Take a file containing a liste of URL, print average, sum and max file size

check_images_sizes

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import requests
from lxml import html
import sys

def sum_avg_max(images):
	
	total = sum(s for url, s in images)
	average = total / len(images)
	max_s = max(s for url, s in images)
	
	return (total, average, max_s)

def get_page_content(url):
	#r = get_page_content("http://www.frandroid.com/produits-android/smartphone/355381_xiaomi-mi-max-apercu-snapdragon-652")
	r = requests.get(url, timeout=15)
	text = r.text
	
	tree = html.fromstring(r.content)
	srcs = tree.xpath('//div[@class="post-content"]//img/@src')

	results = []

	for image in  srcs:

		if image[0:2] == "//":
			image = "http:"+image
	
		try:
			r2 = requests.head(image, timeout=5)
			#print(r2.headers)
			results.append((image, int(r2.headers["content-length"])) )
		except:
			pass
	
	return results
	
def checkimagesize(file):

	fp = open(file, "r")
	for line in fp:
		
		line = line.strip(' \t\n\r')
		if line[0:3] == "www":
			line = "http://"+line
	
		images = get_page_content(line)
		r = sum_avg_max(images)
		print line + (",%d" % len(images)) + (",%d,%d,%d" % r)

checkimagesize(	sys.argv[1])