import timeimport requests,os
import urllib3
import urllib.request
from startm3u8 import get_start_m3u8
import asyncio
import aiofile
import aiohttp
# start_url = "https://www.jijikb.com/play/52825-0-1.html" #一共5集
secend_m3u8 = "https://vod4.buycar5.cn/20210617/DmV0P4zD/1000kb/hls/index.m3u8"
headers = {
'Referer': 'https://vod4.buycar5.cn/',
'host':'vod4.buycar5.cn',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36',
}
def response(url):
rep = requests.get(url=url,headers=headers,timeout = 20,verify =False) #使用Python3 requests发送HTTPS请求，已经关闭认证（verify=False）情况下，控制台会输出以下InsecureRequestWarning
rep.encoding = rep.apparent_encoding
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning) ## 禁用安全请求警告
if rep.status_code == 200:
return rep
else:
print("----没有响应----")
def get_second_m3u8_url(url):
rep = requests.get(url)
print(rep)
with open('first.m3u8','w') as f:
f.write(rep.text)
with open('first.m3u8',"r") as r_f:
for line in r_f:
if line.startswith("#"):
continue
start_m3u8_url = "https://vod4.buycar5.cn" + line
return start_m3u8_url
def get_tc_url(resp):
with open('secend.m3u8', 'wb') as f:
f.write(resp)
tc_urls = []
with open('secend.m3u8',"r") as r_f:
for n in r_f:
if n.startswith("#"):
continue
else:
print(n)
tc_urls.append(n)
return tc_urls
async def mov_down(url,semaphore):
async with semaphore:
async with aiohttp.ClientSession() as session:
tc_name = url.split('/')[-1].strip()
print(tc_name,"---正在下载-----")
async with await session.get(url,headers=headers) as rep:
print(rep.status)
async with aiofile.async_open("mov2/"+tc_name,'wb') as p_f:
print("-----正在存储------")
rep1 = await rep.read()
await p_f.write(rep1)
print(tc_name,'----下载完成---')
"""
urllib.request.urlopen(url, data=None, [timeout, ])
传入的url就是你想抓取的地址；
data是指向服务器提交信息时传递的字典形式的信息，通常来说就是爬去需要登录的网址时传入的用户名和密码，可省略。
timeout参数指的是超时时间，也可省略。
"""
def main():
semaphore = asyncio.Semaphore(100) # 限制并发量为20
start_time = time.time()
if not os.path.exists('mov2'):
os.mkdir("mov2")
start_m3u8_url = get_start_m3u8(start_url)
secend_m3u8_url = get_second_m3u8_url(start_m3u8_url)
print(secend_m3u8_url)
resp = urllib.request.urlopen(secend_m3u8_url).read()
# resp =requests.get(url=secend_m3u8_url,headers=headers) #不知道为什么requests 请求不到
tc_urls = get_tc_url(resp)
tasks = []
for url in tc_urls:
task =asyncio.ensure_future(mov_down(url,semaphore))
tasks.append(task)
loop.run_until_complete(asyncio.wait(tasks))
loop.close()
print(time.time()-start_time)
if __name__ == '__main__':
loop = asyncio.get_event_loop() #建立事件循环
main()
发表于 2021-6-28 21:43
|
发表于 2021-6-28 21:54
