import requests
import bs4
import os

def get_xkcd(comicid):
    r = requests.get('http://www.xkcd.org/{0}/'.format(comicid))
    if r.status_code == 200:
        soup = bs4.BeautifulSoup(r.content)
        img = soup.find("div", {'id':"comic"}).find("img")
        return img['title'], img['src']

def get_explanation(comic_id):
    """dowload explanation from explainxkcd

    ignore transcript for now"""
    r = requests.get('http://www.explainxkcd.com/wiki/index.php/{0}'.format(comic_id))
    soup = bs4.BeautifulSoup(r.content)
    firstp = soup.find('div', {'id':"content"}).find('p')
    allp = [firstp]+firstp.find_next_siblings('p')
    return "".join([t.text for t in allp])

def main():
    # last = sorted([int(f.split("_")[1]) for f in os.listdir("explanations")],
    #               reverse=True)[0]
    # print(last)
    for cid in range(1, 1601):
        with open("explanations/comic_{0}".format(cid), "w") as fh:
            fh.write(get_explanation(cid).encode("utf-8"))

if __name__=="__main__":
    main()