def calcResizeRatio(resizedImgBytes, originImg):
"""Calculate imgage resize ratio
Args:
resizedImgBytes (bytes): resized image binary bytes
originImg (Image): original image Object
Returns:
resize ratio (float)
Raises:
"""
originSize = originImg.width, originImg.height
originBytes = imageToBytes(originImg)
resizedImg = bytesToImage(resizedImgBytes)
resizedSize = resizedImg.width, resizedImg.height
originLen = len(originBytes)
resizedLen = len(resizedImgBytes)
resizeRatio = float(resizedLen) / float(originLen)
resizeRatioPercent = int(resizeRatio * 100)
printStr = "\t-> Compress ratio=%d%%, from [fmt=%s, size=%sx%s, len=%s] to [fmt=%s, size=%sx%s, len=%s]" % (
resizeRatioPercent,
originImg.format, originSize[0], originSize[1], formatSize(originLen),
resizedImg.format, resizedSize[0], resizedSize[1], formatSize(resizedLen)
)
print(printStr)
# logging.debug(printStr)
return resizeRatio
def downloadFile(
url,
fileToSave=None,
proxies=None,
isStreamMode=True,
isResume=True,
):
"""Download file from url then save to file
Args:
url (str): file online url
fileToSave (str): filename or full file path
proxies (dict): requests proxies
isStreamMode (bool): use stream mode or not
Returns:
download ok or not (bool)
Raises:
Examples:
input:
'https://book.crifan.com/books/5g_message_rcs_tech_summary/pdf/5g_message_rcs_tech_summary.pdf'
'downloaded/pdf/5g_message_rcs_tech_summary.pdf'
output:
True
"""
isDownloadOk = False
if not fileToSave:
urlPartList = url.split("/")
fileToSave = urlPartList[-1] # 5g_message_rcs_tech_summary.pdf
try:
if isStreamMode:
totalFileSize = getFileSizeFromUrl(url, proxies) # 154551625
if not totalFileSize:
print("Failed to get total file size from %s" % url)
return isDownloadOk
totalSizeStr = formatSize(totalFileSize)
print("Get total file size %s from %s" % (totalSizeStr, url))
isDownloadedAndValid = isFileExistAndValid(
fileToSave, fullFileSize=totalFileSize)
if isDownloadedAndValid:
print("%s is already download" % fileToSave)
isDownloadOk = True
return isDownloadOk
curDownloadedSize = 0
isExistFile = os.path.isfile(fileToSave)
if isExistFile:
curDownloadedSize = os.path.getsize(fileToSave)
curDownloadedSizeStr = formatSize(curDownloadedSize)
print("Already downloaded %s for %s" %
(curDownloadedSizeStr, fileToSave))
if curDownloadedSize > totalFileSize:
# possible is local is new version, so consider as downloaded
print("Downloaded=%s > online=%s, consider as downloaded" %
(curDownloadedSizeStr, totalSizeStr))
isDownloadOk = True
return isDownloadOk
if not isResume:
curDownloadedSize = 0
isDownloadOk = streamingDownloadFile(
url,
fileToSave=fileToSave,
proxies=proxies,
isShowSpeed=True,
resumeSize=curDownloadedSize,
totalSize=totalFileSize,
)
else:
resp = requests.get(url, proxies=proxies)
with open(fileToSave, 'wb') as saveFp:
saveFp.write(resp.content)
isDownloadOk = True
except BaseException as curException:
print("Exception %s when download %s to %s" %
(curException, url, fileToSave))
return isDownloadOk
def streamingDownloadFile(
url,
fileToSave=None,
proxies=None,
isShowSpeed=True,
chunkSize=1024 * 512,
resumeSize=0,
totalSize=0,
):
"""Download file using stream mode, support showing process with current speed, percent, size
Args:
url (str): file online url
fileToSave (str): filename or full file path
proxies (dict): requests proxies
isShowSpeed (bool): show downloading speed or not
chunkSize (int): when showing download speed, need use stream downloading, need set chunck size
resumeSize (bool): the size to start download, normally is the local already downloaded size
totalSize (int): total file size, only used for calculate downloaded percent
Returns:
download ok or not (bool)
Raises:
Examples:
"""
isDownloadOk = False
if isShowSpeed:
if totalSize == 0:
gotTotalSize = getFileSizeFromUrl(url, proxies) # 154551625
if gotTotalSize:
totalSize = gotTotalSize
headers = {
'Range': 'bytes=%d-' % resumeSize,
# "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.81 Safari/537.36",
}
resp = requests.get(url, proxies=proxies, headers=headers, stream=True)
curDownloadedSize = 0
with open(fileToSave, "ab") as f:
startTime = time.time()
prevTime = startTime
for curChunkBytes in resp.iter_content(chunk_size=chunkSize):
if curChunkBytes:
curTime = time.time() # 1606456020.0718982
f.write(curChunkBytes)
f.flush()
curChunkSize = len(curChunkBytes) # 524288
curDownloadedSize += curChunkSize # 524288
totalDownloadedSize = curDownloadedSize + resumeSize # 12058624
totalDownloadedSizeStr = formatSize(
totalDownloadedSize) # '11.5MB'
curDownloadTime = curTime - prevTime # 15.63818907737732
curSpeed = curChunkSize / curDownloadTime # 670522.651191692
curSpeedStr = formatSize(curSpeed) # '231.3KB'
totalDownloadTime = curTime - startTime # 15.63818907737732
averageSpeed = curDownloadedSize / totalDownloadTime # 670522.651191692
averageSpeedStr = formatSize(averageSpeed) # '231.3KB'
totalDownloadTimeDict = floatSecondsToDatetimeDict(
totalDownloadTime)
totalDownloadTimeStr = datetimeDictToStr(
totalDownloadTimeDict, isShowMilliSecPart=False)
if isShowSpeed:
showStr = "downloading speed: cur=%s/s, avg=%s/s, time: total=%s, size: %s" % (
curSpeedStr, averageSpeedStr, totalDownloadTimeStr,
totalDownloadedSizeStr)
if totalSize > 0:
downloadedPercent100 = round(
100 * totalDownloadedSize / totalSize, 2) # 47.23
downloadedPercent100Str = str(
downloadedPercent100) # '47.23'
percentStr = ", percent: %s%%" % downloadedPercent100Str # ', percent: 47.23%'
else:
percentStr = ""
showStr += percentStr
# 'downloading speed: cur=231.3KB/s, avg=231.3KB/s, time: total=00:00:02, size: 11.5MB, percent: 49.38%'
print(showStr)
prevTime = curTime
return isDownloadOk