#coding:utf-8
import urllib
import urllib2
import requests
import random
import uuid
import time
import sys
from threading import Thread
#img_url = "https://p.ssl.qhimg.com/dm/48_48_100/t017aee03b28107657b.jpg"
my_headers={
"User-Agent":"Mozilla/5.0 (Windows NT 6.3; Win64; x64) \
AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36",
'Referer':'https://www.bilibili.com/bangumi/play/ep250436',
}
img=[
'http://xunleib.zuida360.com/1811/妖精的尾巴最终季-06.mp4',
'http://xunleib.zuida360.com/1811/妖精的尾巴最终季-05.mp4',
'http://vip.zuiku8.com/1810/妖精的尾巴最终季-04.mp4',
'http://vip.zuiku8.com/1810/妖精的尾巴最终季-03.mp4',
'http://vip.zuiku8.com/1810/妖精的尾巴最终季-02.mp4',
'http://vip.zuiku8.com/1810/妖精的尾巴最终季-01.mp4'
]
def chunk_report(bytes_so_far, chunk_size, total_size,filename):
percent = float(bytes_so_far) / total_size
percent = round(percent*100, 2)
if percent %1==0:
sys.stdout.write("Downloaded %s ==> (%0.2f%%)\n" %
(filename, percent))
if bytes_so_far >= total_size:
sys.stdout.write('\n')
def chunk_read(response, url,chunk_size=8192, report_hook=None):
total_size = response.info().getheader('Content-Length').strip()
total_size = int(total_size)
bytes_so_far = 0
path_name=url.split("/")[-1]
path_name=path_name.replace("\n","")
path_name=path_name.decode("utf-8")
print path_name
with open("%s" % path_name, "wb") as f:
while 1:
chunk = response.read(chunk_size)
f.write(chunk)
f.flush()
bytes_so_far += len(chunk)
if not chunk:
break
if report_hook:
report_hook(bytes_so_far, chunk_size, total_size,path_name)
return bytes_so_far
def down_load(img):
while True:
print img
request = urllib2.Request(url=img, headers=my_headers)
response = urllib2.urlopen(request);
chunk_read(response,img, report_hook=chunk_report)
print "downloading with urllib --->"
if __name__ == '__main__':
for i in range(len(img)):
t = Thread(target=down_load,args=(img[i],))
t.start()
Python 多线程爬取视频
最新推荐文章于 2024-06-27 11:08:18 发布