getatmag.py

#!/usr/bin/python

# Depends on wget, swftools, and ImageMagick.

import os
import sys
import re
import requests
from bs4 import BeautifulSoup

#dims = '-X 841 -Y 1189'
dims = '-X 2480 -Y 3508'

try:
    baseURL = sys.argv[1]
except IndexError:
    print 'Usage: getatmag.py <URL>'
    sys.exit(1)

xmlMeta = requests.get(baseURL + '/megazine/megazine.php')

soup = BeautifulSoup(str(xmlMeta.text), 'xml')

toProcess = []

for page in soup.find_all('page'):
    for img in page.find_all('img'):
        if re.match('page(s|images)\/\d+\.(swf|jpg)$', img['src']):
            toProcess.append(re.sub('\?time=\d+', '', img['src']))

print 'Need to get and process ' + str(len(toProcess)) + ' pages'

for page in toProcess:
    os.system('wget -U Mozilla ' + baseURL + '/megazine/' + page)

toBind = []

for page in toProcess:
    if re.search('swf$', page):
        swfName = page.lstrip('pages/')
        pngName = swfName.rstrip('.swf') + '.png'
        print 'processing ' + page + ' ...'
        os.system('swfrender ' + swfName + ' ' + dims + ' -o ' + pngName)
        toBind.append(pngName)
    else:
        toBind.append(page.lstrip('pageimages/'))

print 'binding...'
os.system('convert -adjoin ' + ' '.join(toBind) + ' -page A4 out.pdf')