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
'''loads pdf file in sys.argv[1], extracts URLs, tries to load each URL''' | |
import urllib | |
import sys | |
import PyPDF2 | |
# credits to stackoverflow.com/questions/27744210 | |
def extract_urls(filename): | |
'''extracts all urls from filename''' | |
PDFFile = open(filename,'rb') |