#ICanHazPDF

icanhazpdf.py

#! /usr/bin/env python

import re
import requests
import tempfile
import urllib.request
import random
import sys
import os

# ASCII colors
class acol:
    END = '\033[0m'
    BOLD = '\033[1m'
    RED = '\033[91m'
    GREEN = '\033[92m'
    YELLOW = '\033[93m'
    BLUE = '\033[94m'
    MAGENTA = '\033[95m'
    CYAN = '\033[96m'

def get_scihub_pdf(doi):
    _root = random.choice(["sci-hub.io", "sci-hub.cc"])
    _doi_url = "http://" + _root +  "/" + doi
    print("\t" + acol.MAGENTA + "SciHub:\t" + acol.END + _doi_url + acol.END) 
    getpdf = re.compile(u'<iframe src = "(.+\.pdf)" id = "pdf">')
    try :
        _url = _doi_url
        _redirect_url = requests.get(_url).url
        if not _root in _redirect_url :
            print("\t" + acol.MAGENTA + "Goto:\t" + acol.END + _redirect_url + acol.END) 
            raise ValueError("Redirected")
        _url = _redirect_url
        _url_html_content = requests.get(_url).text
        search_result = re.search(getpdf, _url_html_content)
        if not search_result == None:
            print("\t" + acol.BLUE + "PDF at:\t" + acol.END + search_result.group(1) + acol.END) 
            return search_result.group(1)
        else:
            raise ValueError("Unable to read PDF")
    except :
        raise ValueError("No PDF known to SciHub")

"""
Download the file itself
"""
def download_file(url, fname):
    # Look ma, I'm a browser! Fuck you, publishers.
    header = {'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.9; rv:32.0) Gecko/20100101 Firefox/32.0',}
    r = requests.get(url, stream=True, headers=header)
    with open(fname, 'wb') as f:
        for chunk in r.iter_content(chunk_size=1024): 
            if chunk:
                f.write(chunk)
    return fname

if __name__ == "__main__":
    if len(sys.argv) != 2:
        raise ValueError("usage: ./icanhazpdf.py doi")
    else:
        doi = sys.argv[1]
        _url = None
        try :
            _url = get_scihub_pdf(doi)
        except :
            raise ValueError("Something went wrong.")
        if not _url == None:
            print("\t" + acol.YELLOW + "PDF URL:\t" + acol.END + _url) 
            _fname = '.'.join(doi.split('/'))+".pdf"
            download_file(_url, _fname)
            # Sci Hub might ask captcha
            # This next part is flaky as shit
            try :
                open(_fname).read()
                if not 'captcha' in open(_fname).read():
                    print("\t" + acol.BOLD + acol.GREEN + "#ICanHazPDF! \n") 
            except :
                # If the file can't be read this way, it's likely to be a PDF
                os.remove(_fname)
                print("\t" + acol.BOLD + acol.RED + "Captcha'ed, try again later" + acol.END + "\n")