python - 试图将文件下载缓冲区拆分为单独的线程

Question

我正在尝试将文件缓冲区下载到 5 个线程中，但它似乎出现了乱码。

from numpy import arange
import requests
from threading import Thread
import urllib2

url = 'http://pymotw.com/2/urllib/index.html'
sizeInBytes = r = requests.head(url, headers={'Accept-Encoding': 'identity'}).headers['content-length']

splitBy = 5

splits = arange(splitBy + 1) * (float(sizeInBytes)/splitBy)

dataLst = []

def bufferSplit(url, idx, splits):
    req = urllib2.Request(url,  headers={'Range': 'bytes=%d-%d' % (splits[idx], splits[idx+1])})
    print {'bytes=%d-%d' % (splits[idx], splits[idx+1])}
    dataLst.append(urllib2.urlopen(req).read())


for idx in range(splitBy):
    dlth = Thread(target=bufferSplit, args=(url, idx, splits))
    dlth.start()


print dataLst

with open('page.html', 'w') as fh:
    fh.write(''.join(dataLst))

更新:所以我努力工作，但进展甚微，但是，如果我下载一个 jpg，它似乎已损坏；

from numpy import arange
import os
import requests
import threading
import urllib2

# url ='http://s1.fans.ge/mp3/201109/08/John_Legend_So_High_Remix(fans_ge).mp3'
url = "http://www.nasa.gov/images/content/607800main_kepler1200_1600-1200.jpg"
# url = 'http://pymotw.com/2/urllib/index.html'
sizeInBytes = requests.head(url, headers={'Accept-Encoding': 'identity'}).headers.get('content-length', None)


splitBy = 5

dataLst = []


class ThreadedFetch(threading.Thread):
    """ docstring for ThreadedFetch
    """
    def __init__(self, url, fileName, splitBy=5):
        super(ThreadedFetch, self).__init__()
        self.__url = url
        self.__spl = splitBy
        self.__dataLst = []
        self.__fileName = fileName

    def run(self):
        if not sizeInBytes:
            print "Size cannot be determined."
            return
        splits = arange(self.__spl + 1) * (float(sizeInBytes)/self.__spl)
        for idx in range(self.__spl):
            req = urllib2.Request(self.__url,  headers={'Range': 'bytes=%d-%d' % (splits[idx], splits[idx+1])})
            self.__dataLst.append(urllib2.urlopen(req).read())


    def getFileData(self):
        return ''.join(self.__dataLst)


fileName = url.split('/')[-1]

dl = ThreadedFetch(url, fileName)
dl.start()
dl.join()
content = dl.getFileData()
if content:
    with open(fileName, 'w') as fh:
        fh.write(content)
    print "Finished Writing file %s" % fileName

下面是下载后的图片。

Answer 1

这是该项目的另一个版本。差异:

• 线程代码是一个单独的小函数

• 每个线程下载一个 block ，然后将其存储在全局线程安全字典中

• 线程启动，然后 join()ed -- 它们同时运行

• 全部完成后，数据以正确的顺序重组，然后写入磁盘

• 额外打印，以验证一切正确

• 计算输出文件大小，用于额外比较

来源

import os, requests
import threading
import urllib2
import time

URL = "http://www.nasa.gov/images/content/607800main_kepler1200_1600-1200.jpg"

def buildRange(value, numsplits):
    lst = []
    for i in range(numsplits):
        if i == 0:
            lst.append('%s-%s' % (i, int(round(1 + i * value/(numsplits*1.0) + value/(numsplits*1.0)-1, 0))))
        else:
            lst.append('%s-%s' % (int(round(1 + i * value/(numsplits*1.0),0)), int(round(1 + i * value/(numsplits*1.0) + value/(numsplits*1.0)-1, 0))))
    return lst

def main(url=None, splitBy=3):
    start_time = time.time()
    if not url:
        print "Please Enter some url to begin download."
        return

    fileName = url.split('/')[-1]
    sizeInBytes = requests.head(url, headers={'Accept-Encoding': 'identity'}).headers.get('content-length', None)
    print "%s bytes to download." % sizeInBytes
    if not sizeInBytes:
        print "Size cannot be determined."
        return

    dataDict = {}

    # split total num bytes into ranges
    ranges = buildRange(int(sizeInBytes), splitBy)

    def downloadChunk(idx, irange):
        req = urllib2.Request(url)
        req.headers['Range'] = 'bytes={}'.format(irange)
        dataDict[idx] = urllib2.urlopen(req).read()

    # create one downloading thread per chunk
    downloaders = [
        threading.Thread(
            target=downloadChunk, 
            args=(idx, irange),
        )
        for idx,irange in enumerate(ranges)
        ]

    # start threads, let run in parallel, wait for all to finish
    for th in downloaders:
        th.start()
    for th in downloaders:
        th.join()

    print 'done: got {} chunks, total {} bytes'.format(
        len(dataDict), sum( (
            len(chunk) for chunk in dataDict.values()
        ) )
    )

    print "--- %s seconds ---" % str(time.time() - start_time)

    if os.path.exists(fileName):
        os.remove(fileName)
    # reassemble file in correct order
    with open(fileName, 'w') as fh:
        for _idx,chunk in sorted(dataDict.iteritems()):
            fh.write(chunk)

    print "Finished Writing file %s" % fileName
    print 'file size {} bytes'.format(os.path.getsize(fileName))

if __name__ == '__main__':
    main(URL)

输出

102331 bytes to download.
done: got 3 chunks, total 102331 bytes
--- 0.380599021912 seconds ---
Finished Writing file 607800main_kepler1200_1600-1200.jpg
file size 102331 bytes