PrimeObsession.py

PrimeObsession.py

# -*- coding: utf-8 -*-

import requests
import lxml
import sympy
import numpy


def PeopleSetDetail(PeopleSetID, PrimeObsession=False):
    site = 'http://comics.www.collectors-society.com/'
    url = 'registry/comics/PeopleSetDetail.aspx?PeopleSetID=%s' % PeopleSetID
    req = requests.get(site + url)
    html = lxml.etree.HTML(req.text)
    rows = html.xpath("//table[@class='TopSetsGrid']/tr")
    data = list()
    for row in rows:
        cols = row.xpath("td/a/text()")
        try:
            if sympy.isprime(cols[1]) or not PrimeObsession:
                data.append(cols[-2::-1])
        except (IndexError, ValueError):
            pass
    return numpy.array(data)

print PeopleSetDetail(79399, PrimeObsession=True)