import os, sys, datetime, re
import subprocess
from lxml import etree

def get_pagerank(url):
    parser = etree.HTMLParser()
    tree = etree.parse(url, parser)

    raw = tree.xpath("//li[@id=\"SalesRank\"]/text()")[1]
    rank_commas = re.search(".*\#([\d,]*).*", raw)
    rank = rank_commas.group(1).replace(",", "")
    return rank

os.chdir("/home/mbeckler/mbeckler.org/dog_physics/")

url_book = "http://www.amazon.com/How-Teach-Physics-Your-Dog/dp/1416572287"
url_kindle = "http://www.amazon.com/How-Teach-Physics-Your-ebook/dp/B002ZJCQT2"
url_relativity = "http://www.amazon.com/How-Teach-Relativity-Your-Dog/dp/0465023312"
url_relativity_kindle = "http://www.amazon.com/How-Teach-Relativity-Your-ebook/dp/B0072HV11G/"

#pagerank_book = None
#pagerank_kindle = None
# TODO put this in a while loop with try blocks on the get_pagerank() calls
# or maybe while/try blocks on each page?
# or maybe if not pagerank_book:
#while not pagerank_book and not pagerank_kindle:
pagerank_book = get_pagerank(url_book)
pagerank_kindle = get_pagerank(url_kindle)
pagerank_relativity = get_pagerank(url_relativity)
pagerank_relativity_kindle = get_pagerank(url_relativity_kindle)

datetimestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M")

fid = open("dog_physics_data.txt", "a")
fid.write("%s\t%s\t%s\t%s\t%s\n" % (datetimestamp, pagerank_book, pagerank_kindle, pagerank_relativity, pagerank_relativity_kindle))
fid.close()

# write the current values to a file that is included in the webpage
fid = open("dog_physics_data_current_book.txt", "w")
fid.write("%s" % pagerank_book)
fid.close()

fid = open("dog_physics_data_current_kindle.txt", "w")
fid.write("%s" % pagerank_kindle)
fid.close()

fid = open("dog_physics_data_current_relativity.txt", "w")
fid.write("%s" % pagerank_relativity)
fid.close()

fid = open("dog_physics_data_current_relativity_kindle.txt", "w")
fid.write("%s" % pagerank_relativity_kindle)
fid.close()

subprocess.call(["gnuplot", "dog_physics.gnuplot"])
subprocess.call(["gnuplot", "dog_relativity.gnuplot"])