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

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 bs4 import BeautifulSoup as bs
from urllib.request import (
    urlopen, urlparse, urlunparse, 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(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)
        if image["src"].lower().startswith("http"):
            urlretrieve(image["src"], outpath)
        else:
            urlretrieve(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 2

Ryan's solution is good, but fails if the image source URLs are absolute URLs or anything that doesn't give a good result when simply concatenated to the main page URL. urljoin recognizes absolute vs. relative URLs, so replace the loop in the middle with:

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

Answer 3

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 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

Answer 5

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

Answer 6

If the request need an authorization refer to this one:

r_img = requests.get(img_url, auth=(username, password)) 
f = open('000000.jpg','wb') 
f.write(r_img.content) 
f.close()