Python+PyQueryでスクレイピング ref: http://qiita.com/knoguchi/items/cd51a00de026ef92080a

file1.html

<ul>
  <li x="123" class="red"> item 1 </li>
  <li x="123" class="red"> item 2 </li>
  <li x="123" class="red"> item 3 </li>
</ul>

file1.txt

set(['http://i.yimg.jp/images/sicons/box16.gif',
     'http://k.yimg.jp/images/clear.gif',
     'http://k.yimg.jp/images/common/tv.gif',
     'http://k.yimg.jp/images/icon/photo.gif',
     'http://k.yimg.jp/images/new2.gif',
     'http://k.yimg.jp/images/sicons/ybm161.gif',
     'http://k.yimg.jp/images/top/sp/cgrade/iconMail.gif',
     'http://k.yimg.jp/images/top/sp/cgrade/icon_point.gif',
     'http://k.yimg.jp/images/top/sp/cgrade/info_btn-140325.gif',
     'http://k.yimg.jp/images/top/sp/cgrade/logo7.gif',
     'http://lpt.c.yimg.jp/im_sigg6mIfJALB8FuA5LAzp6.HPA---x120-y120/amd/20150208-00010001-dtohoku-000-view.jpg'])

file3.txt

set(['http://i.yimg.jp/images/sicons/box16.gif',
     'http://k.yimg.jp/images/clear.gif',
     'http://k.yimg.jp/images/common/tv.gif',
     'http://k.yimg.jp/images/icon/photo.gif',
     'http://k.yimg.jp/images/new2.gif',
     'http://k.yimg.jp/images/sicons/ybm161.gif',
     'http://k.yimg.jp/images/top/sp/cgrade/iconMail.gif',
     'http://k.yimg.jp/images/top/sp/cgrade/icon_point.gif',
     'http://k.yimg.jp/images/top/sp/cgrade/info_btn-140325.gif',
     'http://k.yimg.jp/images/top/sp/cgrade/logo7.gif',
     'http://lpt.c.yimg.jp/im_sigg6mIfJALB8FuA5LAzp6.HPA---x120-y120/amd/20150208-00010001-dtohoku-000-view.jpg'])

img_scraper.py

#!/usr/bin/env python
from urlparse import urljoin
from pyquery import PyQuery as pq
from pprint import pprint

url = 'http://www.yahoo.co.jp'

dom = pq(url)
result = set()
for img in dom('img').items():
    img_url = img.attr['src']
    if img_url.startswith('http'):
        result.add(img_url)
    else:
        result.add(urljoin(url, img_url))

pprint(result)

sample.py

from pyquery import PyQuery as pq


html = '''
<ul>
  <li> item 1 </li>
  <li> item 2 </li>
  <li> item 3 </li>
</ul>
'''

dom = pq(html)
dom('li').each(lambda index, node: pq(node).attr(class_='red', x='123'))

print dom