Silver Sevens Casino promotions scraper

silver_sevens.py

'''
Silver Sevens Casino scraper

lxml docs:

    http://lxml.de/api/lxml.etree._Element-class.html

'''
import re
import requests
from lxml import html


class nFile(file):
    "Adds newline onto the end of all writes."

    def __init__(self, name, mode = 'r'):
        self = file.__init__(self, name, mode)
        
    def write(self, string):
        self.writelines(string + '\n')


def re_write(s):
    "Abstract Regex find logic used b/4 writing to the file"
    try:
        return ' '.join(re.findall(pattern, ''.join(s).encode('utf-8')))
    except AttributeError:
        return ''


page = requests.get('http://www.silversevenscasino.com/promotions-special-offers')
tree = html.fromstring(page.text)
# list of divs containing promos
divs = tree.xpath('//div[contains(@class, "views-row views-row-")]') 

pattern = r'[\w\d\.\:\,\-\_\'\"\!]+'


def main():
    f = nFile('outfile.txt', 'w')
    for div in divs:
        # loop through all contents in a single div and write the info wanted

        for node in div.iter('*'):
            if node.tag == 'h4':
                f.write(re_write(node.text))
            if node.tag == 'li':
                try:
                    f.write(re_write(node.text))
                except AttributeError:
                    pass
        # line separator in between promos 
        f.write('')
    # close file when finished scraping
    f.close()


if __name__ == '__main__':
    main()