Wikipdf

wikipdf.py

import requests
import bs4
import io

ADD_URI = 'http://en.wikipedia.org/w/index.php?title=Special:Book&bookcmd=add_article&arttitle={0}&oldid=0'
BOOK_URI = 'http://en.wikipedia.org/wiki/Special:Book'


def wikify(topic):
    return '+'.join(topic.split(' '))

def main(args):
    print '[ Wikipdf ]'
    print '(C) 2012 Aviral Dasgupta - www.aviraldg.com'
    if len(args) < 2:
        print 'Usage: {0} <path.to.page.list>'.format(args[0])
        return

    with io.open(args[1], 'r') as page_list:
        topics = map(lambda t: t.strip(), page_list.readlines())

    print 'Downloading: ' + ', '.join(topics) + '.'
    print '({0} pages; this may take a while)'.format(len(topics))

    s = requests.session()

    for topic in topics:
        print 'Adding {0}'.format(wikify(topic))
        s.get(ADD_URI.format(wikify(topic)))

    print 'Done.'
    p = s.post(BOOK_URI, {'formatSelect': 'rl', 'bookcmd': 'render'})

    print 'Rendering...'
    print 'Render progress page is at {0}'.format(p.url)
    print 'You can check manually or allow Wikipdf to check and download.'
    opt = raw_input('Open web browser with progress page url? [Y/N]')
    if opt.lower().strip().startswith('y'):
        import webbrowser
        webbrowser.open(p.url)
        return

    t = 1
    while True:
        import time
        time.sleep(t)
        print 'Checking ({0}) ...'.format(t)
        t += 1
        p = s.get(p.url)
        if 'finished' in p.text:
            break

    print 'Rendering done; downloading.'
    soup = bs4.BeautifulSoup(p.content)
    pdfuri = soup.find_all('a')[3]['href']

    content = s.get(pdfuri).content

    with io.open(args[1] + '.pdf', 'wb') as out:
        out.write(content)


if __name__ == '__main__':
    import sys
    main(sys.argv)