RembookScraper.py

import requests
from BeautifulSoup import BeautifulSoup as bs 
import re
import ho.pisa as pisa
import os
import sys
import cgi
import cStringIO
import logging
payload = {'username' : '106111062' , 'password': '5' ,'login': 'Log In'}
container  = { }

base_url = 'http://rembook.nitt.edu/home/'
session = requests.session()
r = session.post("http://rembook.nitt.edu/home/login", data=payload)

response = bs(r.text)
links_soup = response.find('div',{'class':'panel','id':'alerts'})
links = links_soup.findAll('a')
rollnos =  set(re.search('(\d+)',link['href']).group() for link in links)
names = {}
for link in links : 
        if link.text == 'comments':
                continue
        names[re.search('(\d+)',link['href']).group()] = link.text

temphtml = """<center><h1>My rembook</h1></center>"""
for rollno in rollnos:
        r= session.get('http://rembook.nitt.edu/home/{0}/#comment'.format(rollno))
        soup = bs(r.text)
        
        comments = [comment.text for comment in soup.findAll('h4')]
        container[rollno] = {'author':names[rollno], 'people call you' : comments[1] , 'you frequently utter' : comments[2] , 'your striking features are': comments[3],'and you are' : comments[4] }
        print container[rollno]
        temphtml+= """<p><img src="http://rembook.nitt.edu/uploads/%s.jpg"><br>Author: %s<br>People call you: %s<br>You Frequently Utter: %s<br> Your striking feature: %s <br>and You Are: %s</p>""" % (rollno, names[rollno], comments[1], comments[2], comments[3], comments[4])
print temphtml
#from fpdf import FPDF, HTMLMixin
# 
#class MyFPDF(FPDF, HTMLMixin):
#    pass
# 
#pdf=MyFPDF()
##First page
#pdf.add_page()
#pdf.write_html(temphtml)
#pdf.output('html.pdf','F')
try:
    pdf = pisa.CreatePDF(
        cStringIO.StringIO(temphtml),
        file('html.pdf', "wb")
        )
except Exception as e:
    print e

if pdf.err:
    dumpErrors(pdf)
else:
    pisa.startViewer('html.pdf')