Created
May 9, 2014 15:34
-
-
Save paulwinex/0c8328353db9a2510314 to your computer and use it in GitHub Desktop.
Download folder structure from http
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import urllib, urllib2 | |
import re | |
import os | |
import shutil | |
import time | |
class downloaderClass(object): | |
def __init__(self): | |
self.v = False | |
def verbos(self, i): | |
self.v = i | |
def message(self, msg): | |
print '>>>', msg | |
def downloadFile(self, url, local): | |
file_size_dl = 0 | |
block_sz = 8192 | |
u = urllib2.urlopen(url) | |
f = open(local, 'wb') | |
if self.v: | |
meta = u.info() | |
file_size = int(meta.getheaders("Content-Length")[0]) | |
self.message("Downloading: %s Bytes: %s" % (local, file_size)) | |
while True: | |
buffer = u.read(block_sz) | |
if not buffer: | |
break | |
file_size_dl += len(buffer) | |
f.write(buffer) | |
if self.v and file_size > block_sz: | |
prc = file_size_dl * 100. / file_size | |
status = '%2f%%' % prc | |
status = status + chr(8)*(len(status)+1) | |
self.message(status) | |
f.close() | |
return True | |
def downloadFolder(self, url, target, ind=''): | |
data = urllib.urlopen(url).read() | |
string = data.decode('utf-8') | |
# find files | |
pat1 = re.compile('> (.+\.[a-zA-Z0-9]+)<') | |
filelist = pat1.findall(string) | |
# find folders | |
pat2 = re.compile('> (.+)/<') | |
folderlist = pat2.findall(string) | |
# download files | |
for f in filelist: | |
remote = '/'.join([url, f]) | |
local = os.path.normpath(os.path.join(target, f)) | |
if os.path.exists(local): | |
os.remove(local) | |
print ind, f | |
self.downloadFile(remote, local) | |
# download folders | |
for f in [x.strip() for x in folderlist]: | |
print ind, f | |
local = os.path.normpath(os.path.join(target, f)) | |
if not os.path.exists(local): | |
os.makedirs(local) | |
else: | |
shutil.rmtree(local) | |
time.sleep(0.3) #for fix WindowsError 5 | |
os.makedirs(local) | |
remote = '/'.join([url, f]) | |
self.downloadFolder(remote, local, ind+' ') | |
#example | |
#url = 'http//site/folder/subfolder' | |
#targetDir = 'c:/tergetFolder' | |
#d = downloaderClass() | |
#d.downloadFolder(url, targetDir) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment