main.py

import re
import codecs
import requests
import glob

AMZN_RE = re.compile(u"https?://amzn.to/([0-9A-Za-z]+)")
ISBN1 = re.compile(u"https://www.amazon.com/(?:[A-Za-z\-]+)/dp/(\d{10})/")
ISBN2 = re.compile(u"https://www.amazon.com/gp/product/(\d{10})/")

def remove_amazon(filename):
    print("Translating %s", filename)
    f = codecs.open(filename, encoding='utf-8').read()
    for cap in re.finditer(AMZN_RE, f):
        url = cap.group(0)
        redirected_to = requests.head(url, allow_redirects=True).url
        capture = ISBN1.match(redirected_to) or ISBN2.match(redirected_to)
        if capture == None:
            print("Could not capture ISBN from %s", redirected_to)
            continue
        isbn = capture.group(1)
        worldcat_permalink = requests.head("http://www.worldcat.org/isbn/%s" % isbn, allow_redirects=True).url
        print(url, worldcat_permalink)
        f = f.replace(
            url,
            worldcat_permalink
        )
    codecs.open(filename, 'w', encoding='utf-8').write(f)


for file in glob.glob('../tmcw.github.com/_posts/*.md'):
    remove_amazon(file)