Update 酒店源.py
This commit is contained in:
frxz751113
GitHub
@@ -76,28 +76,43 @@ for url in urls:
|
|||||||
page_content = driver.page_source
|
page_content = driver.page_source
|
||||||
# 关闭WebDriver
|
# 关闭WebDriver
|
||||||
driver.quit()
|
driver.quit()
|
||||||
# 查找所有符合指定格式的网址
|
|
||||||
pattern = r"http://\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}:\d+" # 设置匹配的格式,如http://8.8.8.8:8888
|
|
||||||
urls_all = re.findall(pattern, page_content)
|
# 查找所有符合指定格式的网址，使用正则表达式匹配页面内容中的URL
|
||||||
# urls = list(set(urls_all)) # 去重得到唯一的URL列表
|
pattern = r"http://\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}:\d+" # 设置匹配的格式，如http://8.8.8.8:8888
|
||||||
urls = set(urls_all) # 去重得到唯一的URL列表
|
urls_all = re.findall(pattern, page_content) # 使用findall方法查找所有匹配的URL
|
||||||
x_urls = []
|
# 使用set去除重复的URL，得到唯一的URL列表
|
||||||
for url in urls: # 对urls进行处理,ip第四位修改为1,并去重
|
urls = set(urls_all)
|
||||||
url = url.strip()
|
# 初始化一个空列表，用于存储处理后的URL
|
||||||
ip_start_index = url.find("//") + 2
|
x_urls = []
|
||||||
ip_end_index = url.find(":", ip_start_index)
|
# 遍历去重后的URL列表
|
||||||
ip_dot_start = url.find(".") + 1
|
for url in urls:
|
||||||
ip_dot_second = url.find(".", ip_dot_start) + 1
|
# 去除URL前后的空白字符
|
||||||
ip_dot_three = url.find(".", ip_dot_second) + 1
|
url = url.strip()
|
||||||
base_url = url[:ip_start_index] # http:// or https://
|
# 找出URL中"http://"后面直到":"之间的部分（即IP地址部分）
|
||||||
ip_address = url[ip_start_index:ip_dot_three]
|
ip_start_index = url.find("//") + 2
|
||||||
port = url[ip_end_index:]
|
ip_end_index = url.find(":", ip_start_index)
|
||||||
ip_end = "1"
|
# 找出IP地址中各八位字节的位置
|
||||||
modified_ip = f"{ip_address}{ip_end}"
|
ip_dot_start = url.find(".") + 1
|
||||||
x_url = f"{base_url}{modified_ip}{port}"
|
ip_dot_second = url.find(".", ip_dot_start) + 1
|
||||||
x_urls.append(x_url)
|
ip_dot_three = url.find(".", ip_dot_second) + 1
|
||||||
urls = set(x_urls) # 去重得到唯一的URL列表
|
# 提取协议头部（http://或https://）
|
||||||
valid_urls = []
|
base_url = url[:ip_start_index]
|
||||||
|
# 提取IP地址
|
||||||
|
ip_address = url[ip_start_index:ip_dot_three]
|
||||||
|
# 提取端口号
|
||||||
|
port = url[ip_end_index:]
|
||||||
|
# 将IP地址的最后一部分修改为"1"，生成新的IP地址
|
||||||
|
ip_end = "1"
|
||||||
|
modified_ip = f"{ip_address[:-1]}{ip_end}"
|
||||||
|
# 构造新的URL
|
||||||
|
x_url = f"{base_url}{modified_ip}{port}"
|
||||||
|
# 将新的URL添加到列表中
|
||||||
|
x_urls.append(x_url)
|
||||||
|
# 再次使用set去除重复的URL，得到最终的唯一URL列表
|
||||||
|
urls = set(x_urls)
|
||||||
|
# 初始化一个空列表，用于存储验证后的可访问URL
|
||||||
|
valid_urls = []
|
||||||
# 多线程获取可用url
|
# 多线程获取可用url
|
||||||
with concurrent.futures.ThreadPoolExecutor(max_workers=100) as executor:
|
with concurrent.futures.ThreadPoolExecutor(max_workers=100) as executor:
|
||||||
futures = []
|
futures = []
|
||||||
@@ -112,148 +127,46 @@ for url in urls:
|
|||||||
valid_urls.append(result)
|
valid_urls.append(result)
|
||||||
for url in valid_urls:
|
for url in valid_urls:
|
||||||
print(url)
|
print(url)
|
||||||
# 遍历网址列表,获取JSON文件并解析
|
# 遍历网址列表,获取JSON文件并解析
|
||||||
for url in valid_urls:
|
for url in valid_urls:
|
||||||
try:
|
try:
|
||||||
# 发送GET请求获取JSON文件,设置超时时间为0.5秒
|
# 发送GET请求获取JSON文件,设置超时时间为0.5秒
|
||||||
json_url = f"{url}"
|
response = requests.get(url, timeout=0.5)
|
||||||
response = requests.get(json_url, timeout=1)################################
|
json_data = response.content.decode('utf-8')
|
||||||
json_data = response.content.decode('utf-8')
|
|
||||||
try:
|
# 按行分割数据
|
||||||
# 按行分割数据
|
lines = json_data.split('\n')
|
||||||
lines = json_data.split('\n')
|
for line in lines:
|
||||||
for line in lines:
|
# 行中需包含hls，但排除udp和rtp
|
||||||
if 'hls' in line and ('udp' not in line or 'rtp' not in line): #行中需包含m3u,但排除udp和trp
|
if 'hls' in line and ('udp' not in line and 'rtp' not in line):
|
||||||
line = line.strip()
|
line = line.strip()
|
||||||
if line:
|
if line:
|
||||||
name, channel_url = line.split(',')
|
# 分割行以获取频道名和原始URL
|
||||||
urls = channel_url.split('/', 3)
|
name, channel_url = line.split(',')
|
||||||
url_data = json_url.split('/', 3)
|
|
||||||
if len(urls) >= 4:
|
# 解析json_url以提取IP和端口
|
||||||
urld = (f"{urls[0]}//{url_data[2]}/{urls[3]}")
|
parsed_json_url = urlparse(url)
|
||||||
else:
|
json_ip = parsed_json_url.hostname
|
||||||
urld = (f"{urls[0]}//{url_data[2]}")
|
json_port = ':' + parsed_json_url.port if parsed_json_url.port else ''
|
||||||
print(f"{name},{urld}")
|
|
||||||
if name and urld:
|
# 替换原始URL中的IP地址和端口为json_url中的IP地址和端口
|
||||||
name = name.replace("高清电影", "影迷电影")
|
new_channel_url = channel_url.replace(channel_url.split('/')[2], json_ip)
|
||||||
name = name.replace("中央", "CCTV")
|
if json_port: # 如果json_url中有端口号，也进行替换
|
||||||
name = name.replace("高清", "")
|
new_channel_url = new_channel_url.replace(f":{channel_url.split(':')[1]}", json_port)
|
||||||
name = name.replace("HD", "")
|
|
||||||
name = name.replace("标清", "")
|
# 构造新的行并打印
|
||||||
name = name.replace("超高", "")
|
new_line = f"{name},{new_channel_url}"
|
||||||
name = name.replace("频道", "")
|
print(new_line) # 打印新的行
|
||||||
name = name.replace("靓妆", "女性时尚")
|
|
||||||
name = name.replace("本港台", "TVB星河")
|
# 写入到文件中
|
||||||
name = name.replace("汉3", "汉")
|
with open('iptv.txt', 'a', encoding='utf-8') as outfile:
|
||||||
name = name.replace("汉4", "汉")
|
outfile.write(new_line + '\n')
|
||||||
name = name.replace("汉5", "汉")
|
except requests.exceptions.RequestException as e:
|
||||||
name = name.replace("汉6", "汉")
|
print(f"Error fetching or processing the JSON data: {e}")
|
||||||
name = name.replace("CHC动", "动")
|
|
||||||
name = name.replace("CHC家", "家")
|
|
||||||
name = name.replace("CHC影", "影")
|
|
||||||
name = name.replace("-", "")
|
|
||||||
name = name.replace(" ", "")
|
|
||||||
name = name.replace("PLUS", "+")
|
|
||||||
name = name.replace("＋", "+")
|
|
||||||
name = name.replace("(", "")
|
|
||||||
name = name.replace(")", "")
|
|
||||||
name = name.replace("L", "")
|
|
||||||
name = name.replace("新农村", "河南新农村")
|
|
||||||
name = name.replace("百姓调解", "河南百姓调解")
|
|
||||||
name = name.replace("法治", "河南法治")
|
|
||||||
name = name.replace("睛彩中原", "河南睛彩")
|
|
||||||
name = name.replace("军事", "河南军事")
|
|
||||||
name = name.replace("梨园", "河南梨园")
|
|
||||||
name = name.replace("相声小品", "河南相声小品")
|
|
||||||
name = name.replace("移动戏曲", "河南移动戏曲")
|
|
||||||
name = name.replace("都市生活", "河南都市生活")
|
|
||||||
name = name.replace("民生", "河南民生")
|
|
||||||
name = name.replace("CCTVNEWS", "CCTV13")
|
|
||||||
name = name.replace("cctv", "CCTV")
|
|
||||||
name = re.sub(r"CCTV(\d+)台", r"CCTV\1", name)
|
|
||||||
name = name.replace("CCTV1综合", "CCTV1")
|
|
||||||
name = name.replace("CCTV2财经", "CCTV2")
|
|
||||||
name = name.replace("CCTV3综艺", "CCTV3")
|
|
||||||
name = name.replace("CCTV4国际", "CCTV4")
|
|
||||||
name = name.replace("CCTV4中文国际", "CCTV4")
|
|
||||||
name = name.replace("CCTV4欧洲", "CCTV4")
|
|
||||||
name = name.replace("CCTV5体育", "CCTV5")
|
|
||||||
name = name.replace("CCTV5+体育", "CCTV5+")
|
|
||||||
name = name.replace("CCTV6电影", "CCTV6")
|
|
||||||
name = name.replace("CCTV7军事", "CCTV7")
|
|
||||||
name = name.replace("CCTV7军农", "CCTV7")
|
|
||||||
name = name.replace("CCTV7农业", "CCTV7")
|
|
||||||
name = name.replace("CCTV7国防军事", "CCTV7")
|
|
||||||
name = name.replace("CCTV8电视剧", "CCTV8")
|
|
||||||
name = name.replace("CCTV8纪录", "CCTV9")
|
|
||||||
name = name.replace("CCTV9记录", "CCTV9")
|
|
||||||
name = name.replace("CCTV9纪录", "CCTV9")
|
|
||||||
name = name.replace("CCTV10科教", "CCTV10")
|
|
||||||
name = name.replace("CCTV11戏曲", "CCTV11")
|
|
||||||
name = name.replace("CCTV12社会与法", "CCTV12")
|
|
||||||
name = name.replace("CCTV13新闻", "CCTV13")
|
|
||||||
name = name.replace("CCTV新闻", "CCTV13")
|
|
||||||
name = name.replace("CCTV14少儿", "CCTV14")
|
|
||||||
name = name.replace("央视14少儿", "CCTV14")
|
|
||||||
name = name.replace("CCTV少儿超", "CCTV14")
|
|
||||||
name = name.replace("CCTV15音乐", "CCTV15")
|
|
||||||
name = name.replace("CCTV音乐", "CCTV15")
|
|
||||||
name = name.replace("CCTV16奥林匹克", "CCTV16")
|
|
||||||
name = name.replace("SCTV5四川影视）", "SCTV5")
|
|
||||||
name = name.replace("CCTV17农业农村", "CCTV17")
|
|
||||||
name = name.replace("CCTV17军农", "CCTV17")
|
|
||||||
name = name.replace("CCTV17农业", "CCTV17")
|
|
||||||
name = name.replace("CCTV5+体育赛视", "CCTV5+")
|
|
||||||
name = name.replace("CCTV5+赛视", "CCTV5+")
|
|
||||||
name = name.replace("CCTV5+体育赛事", "CCTV5+")
|
|
||||||
name = name.replace("CCTV5+赛事", "CCTV5+")
|
|
||||||
name = name.replace("CCTV5+体育", "CCTV5+")
|
|
||||||
name = name.replace("CCTV5赛事", "CCTV5+")
|
|
||||||
name = name.replace("凤凰中文台", "凤凰中文")
|
|
||||||
name = name.replace("凤凰资讯台", "凤凰资讯")
|
|
||||||
name = name.replace("CCTV4K测试）", "CCTV4")
|
|
||||||
name = name.replace("CCTV164K", "CCTV16")
|
|
||||||
name = name.replace("上海东方卫视", "上海卫视")
|
|
||||||
name = name.replace("东方卫视", "上海卫视")
|
|
||||||
name = name.replace("内蒙卫视", "内蒙古卫视")
|
|
||||||
name = name.replace("福建东南卫视", "东南卫视")
|
|
||||||
name = name.replace("广东南方卫视", "南方卫视")
|
|
||||||
name = name.replace("湖南金鹰卡通", "金鹰卡通")
|
|
||||||
name = name.replace("炫动卡通", "哈哈炫动")
|
|
||||||
name = name.replace("卡酷卡通", "卡酷少儿")
|
|
||||||
name = name.replace("卡酷动画", "卡酷少儿")
|
|
||||||
name = name.replace("BRTVKAKU少儿", "卡酷少儿")
|
|
||||||
name = name.replace("优曼卡通", "优漫卡通")
|
|
||||||
name = name.replace("优曼卡通", "优漫卡通")
|
|
||||||
name = name.replace("嘉佳卡通", "佳嘉卡通")
|
|
||||||
name = name.replace("世界地理", "地理世界")
|
|
||||||
name = name.replace("CCTV世界地理", "地理世界")
|
|
||||||
name = name.replace("BTV北京卫视", "北京卫视")
|
|
||||||
name = name.replace("BTV冬奥纪实", "冬奥纪实")
|
|
||||||
name = name.replace("东奥纪实", "冬奥纪实")
|
|
||||||
name = name.replace("卫视台", "卫视")
|
|
||||||
name = name.replace("湖南电视台", "湖南卫视")
|
|
||||||
name = name.replace("少儿科教", "少儿")
|
|
||||||
name = name.replace("TV星河2）", "星河")
|
|
||||||
name = name.replace("影视剧", "影视")
|
|
||||||
name = name.replace("电视剧", "影视")
|
|
||||||
name = name.replace("奥运匹克", "")
|
|
||||||
results.append(f"{name},{urld}")
|
|
||||||
except:
|
|
||||||
continue
|
|
||||||
except:
|
|
||||||
continue
|
|
||||||
channels = []
|
|
||||||
for result in results:
|
|
||||||
line = result.strip()
|
|
||||||
if result:
|
|
||||||
channel_name, channel_url = result.split(',')
|
|
||||||
channels.append((channel_name, channel_url))
|
|
||||||
with open("iptv.txt", 'w', encoding='utf-8') as file:
|
|
||||||
for result in results:
|
|
||||||
file.write(result + "\n")
|
|
||||||
print(result)
|
|
||||||
print("频道列表文件iptv.txt获取完成！")
|
print("频道列表文件iptv.txt获取完成！")
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
for line in fileinput.input("iptv.txt", inplace=True): #打开文件,并对其进行关键词原地替换
|
for line in fileinput.input("iptv.txt", inplace=True): #打开文件,并对其进行关键词原地替换
|
||||||
line = line.replace("河南河南", "河南")
|
line = line.replace("河南河南", "河南")
|
||||||
line = line.replace("河南河南", "河南")
|
line = line.replace("河南河南", "河南")
|
||||||
|
|||||||
Reference in New Issue
Block a user