【爬虫】案例-获取cbh影戏 - qidao123.com技术社区-IT企服评测·应用市场

import requests
url = 'https://v.cdnlz3.com/20240802/25255_00ff1a4b/2000k/hls/819a23c20b1000173.ts'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36',
'referer':'https://www.cupfox.in/'
}
response = requests.get(url)
print(response.status_code)
with open('video.ts', 'wb') as f:
f.write(response.content)

复制代码

import re
import requests
import time
import random
def get_m3u8():
'''
获取m3u8文件
'''
url = 'https://v.cdnlz3.com/20240802/25255_00ff1a4b/2000k/hls/index.m3u8'
resp = requests.get(url).text
# print(resp)
ts_list = re.findall('819a23c20b1000(.*?).ts', resp)
return ts_list
def get_response(ts_list):
for ts in ts_list:
url = f'https://v.cdnlz3.com/20240802/25255_00ff1a4b/2000k/hls/819a23c20b1000{ts}.ts'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36',
'referer':'https://www.cupfox.in/'
}
response = requests.get(url, headers=headers)
try:
with open('video.ts', 'ab') as f:
f.write(response.content)
print(f'下载完成,{ts+1}/{len(ts_list)}')
time.sleep(random.uniform(1, 2))
except Exception as e:
print('报错原因是',e)
if __name__ == '__main__':
'''
关键词.m3u8,它是一个文本文件，里面包含了多个ts
'''
a = get_m3u8() # 通过分析得出 # ts_list = re.findall('819a23c20b10(.*?).ts)', resp)
get_response(a)

复制代码