Python實作影片爬取

 Python可以用來做什麼？公司裡主要是爬取數據，並把爬回來的數據進行分析和挖掘，然而我們自己可以用它來爬取一些資源去使用，比如，想看的劇。本文中，小編將分享爬取影片的程式碼，大家存起來試試看吧！

下載串流文件，requests庫中請求的stream設為True就可以啦，文件在此。

先找一個影片位址試驗一下：

# -*- 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)

發生當頭一棒：

##

AttributeError: __exit__

這文檔也會騙人的麼！

看來是沒有實作上下文所需的__exit__方法。既然只是為了保證要讓r最後close以釋放連接池，那就使用contextlib的closing特性好了：

# -*- 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)

程式正常運行了，不過我盯著這文件，怎麼大小不見變啊，到底完成了多少了呢？還是要讓下好的內容及時存進硬碟，還能省點記憶體是不是：

# -*- 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())

檔以肉眼可見的速度在增大，真心疼我的硬碟，還是最後一次寫入硬碟吧，程式中記個數就好了：

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

結果就很直觀了：

##

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

心懷遠大理想的我怎麼會只滿足於這一個呢，寫個類別一起使用吧：

# -*- 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))

運行：

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 
/////////////////////////////////////////////////

看起來舒服多了。

下面要做的就是多執行緒同時下載了，主執行緒生產url放入佇列，下載執行緒取得url：

# -*- 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()

加了重複下載的判斷，至於怎麼源源不絕的生產url，各位摸索吧，保重身體！

【推薦課程：

Python影片教學

】

以上是Python實作影片爬取的詳細內容。更多資訊請關注PHP中文網其他相關文章！