Arachnida/Spider.py

156 lines
4.6 KiB
Python

import os
import argparse
import requests
import re
from urllib.parse import urlparse
from PIL import Image
from PIL.ExifTags import TAGS
def same_domain(url1, url2):
"""
Return True if url1 and url2 have the same domain name.
Args:
url1 (str): The first URL.
url2 (str): The second URL.
Returns:
bool: True if both URLs have the same domain, False otherwise.
"""
domain1 = urlparse(url1).netloc
domain2 = urlparse(url2).netloc
return domain1 == domain2
def crawl(url, depth, imgs = set()):
"""
Crawl the given URL and extract links and images.
If depth is greater than 0, continue crawling links found on the page.
If depth is 0, only extract images.
Args:
url (str): The URL to crawl.
depth (int): The depth of crawling.
imgs (set): A set to store found image URLs.
Returns:
set: A set of found image URLs.
"""
print(f"\033[92mFetching links from {url} at depth {depth}\033[0m")
try:
response = requests.get(url)
response.raise_for_status()
links = re.findall(r'<a[^>]+href="([^"]+)"', response.text)
for link in links:
if link.startswith(('#', 'mailto:', 'javascript:', 'tel:')):
continue
if not link.startswith('http'):
link = requests.compat.urljoin(url, link)
if not same_domain(url, link):
continue
crawl(link, depth - 1, imgs) if depth > 0 else None
for img in extract_image_sources(url):
if img not in imgs:
print(f"\033[94mFound image: {img}\033[0m")
imgs.add(img)
imgs.update(extract_image_sources(url))
return imgs
except requests.RequestException as e:
print(f"Error fetching {url}: {e}")
return []
def extract_image_sources(url):
"""
Fetch image links from the given URL.
Args:
url (str): The URL to fetch images from.
Returns:
list: A list of image URLs found on the page.
"""
try:
response = requests.get(url)
response.raise_for_status() # Raise an error for bad responses
img_sources = re.findall(r'src="([^"]+(?:jpg|jpeg|gif|png|bmp))"', response.text, re.IGNORECASE)
img_sources = [requests.compat.urljoin(url, src) for src in img_sources]
return img_sources
except requests.RequestException as e:
print(f"Error fetching {url}: {e}")
return []
def download_images(imgs, directory):
"""
Download images to the specified directory.
Args:
imgs (set): A set of image URLs to download.
directory (str): The directory where images will be saved.
Returns:
set: A set of file paths of downloaded images.
"""
downloaded = set()
for img in imgs:
try:
response = requests.get(img)
response.raise_for_status()
filename = get_filename_from_url(img)
filepath = f"{directory}/{filename}"
with open(filepath, 'wb') as file:
file.write(response.content)
downloaded.add(filepath)
except requests.RequestException as e:
print(f"Error downloading {img}: {e}")
return downloaded
def get_filename_from_url(url):
"""
Remove http:// or https:// from the URL and replace / with _ to create a valid filename.
"""
parsed_url = urlparse(url)
filename = parsed_url.netloc + parsed_url.path
filename = filename.replace('/', '_')
return filename if filename else url
def main():
parser = argparse.ArgumentParser(description="Spider Web Crawler")
parser.add_argument("url", type=str, help="The URL to start crawling from")
parser.add_argument("-r", help="Spider the URL")
parser.add_argument("-l", type=int, default=5, help="Depth of crawling")
parser.add_argument("-p", default="./data", help="Output file to save")
args = parser.parse_args()
print(args)
imgs = crawl(args.url, args.l)
print(f"\033[92mFound {len(imgs)} images\033[0m")
if args.p:
if not os.path.exists(args.p):
os.makedirs(args.p)
downloaded = download_images(imgs, args.p)
print(f"\033[92mDownloaded {len(downloaded)} images to {args.p}\033[0m")
# for img in downloaded:
# exif_data = get_exif_data(img)
# if exif_data:
# print(f"\033[93mExif data for {img}:\033[0m")
# for tag, value in exif_data.items():
# print(f" {tag}: {value}")
# return 0
if __name__ == "__main__":
main()