ASSIGNMENT1 CODE

# -*- coding: utf-8 -*-
"""
Created on Thu Jan 17 23:12:53 2019

@author: Ashishn
"""


driver.get('https://science.iit.edu/people/faculty')

#source = driver.page_source
#elements = driver.find_elements_by_class_name('views-field views-field-nothing col-xs-10')
elements = driver.find_elements(By.CLASS_NAME,"views-field") #NEED SPECIFIC CLASS NAME FOR OPTIMIZATION

linkList = []
for oneFaculty in elements:
    try:
        element = oneFaculty.find_elements_by_tag_name("div")
        linkIs = element[0].find_elements_by_tag_name("a")[0].get_attribute("href")

        #trash link condition
        if(linkIs == "https://science.iit.edu/%5Bpath%5D"):
            pass
        else:
            linkList.append(linkIs)
    except:
        pass

from selenium import webdriver
import pandas as pd

from selenium.webdriver.common.by import By
driver = webdriver.Chrome(executable_path ='C:\Program Files (x86)\Google\chromedriver.exe')

for inDetails in linkList:
    #hitting again with same object
    driver.get(inDetails)
    name = driver.find_element(By.CLASS_NAME,"rdf-meta")
    NAME = name.get_attribute('content')
    TITLE = driver.find_element_by_css_selector(".field.field-name-field-faculty-image.field-type-image.field-label-hidden.view-mode-full")
    print(TITLE)
    #TITLE = driver.find_element()
    #source = driver.page_source
    print(name.text)
    #nameis = driver.find_elements(By.ID,"page-title")
    #print(nameis[0].text)


    break


#.find_element_by_css_selector('a').get_attribute('href')


#language_element = driver.find_elements_by_xpath('//[@class=’views-field views-field-nothing col-xs-10 faculty-name’]')



driver.close()



#####################

.field.field-name-field-faculty-title field-type-text.field-label-hidden.view-mode-ful

response = HtmlResponse(url = 'https://science.iit.edu/people/faculty', body = source, encoding='utf-8')