hackernews.py

import requests
from bs4 import BeautifulSoup
url = "https://news.ycombinator.com/"
upvoted = "upvoted?id=your.user.id&p="
fmt = "hn{}.html"
iframe = """<iframe src="{}" title="description" height="1500" width="800"></iframe>"""
cookies = {
	"user":"your cookie"
}

def getUpvoted(page = 0):
	ru = url + upvoted + str(page)
	r = requests.get(ru, cookies=cookies)
	return r

def parse(res):
	soup = BeautifulSoup(res, 'html.parser')
	trs = soup.find_all('tr')
	
	return trs

def doGet(n=32):
	for i in range(1,n):
		r = getUpvoted(i)
		try:
			print r.text
			open(fmt.format(str(i)), "w").write(r.text.encode('utf-8'))
		except:
			print i,"fail"
		# trs = parse(r.text)
		# print [[t.text,t.find_all('a')] for t in trs]

def doMerge(n=32):
	allget = ""
	for i in range(1,n):
		fname = fmt.format(str(i))
		r = open(fname, "r").read()
		allget += iframe.format(fname)+"<br>"
	
	open("alliframe.html", "w").write(allget)

doMerge(32)