Jobsbg viewcount

jobsbg.py

from BeautifulSoup import BeautifulSoup
import urllib2
import math
import re
# coding: utf-8
"""
  Get job views from company postings in jobs.bg
"""


def soup_url(url):
                page=urllib2.urlopen(url)
                page=page.read()
                page=page.decode('utf-8')
                page_text = page.encode('utf-8').decode('ascii', 'ignore')
                soup = BeautifulSoup(page_text)
                return soup

def jobviews(jobid):
                soup = soup_url("http://www.jobs.bg/" + jobid)

def get_pagenum(url):
                soup = soup_url(url)
                pages=soup.find("td",{"class" : "pagingtotal"})
                pages=pages.text.split(" ")
                pages=math.ceil(int(pages[-1])/20.0)
                return pages

def get_views(soup):
                table=soup.findAll("table",{"width" : "980"})
                td=table[1].findAll("td")
                bb=td[0].findAll("b")
                return int(bb[0].text)

def print_jobs(soup):
        joblinks=soup.findAll("a",{"class" : "joblink"})
        for jobs in joblinks:
                soup=soup_url(str("http://www.jobs.bg/%s" % jobs['href']))
                viewz=get_views(soup)
                print "%s %s" % (viewz,jobs.text)

# Company ID from jobs.bg
cid=14495
pages = get_pagenum(str("http://www.jobs.bg/company_profile_view.php?frompage=0&c_sid=%s" % cid))
for i in range(0,int(pages)*20,20):
                soup = soup_url(str("http://www.jobs.bg/company_profile_view.php?frompage=%s&c_sid=%s" % (i,cid)))
                print_jobs(soup)