Skip to content

Instantly share code, notes, and snippets.

@gregorynicholas
Created April 18, 2012 00:58
Show Gist options
  • Select an option

  • Save gregorynicholas/2410227 to your computer and use it in GitHub Desktop.

Select an option

Save gregorynicholas/2410227 to your computer and use it in GitHub Desktop.
Finds and downloads all images from any given URL.: originally from:http://code.activestate.com/recipes/577385-image-downloader/
# imageDownloader.py
# Finds and downloads all images from any given URL recursively.
# FB - 201009094
import urllib2
from os.path import basename
import urlparse
from BeautifulSoup import BeautifulSoup # for HTML parsing
global urlList
urlList = []
# recursively download images starting from the root URL
def downloadImages(url, level, minFileSize): # the root URL is level 0
# do not go to other websites
global website
netloc = urlparse.urlsplit(url).netloc.split('.')
if netloc[-2] + netloc[-1] != website:
return
global urlList
if url in urlList: # prevent using the same URL again
return
try:
urlContent = urllib2.urlopen(url).read()
urlList.append(url)
print url
except:
return
soup = BeautifulSoup(''.join(urlContent))
# find and download all images
imgTags = soup.findAll('img')
for imgTag in imgTags:
imgUrl = imgTag['src']
# download only the proper image files
if imgUrl.lower().endswith('.jpeg') or \
imgUrl.lower().endswith('.jpg') or \
imgUrl.lower().endswith('.gif') or \
imgUrl.lower().endswith('.png') or \
imgUrl.lower().endswith('.bmp'):
try:
imgData = urllib2.urlopen(imgUrl).read()
if len(imgData) >= minFileSize:
print " " + imgUrl
fileName = basename(urlsplit(imgUrl)[2])
output = open(fileName,'wb')
output.write(imgData)
output.close()
except:
pass
print
print
# if there are links on the webpage then recursively repeat
if level > 0:
linkTags = soup.findAll('a')
if len(linkTags) > 0:
for linkTag in linkTags:
try:
linkUrl = linkTag['href']
downloadImages(linkUrl, level - 1, minFileSize)
except:
pass
# main
rootUrl = 'http://www.yahoo.com'
netloc = urlparse.urlsplit(rootUrl).netloc.split('.')
global website
website = netloc[-2] + netloc[-1]
downloadImages(rootUrl, 1, 50000)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment