python下载快手视频教程_python如何下载快手视频

# -*-coding:utf-8-*-

# author : Corleone

import urllib2,urllib

import json,os,re,socket,time,sys

import Queue

import threading

import logging

# 日志模块

logger &＃61; logging.getLogger("AppName")

formatter &＃61; logging.Formatter(&＃39;%(asctime)s %(levelname)-5s: %(message)s&＃39;)

console_handler &＃61; logging.StreamHandler(sys.stdout)

console_handler.formatter &＃61; formatter

logger.addHandler(console_handler)

logger.setLevel(logging.INFO)

video_q &＃61; Queue.Queue()    # 视频队列

def get_video():

url &＃61;"http://101.251.217.210/rest/n/feed/hot?app&＃61;0&lon&＃61;121.372027&c&＃61;BOYA_BAIDU_PINZHUAN&sys&＃61;ANDROID_4.1.2&mod&＃61;HUAWEI(HUAWEI%20C8813Q)&did&＃61;ANDROID_e0e0ef947bbbc243&ver&＃61;5.4&net&＃61;WIFI&country_code&＃61;cn&iuid&＃61;&appver&＃61;5.4.7.5559&max_memory&＃61;128&oc&＃61;BOYA_BAIDU_PINZHUAN&ftt&＃61;&ud&＃61;0&language&＃61;zh-cn&lat&＃61;31.319303 "

data &＃61; {

&＃39;type&＃39;: 7,

&＃39;page&＃39;: 2,

&＃39;coldStart&＃39;:&＃39;false&＃39;,

&＃39;count&＃39;: 20,

&＃39;pv&＃39;:&＃39;false&＃39;,

&＃39;id&＃39;: 5,

&＃39;refreshTimes&＃39;: 4,

&＃39;pcursor&＃39;: 1,

&＃39;os&＃39;:&＃39;android&＃39;,

&＃39;client_key&＃39;:&＃39;3c2cd3f3&＃39;,

&＃39;sig&＃39;:&＃39;22769f2f5c0045381203fc57d1b5ad9b&＃39;

}

req &＃61; urllib2.Request(url)

req.add_header("User-Agent","kwai-android")

req.add_header("Content-Type","application/x-www-form-urlencoded")

params &＃61; urllib.urlencode(data)

try:

html &＃61; urllib2.urlopen(req, params).read()

except urllib2.URLError:

logger.warning(u"网络不稳定 正在重试访问")

html &＃61; urllib2.urlopen(req, params).read()

result &＃61; json.loads(html)

reg &＃61; re.compile(u"[\u4e00-\u9fa5]&＃43;")   # 只匹配中文

for x in result[&＃39;feeds&＃39;]:

try:

title &＃61; x[&＃39;caption&＃39;].replace("\n","")

name &＃61;" ".join(reg.findall(title))

video_q.put([name, x[&＃39;photo_id&＃39;], x[&＃39;main_mv_urls&＃39;][0][&＃39;url&＃39;]])

except KeyError:

pass

def download(video_q):

path &＃61; u"D:\快手"

while True:

data &＃61; video_q.get()

name &＃61; data[0].replace("\n","")

id &＃61; data[1]

url &＃61; data[2]

file &＃61; os.path.join(path, name &＃43;".mp4")

logger.info(u"正在下载&＃xff1a;%s" %name)

try:

urllib.urlretrieve(url,file)

except IOError:

file &＃61; os.path.join(path, u"神经病呀"&＃43;&＃39;%s.mp4&＃39;) %id

try:

urllib.urlretrieve(url, file)

except (socket.error,urllib.ContentTooShortError):

logger.warning(u"请求被断开&＃xff0c;休眠2秒")

time.sleep(2)

urllib.urlretrieve(url, file)

logger.info(u"下载完成&＃xff1a;%s" % name)

video_q.task_done()

def main():

# 使用帮助

try:

threads &＃61; int(sys.argv[1])

except (IndexError, ValueError):

print u"\n用法: " &＃43; sys.argv[0] &＃43; u" [线程数:10] \n"

print u"例如&＃xff1a;" &＃43; sys.argv[0] &＃43;" 10" &＃43; u"  爬取视频 开启10个线程 每天爬取一次 一次2000个视频左右(空格隔开)"

return False

# 判断目录

if os.path.exists(u&＃39;D:\快手&＃39;) &＃61;&＃61; False:

os.makedirs(u&＃39;D:\快手&＃39;)

# 解析网页

logger.info(u"正在爬取网页")

for x in range(1,100):

logger.info(u"第 %s 次请求" % x)

get_video()

num &＃61; video_q.qsize()

logger.info(u"共 %s 视频" %num)

# 多线程下载

for y in range(threads):

t &＃61; threading.Thread(target&＃61;download,args&＃61;(video_q,))

t.setDaemon(True)

t.start()

video_q.join()

logger.info(u"-----------全部已经爬取完成---------------")

main()