lxml または mechanizer を使用して美しいスープをすべて切り取ることで、このスクリプトの速度を向上させる方法はありますか?
パイソン:
import lxml.html as html
import urllib
import urlparse
from BeautifulSoup import BeautifulSoup
import re
import os, sys
print ("downloading and parsing bibles...")
root = html.parse(open('all.html'))
for link in root.findall('//a'):
url = link.get('href')
name = urlparse.urlparse(url).path.split('/')[-1]
dirname = urlparse.urlparse(url).path.split('.')[-1]
f = urllib.urlopen(url)
s = f.read()
if (os.path.isdir(dirname) == 0):
os.mkdir(dirname)
soup = BeautifulSoup(s)
articleTag = soup.html.body.article
converted = str(articleTag)
full_path = os.path.join(dirname, name)
open(full_path, 'w').write(converted)
print(name)
print("downloads complete!")
all.html
<a href="http://www.youversion.com/bible/gen.1.nmv-fas">http://www.youversion.com/bible/gen.1.nmv-fas</a>
<a href="http://www.youversion.com/bible/gen.2.nmv-fas">http://www.youversion.com/bible/gen.2.nmv-fas</a>
<a href="http://www.youversion.com/bible/gen.3.nmv-fas">http://www.youversion.com/bible/gen.3.nmv-fas</a>