Tags-from-joyreactor.py

gistfile1.txt

from bs4 import BeautifulSoup as bs
from urllib2 import urlopen
from time import sleep

soup = bs(html,"lxml")
gen_urls = [x for x in range(80000, 80002)]

base_url = 'http://joyreactor.cc/new/'

enlist_urls =[base_url+str(item) for item in gen_urls]

DATA = {}

for current_page in enlist_urls:
	html = urlopen(current_page).read()

	

	for item in soup.findAll('h2',attrs={'class':'taglist'}):
		DATA[current_page] = item.text
		sleep(1)

if __name__ == '__main__':
	pairs = DATA.items()

	#pairs.sort(key=lambda x: x[1], reverse=True)
	for p in pairs:
		print p[0], p[1]