CODEWITHSUNDEEP
pythonimagepython-3.xbeautifulsoup
Eric
Eric

Reputation: 839

How to use python download all the image including gif file

I use this code to download jpg file without any problem. But as you can see the following page source include a lot of image with path blank.gif. 

<a href="/en/chowchow-puppy-sleeping-dogs-pet-448311/"><img src="/static/img/blank.gif"

My question: Is it possible to add a detect function when it is blank.gif then auto download image file with 640*426 from "https://pixabay.com/en/chowchow-puppy-sleeping-dogs-pet-448311/" and how to archive ??

import random
import requests
from bs4 import BeautifulSoup

# got from http://stackoverflow.com/a/16696317
def download_file(url):
    local_filename = url.split('/')[-1]
    print("Downloading {} ---> {}".format(url, local_filename))
    # NOTE the stream=True parameter
    r = requests.get(url, stream=True)
    with open(local_filename, 'wb') as f:
        for chunk in r.iter_content(chunk_size=1024): 
            if chunk: # filter out keep-alive new chunks
                f.write(chunk)
    return local_filename

def Download_Image_from_Web(url):
    source_code = requests.get(url)
    plain_text = source_code.text
    soup = BeautifulSoup(plain_text, "html.parser")
    for link in soup.findAll('img'):
        image_links = link.get('src')
        if not image_links.startswith('http'):
            image_links = url + '/' + image_links
        download_file(image_links)

Download_Image_from_Web("https://pixabay.com/en/photos/?q=sleeping+puppy&hp=&image_type=&cat=&min_width=&min_height=")

Upvotes: 0

Views: 1329

Answers (1)

Roman Mindlin
Roman Mindlin

Reputation: 842

Updated version. Read comments for additional info.

import random
import requests
from bs4 import BeautifulSoup

# got from http://stackoverflow.com/a/16696317
def download_file(url):
    local_filename = url.split('/')[-1]
    print("Downloading {} ---> {}".format(url, local_filename))
    # NOTE the stream=True parameter
    r = requests.get(url, stream=True)
    with open(local_filename, 'wb') as f:
        for chunk in r.iter_content(chunk_size=1024):
            if chunk: # filter out keep-alive new chunks
                f.write(chunk)
    return local_filename

def Download_Image_from_Web(url):
    source_code = requests.get(url)
    plain_text = source_code.text
    soup = BeautifulSoup(plain_text, "html.parser")
    for link in soup.findAll('img'):
        image_links = link.get('src')
        if image_links.endswith('blank.gif'):
            image_links = link.get('data-lazy')
        if not image_links.startswith('http'):
            image_links = url + '/' + image_links
        download_file(image_links)

Download_Image_from_Web("https://pixabay.com/en/photos/?q=sleeping+puppy&hp=&image_type=&cat=&min_width=&min_height=")

Upvotes: 2

Related Questions