Python实现视频爬取

Python可以用来做什么？公司里主要是爬取数据，并把爬回来的数据进行分析和挖掘，然而我们自己可以用它来爬取一些资源去使用，比如，想看的剧。本文中，小编将分享爬取视频的代码，大家存起来试试吧！

# -*- coding: utf-8 -*-
import requests
def download_file(url, path):
    with requests.get(url, stream=True) as r:
        chunk_size = 1024
        content_size = int(r.headers['content-length'])
        print '下载开始'
        with open(path, "wb") as f:
            for chunk in r.iter_content(chunk_size=chunk_size):
                f.write(chunk)
if __name__ == '__main__':
    url = '就在原帖...'
    path = '想存哪都行'
    download_file(url, path) 

# -*- coding: utf-8 -*-
import requests
from contextlib import closing
def download_file(url, path):
    with closing(requests.get(url, stream=True)) as r:
        chunk_size = 1024
        content_size = int(r.headers['content-length'])
        print '下载开始'
        with open(path, "wb") as f:
            for chunk in r.iter_content(chunk_size=chunk_size):
                f.write(chunk) 

# -*- coding: utf-8 -*-
import requests
from contextlib import closing
import os
def download_file(url, path):
    with closing(requests.get(url, stream=True)) as r:
        chunk_size = 1024
        content_size = int(r.headers['content-length'])
        print '下载开始'
        with open(path, "wb") as f:
            for chunk in r.iter_content(chunk_size=chunk_size):
                f.write(chunk)
                f.flush()
                os.fsync(f.fileno()) 

def download_file(url, path):
    with closing(requests.get(url, stream=True)) as r:
        chunk_size = 1024
        content_size = int(r.headers['content-length'])
        print '下载开始'
        with open(path, "wb") as f:
            n = 1
            for chunk in r.iter_content(chunk_size=chunk_size):
                loaded = n*1024.0/content_size
                f.write(chunk)
                print '已下载{0:%}'.format(loaded)
                n += 1 

已下载2.579129%
已下载2.581255%
已下载2.583382%
已下载2.585508% 

# -*- coding: utf-8 -*-
import requests
from contextlib import closing
import time
def download_file(url, path):
    with closing(requests.get(url, stream=True)) as r:
        chunk_size = 1024*10
        content_size = int(r.headers['content-length'])
        print '下载开始'
        with open(path, "wb") as f:
            p = ProgressData(size = content_size, unit='Kb', block=chunk_size)
            for chunk in r.iter_content(chunk_size=chunk_size):
                f.write(chunk)
                p.output()
class ProgressData(object):
    def __init__(self, block,size, unit, file_name='', ):
        self.file_name = file_name
        self.block = block/1000.0
        self.size = size/1000.0
        self.unit = unit
        self.count = 0
        self.start = time.time()
    def output(self):
        self.end = time.time()
        self.count += 1
        speed = self.block/(self.end-self.start) if (self.end-self.start)>0 else 0
        self.start = time.time()
        loaded = self.count*self.block
        progress = round(loaded/self.size, 4)
        if loaded >= self.size:
            print u'%s下载完成\r\n'%self.file_name
        else:
            print u'{0}下载进度{1:.2f}{2}/{3:.2f}{4} 下载速度{5:.2%} {6:.2f}{7}/s'.                  format(self.file_name, loaded, self.unit,                  self.size, self.unit, progress, speed, self.unit)
            print '%50s'%('/'*int((1-progress)*50)) 

下载开始
下载进度10.24Kb/120174.05Kb 0.01% 下载速度4.75Kb/s 
///////////////////////////////////////////////// 
下载进度20.48Kb/120174.05Kb 0.02% 下载速度32.93Kb/s 
///////////////////////////////////////////////// 

# -*- coding: utf-8 -*-
import requests
from contextlib import closing
import time
import Queue
import hashlib
import threading
import os
def download_file(url, path):
    with closing(requests.get(url, stream=True)) as r:
        chunk_size = 1024*10
        content_size = int(r.headers['content-length'])
        if os.path.exists(path) and os.path.getsize(path)>=content_size:
            print '已下载'
            return
        print '下载开始'
        with open(path, "wb") as f:
            p = ProgressData(size = content_size, unit='Kb', block=chunk_size, file_name=path)
            for chunk in r.iter_content(chunk_size=chunk_size):
                f.write(chunk)
                p.output()

class ProgressData(object):
    def __init__(self, block,size, unit, file_name='', ):
        self.file_name = file_name
        self.block = block/1000.0
        self.size = size/1000.0
        self.unit = unit
        self.count = 0
        self.start = time.time()
    def output(self):
        self.end = time.time()
        self.count += 1
        speed = self.block/(self.end-self.start) if (self.end-self.start)>0 else 0
        self.start = time.time()
        loaded = self.count*self.block
        progress = round(loaded/self.size, 4)
        if loaded >= self.size:
            print u'%s下载完成\r\n'%self.file_name
        else:
            print u'{0}下载进度{1:.2f}{2}/{3:.2f}{4} {5:.2%} 下载速度{6:.2f}{7}/s'.                  format(self.file_name, loaded, self.unit,                  self.size, self.unit, progress, speed, self.unit)
            print '%50s'%('/'*int((1-progress)*50))

queue = Queue.Queue()
def run():
    while True:
        url = queue.get(timeout=100)
        if url is None:
            print u'全下完啦'
            break
        h = hashlib.md5()
        h.update(url)
        name = h.hexdigest()
        path = 'e:/download/' + name + '.mp4'
        download_file(url, path)
def get_url():
    queue.put(None)

if __name__ == '__main__':
    get_url()
    for i in xrange(4):
        t = threading.Thread(target=run)
        t.daemon = True
        t.start() 

加了重复下载的判断，至于怎么源源不断的生产url，诸位摸索吧，保重身体！

【推荐课程：Python视频教程】

以上就是Python实现视频爬取的详细内容，更多请关注Gxl网其它相关文章！

查看更多关于Python实现视频爬取的详细内容...