Update IPTV搜索引擎采集.py

This commit is contained in:
frxz751113
2025-03-12 16:41:11 +08:00
committed by GitHub
parent 93bd47c8d2
commit 52e029f599
+22 -12
View File
@@ -33,29 +33,39 @@ header = {
import requests import requests
from lxml import etree from lxml import etree
# 假设header已经定义好,这里简单示例一个User-Agent
header = {
"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"
}
def via_tonking(url): def via_tonking(url):
headers = { headers = {
'Referer': 'http://tonkiang.us/hotellist.html', 'Referer': 'http://tonkiang.us/hotellist.html',
'User-Agent': header["User-Agent"], 'User-Agent': header["User-Agent"],
} }
try: try:
# 提取 IP 地址部分,去除协议 cities = ['北京市', '江苏省']
ip_address = url.split("//")[-1] for city in cities:
response = requests.get( # 提取 IP 地址部分,去除协议
#url=f'http://tonkiang.us/hoteliptv.php?s={ip_address}&c=false&y=false', ip_address = url.split("//")[-1]
url=f'https://tonkiang.us/hoteliptv.php?page=1&iphone16={ip_address}&code=', response = requests.get(
headers=headers, url=f'https://tonkiang.us/hoteliptv.php?page=1&iphone16={city}&code=',
timeout=10 headers=headers,
) timeout=10
response.raise_for_status() )
et = etree.HTML(response.text) response.raise_for_status()
div_text = et.xpath('//div[@class="result"]/div/text()')[1] et = etree.HTML(response.text)
return "暂时失效" not in div_text div_text = et.xpath('//div[@class="result"]/div/text()')[1]
if "暂时失效" not in div_text:
return True
return False
except Exception as e: except Exception as e:
print(f"验证 IP 时发生错误: {e}") print(f"验证 IP 时发生错误: {e}")
return False return False
# 从tonkiang获取可用IP # 从tonkiang获取可用IP
def get_tonkiang(keyword): def get_tonkiang(keyword):
data = { data = {