meibutu.name

meibutu.py

from bs4 import BeautifulSoup as Magic
import urllib



# urllib.urlretrieve("http://www.gunnerkrigg.com//comics/00000001.jpg",
# "1.jpg")



base = "http://www.gojapan.jp/toku3/"
html = urllib.urlopen(base).read()
soup = Magic(html)
divs = soup.find_all(class_="top02")
content = []

def fix_encode (text):
    return unicode(text).encode('utf-8')

def get_image(url, path):
    urllib.urlretrieve(url, path)


for div in divs:
    links = div.find_all('a')
    for link in links:
        content.append( fix_encode(link.get_text()) )


f = open("meibutu", "w")
f.write('\n'.join(content))
print 'done'