imgscraper

imgscr.py

# a simple image scraper by tlehman
# this code is too basic for me to care what you do with it, so have at it.
# 
from urllib import urlopen
from BeautifulSoup import BeautifulSoup

# usage: getimg(url, filetype)
#    return will be list of src attributes of a tags in page 
#    referred to by url
def getimg(url, filetype):
    # get html source from url
    text = urlopen(url).read()
    # parse the html source using BeautifulSoup
    soup = BeautifulSoup(text)
    
    # set of image urls to be returned
    imgurls = set()
    for img in soup.findAll('img'):
        s=str(img['src'])
        if s[len(s)-3:] == filetype:
            imgurls.add(s)
                
    return list(imgurls)

This used to be a github repository, but it is too small, so I made it into a gist.