def strip_article(url):
htmlcode = urllib2.urlopen(url).read().decode('utf-8')
article = readability.Readability(htmlcode, url)
#data = urllib2.urlopen(url).read()
print article.content
def get_html(url):
print url
page = s.get(url, headers=headers, verify=False).text
page = page.encode("utf-8")
html = readability.Readability(page, url)
filename = "./coolshell/" + html.getArticleTitle().encode(
"utf-8") + ".html"
print filename
#filename = filename.decode("utf-8").encode("gbk","ignore")
content = html.grabArticle().encode("utf-8")
content = content.decode("utf-8").encode("gbk", "ignore")
save_file(filename, content)
def LIXscore(text):
rd = readability.Readability(text)
score = rd.LIX()
return float(score)
def ARIscore(text):
rd = readability.Readability(text)
score = rd.ARI()
return float(score)
def computeRead(text):
rd = readability.Readability(text)
score = rd.FleschKincaidGradeLevel()
return int(score)