千聊视频的爬取

import requests
import random
import os


filedir = '摩羯座周期下的黄金市场'

if not os.path.exists(filedir):
   os.makedirs(filedir)
   print("目录创建成功!")

abspath = os.path.abspath(__file__)
abspath = abspath[0:abspath.rfind('\\',1)]

fi =open(filedir + ".txt",'r')

for line in fi:

    url = line.strip()
    url = url[0:url.rfind('?', 1)]         #	取?号之前的字符串
    filename = url[url.rfind('/', 1) + 1:] #  从字符串中取出文件名
    #print('../'+filedir+'/'+filename)
    if os.path.exists(abspath+'\\' + filedir+'\\'+ filename[filename.rfind('_', 1) + 1:] ): # 文件名只取 最后的序列号
         print('已存在,跳下一行')
         continue
    print(filename + " 开始下载,请稍后... ...")


    ##    1找到url

    #url ="http://v.stu.126.net/mooc-video/nos/mp4/2017/02/28/1005853348_f171329df9a543528f1d3661025dafb4_shd.mp4"

    headers ={"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11"}  

    user_agent = [
    "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
    "Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
    "MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
    "Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",
    "NOKIA5700/ UCWEB7.0.2.37/28/999",
    "Openwave/ UCWEB7.0.2.37/28/999",
    ]

    headers = {'User-Agent': random.choice(user_agent)}

    ##    2解析url
    
    r = requests.get(url,headers =headers)
    
    ##    3提取数据
    
    ret =r.content  #这个url的二进制数据
    
    ##    4保存数据
    
    with open('./{0}/{1}'.format(filedir,filename[filename.rfind('_', 1) + 1:]),'wb') as f:
        f.write(ret)

    
print(" 下载完成")

fi.close()

自动设置目录 爬取千聊视频。

txt 内容为视频源地址,用猫爪抓取,如下

https://1301324389.vod2.myqcloud.com/d7beb5c4vodcq1301324389/c6deae8d5285890811258630980/1718060644_1442716530_1.ts?start=0&end=3029995&type=mpegts&resolution=3200x1800&us=46a94eca-f883-49a1-b9d4-7a66725ce52e&sign=5bcb5f8814607cf3c8519647d6200cb3&t=5fd5e5da
https://1301324389.vod2.myqcloud.com/d7beb5c4vodcq1301324389/c6deae8d5285890811258630980/1718060644_1442716530_1.ts?start=3029996&end=6094771&type=mpegts&resolution=3200x1800&us=46a94eca-f883-49a1-b9d4-7a66725ce52e&sign=5bcb5f8814607cf3c8519647d6200cb3&t=5fd5e5da
https://1301324389.vod2.myqcloud.com/d7beb5c4vodcq1301324389/c6deae8d5285890811258630980/1718060644_1442716530_1.ts?start=6094772&end=9157667&type=mpegts&resolution=3200x1800&us=46a94eca-f883-49a1-b9d4-7a66725ce52e&sign=5bcb5f8814607cf3c8519647d6200cb3&t=5fd5e5da
https://1301324389.vod2.myqcloud.com/d7beb5c4vodcq1301324389/c6deae8d5285890811258630980/1718060644_1442716530_1.ts?start=9157668&end=12223007&type=mpegts&resolution=3200x1800&us=46a94eca-f883-49a1-b9d4-7a66725ce52e&sign=5bcb5f8814607cf3c8519647d6200cb3&t=5fd5e5da
https://1301324389.vod2.myqcloud.com/d7beb5c4vodcq1301324389/c6deae8d5285890811258630980/1718060644_1442716530_1.ts?start=12223008&end=15287031&type=mpegts&resolution=3200x1800&us=46a94eca-f883-49a1-b9d4-7a66725ce52e&sign=5bcb5f8814607cf3c8519647d6200cb3&t=5fd5e5da
https://1301324389.vod2.myqcloud.com/d7beb5c4vodcq1301324389/c6deae8d5285890811258630980/1718060644_1442716530_1.ts?start=15287032&end=18351243&type=mpegts&resolution=3200x1800&us=46a94eca-f883-49a1-b9d4-7a66725ce52e&sign=5bcb5f8814607cf3c8519647d6200cb3&t=5fd5e5da
https://1301324389.vod2.myqcloud.com/d7beb5c4vodcq1301324389/c6deae8d5285890811258630980/1718060644_1442716530_1.ts?start=18351244&end=21729791&type=mpegts&resolution=3200x1800&us=46a94eca-f883-49a1-b9d4-7a66725ce52e&sign=5bcb5f8814607cf3c8519647d6200cb3&t=5fd5e5da
https://1301324389.vod2.myqcloud.com/d7beb5c4vodcq1301324389/c6deae8d5285890811258630980/1718060644_1442716530_1.ts?start=21729792&end=24789303&type=mpegts&resolution=3200x1800&us=46a94eca-f883-49a1-b9d4-7a66725ce52e&sign=5bcb5f8814607cf3c8519647d6200cb3&t=5fd5e5da
https://1301324389.vod2.myqcloud.com/d7beb5c4vodcq1301324389/c6deae8d5285890811258630980/1718060644_1799471148_2.ts?start=0&end=3054247&type=mpegts&resolution=3200x1800&us=46a94eca-f883-49a1-b9d4-7a66725ce52e&sign=5bcb5f8814607cf3c8519647d6200cb3&t=5fd5e5da
https://1301324389.vod2.myqcloud.com/d7beb5c4vodcq1301324389/c6deae8d5285890811258630980/1718060644_1799471148_2.ts?start=3054248&end=6113007&type=mpegts&resolution=3200x1800&us=46a94eca-f883-49a1-b9d4-7a66725ce52e&sign=5bcb5f8814607cf3c8519647d6200cb3&t=5fd5e5da
https://1301324389.vod2.myqcloud.com/d7beb5c4vodcq1301324389/c6deae8d5285890811258630980/1718060644_1799471148_2.ts?start=6113008&end=9171955&type=mpegts&resolution=3200x1800&us=46a94eca-f883-49a1-b9d4-7a66725ce52e&sign=5bcb5f8814607cf3c8519647d6200cb3&t=5fd5e5da
https://1301324389.vod2.myqcloud.com/d7beb5c4vodcq1301324389/c6deae8d5285890811258630980/1718060644_1799471148_2.ts?start=9171956&end=12229963&type=mpegts&resolution=3200x1800&us=46a94eca-f883-49a1-b9d4-7a66725ce52e&sign=5bcb5f8814607cf3c8519647d6200cb3&t=5fd5e5da
https://1301324389.vod2.myqcloud.com/d7beb5c4vodcq1301324389/c6deae8d5285890811258630980/1718060644_1799471148_2.ts?start=12229964&end=15289287&type=mpegts&resolution=3200x1800&us=46a94eca-f883-49a1-b9d4-7a66725ce52e&sign=5bcb5f8814607cf3c8519647d6200cb3&t=5fd5e5da
https://1301324389.vod2.myqcloud.com/d7beb5c4vodcq1301324389/c6deae8d5285890811258630980/1718060644_1799471148_2.ts?start=15289288&end=18346919&type=mpegts&resolution=3200x1800&us=46a94eca-f883-49a1-b9d4-7a66725ce52e&sign=5bcb5f8814607cf3c8519647d6200cb3&t=5fd5e5da
https://1301324389.vod2.myqcloud.com/d7beb5c4vodcq1301324389/c6deae8d5285890811258630980/1718060644_1799471148_2.ts?start=18346920&end=21404927&type=mpegts&resolution=3200x1800&us=46a94eca-f883-49a1-b9d4-7a66725ce52e&sign=5bcb5f8814607cf3c8519647d6200cb3&t=5fd5e5da
https://1301324389.vod2.myqcloud.com/d7beb5c4vodcq1301324389/c6deae8d5285890811258630980/1718060644_1799471148_2.ts?start=21404928&end=24464627&type=mpegts&resolution=3200x1800&us=46a94eca-f883-49a1-b9d4-7a66725ce52e&sign=5bcb5f8814607cf3c8519647d6200cb3&t=5fd5e5da
https://1301324389.vod2.myqcloud.com/d7beb5c4vodcq1301324389/c6deae8d5285890811258630980/1718060644_1481620958_3.ts?start=0&end=3057631&type=mpegts&resolution=3200x1800&us=46a94eca-f883-49a1-b9d4-7a66725ce52e&sign=5bcb5f8814607cf3c8519647d6200cb3&t=5fd5e5da

  • 3
    点赞
  • 14
    收藏
    觉得还不错? 一键收藏
  • 4
    评论
评论 4
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值