def get_excerpt(html, try_meta=False, max_chars=10000):
"""Extract excerpt from this HTML by finding largest text block
try_meta indicates whether to try extracting from meta description tag
max_chars is the maximum number of characters for the excerpt
"""
# try extracting meta description tag
excerpt = ''
if try_meta:
excerpt = xpath.get(html, '/html/head/meta[@name="description"]/@content')
if not excerpt:
# remove these tags and then find biggest text block
bad_tags = 'hr', 'br', 'script', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'footer'
content = common.remove_tags(xpath.get(html, '/html/body', remove=bad_tags))
if content:
excerpt = max((len(p.strip()), p) for p in content.splitlines())[1]
return common.unescape(excerpt.strip())[:max_chars]
def get_excerpt(html, try_meta=False, max_chars=255):
"""Extract excerpt from this HTML by finding largest text block
try_meta indicates whether to try extracting from meta description tag
max_chars is the maximum number of characters for the excerpt
"""
# try extracting meta description tag
excerpt = ''
if try_meta:
excerpt = xpath.get(html, '/html/head/meta[@name="description"]/@content')
if not excerpt:
# remove these tags and then find biggest text block
bad_tags = 'hr', 'br', 'script', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6'
content = common.remove_tags(xpath.get(html, '/html/body', remove=bad_tags))
if content:
excerpt = max((len(p.strip()), p) for p in content.splitlines())[1]
return common.unescape(excerpt.strip())[:max_chars]