|
| 1 | +import argparse |
| 2 | +from bs4 import BeautifulSoup |
| 3 | +import requests |
| 4 | +from tqdm import tqdm |
| 5 | +from urllib.parse import urlparse |
| 6 | + |
| 7 | + |
| 8 | +class ImageDownloader: |
| 9 | + """ |
| 10 | + This class is used to download all the images on the webpage |
| 11 | + Takes only one param |
| 12 | + |
| 13 | + :param -- Valid URL for the website |
| 14 | + """ |
| 15 | + |
| 16 | + def __init__(self, scrap_url): |
| 17 | + self.url = scrap_url |
| 18 | + self.image_urls = list() |
| 19 | + self.get_images() |
| 20 | + self.download() |
| 21 | + |
| 22 | + def download(self): |
| 23 | + |
| 24 | + if self.image_urls: |
| 25 | + |
| 26 | + for url in self.image_urls: |
| 27 | + |
| 28 | + # Download the body of response by chunk |
| 29 | + response = requests.get(url, stream=True) |
| 30 | + |
| 31 | + # Get the total file size |
| 32 | + file_size = int(response.headers.get("Content-Length", 0)) |
| 33 | + |
| 34 | + # Get the file name |
| 35 | + filename = url.split("/")[-1] |
| 36 | + |
| 37 | + # Progress bar |
| 38 | + progress = tqdm(response.iter_content(1024), f"Downloading {filename}", total=file_size, unit="B", |
| 39 | + unit_scale=True, |
| 40 | + unit_divisor=1024) |
| 41 | + |
| 42 | + # Write to file |
| 43 | + with open(filename, "wb") as f: |
| 44 | + |
| 45 | + for data in progress: |
| 46 | + # Write data to the file |
| 47 | + f.write(data) |
| 48 | + |
| 49 | + # Update the progress bar |
| 50 | + progress.update(len(data)) |
| 51 | + |
| 52 | + def get_images(self): |
| 53 | + |
| 54 | + # try, except block |
| 55 | + try: |
| 56 | + |
| 57 | + # Get the page, with the timeout set to 5 |
| 58 | + resp = requests.get(self.url, timeout=5) |
| 59 | + |
| 60 | + # Check the response code, 200 for valid |
| 61 | + if resp.status_code == 200: |
| 62 | + |
| 63 | + # Create the soup |
| 64 | + soup = BeautifulSoup(resp.content, "html.parser") |
| 65 | + |
| 66 | + # Find all the img tags from the page |
| 67 | + links = soup.find_all('img') |
| 68 | + |
| 69 | + # Extract the src of the images |
| 70 | + data = [y.attrs['src'] for y in links if y.name == 'img'] |
| 71 | + |
| 72 | + # Get the original URL domain |
| 73 | + url_parsing = urlparse(self.url) |
| 74 | + domain = url_parsing.netloc |
| 75 | + |
| 76 | + for img_url in data: |
| 77 | + # Parse the image url |
| 78 | + img_url_parsing = urlparse(img_url) |
| 79 | + img_path = img_url_parsing.path |
| 80 | + |
| 81 | + # Check if the image url contains the domain and use it |
| 82 | + if img_url_parsing.netloc != '': |
| 83 | + |
| 84 | + # Create the complete URL |
| 85 | + comp_url = f"https://{img_url_parsing.netloc}{img_path}" |
| 86 | + |
| 87 | + # Append it into the list |
| 88 | + self.image_urls.append(comp_url) |
| 89 | + |
| 90 | + # Else use the default domain if the site |
| 91 | + else: |
| 92 | + |
| 93 | + # Create the complete URL |
| 94 | + comp_url = f"https://{domain}{img_path}" |
| 95 | + |
| 96 | + # Append it into the list |
| 97 | + self.image_urls.append(comp_url) |
| 98 | + |
| 99 | + # Not a valid response code is given by the site |
| 100 | + else: |
| 101 | + print(f"Status Code: {resp.status_code}, For URL: {self.url}") |
| 102 | + |
| 103 | + # Tries to connect to the site |
| 104 | + except requests.exceptions.ConnectionError: |
| 105 | + print(f"No Response From URL: {self.url}") |
| 106 | + |
| 107 | + # Generic exception |
| 108 | + except Exception as err: |
| 109 | + print(f"Exception Raised: {err}") |
| 110 | + |
| 111 | + |
| 112 | +def main(): |
| 113 | + parser = argparse.ArgumentParser(description='Download Images From Webpage') |
| 114 | + |
| 115 | + # Argument is to input the url to download images from |
| 116 | + parser.add_argument('-u', dest='url', type=str, help='URL to extract links from', required=True) |
| 117 | + |
| 118 | + args = parser.parse_args() |
| 119 | + |
| 120 | + if args.url: |
| 121 | + |
| 122 | + url = args.url |
| 123 | + |
| 124 | + # Check if the url starts with wither http or https |
| 125 | + if not url.startswith("http") and not url.startswith("https"): |
| 126 | + # Add the https in front of the url |
| 127 | + url = "https://" + url |
| 128 | + |
| 129 | + # Call to the function |
| 130 | + ImageDownloader(url) |
| 131 | + |
| 132 | + |
| 133 | +if __name__ == '__main__': |
| 134 | + main() |
0 commit comments