(Not Done Yet) Merge all pdf files in QC course

PdfMerger.py

# Find links to pdf files in HTML with BeautifulSoup
import os
import urllib
from bs4 import BeautifulSoup
from PyPDF2 import PdfFileMerger
import numpy as np 
def download_file(download_url, filename):
    response = urllib.request.urlopen(download_url)    
    file = open(filename, 'wb')
    file.write(response.read())
    file.close()

def reset_eof_of_pdf_return_stream(pdf_stream_in:list):
    # find the line position of the EOF
    for i, x in enumerate(pdf_stream_in[::-1]):
        if b'%%EOF' in x:
            actual_line = len(pdf_stream_in)-i
            print(f'EOF found at line position {-i} = actual {actual_line}, with value {x}')
            break
    # return the list up to that point
    return pdf_stream_in[:actual_line]

my_url = 'https://homepages.cwi.nl/~fehr/QC2020/'
html=urllib.request.urlopen(my_url).read()
content = BeautifulSoup(html)
current_link = ''

pdfs = []
for link in content.find_all('a'):
    current_link = link.get('href')
    if current_link.endswith('pdf') and "/" not in current_link: 
        print('link of pdf: ' + current_link)
        pdfs.append(current_link)

np.savetxt("pdfs.txt",pdfs,fmt="%s")

# for pdf in pdfs: 
#     download_file(my_url, pdf)

# for pdf in pdfs:
#     # opens the file for reading
#     with open('pdf_files/'+pdf, 'rb') as p:
#         txt = (p.readlines())

#     # get the new list terminating correctly
#     txt_right_eof = reset_eof_of_pdf_return_stream(txt)

#     # write to new pdf
#     with open(pdf.split('.')[0]+"_fixed.pdf"), 'wb' as f:
#         f.writelines(txt_right_eof)

# merger = PdfFileMerger()

# for pdf in pdfs:
#     merger.append(pdf)

# merger.write("qc_book_all.pdf")
# merger.close()


# #Create and instance of PdfFileMerger() class
# merger = PdfFileMerger()
# #Create a list with PDF file names
# path_to_files = r'pdf_files/'
# #Get the file names in the directory
# for root, dirs, pdfs in os.walk(path_to_files):
#     #Iterate over the list of file names
#     for file_name in pdfs:
#         #Append PDF files
#         merger.append(path_to_files + file_name)
# #Write out the merged PDF
# merger.write("merged_all_pages.pdf")
# merger.close()


# import unicodedata
# import numpy as np 
# import re
# full = np.loadtxt("pdfs.txt")
# half = np.copy(full)
# for txt in half:
#     txt = unicodedata.normalize('NFKC', res = (re.sub('.', lambda x: r'\u % 04X' % ord(x.group()), txt))).encode('ascii', 'ignore')
# np.savetxt("pdfs_half.txt",half)