springer.py

springer.py

import sys
import csv
import requests
from pathlib import Path

if __name__ == '__main__':
    with open(sys.argv[1]) as csv_file:
        csv = csv.DictReader(csv_file, delimiter=",", quoting=csv.QUOTE_ALL)

        next(csv)

        for row in csv:
            print(f'Processing {row["Item Title"]} by {row["Authors"]}')

            try:
                print("Downloading PDF")

                url = f'https://link.springer.com/content/pdf/{row["Item DOI"]}.pdf'
                content = requests.get(url)

                if len(content.content) < 500:
                    raise Exception("Not a PDF")
                open(f'{Path(sys.argv[1]).parent}/{row["Item Title"]} - {row["Authors"]}.pdf', 'wb').write(content.content)
            except:
                print(f'Failed to download PDF for {row["Item Title"]} by {row["Authors"]}')

            try:
                print("Downloading EPUB")

                url = f'https://link.springer.com/download/epub/{row["Item DOI"]}.epub'
                content = requests.get(url)

                if len(content.content) < 500:
                    raise Exception("Not a EPUB")
                open(f'{Path(sys.argv[1]).parent}/{row["Item Title"]} - {row["Authors"]}.epub', 'wb').write(content.content)
            except:
                print(f'Failed to download EPUB for {row["Item Title"]} by {row["Authors"]}')

Improved version: https://gist.github.com/CrazyCoder/2e2788c1542b93869c8b31948cde198a

• Can continue download (skips existing files)
• Removes special characters from the file names so that the file path is always valid (paths with : and other special chars will fail on Windows)
• Refactored code a bit to remove duplication for PDF/EPUB
• Proper file name encoding

👍