简单的批量下载工具代码,Python代码库,德仔网

代码语言

代码分类

【Python】简单的批量下载工具

作者:Darren_Chan / 发布于2013/8/5/ 884


	#!/usr/bin/python
	# -*- coding: utf-8 -*-

	import sys, os
	import urllib.request

	'''
	Author: Bouygues
	Date: 4th August, 2013
	Version: 1.1

	Update Logs:
	version 1.0: created
	version 1.1: add try ... catch for HttpError handling
	version 1.2: can save file to disk by chunk
	'''

	# --- class ---
	class MultiDownload():
	 '''
	 download urls in list, ignore one not in self.pfix
	 save each name according to its url name;
	 save them into directory fold;
	 '''
	 def __init__(self, urls, fold):
	 self.urls = urls
	 self.fold = self.pathFormat(fold)
	 # download by chunk
	 self.chunk = 512
	 self.pfix = ("jpg", "JPG", "JPEG", "jpeg", "png", "PNG")
	
	 def pathFormat(self, path):
	 """
	 make sure the path is a right directory path;
	 and end with '/'
	 """
	 path = path.strip()
	 path = path.replace("\\", "/")
	 size = len(path)
	 if(path[size-1]!="/"):
	 path += "/"
	 return path
	
	 def getPostfix(self, url):
	 if "." not in url:
	 return None
	 p = url.rfind(".") + 1
	 return url[p:]

	 def getFileName(self, url):
	 if "/" not in url:
	 return None
	 p = url.rfind("/") + 1
	 return url[p:]
	
	 def down(self, url):
	 filename = self.getFileName(url)
	 path = self.fold + filename
	 f = open(path, 'wb')
	 try:
	 w = urllib.request.urlopen(url)
	 except:
	 print("[ERROR] %s" % (url))
	 else:
	 # save file by chunk (if file size is too big)
	 while True:
	 chunkD = w.read(self.chunk*1024)
	 if len(chunkD)==0 :
	 break
	 f.write(chunkD)
	 print(" - Download %dK data" % (len(chunkD)/1024))
	 #data = w.read()
	 #f.write(data)
	 w.close()
	 finally:
	 f.close()
	
	 def run(self):
	 for line in self.urls:
	 #if self.getPostfix(line) not in self.pfix:
	 # continue
	 self.down(line)
	 print(line)
	 return True
	

	# --- global functions ---

	

	# --- main ---
	'''
	download files listed in file
	'''
	# variables
	inputfile = input("input filename: ")
	targetList = set()
	basedir = input("where do you want to save files? ")

	
	# get url list
	f = open(inputfile, 'r')
	for line in f:
	 line = line.strip()
	 if len(line)>3:
	 targetList.add(line)
	f.close()

	# download each file
	md = MultiDownload(targetList, basedir)
	md.run()

试试其它关键字

　批量下载　

同语言下

可能有用的

Darren_Chan贡献的其它代码(1)

.简单的批量下载工具