Created
February 10, 2012 22:18
-
-
Save djipko/1793535 to your computer and use it in GitHub Desktop.
Emebdly solution #2
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from HTMLParser import HTMLParser | |
from operator import add | |
from math import sqrt, pow | |
import requests | |
class EmbedlyParser(HTMLParser): | |
depth = 1 | |
ps = [] | |
article = False | |
def handle_starttag(self, tag, atrs): | |
if tag == 'article': | |
self.article = True | |
if self.article: | |
if tag != 'p': | |
self.depth += 1 | |
else: | |
self.ps.append(self.depth) | |
def handle_endtag(self, tag): | |
if tag == 'article': | |
self.article = False | |
if self.article and tag != 'p': | |
self.depth -= 1 | |
if __name__ == "__main__": | |
r = requests.get("http://apply.embed.ly/static/data/2.html") | |
parser = EmbedlyParser() | |
parser.feed(r.content) | |
mean = float(reduce(add, parser.ps))/float(len(parser.ps)) | |
dif_sq = [pow((p - mean),2) for p in parser.ps] | |
dif_sq_mean = float(reduce(add, dif_sq))/float(len(dif_sq)) | |
dev = sqrt(dif_sq_mean) | |
print "Deviation is %f" %dev |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment