bookextractor.py

import io      # Operating system I/O
import re      # Regular expression module
import pycurl  # Curl module

def log(text, end='\n'):
    print(text, end=end, flush=True)

c = pycurl.Curl()
buffer = io.BytesIO()

log('* Retrieving URL data... ', end='')

# Retrieving original URL
c.setopt(c.URL, 'https://blogs.msdn.microsoft.com/mssmallbiz/2017/07/11/largest-free-microsoft-ebook-giveaway-im-giving-away-millions-of-free-microsoft-ebooks-again-including-windows-10-office-365-office-2016-power-bi-azure-windows-8-1-office-2013-sharepo/')
c.setopt(c.WRITEDATA, buffer)
c.perform()

body = buffer.getvalue()

log('done.')
log('* Parsing data... ', end='')

# We use a regular expression to easily extract titles and URLs
rexp = re.compile('<td valign="top" width="673"><font size="2" face="Arial">(.{1,120})</font></td>.<td width="77"><a href="(http://ligman.me/.{7})" target="_blank"><font size="2" face="Arial">PDF</font></a><font size="2" face="Arial">', re.DOTALL)
result = rexp.findall(body.decode('utf-8', errors='ignore'))

log('done.')
log('* Extracting documents... ', end='')

try:
    counter = 1
    for doc in result:
        log('.', end='')
        counter = counter + 1

        path = doc[0] + '.pdf'
        output = open(path, 'wb')

        c.setopt(c.URL, doc[1])
        c.setopt(c.WRITEDATA, buffer)
        c.setopt(c.FOLLOWLOCATION, True)
        c.perform()

        result = buffer.getvalue()
        output.write(result)
        output.close()
except KeyboardInterrupt:
    log(' ABORTED!', end='')
except Exception as e:
    log('\n')
    log(e)

c.close()
log('')
log('Process finished (extracted ' + str(counter - 1) + ' document/s).')