def bs_preprocess(html):
"""remove distracting whitespaces and newline characters"""
pat = re.compile('(^[\s]+)|([\s]+$)', re.MULTILINE)
html = re.sub(pat, '', html) # remove leading and trailing whitespaces
html = re.sub('\n', ' ', html) # convert newlines to spaces
# this preserves newline delimiters
html = re.sub('[\s]+<', '<', html) # remove whitespaces before opening tags
html = re.sub('>[\s]+', '>', html) # remove whitespaces after closing tags
return html
BeautifulSoup处理空行
猜你喜欢
转载自my.oschina.net/u/3238650/blog/2253390
今日推荐
周排行