提取到m3u8: {url}")
|
||||
return result
|
||||
|
||||
# 如果id是详情页链接，重新解析详情页
|
||||
print(f"重新解析详情页获取m3u8: {id}")
|
||||
detail_result = self.detailContent([id])
|
||||
|
||||
if detail_result and 'list' in detail_result and detail_result['list']:
|
||||
vod = detail_result['list'][0]
|
||||
play_url = vod.get('vod_play_url', '')
|
||||
print(f"从详情页获取的播放链接: {play_url}")
|
||||
|
||||
# 解析播放链接
|
||||
if '#' in play_url:
|
||||
play_sources = play_url.split('#')
|
||||
for source in play_sources:
|
||||
if '$' in source:
|
||||
_, url = source.split('$', 1)
|
||||
if '.m3u8' in url:
|
||||
result["parse"] = 0
|
||||
result["playUrl"] = ""
|
||||
result["url"] = url
|
||||
result["header"] = self.header
|
||||
print(f"最终提取到m3u8: {url}")
|
||||
return result
|
||||
|
||||
# 如果没有找到m3u8，使用第一个播放源
|
||||
if play_sources:
|
||||
first_source = play_sources[0]
|
||||
if '$' in first_source:
|
||||
_, url = first_source.split('$', 1)
|
||||
result["parse"] = 0
|
||||
result["playUrl"] = ""
|
||||
result["url"] = url
|
||||
result["header"] = self.header
|
||||
print(f"使用第一个播放源: {url}")
|
||||
return result
|
||||
|
||||
# 如果所有方法都失败，返回空结果
|
||||
print("无法提取播放链接，返回空结果")
|
||||
return {}
|
||||
|
||||
except Exception as e:
|
||||
print(f"解析播放页面失败: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
return {}
|
||||
|
||||
def getFullUrl(self, url):
|
||||
"""获取完整的URL"""
|
||||
if not url:
|
||||
return ""
|
||||
if url.startswith('http'):
|
||||
return url
|
||||
if url.startswith('//'):
|
||||
return f"https:{url}"
|
||||
return f"{self.host.rstrip('/')}{url}"
|
||||
|
||||
config = {
|
||||
"player": {},
|
||||
"filter": {}
|
||||
}
|
||||
header = {
|
||||
"User-Agent": "Mozilla/5.0 (iPhone; CPU iPhone OS 16_6 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.6 Mobile/15E148 Safari/604.1",
|
||||
"Referer": "https://hsck123.com/"
|
||||
}
|
||||
|
||||
def localProxy(self, param):
|
||||
action = {}
|
||||
return action
|
||||
+271
@@ -0,0 +1,271 @@
|
||||
"""
|
||||
@header({
|
||||
searchable: 1,
|
||||
filterable: 1,
|
||||
quickSearch: 1,
|
||||
title: '神秘影院[密]',
|
||||
lang: 'hipy'
|
||||
})
|
||||
"""
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
#恰逢
|
||||
import re
|
||||
import urllib.parse
|
||||
from base.spider import Spider as BaseSpile
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
|
||||
|
||||
class VideoDecryptor:
|
||||
"""XOR 128 解密"""
|
||||
@staticmethod
|
||||
def decrypt(text: str) -> str:
|
||||
if not text:
|
||||
return ""
|
||||
try:
|
||||
return ''.join(chr(128 ^ ord(c)) for c in text)
|
||||
except:
|
||||
return text
|
||||
|
||||
@staticmethod
|
||||
def from_js(js: str) -> str:
|
||||
return VideoDecryptor.decrypt(m.group(1)) if (m := re.search(r"document\.write\(l\('([^']+)'\)\)", js)) else ""
|
||||
|
||||
|
||||
class Spider(BaseSpile):
|
||||
|
||||
def init(self, extend=""):
|
||||
self.host = "https://h4ivs.sm431.vip"
|
||||
self.video_host = "https://m3u8.nl:88"
|
||||
self.image_host = "https://3334.nl:33"
|
||||
self.headers = {
|
||||
"User-Agent": "Mozilla/5.0 (Linux; Android 13; 22127RK46C Build/TKQ1.220905.001; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/104.0.5112.97 Mobile Safari/537.36",
|
||||
"Referer": self.host,
|
||||
"Accept-Language": "zh-CN,zh;q=0.9",
|
||||
}
|
||||
self.cache = {}
|
||||
|
||||
def get(self, url):
|
||||
try:
|
||||
r = requests.get(url, headers=self.headers, timeout=15)
|
||||
r.raise_for_status()
|
||||
r.encoding = "utf-8"
|
||||
return r.text
|
||||
except:
|
||||
return ""
|
||||
|
||||
def img_url(self, url):
|
||||
"""格式化图片URL"""
|
||||
if not url:
|
||||
return ""
|
||||
if url.startswith("//"):
|
||||
url = "https:" + url
|
||||
elif url.startswith("/"):
|
||||
url = self.image_host + url
|
||||
return f"{url}@User-Agent={self.headers['User-Agent']}@Referer={self.host}/"
|
||||
|
||||
def parse(self, el):
|
||||
"""解析卡片"""
|
||||
a = el if el.name == 'a' else el.find('a')
|
||||
if not a or not (href := a.get("href", "")):
|
||||
return None
|
||||
|
||||
href = self.host + href if href.startswith("/") else href
|
||||
if not (vid := re.search(r"/vid/(\d+)", href)):
|
||||
return None
|
||||
|
||||
vid = vid.group(1)
|
||||
title = ""
|
||||
|
||||
# 解密标题
|
||||
if p := el.find('p'):
|
||||
if s := p.find('script'):
|
||||
if s.string:
|
||||
title = VideoDecryptor.from_js(s.string)
|
||||
title = title or p.get_text(strip=True)
|
||||
|
||||
if not title:
|
||||
for attr in ['data-title', 'data-name', 'title']:
|
||||
if el.has_attr(attr) and (val := el[attr]):
|
||||
if (de := VideoDecryptor.decrypt(val)) and len(de) > 3:
|
||||
title = de
|
||||
break
|
||||
|
||||
title = title or "未知标题"
|
||||
if title != "未知标题":
|
||||
self.cache[vid] = title
|
||||
|
||||
# 图片
|
||||
img = ""
|
||||
if node := el.select_one("img"):
|
||||
img = node.get("data-src") or node.get("src") or ""
|
||||
img = img or f"{self.image_host}/{vid}.jpg"
|
||||
|
||||
return {
|
||||
"vod_id": vid,
|
||||
"vod_name": title,
|
||||
"vod_pic": self.img_url(img),
|
||||
"vod_remarks": "",
|
||||
}
|
||||
|
||||
def get_title(self, vid):
|
||||
"""从缓存或首页获取标题"""
|
||||
if vid in self.cache:
|
||||
return self.cache[vid]
|
||||
|
||||
if html := self.get(self.host):
|
||||
soup = BeautifulSoup(html, "html.parser")
|
||||
for link in soup.select('a[href*="/vid/"]'):
|
||||
if f'/vid/{vid}' in link.get('href', ''):
|
||||
if p := link.find('p'):
|
||||
if s := p.find('script'):
|
||||
if s.string and (t := VideoDecryptor.from_js(s.string)):
|
||||
self.cache[vid] = t
|
||||
return t
|
||||
if t := p.get_text(strip=True):
|
||||
self.cache[vid] = t
|
||||
return t
|
||||
return None
|
||||
|
||||
def homeContent(self, filter):
|
||||
return {
|
||||
"class": [
|
||||
{"type_name": "国产", "type_id": "1"},
|
||||
{"type_name": "日本", "type_id": "2"},
|
||||
{"type_name": "韩国", "type_id": "3"},
|
||||
{"type_name": "欧美", "type_id": "4"},
|
||||
{"type_name": "三级", "type_id": "5"},
|
||||
{"type_name": "动漫", "type_id": "6"},
|
||||
]
|
||||
}
|
||||
|
||||
def homeVideoContent(self):
|
||||
if not (html := self.get(self.host)):
|
||||
return {"list": []}
|
||||
|
||||
soup = BeautifulSoup(html, "html.parser")
|
||||
videos = [v for v in (self.parse(el) for el in soup.select(".vodbox, .stui-vodlist__box, .vodlist__box, .video-card, .item")) if v]
|
||||
|
||||
if not videos:
|
||||
videos = [{"vod_id": v, "vod_name": "未知标题", "vod_pic": self.img_url(f"{self.image_host}/{v}.jpg"), "vod_remarks": ""}
|
||||
for v in re.findall(r'\[]\(/vid/(\d+)\.html\)', html)]
|
||||
|
||||
return {"list": videos}
|
||||
|
||||
def categoryContent(self, tid, pg, filter, extend):
|
||||
if tid == "0":
|
||||
url = self.host if int(pg) == 1 else f"{self.host}/page/{pg}.html"
|
||||
else:
|
||||
url = f"{self.host}/list/{tid}.html" if int(pg) == 1 else f"{self.host}/list/{tid}/{pg}.html"
|
||||
|
||||
if not (html := self.get(url)):
|
||||
return {"list": [], "page": pg, "pagecount": 1, "limit": 30, "total": 0}
|
||||
|
||||
soup = BeautifulSoup(html, "html.parser")
|
||||
videos = [v for v in (self.parse(el) for el in soup.select(".vodbox, .stui-vodlist__box, .vodlist__box, .video-card, .item")) if v]
|
||||
|
||||
if not videos:
|
||||
videos = [{"vod_id": v, "vod_name": "未知标题", "vod_pic": self.img_url(f"{self.image_host}/{v}.jpg"), "vod_remarks": ""}
|
||||
for v in re.findall(r'\[]\(/vid/(\d+)\.html\)', html)]
|
||||
|
||||
last = max([int(m.group(1)) for a in soup.select("a[href*='list/']") if (m := re.search(r"/list/\d+/(\d+)\.html", a.get("href", "")))], default=int(pg))
|
||||
|
||||
return {"list": videos, "page": pg, "pagecount": max(last, 1), "limit": 30, "total": 99999}
|
||||
|
||||
def searchContent(self, key, quick, pg="1"):
|
||||
url = f"{self.host}/so.html"
|
||||
params = {"wd": key}
|
||||
if int(pg) > 1:
|
||||
params["page"] = pg
|
||||
|
||||
html = ""
|
||||
for method in [requests.get, requests.post]:
|
||||
try:
|
||||
r = method(url, params=params if method == requests.get else None,
|
||||
data=params if method == requests.post else None,
|
||||
headers=self.headers, timeout=15)
|
||||
r.raise_for_status()
|
||||
r.encoding = "utf-8"
|
||||
html = r.text
|
||||
break
|
||||
except:
|
||||
continue
|
||||
|
||||
if not html:
|
||||
return {"list": []}
|
||||
|
||||
soup = BeautifulSoup(html, "html.parser")
|
||||
videos = [v for v in (self.parse(el) for el in soup.select(".vodbox, .stui-vodlist__box, .vodlist__box, .video-card, .item")) if v]
|
||||
|
||||
if not videos:
|
||||
videos = [{"vod_id": v, "vod_name": "未知标题", "vod_pic": self.img_url(f"{self.image_host}/{v}.jpg"), "vod_remarks": ""}
|
||||
for v in re.findall(r'\[]\(/vid/(\d+)\.html\)', html)]
|
||||
|
||||
last = max([int(m.group(1)) for a in soup.select("a[href*='so.html'], .pagination a, .page-link")
|
||||
if (m := re.search(r"[?&]page=(\d+)", a.get("href", "")))], default=int(pg))
|
||||
|
||||
return {"list": videos, "page": pg, "pagecount": max(last, 1), "limit": 30, "total": 99999}
|
||||
|
||||
def detailContent(self, ids):
|
||||
vid = ids[0]
|
||||
if not (html := self.get(f"{self.host}/vid/{vid}.html")):
|
||||
return {"list": []}
|
||||
|
||||
soup = BeautifulSoup(html, "html.parser")
|
||||
|
||||
# 标题
|
||||
title = self.get_title(vid)
|
||||
if not title:
|
||||
if t := soup.find('title'):
|
||||
title = re.sub(r'\s*[-_|]\s*.{0,20}$', '', t.get_text(strip=True)).strip()
|
||||
|
||||
if not title or len(title) < 5:
|
||||
for sel in ['h1', 'h2', '.video-title', '.title']:
|
||||
if (el := soup.select_one(sel)) and (txt := el.get_text(strip=True)) and len(txt) > 5:
|
||||
title = txt
|
||||
break
|
||||
|
||||
title = title or f"视频{vid}"
|
||||
|
||||
# 图片
|
||||
pic = ""
|
||||
for sel in ['.picbox img', '.vodimg img', '.video-pic img', '.poster img', 'img[data-id]']:
|
||||
if (node := soup.select_one(sel)) and (p := node.get("data-src") or node.get("src")) and 'favicon' not in p.lower():
|
||||
pic = p
|
||||
break
|
||||
|
||||
if not pic or 'favicon' in pic.lower():
|
||||
if meta := soup.select_one('meta[property="og:image"]'):
|
||||
pic = meta.get('content', '')
|
||||
|
||||
pic = pic or f"{self.image_host}/{vid}.jpg"
|
||||
|
||||
# 简介
|
||||
desc = soup.select_one(".vodinfo, .video-info, .content, .intro, .description")
|
||||
desc = desc.get_text(strip=True) if desc else ""
|
||||
|
||||
return {"list": [{
|
||||
"vod_id": vid,
|
||||
"vod_name": title,
|
||||
"vod_pic": self.img_url(pic),
|
||||
"vod_content": desc,
|
||||
"vod_play_from": "七哥比较瑟",
|
||||
"vod_play_url": f"狗哥特别瑟${vid}@@0@@1",
|
||||
}]}
|
||||
|
||||
def playerContent(self, flag, id, vipFlags):
|
||||
vid = id.split("@@")[0]
|
||||
return {"parse": 0, "url": f"{self.video_host}/{vid}/hls/index.m3u8", "header": self.headers}
|
||||
|
||||
def localProxy(self, param):
|
||||
return {"code": 404, "content": ""}
|
||||
|
||||
def isVideoFormat(self, url):
|
||||
return ".m3u8" in url.lower()
|
||||
|
||||
def manualVideoCheck(self):
|
||||
pass
|
||||
|
||||
def destroy(self):
|
||||
pass
|
||||
Reference in New Issue
Block a user