OnePieceCrawling

#!//usr/bin/python

import re
import urllib2
import PyRSS2Gen

from bs4 import BeautifulSoup

url = 'https://one-piecex.com.br/'
user_agent = 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:41.0) Gecko/20100101 Firefox/41.0'

req = urllib2.Request(url, headers={'User-Agent' : user_agent})
con = urllib2.urlopen(req)

soup = BeautifulSoup(con.read())
mylist = soup.findAll("li", { "class" : "destaque" })

selected = [element.findAll("a")[0].attrs['href'] for element in mylist]

def format_title(link):
	pattern = r".*\/(.+?)\/$"
	match = re.search(pattern, link)

	title = (" ".join(match.group(1).split("-"))).title()
	return title

headlines = [PyRSS2Gen.RSSItem(link=link, title=format_title(link)) for link in selected]

rss = PyRSS2Gen.RSS2(title = "One Piece Hot News", link="localhost", description="After..",items=headlines)
rss.write_xml(open("one_piece.xml", "w"))