Download image file from the HTML page source using python?

Question

I am writing a scraper that downloads all the image files from a HTML page and saves them to a specific folder. all the images are the part of the HTML page.

Answer 1

You have to download the page and parse html document, find your image with regex and download it.. You can use urllib2 for downloading and Beautiful Soup for parsing html file.

Answer 2

Use htmllib to extract all img tags (override do_img), then use urllib2 to download all the images.

Answer 3

Here is some code to download all the images from the supplied URL, and save them in the specified output folder. You can modify it to your own needs.

"""
dumpimages.py
    Downloads all the images on the supplied URL, and saves them to the
    specified output file ("/test/" by default)

Usage:
    python dumpimages.py http://example.com/ [output]
"""

from BeautifulSoup import BeautifulSoup as bs
import urlparse
from urllib2 import urlopen
from urllib import urlretrieve
import os
import sys

def main(url, out_folder="/test/"):
    """Downloads all the images at 'url' to /test/"""
    soup = bs(urlopen(url))
    parsed = list(urlparse.urlparse(url))

    for image in soup.findAll("img"):
        print "Image: %(src)s" % image
        filename = image["src"].split("/")[-1]
        parsed[2] = image["src"]
        outpath = os.path.join(out_folder, filename)
        urlretrieve(urlparse.urlunparse(parsed), outpath)

def _usage():
    print "usage: python dumpimages.py http://example.com [outpath]"

if __name__ == "__main__":
    url = sys.argv[-1]
    out_folder = "/test/"
    if not url.lower().startswith("http"):
        out_folder = sys.argv[-1]
        url = sys.argv[-2]
        if not url.lower().startswith("http"):
            _usage()
            sys.exit(-1)
    main(url, out_folder)

Edit: You can specify the output folder now.

Answer 4

And this is function for download one image:

def download_photo(self, img_url, filename):
    file_path = "%s%s" % (DOWNLOADED_IMAGE_PATH, filename)
    downloaded_image = file(file_path, "wb")

    image_on_web = urllib.urlopen(img_url)
    while True:
        buf = image_on_web.read(65536)
        if len(buf) == 0:
            break
        downloaded_image.write(buf)
    downloaded_image.close()
    image_on_web.close()

    return file_path