Python: Download papers from ScienceDirect by DOI with requests

Question

I have an excel list of DOIs of papers I'm interested in. Based on this list, I would like to download all the papers.

I tried to do it with request, as recommended in their documentation. But the pdf files I get are damaged. They are just some KB big. I changed the chunk_size several times from None till 1024*1024 and I have read many posts already. Nothing helps.

Please, what are your ideas?

import pandas as pd
import os
import requests


def get_pdf(doi, file_to_save_to):
    url = 'http://api.elsevier.com/content/article/doi:'+doi+'?view=FULL'
    headers = {
        'X-ELS-APIKEY': "keykeykeykeykeykey",
        'Accept': 'application/pdf'
    }
    r = requests.get(url, stream=True, headers=headers)
    if r.status_code == 200:
        for chunk in r.iter_content(chunk_size=1024*1024):
            file_to_save_to.write(chunk)
            return True


doi_list = pd.read_excel('list.xls')
doi_list.columns = ['DOIs']
count = 0
for doi in doi_list['DOIs']:
    doi = doi.replace('DOI:','')
    pdf = doi.replace('/','%')
    if not os.path.exists(f'path/{pdf}.pdf'):
        file = open(f'path/{pdf}.pdf', 'wb') 
        get_pdf(doi, file)
        count += 1
        print(f"Dowloaded: {count} of {len(doi_list['DOIs'])} articles")

Answer 1

I think your problem is the return True in for chunk in r.iter_content. With that line, you'll only ever write one chunk of the PDF of size chunk_size.

You should also open files using with; as is, you'll never close the file handles.

import pandas as pd
import os
import requests


HEADERS = {
    'X-ELS-APIKEY': "keykeykeykeykeykey",
    'Accept': 'application/pdf'
}


def get_pdf(doi, file_to_save_to):
    url = f'http://api.elsevier.com/content/article/doi:{doi}?view=FULL'
    with requests.get(url, stream=True, headers=HEADERS) as r:
        if r.status_code == 200:
            for chunk in r.iter_content(chunk_size=1024*1024):
                file_to_save_to.write(chunk)


doi_list = pd.read_excel('list.xls')
doi_list.columns = ['DOIs']
count = 0
for doi in doi_list['DOIs']:
    doi = doi.replace('DOI:','')
    pdf = doi.replace('/','%')
    if not os.path.exists(f'path/{pdf}.pdf'):
        with open(f'path/{pdf}.pdf', 'wb') as file:
            get_pdf(doi, file)
        count += 1
        print(f"Dowloaded: {count} of {len(doi_list['DOIs'])} articles")