def strip_html(value):
'''
>>> strip_html('a<b>b</b>c')
'abc'
'''
value = util.compact_html(value)
return re.sub('<.+?>', '', value)
def filter(self, value):
'''
>>> f = StripHtmlFilter()
>>> f.filter(None) is None
True
>>> f.filter('a<b>b</b>c')
'abc'
'''
if value is None:
return None
value = util.compact_html(value)
return re.sub('<.+?>', '', value)
def extract_from_url(url, rule, charset=None, fmt='yaml'):
html = util.curl(url, charset=charset)
html = util.compact_html(html)
return extract(html, rule, fmt=fmt)
def extract_from_url(url, rule, fmt='yaml'):
from textminer import util
html = requests.get(url).text
html = util.compact_html(html)
return extract(html, rule, fmt=fmt)
def extract_from_url(url, rule, charset=None, fmt='yaml'):
html = util.curl(url, charset=charset)
html = util.compact_html(html)
return extract(html, rule, fmt=fmt)