Last active
May 11, 2024 04:01
-
-
Save drelatgithub/6f2888c2109f29206786105f2d00db5e to your computer and use it in GitHub Desktop.
Docin document downloader
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
############################################################################### | |
# | |
# Docin document downloader | |
# | |
# Valid as of 2022-12-13 | |
# | |
############################################################################### | |
import argparse | |
import os | |
from types import SimpleNamespace | |
import urllib.request | |
conf = SimpleNamespace( | |
docin_pid = 0, | |
output_dir = "" | |
) | |
def download_image(pid): | |
i = 0 | |
while True: | |
i += 1 | |
try: | |
urllib.request.urlretrieve( | |
"http://211.147.220.164/index.jsp?file={}&pageno={}".format(pid, i), | |
os.path.join(conf.output_dir, "{}.png".format(i)) | |
) | |
except urllib.error.HTTPError: | |
break | |
else: | |
print("Page", i, "saved.") | |
if __name__ == "__main__": | |
# Parse the arguments | |
parser = argparse.ArgumentParser() | |
parser.add_argument("docin_pid", type=str, help="The number after \"p-\" in docin url") | |
parser.add_argument("output_dir", type=str, help="The output directory") | |
args = parser.parse_args() | |
conf.docin_pid = args.docin_pid | |
conf.output_dir = args.output_dir | |
# Do the work | |
download_image(conf.docin_pid) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
import os
import urllib.request
from PIL import Image
def download_images(pid, output_dir):
images = []
i = 1
while True:
try:
file_name = f"{i}.png"
file_path = os.path.join(output_dir, file_name)
url = f"http://211.147.220.164/index.jsp?file={pid}&pageno={i}"
urllib.request.urlretrieve(url, file_path)
print(f"Page {i} downloaded.")
images.append(file_path)
i += 1
except urllib.error.HTTPError:
print("Download completed or no more pages to fetch.")
break
return images
def images_to_pdf(images, output_dir):
pdf_path = os.path.join(output_dir, "document.pdf")
image_list = [Image.open(image).convert('RGB') for image in images]
if image_list:
image_list[0].save(pdf_path, save_all=True, append_images=image_list[1:])
print(f"PDF saved at {pdf_path}")
if name == "main":
pid = 2064621039 # Example PID, replace with the actual PID you want to use
output_dir = "/content/drive/MyDrive/Data" # Change to your desired output directory
Here is new code