def parse_article(fn):
parser = etree.HTMLParser()
tree = etree.parse(open(fn), parser)
e = tree.getroot()
for i in e.xpath('.//img'):
try:
print layout.norm_ext_img_url(i.get('src'))
except UnicodeEncodeError:
sys.stderr.write('UnicodeError %s %r \n' %(fn, i.get('src')))
def parse_css(css, cssimagedir):
urls = [u for u in re.findall('url\((.*?)\)', css) if not u.startswith('data:')] + extra
for u in urls:
url = layout.norm_ext_img_url(u)
lurl = layout.ext_img_url2local_cssimg_url(url)
fn = layout.ext_img_url2fn(url, keep_ext=False)
ofn = os.path.join(cssimagedir, fn)
#print url, lurl, fn, ofn
try:
open(ofn, 'w').write( urllib2.urlopen(url).read() )
css = css.replace(u, lurl)
except urllib2.URLError, e:
print 'ERR', e, url
